Streaming

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 18% on the four weeks before. 0.2% of all new papers.

Jul 6Week of Sep 21

Latest papers 171

Jul 24, 2026cs.LG

Pretraining EHR Foundation Models with Patient-Aware Sampling

Autoregressive foundation models for electronic health records (EHRs) typically inherit pretraining methods from language modeling, where patient trajectories are concatenated into a single token stream and windows are sampled from that stream. In EHR data, this choice is consequential: windows may mix multiple patients, and patients with longer records contribute more optimization updates, potentially introducing bias. We propose Patient Sampling, a pretraining sequence-construction method that allows us to control how training signal is distributed across patients. We compare this method to the standard approach, which we refer to as Global Stream. We show that stochastic Patient Sampling with controllable weighting improves performance on real-world EHR data. Across downstream clinical tasks on MIMIC-IV v2.2 and v3.1, Patient Sampling improves Macro AUROC and AUPRC over the Global Stream baseline. These results identify training and validation sequence construction as important and underexplored design choices for autoregressive EHR foundation models.

Joshua Placidi, Yuxuan Liu, Jinpei Han +2

Dept. of Computing, Imperial College London, London, United Kingdom · Dept. of Bioengineering, Imperial College London, London, United Kingdom · UKRI Centres in AI for Health, United Kingdom +1

Medical World Model Mimic-Iv Datasets Streaming Dataset Construction

Jul 23, 2026cs.CV

Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evolve across views. Existing autoregressive video diffusion pipelines carry forward observation history as conditioning context, which makes shared state difficult to maintain in multi-agent and multi-view settings. We present WorldWeaver (W^2), a streaming multi-agent video diffusion model that augments rollout with cross-agent world state registers: learnable tokens that store shared world information, track individual agent status, and are dynamically updated after each generated chunk. We ground these registers with supervision signals spanning individual agent status, global state views including bird's-eye views, and scene text. We further improve the architecture with a Mixture-of-Transformers design that uses separate weights for world state modeling and visual frame modeling. Extensive experiments in two-agent Minecraft video generation show that explicit world-state modeling improves logical consistency and generation quality.

Sicheng Mo, Yuheng Li, Ziyang Leng +2

University of California, Los Angeles · Adobe Research

Video World Models Autoregressive Video Diffusion Models Autoregressive Diffusion Video Diffusion Models World Models Diffusion Models+1

Jul 23, 2026cs.AI

Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs

Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deployment in production applications that require low latency. IndexTTS-2 is a state-of-the-art autoregressive TTS model consisting of a GPT, a flow-matching Diffusion Transformer, and a vocoder. Despite its high synthesis quality, its inference speed barely reaches real-time without streaming or batching support. We present Faster IndexTTS-2, which accelerates all neural network components of IndexTTS-2 for production deployment on GPUs using NVIDIA TensorRT and TensorRT-LLM. Faster IndexTTS-2 also enables streaming synthesis for latency-sensitive interactive applications, and batched inference across all components to maximize GPU utilization. Experiments on the Seed-TTS benchmark for both English and Chinese demonstrate up to 5.0

\times

speedup on the autoregressive GPT and 3.6

\times

end-to-end, with minimal degradation in word error rate, speaker similarity, and naturalness. Our methodology provides a practical reference for efficiently accelerating similar autoregressive speech models on GPUs.

Muyang Du, Shuang Yu, Junjie Lai

NVIDIA · Shanghai, China

Autoregressive Text-To-Speech Seed-Tts-Eval Benchmark Streaming Synthesis

Jul 22, 2026cs.LG

Online Variance Reduction for Domain Adaptation on Streaming Data

This paper studies the problem of stochastic variance reduction (SVR) for the maximum mean discrepancy (MMD) and correlation alignment (CORAL) loss functions. Although various offline SVR algorithms for these losses have been proposed, these are incompatible with online, distributed, or incremental learning settings. This paper presents Adaptive vaRiance Reduction via Online reWeighting (ARROW), the first online SVR algorithm for the MMD and CORAL for streamed data. The method maintains moving average references of the alignment statistics, and adaptively reweights incoming minibatches so that the minibatch and reference statistics are aligned. Further, we propose a relaxed reweighting scheme so that the ensuing weight-optimisation problem is tractable. In experiments and simulations, we show that ARROW performs competitively with offline algorithms in terms of runtime, degree of variance reduction achieved, and target domain accuracy.

Andrea Napoli

Department of Electronics and Computer Science University of Southampton, UK

Variance Reduction Domain Adaptation Learning-Augmented Algorithms Reweighting Streaming Loss Function

Jul 22, 2026cs.CV

StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation

Existing human--object interaction (HOI) video generation methods are largely limited to offline short-video generation with complex driving conditions, making them unsuitable for real-time interactive applications. We present \emph{StreamHOI}, a low-latency streaming framework for long-duration HOI video generation. Instead of converting heavily conditioned HOI pipelines into streaming systems, we study how an image-to-video streaming generator should organize historical memory to preserve interactions under bounded latency. We find that the standard sink-local memory design faces a trade-off in streaming HOI generation, and different transformer blocks show different historical-memory preferences for HOI regions and surrounding regions. To match memory composition with block behavior, StreamHOI performs offline HOI-aware block profiling and applies bias-guided memory-specialized training to adapt the generator to block-specific memory layouts. We further introduce a memory distance scaling module to strengthen long-range access to early interaction states. Extensive comparisons with both long-video baselines and recent HOI generation methods demonstrate that StreamHOI achieves strong interaction plausibility, object fidelity, human quality and efficiency, reaching 17.6 FPS with 0.75s first-chunk latency.

Zejing Rao, Haoxian Zhang, Xiaoqiang Liu +5

National Cheng Kung University, Tainan, Taiwan

Streaming Peak Memory Water

Jul 22, 2026cs.SD

Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting

State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for short audio tasks. We study cumsum-composable phase transport, a streaming-native temporal layer for keyword spotting. Each layer projects acoustic frames to complex channels, transports them by learned unitary rotations, accumulates a finite window using prefix differences, and applies a gated residual update. The same prefix representation gives exact batched training with ordinary cumulative sums and exact online inference with one prefix update per frame. Unitary transport is the key constraint: inverse rotations have norm one, keeping prefix terms well conditioned while memory is supplied by windows or block readouts. On Google Speech Commands v2 with 12 labels, mel+cumsum models retain competitive accuracy with compact baselines. The strongest single-seed run reaches 97.3% test accuracy; a 51.6K-parameter tied model also reaches 97.3%, and a 24.8K tied model reaches 96.8% versus 97.1% for a 25.6K MelCNNMaxPool baseline. In a matched cumsum-versus-scan benchmark, cumsum+window gives comparable accuracy, 94.82% versus 94.33%, while training 1.07x faster and reducing single-example latency from 7.09 ms to 5.01 ms on a Tesla T4. These results support cumsum phase transport as a simple low-cost temporal primitive for streaming keyword spotting.

Mahesh Godavarti

A Carrot, Inc

Keyword Spotting Streaming Latent Transport Batch

Jul 21, 2026cs.CV

IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer

Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding. Meanwhile, existing semantic reconstruction and 3D-aware vision-language methods largely rely on externally extracted 2D semantic cues or loosely coupled geometry inputs, limiting unified geometry-instance learning in long dynamic scenes. In this paper, we propose IGGT4D, a streaming instance-grounded geometry Transformer for online 4D scene understanding. IGGT4D processes video frames sequentially, reuses historical context through causal spatial-temporal modeling, and incrementally updates a unified representation of camera motion, geometry, and object identity. This enables long-sequence feed-forward reconstruction with geometry-instance consistency in dynamic environments. To address the lack of high-quality 4D supervision, we further construct InsScene4D-147K, a large-scale dataset spanning real/synthetic and static/dynamic scenes, with RGB images, depth, poses, and temporally consistent instance masks generated by an automated geometry-guided annotation pipeline. Experiments on 3D reconstruction, pose estimation, instance spatial tracking, and open-vocabulary segmentation demonstrate that IGGT4D outperforms existing streaming baselines while maintaining scalable online inference for long dynamic sequences.

Zhengyu Zou, Hao Li, Kuixuan Jiao +7

Horizon Robotics · S-Lab, Nanyang Technological University · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center

Visual Geometry Grounded Transformer 4D Reconstruction Robust Geometric Model Estimation 4D Streaming Spatiotemporal

Jul 20, 2026cs.LG

Sobek: Streaming Equivariant Tensor Product Convolutions

Equivariant graph neural networks repeatedly apply edge-conditioned tensor-product convolutions over graph edges. Conventional implementations materialize edge-specific weights, messages, and adjoints, causing tensor-product workspace and memory traffic to grow rapidly with graph size and operator width. This limits feasible workloads and can prevent larger problems from fully utilizing the GPU. We show that these edge-sized intermediates are artifacts of the execution schedule, not requirements of the equivariant operator. By reassociating radial projection, spherical-harmonic coupling, and graph aggregation, edge-local products can be consumed directly into bounded receiver-side state. The resulting streaming formulation preserves fully connected multiplicity mixing and extends through forward, backward, and double backward. We implement this formulation in Sobek, a generated-CUDA backend, and evaluate it across edge-scaling regimes and varied feature structures. Across two operator families and all three differentiation orders, Sobek is faster in all 75 capacity-matched comparisons, with speedups ranging from

1.2\times

to

49.7\times

, and reduces peak allocated memory by up to 99%. It also executes workloads up to two orders of magnitude beyond OpenEquivariance's capacity while retaining near-peak throughput. These results show that edge-scaled tensor-product workspace is a property of the conventional schedule, not of equivariant convolution itself.

