Multimodal Foundation Models

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 117% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 303

Jun 10, 2026cs.CV

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video. In this paper, we propose MultiToP, a multimodal-context-aware visual token patching framework that mitigates hallucinations by refining unreliable visual tokens before language generation. MultiToP introduces a lightweight Visual Token Patcher to predict token-level replacement distributions and selectively substitute unreliable visual tokens with a dynamic global patch token. To train the patcher effectively, we further propose information-guided rank calibration, which uses answer-conditioned frame-level information cues derived from the backbone to guide token replacement. Combined with ground-truth answer supervision and sparsity regularization, MultiToP enables localized visual evidence refinement without modifying the original model. Extensive experiments demonstrate that MultiToP effectively reduces hallucinations on Vript-HAL with negligible inference overhead, improving the F1 scores of Qwen3-VL-4B-Instruct by 50.60% over the vanilla model. Meanwhile, MultiToP preserves general video understanding ability, yielding an 18.58% relative accuracy gain on ActivityNet-QA for Video-LLaVA-7B.

Yuansheng Gao, Wenbin Xing, Jiahao Yuan +4

Zhejiang University · Sun Yat-sen University · East China Normal University

Video-Language Models Multimodal Foundation Models VLM Hallucination Mitigation Multimodal Understanding

Jun 9, 2026cs.CV

ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations

This paper introduces ARM, a discrete representation-based AutoRegressive Model that unifies image understanding, generation, and editing within a next-token prediction framework. ARM is built on three efforts: first, we train a discrete semantic visual tokenizer that maps images into compact token sequences. Our tokenizer is supervised with multiple objectives that jointly promote semantic discriminability, language alignment and faithful reconstruction, thereby supporting diverse tasks in a shared latent space. With this, we train a 7B autoregressive model over large-scale text and image token sequences, seamlessly developing vision-language perception and generation capabilities. Finally, to further improve preference-aligned behavior for text-to-image generation and instruction-guided editing, ARM applies reinforcement learning (RL) to optimize task-level objectives such as visual quality, instruction adherence, and edit consistency. Surprisingly, the results show that RL not only substantially improves performance on the target tasks (e.g., raising WISE overall from 0.50 to 0.56, GEdit-Bench-EN G_O from 5.75 to 6.68), but also induces cross-task synergy between text-to-image generation and editing. Collectively, these findings highlight autoregressive modeling, when paired with strong representations and preference optimization, as a scalable foundation for multimodal intelligence. Code: https://github.com/wdrink/ARM.

Junke Wang, Xiao Wang, Jiacheng Pan +16

Institute of Trustworthy Embodied AI, Fudan University

Text-Guided Image Editing Unified Multimodal Models Visual Tokenization Autoregressive Image Generation Multimodal Foundation Models

Jun 9, 2026cs.CV

Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks

RS-MLLMs enable natural-language understanding and spatial reasoning over earth observation imagery. However, existing models support only a narrow range of sensor types and tasks, yielding a fragmented view of the earth and leaving cross-modal geoscientific knowledge largely unexploited. This work presents Earth-OneVision, a 2B RS-MLLM that unifies six sensor modalities (i.e., optical, SAR, infrared, multispectral, temporal, and video) and cross-sensor fusion across 9 task categories within a single autoregressive framework. Three dedicated mechanisms address three bottlenecks. Full-Granularity Vision-Language Alignment (FGVLA) aligns multi-level visual features with the multi-dimensional language space. Spatial-Linguistic Isomorphic Serialization (SLIS) unifies heterogeneous spatial outputs as autoregressive tokens. Progressive Cross-Modality Adaptation (PCMA) decomposes the compound domain gap into sequential stages, tackling the viewpoint and imaging physics gaps in turn. To support joint training, MMRS-OneVision is constructed with ~34M QA pairs spanning all six sensor modalities and cross-sensor fusion across 9 task categories, substantially exceeding existing RS multimodal instruction datasets. With only 2B parameters, Earth-OneVision achieves competitive or state-of-the-art results across extensive benchmarks, consistently matching or outperforming 4B-72B RS-MLLMs. It achieves 87.52% [email protected] on the OPT-RSVG testset for optical visual grounding and 80.68% on the SAR VQA benchmark SARLANG-Bench, exceeding 7B models by over 7%. It further achieves 75.74% recall on the BigEarthNet-MS testset for multispectral classification, and 81.94% MCQ accuracy on EarthMind-Bench for cross-modality reasoning.