Vladimir Chorošajev, Cédric Bény

Cortex Discovery

Convolutional Graph Neural Networks Streaming Network Traffic

Jul 19, 2026cs.AI

Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing

Stream-processing systems increasingly operate across heterogeneous mobile edge--cloud infrastructures, where workload volatility, resource contention, and stringent quality-of-service (QoS) requirements complicate decentralized scheduling. This paper proposes \emph{MAS-DecStream}, whose main contribution is \emph{LLM-MR-CNP}: an extension of the classical Contract Net Protocol with semantic CFP formulation, progressive context disclosure, multi-round proposal revision, negotiation memory, and deterministic validation. Edge-cluster agents refine natural-language offloading proposals from local observations, predicted resource states, and qualitative runtime context, while hard resource and QoS constraints remain deterministic. Experiments derived from the Alibaba ASI Trace evaluate the extension at three levels: single- versus multi-round CNP, rule-based versus LLM-assisted refinement, and fixed-model single- versus multi-round negotiation. Under the evaluated configurations, MAS-DecStream reduces latency violations to 3%, eliminates resource overcommitment, reaches a conflict-resolution rate of 0.91 with 20 agents, and improves utility by up to 22% over the multi-round rule-based baseline. A separate 25-case evaluation shows model- and prompt-dependent accuracy--cost trade-offs. The results provide initial evidence that multi-round CNP refinement is the principal protocol-level gain, with LLM assistance adding value for qualitative and uncertain runtime context.

Sabeur Lajili, Zaki Brahmi

University of Sousse, Tunisia

Edge Devices Schedulers Negotiation Edge Streaming Protocol+1

Jul 18, 2026cs.LG

Dimension-Calibrated Unexplained Mass: An Interpretable Drift Statistic for Contamination Monitoring in Data Streams

Drift detectors that work tend not to explain themselves, and drift detectors that explain themselves tend to fail in high dimension. We close that gap for Gaussian mixture models (GMMs): each fitted component is a named "regime," and the fraction of a stream window matching no regime -- its unexplained mass -- is a drift signal that is simultaneously its own explanation. We identify why this statistic collapses in high dimension and repair it. Under a correct component a normal point in d dimensions lies about sqrt(d) sigma from the mean, so once d exceeds 9 essentially every point exceeds a fixed 3-sigma radius: window-level ROC-AUC is exactly 0.50 on Satellite (d=36) and Optdigits (d=64). Calibrating the radius to sqrt(chi-squared_d(0.99)) removes the collapse -- AUC 1.00 and 0.89 -- while leaving low dimensions unchanged. Across seven public benchmarks, five seeds, and eight model-free detectors spanning the kernel, classifier, projection, density-difference, transport, likelihood and partition families, the repaired statistic is best or tied-best on five of seven datasets at 10% window contamination (its two losses are Pendigits, where the whole field beats it, and Optdigits), and as contamination becomes sparse the sample-level detectors fade toward chance while it degrades most gracefully: at 2% its mean AUC across the benchmarks is 0.86 against at most 0.73 for any model-free detector (1.00 vs. MMD's 0.72 on KDD-http) -- while alone among them reporting which regime the data left and how far outside it the window lies. We delimit its scope honestly: unexplained mass detects and explains novel-regime drift but is blind by construction to in-support re-weighting of known regimes, where distribution-level tests are required and explain nothing; and the underlying density model's EVT-calibrated false-alarm rates degrade above d of about 36. All code and experiments are released.

Behnam Asadi

Gaussian Mixture Models Unsupervised Detection Statistical Inference Streaming

Jul 16, 2026cs.CV

Video = World + Event Stream

We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persistent context in which a video unfolds, including the environment, scene, subjects, ambient acoustic conditions, voice characteristics, and other relatively stable conditions. The event stream is everything that changes over time within that world, including scene or environmental changes, subject behavior, speech, and other sounds. This yields a general-purpose pretraining task over large amounts of real video: given a world and incoming input, predict how the world moves, changes, and responds in real time. The resulting competence can be specialized to a broad family of real-time downstream tasks. We instantiate it on real-time full-duplex audio-visual interaction, where the event stream is the agent's speech together with free-form behavior. Functionally, the model's multimodal understanding process is vision-language-action-like: it maps multimodal user input to language-form speech and behavior actions. Wan-Streamer v0.3 preserves the v0.2 operating point: 640x368 video at 25 FPS, a 160 ms streaming unit, approximately 200 ms model-side response latency, and approximately 550 ms total interaction latency under a 350 ms bidirectional network budget.

Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +24

Wan Team, Alibaba Group

Streaming Multimodal Understanding Full-Duplex Speech Models World

Jul 16, 2026cs.CV

FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers

Real-time video generation demands fast decoding as much as fast denoising, yet current latent video diffusion models rely on 3D convolutional decoders that are slow and memory-intensive at high resolutions or for long video. We introduce FlashDecoder, a fast, memory-efficient pure-Transformer video decoder that decodes latents to pixels frame by frame. At each step, the current frame attends only to a fixed-size window of past frames through a rolling KV cache. The fixed temporal window keeps decoding fast and memory bounded regardless of video length, enabling constant-latency streaming. Because frames are processed sequentially, temporal causality is enforced without explicit attention masks, enabling training at resolutions up to 1080p and matching the reconstruction quality of convolutional decoders. On the Wan2.1 and Wan2.2 latent spaces, FlashDecoder matches each convolutional decoder in reconstruction quality (e.g., 41.55dB vs. 41.49dB PSNR at 1080p) while decoding 3.6x-4.7x faster with up to 11x less memory on a single H100 GPU. With architecture-aware inference optimizations, the speedup widens to 12x.

Minguk Kang, Suha Kwak

Pika Labs · POSTECH

Video Diffusion Models Intermediate Decoder Layers Video Latents Streaming Transformer Architectures

Jul 15, 2026cs.CV

M $^\text{4}$ World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming

Driving-world generation has emerged as a core capability for scalable autonomous-driving simulation, yet existing methods remain limited in object-level controllability and long-horizon stability. We present M

^\text{4}

World, a Multi-view and Multimodal generative driving world model that synthesizes future surround-view video streams and synchronized LiDAR scans while supporting interactive object Manipulation and stable Minute-long streaming. Fine-grained object manipulation is realized through a flexible conditioning interface that supports explicit control over both the spatial layout and visual appearance of individual objects. Stable minute-long streaming, on the other hand, is achieved through a multi-stage training framework that enables online causal generation in only four denoising steps while maintaining coherent world dynamics throughout extended rollouts. Building on these components, we introduce an efficient few-clip post-training as well as a suite of visual reference-conditioned generation models, preserving general generation ability while allowing rare-case customization for long-tail controllability. To assess controllability beyond realism, we further introduce an automated VLM-based judging pipeline that evaluates scene-level condition adherence, view-wise object controllability, and cross-view object consistency. Comprehensive experiments show that M

^\text{4}

World consistently delivers high generation quality, precise controllability, and stable minute-long streaming. Together with downstream long-tail augmentation and scene editing, these results demonstrate the potential of M

^\text{4}

World for controllable, scalable driving simulation.

Ke Cheng, Hanqiao Ye, Lei Shi +8

1Meituan · Institute of Automation, Chinese Academy of Sciences · 3Beijing Institute of Technology

Autonomous Driving Simulation World Models Controllability Streaming Multi-View

Jul 14, 2026cs.CL

Do LLMs Need Architectural Changes for Simultaneous Speech Translation? A Prefix-to-Prefix Data Driven Approach

Simultaneous speech translation (SimulST) requires incremental translation under strict latency constraints, yet remains challenging for decoder-only LLM systems due to limited context and cross-lingual reordering. Recent approaches often introduce architectural changes or explicit read/write policies to control output timing, which can be brittle in conversational speech where segmentation boundaries are ambiguous. We present a simple data-driven alternative: fixed-length chunks for cumulative streaming decoding with a rewind-based committed prefix, and teacher-labeled prefix-to-prefix (P2P) targets with bounded waiting for fine-tuning, yielding CSSEL-P2P, where CSSEL is our proposed chunked streaming speech encoder LLM. In our in-house conversational speech evaluation, CSSEL-P2P improves streaming quality by +1.54 COMETKiwi over the CSSEL streaming baseline at comparable latency (+0.15s Average Lagging), suggesting effective SimulST without architectural changes via P2P supervision.

Junkun Chen, Jian Xue, Ming Tang +4

Microsoft, USA

Speech Translation Streaming

Jul 8, 2026cs.LG

Robust Federated Learning Under Real-World Client Churn

Federated Learning (FL) enables training shared models on private, on-device data, but production deployments remain constrained to slow, multi-day refresh cycles due to the complexity of coordinating massive client populations. For applications such as feed ranking, ad targeting, and personalized recommendation, model freshness: the ability to rapidly adapt to new user-local data is critical for maximizing objectives like click-through rate. This lag leaves models stale and unresponsive to volatile data distributions driven by viral trends and shifting user intent. Bridging this gap requires addressing three challenges overlooked by existing FL systems: transient client availability, dynamic data heterogeneity, and delays between model predictions and observable outcomes. We present FeLiX, an FL orchestration framework that minimizes wall-clock time-to-target accuracy on live interaction streams. FeLiX introduces three primitives: (i) streaming-aware availability tiers that leverage lightweight telemetry to identify ready clients at scale; (ii) fresh-utility selection, a dual-tier mechanism that prioritizes statistically valuable updates from devices able to meet tight refresh deadlines; and (iii) informativeness-aware, delay-robust aggregation that incorporates late, high-value updates containing ground-truth outcomes without biasing the global model toward stale distributions. Unlike prior systems that rely on unrealistic oracular knowledge of client availability, FeLiX achieves near-oracular performance in real-world settings. Across CIFAR-10, Google Speech, and realistic low-availability traces, FeLiX reduces wall-clock time-to-target accuracy by up to 2.37X while reducing communication bandwidth by 1.30X compared to state-of-the-art synchronous and asynchronous FL baselines.

Dhruv Garg, Neha Lakhani, Debopam Sanyal +3

Georgia Tech USA · Cisco Research USA

Federated Learning Heterogeneity Churn Prediction Streaming Real-World

Jul 7, 2026cs.CV

ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitions

Generating temporally continuous and socially coherent human motion from text remains a fundamental challenge, particularly in realistic streams where people act alone, enter interactions, and later disengage. Most existing methods generate fixed-length motion clips under static agent configurations, which makes them brittle to solo-social transitions and unsuitable for incremental generation over long horizons. We propose ARMS, an Anchor-Relational Motion Streaming framework that unifies solo motion and human-human interaction within a single causal generative process. ARMS introduces a dynamics-asymmetric representation that decouples per-person temporal evolution from inter-person alignment via a partner-referenced relative-translation term, enabling seamless switching of social coupling without sacrificing long-horizon stability or spatial consistency between agents. On top of a causal latent space, a causal relational diffusion model progressively refines motion segment by segment using only past context, capturing both intra-person temporal dependencies and inter-person relations. Mode-aware relational gating activates or masks cross-agent connections, allowing the same model to support both solo and interaction generation. Experiments show that ARMS improves transition smoothness and social coherence compared to interaction-centric baselines, while also achieving competitive results on human-human interaction benchmarks.

Huakun Liu, Qing Yu, Kent Fujiwara +2

Nara Institute of Science and Technology, Ikoma, Japan · LY Corporation, Tokyo, Japan

Human Motion Generation Human Motion Sharp Transitions Interaction Data Streaming Temporal Dynamics

Jul 6, 2026cs.CV

ReCal3R: Reliability-Calibrated Learning Rates for Streaming 3D Reconstruction

Streaming 3D reconstruction relies on a compact recurrent scene state to process long image streams in linear time and bounded memory. However, repeated updates can gradually corrupt this state, causing reliable historical information to be overwritten by noisy or ambiguous observations. We introduce ReCal3R, a reliability-calibrated learning rate method for recurrent 3D reconstruction. Instead of directly applying a candidate learning rate, our method estimates state token reliability from the maintained scene state and uses it to calibrate a candidate learning rate derived from token alignment, state reconstruction residual, and recent update pressure. The resulting token-wise learning rate interpolates between a conservative base rate and the candidate rate, suppressing aggressive updates on unreliable tokens while preserving adaptation to informative frames. Applied to CUT3R as a training-free calibration rule, ReCal3R reaches strong performance on long sequences in pose, depth, and reconstruction quality, including a 3.7

\times

reduction in ATE, with comparable runtime and memory. Code is available at: https://github.com/Powertony102/ReCal3R.

Xinze Li, Yiyuan Wang, Pengxu Chen +4

Beijing Normal-Hong Kong Baptist University · Hong Kong Baptist University · Jilin University +2

3D Reconstruction Recurrent State Recast Streaming Batch

Jul 2, 2026cs.SE

SMOCS: A Streaming Framework for Simplified Deployment, Monitoring, and Optimization of ML Systems in Production

Machine learning has demonstrated significant potential for real-time monitoring, optimization, and control of scientific facilities. However, deploying and maintaining ML models in operational environments remains a substantial engineering challenge. Each facility presents unique data protocols, non-standard formats, and infrastructure constraints, forcing teams to rebuild integration pipelines for every new application. We present SMOCS (Streaming Monitoring Optimization and Control System), a Kafka-based containerized framework that addresses this challenge through three contributions: 1) a layered abstraction over Apache Kafka that separates infrastructure from application logic, 2) a three-thread agent architecture that temporally decouples data ingestion, model training, and real-time inference enabling continuous online learning from live data streams, and 3) a configuration-driven deployment model that enables domain experts to operate ML pipelines without software engineering expertise. SMOCS is facility platform-agnostic, fault-isolated by design, and horizontally scalable through Docker containerization. The framework is publicly available as open-source software on the Jefferson Lab Github.

Armen Kasparian, Kishansingh Rajput, Malachi Schram +1

Streaming Ai-Based Framework

Jul 2, 2026cs.CV

S-EMBER: A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval

As wearable devices enable continuous first-person recording, AI assistants must reason across long time horizons to recall past experiences-a capability known as episodic memory. Current benchmarks often rely on offline evaluation with access to entire video files, failing to simulate the streaming reality of wearable intelligence. We introduce S-EMBER (Streaming Egocentric Memory Benchmark for Episodic Retrieval), a large-scale benchmark comprising 3,141 videos totaling 388 hours of organic activity captured via Ray-Ban Meta smart glasses. S-EMBER formalizes grounded streaming episodic retrieval, a paradigm shift from global offline search to causal, active recall triggered by visual events in a continuous stream. We provide 9,448 QA pairs requiring manual visual proof through precise temporal localization and supporting flexible response lengths to simulate natural human-AI interaction. Our extensive benchmarking of frontier models uncovers a localization paradox: while semantic reasoning improves with parameter scale, temporal grounding precision remains a stagnant architectural bottleneck that does not benefit from brute-force increases in model size, resolution, or frame density. S-EMBER establishes a hardware-authentic foundation for developing grounded, reliable episodic memory in the next generation of wearable AI agents.

Xiaodong Wang, Xuanyi Zhao, Pedro Rodriguez +7

1FAIR, Meta · 2Reality Labs, Meta

Episodic Memory Streaming Large-Scale Benchmark Temporal Grounding

Jul 2, 2026cs.CV

MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding

Existing medical video benchmarks primarily evaluate whether a model produces the correct answer, but rarely assess whether it answers at the right time. In real clinical settings, AI systems must decide not only what to predict, but also when to answer, defer judgment, or proactively raise alerts. This creates a critical gap between benchmark evaluation and deployment requirements. We present MedStreamBench, a benchmark for time-aware medical video understanding. MedStreamBench integrates 22 medical datasets and 5,419 QA instances across four temporal settings: retrospective, present, future, and proactive. Unlike conventional benchmarks that assume full-video access, MedStreamBench restricts models to temporally bounded evidence windows and supports both single-turn and streaming evaluation. We further introduce a proactive monitoring setting that requires models to determine whether and when clinically relevant alerts should be triggered. Beyond answer correctness, MedStreamBench evaluates temporal behavior through responsiveness and post-evidence stability. Experiments on leading general-purpose and medical vision-language models reveal a substantial gap between offline recognition and temporally grounded decision-making, with performance dropping markedly in streaming and proactive settings. Our benchmark is available at https://huggingface.co/datasets/Venn2024/MedStreamBench.

Yuan Wang, Shujian Gao, Songtao Jiang +2

College of Computer Science and Technology, Zhejiang University, Zhejiang, China · Insititute of Trustworthy Embodied AI, Fudan University, Shanghai, China · Department of Electrical and Computer Engineering, Carnegie Mellon University, Pennsylvania, USA

Medical Visual Question Answering Diagnostic Benchmark Streaming

Jul 1, 2026cs.LG

TiRex-2: Generalizing TiRex to Multivariate Data and Streaming

We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. Real-world forecasting is inherently sequential: observations arrive continuously, variables evolve jointly, and a subset of covariates is known ahead of time. Existing Transformer-based time series foundation models capture cross-variate dependencies but incur quadratic complexity in context length and require full-history recomputation as new observations arrive. TiRex-2 addresses these limitations through a memory-centric recurrent design that operates at constant per-patch cost under streaming. The model combines a bidirectional time mixer with an asymmetric grouped-attention variate mixer, enabling the integration of future-known covariates while preserving strict causality over target variables. To our knowledge, this is the first time series foundation model that achieves this combination of properties. To support scalable multivariate pretraining, we propose a synthetic coupling pipeline that composes diverse multivariate samples on the fly from large univariate corpora. Empirically, TiRex-2 achieves state-of-the-art zero-shot performance on GIFT-Eval and fev-bench, remains stable when streamed to arbitrary context lengths, and maintains constant inference cost per patch. The model uses 38.4M active parameters in univariate mode, with an additional 44.1M parameters activated for multivariate forecasting.

Patrick Podest, Marco Pichler, Elias Bürger +7

ELLIS Unit Linz, LIT AI Lab & Institute for Machine Learning, JKU Linz, Austria · NXAI Lab, Linz, Austria · NXAI GmbH, Linz, Austria +1

Time Series Foundation Models Asymmetric Grouped-Attention Variate Mixer Recurrent Model Streaming

Jul 1, 2026cs.SD

NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs

We present NPUsper, a live transcription system that makes Whisper efficient on mobile NPUs by eliminating redundant computation. To avoid the heavy padding used by prior streaming systems, NPUsper detects hallucinated tokens online from temporal patterns in decoder cross-attention, allowing each inference round to process short audio inputs with minimal carryover. For efficient mobile-NPU execution, we propose controlled unrolling, which executes autoregressive decoding as K-step chunk graphs, removing unnecessary KV-cache computation and reducing graph-dispatch overhead. NPUsper achieves up to 4.84x lower per-word latency, up to 33.2x lower time-to-first-token (TTFT), and up to 88.64% lower average power consumption compared with baselines, while maintaining comparable transcription accuracy. The code is available at https://github.com/npusper/NPUsper.

Sihyeon Lee, Hojeong Lee, Sungwon Woo +3

Korea University · University of Wisconsin–Madison

Whisper-Large-V3 Neural Processing Units Transcript Streaming Redundancy

Jul 1, 2026cs.AI

PedNStream: Scalable Network Flow Simulation for Pedestrian Traffic Management

Large-scale crowd management requires pedestrian simulations that are both computationally efficient and compatible with feedback-based control. However, most open-source tools are either microscopic or not designed for network-scale closed-loop evaluation. This paper presents PedNStream (Pedestrian Network Flow Simulation), an open-source, Python-native simulator for macroscopic pedestrian network loading based on the Link Transmission Model (LTM). The framework extends LTM-based pedestrian models by incorporating stochastic link dynamics that capture diffusion and activity-induced variability, and replaces dynamic user equilibrium route choice with a utility-based formulation suited to uncertain, intervention-driven settings. PedNStream is implemented as a modular framework with built-in controller interfaces for interventions such as gating, flow separation, and route guidance. We evaluate the framework in a staged manner. Synthetic scenarios verify key mechanisms, including queue formation, spillback, congestion dissipation, and adaptive rerouting. Real-network experiments assess large-scale behavior and consistency with observed pedestrian counts. A closed-loop case study demonstrates controller integration, and a runtime analysis quantifies scalability. These results establish PedNStream as an efficient and practical testbed for large-scale pedestrian network simulation and control.

Weiming Mai, Dorine Duives, Serge Hoogendoorn

Department of Transportation and Planning, Delft University of Technology, Delft, Netherlands

Microscopic Traffic Simulations Flow Models Streaming Bellman Equation

Jun 30, 2026cs.CV

MSNN-LINet: Cross-Modal Learning via Continuous Linear Integration

We present LINet (Linear Integration Network), a Multi-Stream Neural Network (MSNN) for RGB-D scene classification. Current multi-modal architectures treat feature fusion as a discrete, ad-hoc event: early fusion entangles representations prematurely, late fusion isolates them until the final layer, and hybrid or attention-based methods require architectural guesswork to place intermediate fusion blocks. LINet addresses this structural compromise by maintaining three dedicated parallel streams (RGB, depth, and integration) where a novel Linear Integration Convolution (LIConv2d) operator enables continuous cross-modal learning at every layer. The integration stream receives raw filtered signals from both modality streams and combines them before the nonlinear activation threshold, conceptually inspired by somatic integration preceding the neuronal firing decision. Implementing continuous integration exposes a critical initialization pathology: Kaiming initialization of the bridging weights scrambles gradients before they reach the stream backbones, producing a failure mode that resembles overfitting but is corrupted gradient flow. A 1/N constant initialization mitigates this. We employ progressive modality dropout, a curriculum adapted to continuous fusion in which blanking probability increases from zero, preventing pathway collapse, a form of negative co-learning, by forcing robust independent stream representations. Trained from scratch on SUN RGB-D 19-class scene classification, LINet reaches 45.2% mean class accuracy at ResNet18 scale, outperforming prior from-scratch results, and rises to 49.6% with in-domain RGB-D (ScanNet) pretraining.

Gabriel Clinger

The George Washington University

Cross-Modal Rgb-Depth Cameras Streaming Time Discretization

Jun 29, 2026cs.LG

Hybrid Active-Online Learning Framework for Label-Efficient Concept Drift Adaptation in Optical Network Failure Detection

We propose a hybrid active-online learning framework for label-efficient concept drift adaptation in optical network failure detection. Using margin-based selective labeling, our method achieves nearceiling accuracy and AUC scores while querying only 3.4% of streaming samples, with negligible latency overhead compared to static inference.

Yousuf Moiz Ali, Jaroslaw E. Prilepsky, João Pedro +4

Aston University, Birmingham, UK · Nokia, Optical Networks, Carnaxide, Portugal · Nokia, Munich, Germany

Pool-Based Active Learning Label Propagation Learning-Augmented Algorithms Optical Networks Early Failure Prediction Streaming

Jun 27, 2026cs.CV

DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming

3D Gaussian Splatting~(3DGS) has emerged as a promising paradigm for reconstructing streamable free-viewpoint video~(FVV) from multi-view videos. However, 3DGS-based FVVs typically lack user interaction and editing capabilities, which diminishes the immersive experience. Recent research has integrated language features from CLIP into 3DGS via distillation, enabling open-vocabulary queries and supporting many downstream applications. Nevertheless, the stringent requirements of FVV, low frame size and high FPS, make current language Gaussian representations unsuitable for language-embedded FVV. In this paper, we propose DLGStream, a novel language-embedded FVV representation that streams time-varying language features alongside Gaussian attributes to support 4D environment interaction, scene editing, and spatial intelligence. Specifically, we propose a dual-opacity dynamic language Gaussian representation, which maintains two opacity attributes for color and language features to deal with performance degradation that occurs when colors and features are jointly optimized. Furthermore, we introduce an interpolation-based deformation field to reduce temporal redundancy. This deformation field can also be used for 4D frame interpolation, boosting FVV sequences from low to high FPS. Experimental results demonstrate that DLGStream achieves superior performance in both on open-vocabulary segmentation and reconstruction quality with an average frame size of merely 43 KB. The code is available on \href{https://github.com/kkkzh/DLGStream}{https://github.com/kkkzh/DLGStream}.

Zhihui Ke, Yuyang Liu, Xiaobo Zhou +1

School of Computer Science and Technology, Tianjin University, China

Volumetric Video Streaming Interpolation

Jun 27, 2026cs.LG

Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems

Streaming inference pipelines increasingly pair lightweight fast models with Large Language Models (LLMs) that provide rich semantic understanding at substantial cost. The central question of when to invoke the LLM has received limited formal treatment. We cast this as a risk-based sequential stopping problem, where a trigger policy fires when a risk functional over the observation history exceeds a threshold. Within this framework, we prove six results: a minimum inter-event time bound excluding trigger chattering; optimality of threshold policies via smooth pasting; approximate SPRT guarantees under estimated parameters; O(sqrt(T log T)) regret for stationary streams, extending to O(sqrt((C_T + 1) T log T)) under C_T changepoints; O(1/sqrt(T)) convergence of online gradient descent for adaptive thresholds; and a calibration-to-miss-rate transfer inequality. Several classical trigger families, including event-triggered, optimal stopping, SPRT, CUSUM, and Bayesian triggers, can be expressed as special cases of this framework. On turbofan degradation data (CMAPSS) with real LLM calls, we empirically verify the theoretical assumptions, ablate the risk function design, compare against six baselines including a RouteLLM-style router and contextual bandits, and analyze cost sensitivity and LLM failure modes. The results confirm sublinear regret, with alpha < 1 for all principled triggers; high diagnostic quality, with 92.9 percent of 1600 LLM diagnoses reaching grounding score >= 0.75 under our rubric; and that anomaly-score-driven risk functions dominate alternatives by roughly an order of magnitude on the Pareto AUC.

Zhaohui Wang

Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA

Streaming Inference Large Language Models Fail Streaming Optimal Stopping

Jun 23, 2026cs.CV

Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. Wan-Streamer seamlessly models language, audio, and video as both input and output within a single Transformer, where the sequence is represented as interleaved visual, audio, and text input tokens together with visual, audio, and text output tokens, coordinated by block-causal attention for incremental streaming. Unlike cascaded interactive systems that rely on separate VAD, ASR, language, TTS, audio-driven animation, or video-generation modules, Wan-Streamer does not rely on external language, speech, avatar, or video-generation modules: perception, reasoning, generation, response timing, turn management, and cross-modal synchronization are learned jointly within one unified model, reducing pipeline latency and error accumulation. To support natural audio-visual responsiveness, we redesign the entire stack around streamability, including causal encoders, causal decoders, block-causal attention, and low-latency multimodal token scheduling, enabling streaming units as short as 160 ms at 25 fps. Wan-Streamer achieves approximately 200 ms model-side response latency and approximately 550 ms total interaction latency when combined with 350 ms bidirectional network latency, supporting sub-second duplex audio-visual communication. These results position Wan-Streamer as a unified, end-to-end, multimodal interactive foundation model for low-latency streaming interaction.

Lianghua Huang, Zhi-Fan Wu, Wei Wang +22

Wan Team, Alibaba Group

Streaming Full-Duplex Speech Models Multimodal Foundation Model Wireless Foundation Models

Jun 22, 2026cs.CV

InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars

Recent diffusion-based models have enabled realistic audio-driven avatar generation in real-time streaming. However, existing approaches struggle to maintain visual temporal consistency and fail to explicitly perceive user intent in complex interactive streaming scenarios. To address these challenges, we propose InteractiveAvatar, a real-time infinite-streaming video generation framework that supports visually consistent avatar video generation and intent-aware interactions. With autoregressive distillation, InteractiveAvatar achieves real-time str-eaming generation of human avatars over arbitrarily long durations. For visual consistency, we introduce a Long-Short Visual Memory (LSVM) mechanism that flexibly compresses historical visual information into compact tokens, preserving both short-range coherence and long-term consistency. To generate avatars with speeches and actions aligned with user intent, we propose a Reasoning-Reaction Module (RRM), which incorporates a State-Cycling strategy and a Cache-Switching mechanism. Extensive experimental results over diverse scenarios demonstrate that our method achieves state-of-the-art visual consistency in long-duration generation, while enabling complex user-avatar interaction in real time.

Quanyue Song, Yishan He, Yanfei Zhang +6

State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, China · China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd., China · State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, China +1

Interactive Video Generation Avatars Streaming Real-Time Systems Visual Memory

Jun 22, 2026cs.CV

CoVStream: Edge-Cloud Collaboration for Understanding of Long Video Streams

Long, continuous video streams are an increasingly critical driver of multimedia intelligence. Existing efforts often handle long videos with a sample-encode-reason approach using large models. However, they overlook a crucial deployment fact: the stream is often produced by computationally constrained devices. This forces an untenable compromise: cloud offloading unlocks strong reasoning but incurs prohibitive bandwidth overhead, while on-device processing remains limited by edge hardware capacity. Therefore, we propose CoVStream, the first edge-cloud collaborative framework for understanding long video streams. The edge node distills raw video streams into compact visual features and semantic captions for transmission to the cloud, minimizing bandwidth costs, while the cloud server integrates this data into an entity graph and global visual context, activating the heavy reasoning model only when a user query arrives. Experiments on VideoMME-Long, LVBench, and RTV-Bench show that CoVStream reduces bandwidth usage by 87.6% while retaining 99.2% of the cloud baseline accuracy on LVBench.

Xu Liu, Guikun Chen, Zihao Yan +2

The State Key Lab of Brain-Machine Intelligence, Zhejiang University · vivo Mobile Communication Co., Ltd., Shenzhen, China.

Streaming Video Edge Platforms Streaming Long Videos Long-Term

Jun 20, 2026cs.SD

Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead

Streaming text-to-speech synthesis in cascaded LLM-TTS systems still faces latency challenges as most TTS models require full context before initiating generation. We present S5-TTS, a streaming variant of T5-TTS that enables low-latency, word-by-word incremental speech synthesis through encoder-decoder language modeling and monotonic alignment learning. S5-TTS begins generating speech immediately after receiving the first few words, substantially reducing end-to-end response latency. To maintain quality under limited lookahead, we introduce a lookahead-causal masking mechanism with Conv-based auxiliary attention that preserves intelligibility and speaker similarity, and employ interleaved multi-source distillation to further restore naturalness. Experiments show that S5-TTS achieves comparable quality to full-context T5-TTS, supports zero-shot synthesis with high speaker similarity, and significantly reduces end-to-end latency for practical conversational AI systems.

Muyang Du, Jason Roche, Junjie Lai

1NVIDIA, China · 2NVIDIA, USA

Text-To-Speech Synthesis F5-Tts Speaker Similarity Streaming Lookahead Probe-Logit Distillation

Jun 19, 2026cs.LG

DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

Massive unstructured multimodal streams suffer from high "data entropy," impeding both efficient human knowledge acquisition and high-quality AI post-training. Existing passive annotation paradigms, heavily reliant on heuristic rules or general VLMs, are costly, monotonous, and fail to unlock the deep procedural logic embedded in raw data. We elevate data processing to a learnable capability, proposing a paradigm shift towards Agentic Data Tailoring, which actively refining and structuring data to align with diverse user and downstream intents. To overcome the data scarcity bottleneck in training such high-order capabilities, we design a two-stage pipeline grounding generative semantic synthesis in deterministic Factual Anchors, yielding a large-scale dataset spanning five core physical and digital domains. Building upon this,

\text{DataClaw}_0

-9B model synergizes Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), achieving robust alignment with complex refinement and tailoring intents. To systematically quantify this capability, we construct

\text{DataClaw}_0

-val, the first benchmark dedicated to data refinement. Crucially, we adopt downstream post-training as the ultimate validation touchstone. Evaluations on video generation, real-world VQA, and GUI navigation confirm that

\text{DataClaw}_0

delivers high-information-density tailored data, facilitating efficient model adaptation to new tasks under limited training data regimes. Project page: https://czjdsg.github.io/MakeAnyData

Cong Wan, Zeyu Guo, Zijian Cai +6

Xi’an Jiaotong University · University of Chinese Academy of Sciences · Shenzhen University of Advanced Technology +1

Multimodal Continual Instruction Tuning Data Science Agents Multimodal Generation Data Generation Pipelines Multimodal Agents Claw-Like Agent+2

Jun 19, 2026cs.LG

SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning

Semi-supervised learning (SSL) on data streams is challenging due to the continuous evolution of high-volume data and the scarcity of labels. Existing methods are limited in leveraging the intrinsic relationships among samples because they typically rely on fixed similarity measures or static graph structures, which cannot capture how relationships evolve over time. We propose SLeDGe, an SSL method for data streams that jointly learns a predictive model and an adaptive graph structure under strict memory and label constraints. SLeDGe maintains compact labeled and unlabeled memories using distinct update strategies, balancing rapid adaptation to novel features with the retention of historical consistency. In addition, by encouraging sparsity in the relational graph, SLeDGe filters out spurious connections and enables effective propagation of label supervision. Across 12 datasets, SLeDGe outperforms state-of-the-art competitors, achieving average relative accuracy gains of 31.7% with 0.1% labels and 14.8% with 1% labels.

Heechan Moon, Kijung Shin

KAIST, Seoul, Republic of Korea

Semi-Supervised Learning Graph Representation Learning Replay-Based Continual Learning Streaming Semantic Memory

Jun 18, 2026cs.SD

Zero-VC: Zero-Lookahead Streaming Voice Conversion via Speaker Anonymization

Streaming zero-shot voice conversion struggles to disentangle timbre from linguistic content without degrading utility or inflating latency. Current methods rely on information bottleneck (IB) or speaker perturbation. While IB filters out timbre, it discards prosody, forcing models to explicitly inject features like fundamental frequency. This often requires buffering future frames, creating algorithmic lookahead latency. On the other hand, existing perturbation methods largely overlook the crucial trade-off between timbre leakage and utility preservation. Recognizing this neglected trade-off, we find that the inherent objective of Speaker Anonymization (SA) aligns well with balancing these factors. Thus, we introduce SA as a novel perturbation mechanism to explicitly mitigate timbre leakage while retaining prosodic utility. Crucially, SA's robust representations significantly alleviate the generator's reliance on future context, enabling our strictly causal, zero-lookahead network. Audio samples are available at https://amphionteam.github.io/Zero-VC-demo/.

Yudong Li, Zihao Fang, Junwen Qiu +4

The Chinese University of Hong Kong, Shenzhen · Shenzhen Transsion Holdings Co., Ltd. · Shenzhen Loop Area Institute +1

Speaker Prosody Anonymization Streaming Lookahead

Jun 18, 2026cs.CL

When Does Streaming Tool Use Help? Characterizing Tool-Intent Stabilization in Streaming Retrieval-Augmented Generation

Streaming Retrieval-Augmented Generation (Streaming RAG) hides tool latency by issuing retrieval queries in parallel with the user's still-arriving input, before the utterance is complete. Speculation can only help, though, when the correct query becomes determinable before the user stops speaking or typing -- a property of the query, not the system. We name and measure this property, tool-intent stabilization: the point in the input stream at which a speculative query's retrieval converges on the answer-bearing result. On the CRAG benchmark (1371 validation questions) we (i) characterize how stabilization is distributed across queries; (ii) derive a model-agnostic bound H on the share of tool latency hideable behind the remaining input, given tool latency L and input cadence delta; (iii) validate it against a working streaming pipeline; and (iv) ask which query properties predict early versus late stabilization. Stabilization is typically early: at a realistic operating point a 73.9% streamable fraction of the benchmark admits latency hiding, and H acts as a conservative aggregate floor that realized savings meet or exceed -- though it does not predict savings query by query. Question type yields a statistically significant but small early/late split. The study needs no model training and runs on commodity CPU hardware; a dense-retriever replication confirms the early-stabilization effect is not a BM25 lexical artifact.

Elroy Galbraith

SMG Labs

Streaming Stabilization Convergence

Jun 18, 2026cs.CV

ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference

Streaming VideoLLMs must continuously process incoming video while maintaining low query latency, making both video-ingestion throughput and query-time responsiveness critical for real-time deployment. Existing methods largely focus on accelerating individual modules, such as visual encoding, token pruning, or KV-cache compression, but provide limited insight into whether the resulting system can sustain real-time streaming performance. We formulate streaming VideoLLM inference as a coordinated pipeline spanning visual preprocessing, visual encoding, token dropping, and LLM prefilling/decoding. Building on this formulation, we propose ViCoStream (Video Coordinated Streaming), a stage-wise coordinated streaming framework that combines chunk-wise execution, CUDA-stream overlap, visual token control, bounded visual attention, and query-side retrieval to bound per-chunk computation and memory costs. We further provide a systematic study of bottleneck migration, revealing how chunk size, token retention, attention locality, and retrieval scope shape the throughput-accuracy trade-off. Experiments with Qwen2.5-VL-3B/7B-Instruct across multiple streaming benchmarks show that ViCoStream achieves 134 FPS video throughput and less than 50 ms TTFT on a single A100 GPU while maintaining accuracy close to full-history baselines.

Yang Tan, Junlong Tong, Linan Yue +3

Southeast University · Eastern Institute of Technology, Ningbo · Shanghai Jiao Tong University

Streaming Video Streaming Key-Value Cache Compression False-Negative Rate

Jun 15, 2026cs.DB

Decoupling Inference from State Updates in Low-Latency Feature Engines via Probabilistic Thinning

Streaming data systems increasingly underpin Machine Learning workflows that maintain large numbers of continuously updated aggregations. In production settings, each incoming event typically triggers read-modify-write operations to persistent storage, making high-frequency state updates a dominant source of latency, contention, and operational cost. In this work, we decouple inference from state persistence in streaming Machine Learning pipelines via probabilistic thinning: every event is scored, but durable state updates are selectively triggered by informative events. Unlike approaches that shed input or state, we show that persistence-path control is achievable without a high-frequency in-memory control plane or cross-worker coordination, relying exclusively on approximate statistics retrieved from disk-backed key-value stores. We model the resulting stochastic processes, derive bounds on filtering rates, and prove that common time-based aggregations remain unbiased under variance-aware formulations, preventing systemic error accumulation. We evaluate the approach in a controlled setting that isolates per-event costs, demonstrating substantial reductions in storage Input/Output and serialization overhead. Across experiments, up to 90% of events are excluded from the persistence path while preserving and in some cases improving downstream utility.

Augusto Peres, Iker Perez, Pedro Valdeira +4

Feedzai

Streaming Persistence State-Tracking Variance Reduction

Jun 15, 2026cs.CV

What Should a Streaming Video Model Remember?

Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory and computation budgets. Existing methods address this by adding memory banks, retrieval modules, or visual token compression to preserve long-range history. However, strong recent-window baselines show that indiscriminate history injection can dilute current-scene perception, suggesting that the key challenge is not whether to use memory, but how to allocate it selectively. We formulate this as budgeted online latent evidence allocation and propose \textbf{SelectStream}, a selective latent-memory framework that keeps the current observation directly visible to a frozen VLM while exposing historical information only through a compact, query-conditioned evidence budget. Three coordinated mechanisms govern when to write, what to preserve, and how to retrieve: surprise-driven adaptive windowing, priority-preserving consolidation, and query-conditioned graph reasoning over a fixed-capacity latent memory graph. Retrieved evidence is calibrated and injected as latent tokens for answer generation, without replaying frames or growing the context with stream length. Experimental results show that SelectStream achieves strong online streaming performance and preserves general video understanding, reaching 82.67% on StreamingBench, 67.03% on OVO-Bench, and 74.4% average accuracy on offline video benchmarks, while outperforming strong recent-window baselines and prior streaming memory methods.

Haonan Ge, Yiwei Wang, Hang Wu +1

University of California, Santa Barbara · University of California, Merced · The University of Queensland

Streaming Video Understanding Streaming Long-Term Memory

Jun 12, 2026cs.SD

Efficiency-Performance Trade-offs in Neural Speaker Diarization via Structured Pruning and Low-Bit Quantization

Streaming speaker diarization is crucial for time-critical medical dispatch, but deploying it on resource-constrained hardware requires smaller, faster models. Using SIMSAMU, a dataset of simulated medical-dispatch conversations, we evaluate streaming behavior before compressing the segmentation model with pruning and low-bit quantization. We characterize performance across a range of streaming latency budgets and find that additional buffering is not consistently beneficial, while very low-latency operating points can substantially degrade performance. Our study shows that model compression trades performance for memory footprint, and we highlight an operating point where FP16 reduces model size by half with essentially unchanged real-time factor, at a cost of a 40% relative DER increase against the baseline. This work characterizes the trade-offs for real-time deployment and contributes to speech technology that can enable reliable human communication in time-critical contexts.

Rishit Chatterjee, Tahiya Chowdhury

Department of Computer Science, Colby College, Waterville, Maine, United States

Speaker Diarization Neural Speech Codecs Streaming Structured Pruning Trade-Off Emergency Departments+1

Jun 11, 2026cs.LG

Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting

Real-world time series are often highly incomplete and irregular due to sensor dormancy, transmission delays, and event-driven sampling, making reliable forecasting fundamentally challenging. Existing methods have evolved from impute-then-forecast pipelines to continuous-time models such as Neural ODEs and continuous-time graph networks. While these approaches improve the modeling of historical irregularity, they still rely on an implicit oracle assumption at inference time: the timestamps of future valid observations are presumed to be known in advance. This assumption limits practical relevance, since in many real systems the more fundamental question is not only what the future value will be, but also whether a valid observation will occur at all. In this paper, we propose Timeflies, a unified framework that reformulates forecasting as a joint problem of future observability inference and value estimation. To explicitly model the interaction between observation dynamics and state evolution, Timeflies adopts an observation stream and a value stream, coupled through three dedicated modules for reliability-aware embedding, observation-guided dependency modeling, and joint prediction. We further construct Shadow, a benchmark that combines natural missingness from public datasets with real-world industrial data, and introduce the Observation-Value Joint Entropy (OVJE) metric to comprehensively evaluate this coupled predictability. Extensive experiments show that Timeflies consistently outperforms existing methods, highlighting the importance of explicitly modeling future observability in time series forecasting with missing values. Code and dataset are available in https://github.com/ant-intl/Timeflies.

Yifan Hu, Hongzhou Chen, Peiyuan Liu +3

Ant International

Imputation Partial Observability Streaming

Jun 10, 2026stat.ML

Renewable Lasso without Batch-Number Constraints: A Gradient-Enhanced Approach

We study online estimation for high-dimensional generalized linear models with streaming data. First, for the non-distributed setting, we propose a gradient-enhanced surrogate loss that approximates the cumulative loss using only historical summaries, which modifies and improves upon the existing renewable estimation approach for the same model in the high-dimensional setting, and removes the batch-number constraint in previous studies. We then extend the method to distributed streaming data under the master-client architecture, where batches are partitioned across sites and only summaries (gradient vectors) are exchanged. Instead of directing applying the popular method of Jordan et al. (2019) to the surrogate quadratic loss, our adjusted approach does not require the clients to compute the full surrogate loss. We derive non-asymptotic error bounds under the high-dimensional scaling, without the stringent constraint on the number of batches in the previous studies. Simulation results under linear and logistic models, together with a real-data application, show improved accuracy over existing renewable estimators.

Junzhuo Gao, Ling Peng, Xu Guo +1

a Department of Mathematics, City University of Hong Kong, Hong Kong, China · e CityUHK Shenzhen Research Institute, Shenzhen, China[stat.ML] · b School of Statistics and Data Science, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China +2

Surrogate Gradient Stochastic Gradient Descent Streaming Structural Constraints Dynamic Rope Manipulation Image Enhancement

Jun 8, 2026stat.ML

Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising

We develop a decision-calibrated conformal framework for pacing decisions in streaming advertising. Pacing depends on uncertain future inventory, demand pressure, incremental response, and member-experience load. Instead of calibrating a generic forecast residual, the framework measures forecast error by its largest impact on the policies that could actually be deployed. The main theorem shows that the proposed score is the smallest valid uncertainty measure that uniformly protects all deployable pacing policies. Geometrically, it is the support function of the signed policy sensitivity set. Split conformal calibration gives finite-sample coverage for this score. A high-dimensional separation theorem shows that traditional residual calibration can be arbitrarily more conservative by paying for nuisance inventory dimensions, and a robust pacing result combines inventory, response, and experience uncertainty. On public-data-calibrated pacing replays built from Criteo Uplift and KuaiRand datasets, traditional conformal pacing remains unresolved with high residual radii of 7236.7 on Criteo and 4629.4 on KuaiRand. With the proposed decision calibration approach, the uncertainty radii are reduced to 18.4 and 278.6 respectively, with separate margins for value, delivery, budget, and member load. On Criteo, the proposed method certifies a less aggressive pacing policy than the point-forecast baseline, and reduces held-out any-violation rate from 16.7% to 3.3%, with zero budget and member-load violations. On KuaiRand, the choice remains unresolved. In a nutshell, the paper establishes that forecasts, response estimates, and member-experience models should be judged by whether they shrink the uncertainty that the pacing decision uses, as this leads to confident decisions that are not overly conservative.

Prashant Shekhar, Caroline Howard

Department of Mathematics Embry-Riddle Aeronautical University Daytona Beach, FL, USA

Calibrated Uncertainty Ads Uncertainty Streaming

Jun 8, 2026cs.LG

Structured Adaptive Tensor Prediction for Streaming Data

Matrix-valued time series arise in a wide range of applications, such as spatio-temporal data from medical imaging and geophysics. Existing methods are mainly designed for static settings and lack adaptability to streaming and time-varying environments. Adaptive filtering techniques have also been largely limited to data with scalar or vector values, leaving adaptive forecasting for matrix-valued time series inadequately understood. To bridge these gaps, we develop an adaptive tensor regression framework that includes Matrix-on-Matrix (MoM) and Tensor-on-Matrix (ToM) formulations for streaming matrix-valued prediction. The two formulations differ in whether to directly model matrix-valued outputs or to exploit temporal structure via higher-order tensor representations. For the proposed tensor regression framework, we develop stochastic gradient descent (SGD) algorithms for online learning. We show that stacking multiple responses across time into higher-order tensors improves performance; in particular, the ToM achieves lower steady-state error and stronger denoising capability than MoM, motivating our focus on the ToM model. We further characterize the tracking behavior of SGD under time-varying dynamics. From a statistical perspective, we establish fixed-time recovery guarantees for ToM under general low-dimensional structures, including sparsity, low-rankness, and their joint sparselow-rank models.

Zhen Qin, Yang Chen

Michigan Institute for Computational Discovery and Engineering, Department of Statistics, Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI 48109 USA · Department of Statistics, University of Michigan, Ann Arbor, MI 48109 USA

Multivariate Time-Series Autoregressive Model Streaming

Jun 8, 2026cs.CV

Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?

Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos. This opens the door to the use of video (and multimodal) large language models (LLMs) as task guidance assistants. A crucial capability for the real-world success of a prospective task guidance assistant is it's ability to intervene proactively as soon as a mistake is apparent in order to guide the user. To evaluate this crucial capability, we introduce Ego-MC-Bench (Mistake Corrections), a benchmark for evaluating reactive, step-by-step task guidance in realistic cooking scenarios. Extensive experiments show that Ego-MC-Bench is highly challenging for state-of-the-art video LLMs. We argue that a key reason is the limited availability of training data for fine-tuning models on this task. Although there exists a wide range of cooking video datasets, existing datasets lack examples of mistakes along with appropriately timed interventions. To help address this data limitation, we also introduce Ego-CoMist, a counterfactual synthetic dataset created by transforming non -interactive cooking videos into supervised training examples showing proactive interventions. We show that fine-tuning on Ego-CoMist yields performance gains especially for smaller and more efficient video LLMs that are well suited for delivering assistance on edge devices.

Apratim Bhattacharyya, Shweta Mahajan, Sanjay Haresh +5

Qualcomm AI Research · York University · Vector Institute for AI

Large Language Models Fail Instruction-Tuned Models Video Dataset Streaming

Jun 8, 2026cs.CV

Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions

While recent autoregressive video diffusion models achieve remarkable streaming quality, they remain confined to low resolutions (e.g., 480P), leaving efficient, scalable, real-time high-resolution video generation a fundamental open challenge. To bridge this gap, we present Ultra Flash, a cascaded streaming framework capable of real-time high-resolution video generation. Ultra Flash achieves ~30 FPS at 1K resolution and ~18 FPS at 2K resolution on a single GPU through three key contributions: (1) an architecture-preserving T2V-to-TV2V super-resolution training paradigm coupled with an AIGC-oriented data degradation pipeline that effectively preserves the generative capability of the base model, enabling enhanced high-resolution detail when cascaded after mainstream low-resolution generative models; (2) a causal streaming latent upsampler paired with a high-resolution decoder, which enhances spatiotemporal coherence while enabling efficient latent spatial scaling and precise high-resolution decoding with negligible computational overhead; and (3) a cascade high-resolution streaming video generation optimization scheme that first performs hybrid-reward-enhanced sparse causalization and single-step distillation of the super-resolution model, then introduces cascaded streaming self-forcing preference optimization with dynamic cache management, jointly enhancing overall coherence, improving quality, and enabling real-time high-resolution streaming video generation. Extensive experiments demonstrate that Ultra Flash reliably produces ultra-high-resolution streaming video while maintaining state-of-the-art visual quality and superior efficiency. Project Page: https://xin1u.github.io/UltraFlash/

Luxury, Jie Huang, Zihao Fan +25

1JD Explore Academy · 2USTC · 3PKU +6

Autoregressive Video Diffusion Models Video Generation High-Resolution Streaming Flash

Jun 8, 2026eess.AS

FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation

Recent progress in speech dialogue systems requires Text-to-Speech (TTS) models to be faster and more responsive. Modern speech dialogue systems impose two primary requirements on TTS models: low latency and support for streaming inputs and outputs. However, most existing single-codebook LLM-based TTS methods rely on multi-stage pipelines that lack native streaming capabilities. These systems typically suffer from high end-to-end latency due to slow autoregressive prediction and multi-step flow matching. To address these limitations, we propose FlashTTS, an open-source and low-latency streaming TTS framework. FlashTTS introduces a lagged multi-track architecture that natively processes streaming text and speech inputs, thereby eliminating the need for sentence-level buffering. To accelerate acoustic generation, we integrate parallel Multi-Token Prediction (MTP) with an X-pred mean flow matching decoder. This configuration achieves high-fidelity token-to-mel generation in exactly two function evaluations (2-NFE). By jointly optimizing input processing and decoding efficiency, FlashTTS offers a practical foundation for real-time speech dialogue systems. Experiments show that FlashTTS substantially reduces First-Packet Latency to 325ms compared to robust streaming baselines, all while preserving strong zero-shot voice cloning and cross-lingual intelligibility. Speech samples are available. The model code and checkpoints will be released as open source.

Hanke Xie, Xiaming Ren, Dake Guo +10

Huawei Technologies Co., Ltd

Text-To-Speech Synthesis Streaming Multi-Token Prediction Flash

Jun 8, 2026eess.AS

MeanVC 2: Robust Low-Latency Streaming Zero-Shot Voice Conversion

Streaming zero-shot voice conversion (VC) has become increasingly popular due to its potential for real-time applications. The recently proposed MeanVC achieves lightweight streaming zero-shot VC, but it has several limitations: its chunk-wise autoregressive denoising doubles the effective training sequence length, conversion quality degrades under small-chunk settings, and its timbre encoder directly relies on reference mel-spectrograms, making it sensitive to reference audio quality. To address these limitations we propose MeanVC 2. We introduce future-receptive chunking (FRC), which explicitly schedules past and future receptive fields across diffusion transformer decoder layers and removes clean-chunk teacher forcing. By incorporating bounded future context, FRC enables stable conversion with a 40 ms chunk size. We further introduce a universal timbre token encoder, which constructs a timbre representation from a global speaker embedding and retrieves fine-grained timbre cues via cross-attention, improving robustness to low-quality references and enhancing zero-shot speaker similarity. Experimental results show that MeanVC 2 significantly outperforms MeanVC, while reducing latency from 211 ms to 110 ms. Audio samples are publicly available. The source code will be publicly released.

Guobin Ma, Yuxuan Xia, Yuepeng Jiang +6

The University of New South Wales, Australia · WeNet Open Source Community, China

Voice Conversion Streaming Zero-Shot Autoregressive Diffusion

Jun 6, 2026cs.LG

A Unifying View of Attention Sinks: Two Algorithms, Two Solutions

When attention concentrates on a single token, a sink, what is the model actually computing? Attention sinks are ubiquitous in softmax transformers, yet this shared visual signature can hide fundamentally different algorithms. We show that visually similar sink patterns can reflect two distinct mechanisms: {i} adaptive nop, where a head suppresses its update by routing to a null token, and {ii} broadcast, where a sink aggregates and redistributes global information. In that case, sinks serve an analogous role: a safe destination when there is nothing useful to compute. Proposed interventions like gating or registers work because they implicitly target one or the other, revealing a duality between method and assumed mechanism: gating implicitly assumes nop; registers implicitly assume broadcast. Each mechanism leaves distinct traces (nop sinks exhibit negligible value norms; broadcast sinks induce low-rank outputs) which we formalize on synthetic tasks and use to derive practical diagnostics. Applied to pretrained vision transformers, these diagnostics reveal that both mechanisms exist at scale: sinks transition from CLS in early layers to patches in deeper layers, and concentrate in specialized heads. Strikingly, register tokens, designed for broadcast, are repurposed to also serve nop, confirming that neither intervention alone suffices. Combining gating with registers yields complementary gains in stability and performance. Overall, we find that the same attention pattern can reflect two very different computations and effective intervention requires first asking what the model is actually computing.

Lukas Fesser, Mozes Jacobs, Thomas Fel +2

Kempner Institute Harvard University Cambridge, MA

Perspective Streaming Synthetic Task

Jun 5, 2026cs.CV

Streaming Video Generation with Streaming Force Control

We introduce StreamForce, a streaming video generation framework that enables physically grounded control through continuous force inputs. Unlike prior video models that train separate models for different force types, assume fixed forces, or rely on non-causal processing, StreamForce is a causal and unified model that responds instantly and coherently to both local and global, time-varying forces. To achieve this, we design a unified force representation as a control signal and develop a distillation pipeline for force-controllable video generation. Our model combines autoregressive efficiency with force responsiveness, sustaining stable photometric and dynamic realism. StreamForce runs at up to 16.6 FPS on a single GPU, achieving state-of-the-art performance in both force adherence and motion realism. Project website: https://neu-vi.github.io/StreamForce/

Hanhui Wang, Yiming Xie, Haiwen Feng +3

1Northeastern University · 2Impossible Research · University of California, Berkeley +1

Streaming Unified Representation

Jun 5, 2026cs.CV

STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation

Synthetic histopathology image generation addresses critical challenges in computational pathology, including patient privacy and the growing need for large-scale training data for foundation models. Latent diffusion models have dominated the image generation domain, with recent works emphasizing that the choice of latent space is critical to the quality of generated images. Existing state-of-the-art generative models in histopathology use pretrained Vision Foundation Models (VFMs) as conditioning signals, and we observe that this leads to "conditioning collapse," where the conditioning signal dominates the latent space and lowers the quality and diversity of generated samples. Therefore, we instead use pretrained histopathology VFMs as the latent space itself, leveraging their patch-token features that encode rich semantic information. We empirically show that these features are

\ell_2

-normalized and lie on the unit hypersphere

\mathcal{S}^{d-1}

with strong angular dominance and intrinsic curvature, making them naturally suited for a Riemannian formulation. We therefore present STREAM, the first framework to apply Riemannian flow matching in the pathology domain. STREAM consists of two stages: 1) a bridge-type stochastic perturbation that establishes per-token rectifiability on

\mathcal{S}^{d-1}

for training a Diffusion Transformer (DiT) in latent space, and 2) a novel anisotropic decoder that allocates robustness to low-energy directions of the velocity-field Jacobian while preserving fidelity along its high-energy directions. Together, STREAM achieves state-of-the-art reconstruction and generation performance on breast and colorectal cancer datasets. The code will be publicly released upon acceptance.

Won June Cho, Daeky Jeong, Hyeongyeol Lim +1

DEEPNOID Inc.

Diffusion Transformers Riemannian Flow Matching Latent Space Streaming Collapse

Jun 3, 2026cs.CL

Streaming Communication in Multi-Agent Reasoning

Multi-agent reasoning systems adopt a "generate-then-transfer" paradigm that forces end-to-end latency to scale linearly with pipeline depth. We introduce StreamMA, a multi-agent reasoning system that streams each reasoning step to downstream agents as soon as it is generated, pipelining adjacent agents and thus reducing latency. Surprisingly, this pipelining also improves effectiveness: because multi-step reasoning quality is non-uniform and early steps are more reliable than later ones, working with these reliable early steps instead of the full chain prevents error-prone late steps from misleading downstream agents. We formalize both advantages with the first closed-form joint analysis of stream, serial, and single protocols, deriving the effectiveness ordering, speedup upper bound, and cost ratio. Across eight reasoning benchmarks spanning mathematics, science, and code, two frontier LLMs (Claude Opus 4.6 and GPT-5.4), and three topologies (Chain, Tree, Graph), StreamMA outperforms both baselines (avg. +7.3 pp, max +22.4 pp on HMMT 2026; Claude Opus 4.6-high). Beyond these contributions, we discover a "step-level scaling law": increasing per-agent steps consistently improves both effectiveness and efficiency, a new scaling dimension orthogonal to and composable with agent-count scaling.

Zhen Yang, Xiaogang Xu, Wen Wang +3

HKUST(GZ) · ZJU · Alibaba Group +1

Multi-Agent Reasoning Streaming Rate Scaling Scaling Laws

Jun 2, 2026cs.DC

UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute stragglers, token all-to-all bottlenecks, and activation-memory spikes. Existing balancers redistribute experts periodically based on historical load, which becomes unreliable for production deployments with non-stationary load patterns. We present UltraEP, the first exact-load, real-time balancer for large-EP MoE training and serving prefill on rack-scale nodes (RSNs). Leveraging the extended scale-up connectivity among dozens of GPUs within RSNs, UltraEP rebalances every microbatch and layer on critical paths, which requires nontrivial co-design of plan solving and expert replication communication to minimize exposed overhead. To this end, UltraEP eagerly reacts to post-gating load with an efficient quota-driven planner, and executes the resulting irregular expert-state transfers with RSN-native persistent tile streaming and relay-based fan-out mitigation. We evaluate UltraEP in a multi-RSN deployment of up to 256 GPUs, using cutting-edge MoE models from 106B to 671B parameters. Averaged across training and serving, UltraEP achieves 94.3% of the force-balanced ideal throughput, delivering 1.49

\times

improvement over no-balancing, while reducing the final inter-rank imbalance from 1.30

-

4.01 to 1.01

-

1.04.

Xinming Wei, Chao Jin, Tuo Dai +10

School of Computer Science, Peking University · Xiaohongshu Inc. · Shanghai AI Laboratory +1

Load Balancing Mixture-Of-Expert Inference Mixture-Of-Experts Ultrafast Streaming

Jun 2, 2026cs.CV

FreeStreamGS: Online Feed-forward 3D Gaussian Splatting from Unposed Streaming Inputs

Feed-forward 3D Gaussian Splatting (3DGS) allows efficient and high-fidelity novel view synthesis (NVS) from an offline recorded image sequence. However, achieving online NVS from streaming and unposed image inputs remains challenging. Although online feed-forward geometric estimation methods have been proposed for streaming depth and point cloud recovery, they cannot be adapted to NVS due to severe rendering artifacts. This is because NVS demands stricter multi-view consistency in Gaussian scales and pose-geometry alignment; even minor deviations would accumulate over time and visibly degrade rendering quality. To this end, we propose FreeStreamGS, a robust online feed-forward framework for efficient and high-quality NVS. We introduce two key mechanisms: a Decoupled Intrinsic Recovery Head that removes cumulative camera intrinsic bias and prevents scene scale jitter during long-term streaming, and a Dynamic Point Refinement Offset strategy that relaxes rigid unprojection to correct coupled pose-depth drift. Extensive experiments show that FreeStreamGS achieves rendering quality competitive with state-of-the-art offline feed-forward 3DGS methods, despite operating without access to future frames.

Ruiyang Chen, Feiran Li, Chu Zhou +3

Beijing University of Posts and Telecommunications, China · Independent Researcher · National Institute of Informatics, Japan

Feed-Forward 3D Gaussian Feed-Forward 3D Gaussian Splatting Novel View Synthesis Streaming Camera Point Clouds

Jun 1, 2026cs.CV

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding

While video streaming understanding has made significant strides, real-world applications, such as live sports broadcasting, autonomous driving, and multi-screen collaboration, inherently demand continuous, multi-stream interactions. However, existing benchmarks are confined to single-stream paradigms, leaving a critical gap in evaluating online, cross-stream reasoning. To bridge this, we introduce X-Stream, the first benchmark dedicated to multi-stream streaming understanding. Comprising 4,220 rigorously curated QA pairs across 932 videos, X-Stream evaluates 11 subtasks across multi-window, multi-view, and multi-device scenarios. Crucially, our dataset is constructed using a novel dual-verification pipeline that prevents over-reliance on a single stream. Furthermore, we pioneer the conceptualization of multi-modal large language models (MLLMs) as naive multiplexers, systematically evaluating their performance through the lens of Signal Multiplexing Theory. Our extensive online inference experiments reveal a stark reality: state-of-the-art MLLMs struggle significantly with concurrent streams, achieving only about 50% score and exhibiting poor proactive ability. Ultimately, X-Stream exposes the trade-off of current multiplexing schemes, providing both a practical evaluation protocol and empirical guidance for next-generation multi-stream agents.

Peiwen Sun, Xudong Lu, Huadai Liu +10

MMLab, Chinese University of Hong Kong · Hong Kong University of Science and Technology · Huawei Research

Streaming Multimodal Large Language Models Fast Inference

May 28, 2026cs.CV

Dex2HOI: Dexterous Bimanual Two-Object Interaction Generation

Recent advances in 4D Human-Object Interaction (HOI) generation have enabled increasingly realistic motion synthesis, particularly for single-object manipulation. Yet current research overlooks an inherent property of human behavior: people naturally coordinate both hands and manipulate multiple objects simultaneously. To address this gap, we present Dex2HOI, a unified diffusion model for single- and two-object HOI synthesis from text. At its core, Dex2HOI employs a Dual-Stream Diffusion approach, where each object is processed in a dedicated interaction stream and coordinated through bidirectional cross-attention. To synthesize the final motion, we introduce a Motion Fusion Network integrated with novel hand-relative object representations and contact-aware conditioning applied across the whole sequence. By sampling the diffusion process autoregressively over prefix-conditioned windows, Dex2HOI generates arbitrarily long sequences at real-time speed omitting redundant test-time optimization, achieving up to x540 inference speed-up over prior state-of-the-art methods. Extensive evaluation on both single- and two-object benchmarks demonstrates state-of-the-art quantitative results, marking a step beyond conventional single-object HOI generation and toward expressive multi-object manipulation. Project: https://cpratikaki.github.io/dex2hoi/

Chrysa Pratikaki, Pablo Ruiz-Ponce, Jiankang Deng +2

Imperial College London, UK · University of Alicante, Spain

Hand-Object Interaction Detection Articulated Objects Human Motion Generation Bimanual Manipulation Streaming

May 28, 2026cs.AI

Make LLM Learn to Synthesize from Streaming Experiences through Feedback

Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing studies treat synthesis as a set of isolated tasks and overlook a more fundamental question: whether a model can learn to synthesize by accumulating experience from past tasks and transferring it to future ones. In this work, we introduce StreamSynth, a new setting in which synthesis tasks arrive sequentially and experience from historical tasks provides informative signals for future synthesis. To address this setting, we propose SynLearner, a general framework that enables synthesis models to acquire reusable synthesis experience over a task stream. Instead of generating data independently for each task, SynLearner encourages the model to explore diverse synthesis patterns, learn from feedback, and balance sample quality with set-level diversity as tasks evolve. Extensive experiments across multiple benchmarks show that SynLearner effectively leverages experience from earlier tasks to improve synthesis performance on later ones, exhibiting consistent cross-task transferability. These findings provide evidence for the feasibility of StreamSynth and highlight synthetic data generation as an experience-driven process that can benefit from task streams.

Zhenlin Hu, Yan Wang, Zhen Bi +7

Huzhou Normal University · Alibaba Group · Zhejiang Key Laboratory of Intelligent Education Technology and Application +1

Synthesizer Synagent Synthesis Streaming Feedback

May 27, 2026cs.CV

DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing

We study real-time audio-responsive character control as a deployment-faithful problem: strictly causal, bounded-latency streaming that must generate coherent full-body motion at interactive frame rates while the audio condition can change abruptly, including tempo shifts, drops, or user edits. Prior music-to-motion systems are largely optimized for offline generation with global context, and degrade in streaming rollouts where conditioning history becomes stale or unreliable. We introduce DiscoForcing, a streaming audio-driven diffusion framework that combines a causal music encoder that captures rhythmic structure and phase dynamics with a diffusion-forcing sequence model trained under heterogeneous noise levels across the temporal horizon. Building on this, we design a hybrid temporal schedule and a history-guided streaming sampler to explicitly trade off responsiveness against long-horizon consistency under non-stationary audio. Implemented in an end-to-end real-time interactive system with online avatar playback and humanoid deployment workflows, DiscoForcing delivers more stable long-horizon rollouts and sharper audio-motion alignment than prior baselines under matched causality and latency constraints while maintaining real-time throughput.

Kaiyang Ji, Bingsheng Qian, Binghuan Wu +3

1ShanghaiTech University · 2InstAdapt.

Duet Autoregressive Diffusion Human Motion Generation Real-Time Systems Streaming Whole-Body Motion+1

May 27, 2026cs.CV

EchoAvatar: Real-time Generative Avatar Animation from Audio Streams

Real-time synthesis of high-fidelity 3D character motion from audio is a pivotal component for next-generation interactive avatars and virtual assistants. However, most existing approaches are limited to offline processing of complete audio sequences or are constrained to specific domains, rarely handling both speech and music effectively. In this paper, we introduce a novel framework designed to generate continuous, coherent full-body motion from streaming speech and music with low latency. Central to our approach is a unified streaming architecture capable of synthesizing continuous motion from incremental audio inputs. We employ a robust training strategy that enforces strong audio dependency, allowing the model to seamlessly generalize across conversational speech and rhythmic music without requiring explicit domain labels or mode switching. Additionally, we explored Reinforcement Learning to refine the quality of online generation. Furthermore, we bridge reactive animation with intent-driven behavior via a tool-call interface that allows upstream Large Language Models to inject explicit semantic control. By combining this controllability with stream audio-driven synthesis, our framework serves as a plug-and-play solution for transforming voice agents into interactive humanoid avatars. Extensive experiments demonstrate that our method outperforms state-of-the-art realtime baselines in motion quality and synchronization while maintaining the flexibility required for live deployment. Our code, pre-trained models, and videos are available at https://robinwitch.github.io/EchoAvatar-Page.

Bohong Chen, Yumeng Li, Yinglin Xu +3

State Key Lab of CAD&CG, Zhejiang University, China

Avatars Human Motion Generation Streaming Audio Understanding

May 27, 2026cs.LG

RW-TTT: Batched Serving for Request-Owned Test-Time Training State

Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streaming learner state. This breaks batched LLM serving, which assumes shared static weights: serial execution is correct but slow, while naive batching can corrupt request state. We formulate this problem as read-write TTT serving and present RW-TTT , which tags each decode step with its owner, version, and READ/WRITE effect, batches only compatible phases, and commits updates only to the owner. On one GPU with eight fast-weight InPlace-TTT streams, RW-TTT reaches 274.61 aggregate tok/s, 9.31x over sequential serving and 3.44x over per-stream replicas under the same memory budget. It preserves behavior on RULER, a long-context benchmark, and passes owner/version checks.

Jian Yang, Zhizhuo Kou, Yao Tian +4

1The Hong Kong University of Science and Technology · 2The Chinese University of Hong Kong · 3National University of Singapore

Large Language Model Serving Time-To-First-Token Test-Time Training Streaming

May 26, 2026cs.AI

OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs

Audio-visual large language models (LLMs) hold strong promise for long-form video understanding, yet their long-video inference is fundamentally limited by the linear growth of video tokens and key-value (KV) caches. We present OmniMem, a memory-efficient streaming framework designed specifically for audio-visual LLMs. Unlike existing compression methods that treat all tokens uniformly, OmniMem introduces a modality-aware memory allocation strategy that separately manages visual and audio contexts, addressing the severe token imbalance between the two modalities. OmniMem further preserves informative and non-redundant KV states through perturbation-aware memory selection, enabling compact memory without sacrificing long-range understanding. To strengthen compression under realistic deployment constraints, we also explore budget-aware fine-tuning, which encourages the model to consolidate useful information into retained memory. Experiments on VideoMME Long, LVBench, and LVOmniBench with video-SALMONN 2+ and Qwen-2.5-Omni show that OmniMem consistently improves over strong training-free compression baselines by 2-4% absolute accuracy under the same memory budgets, with an additional 1-2% gain after fine-tuning.

Guangzhi Sun, Yixuan Li, Yudong Yang +1

ByteDance · Department of Engineering, University of Cambridge · Tsinghua University

Modern Data-Streaming Systems Large Audio Language Models Streaming Omnimem