Miaoxin Cai, Guanqun Wang, Wei Zhang +6

National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing (SBIIP), Beijing Institute of Technology, Beijing 100081, China · Advanced Research Institute of Multidisciplinary Sciences, Beijing Institute of Technology, Beijing 100081, China · School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China +5

Remote Sensing Image Understanding Multimodal Grounding Remote Sensing VQA Multimodal Large Language Models Multimodal Reasoning Multimodal Foundation Models+2

Jun 9, 2026cs.CV

Kwai Keye-VL-2.0 Technical Report

We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To address the challenges of ultra-long contexts, information redundancy, and prohibitive computational costs inherent in hour-level videos, Keye-VL-2.0 is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based multimodal architectures, enabling lossless 256K context processing while capturing critical frames and long-range temporal dependencies. This architecture is underpinned by a highly optimized training and inference infrastructure, including scalable video I/O, heterogeneous ViT-LM parallelism, and custom DSA kernels that significantly maximize throughput and minimize computational overhead. Furthermore, to overcome the algorithmic dilemma of catastrophic forgetting during multi-task alignment, we introduce Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) paired with Context-RL and Video-RL. By distilling dense token-level teacher feedback from on-policy rollouts back into the MoE backbone, which activates only 3B parameters, Keye-VL-2.0 natively empowers advanced agent collaboration across Code, Tool, and Search scenarios with multimodal self-correction. Extensive evaluations across video understanding, temporal grounding, reasoning, STEM, and agent benchmarks demonstrate that Keye-VL-2.0-30B-A3B achieves state-of-the-art performance among models of similar scale, particularly excelling in fine-grained temporal localization on TimeLens and long-video comprehension on Video-MME-v2 and LongVideoBench. We release our model checkpoints to accelerate community progress toward scalable and robust multimodal agentic applications.

Kwai Keye Team, Bin Wen, Changyi Liu +50

Temporal Video Grounding Long-Context Modeling On-Policy Distillation Multimodal Foundation Models Multimodal Agents Temporal Video Understanding+1

Jun 8, 2026cs.SD

RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification

Respiratory diseases remain a leading cause of global mortality, where timely and accurate diagnosis is critical to improving patient outcomes and reducing healthcare burdens. While prior work has explored audio-based models for respiratory disease detection, such unimodal approaches often suffer from limited generalizability and diagnostic precision. In this paper, we propose RespiraMFM, a Multimodal Foundation Model that integrates respiratory sounds with patient medical history and symptoms to enhance diagnostic accuracy and disease detection capabilities. We introduce an effective contrastive alignment strategy for audio-text multimodal integration, allowing the model to learn better cross-modal representations between respiratory sounds and corresponding textual clinical information. We evaluate RespiraMFM across five major respiratory diseases using seven real-world datasets in both supervised fine-tuning and zero-shot settings, achieving a 9.15% improvement in AUROC on supervised tasks and a 20.98% gain on zero-shot tasks over existing baselines. These findings underscore the potential of our framework to advance early diagnosis and improve clinical decision-making in respiratory disease management.

Shakhrul Iman Siam, Tiantian Feng, Jiankun Zhang +2

The Ohio State University · University of Southern California · University of Chicago

Healthcare Audio-Language Models Multimodal Foundation Models Multimodal Contrastive Learning Audio Classification Multimodal Learning+1

Jun 8, 2026cs.AI

Next-Token Prediction Learns Generalisable Representations of Sleep Physiology

Foundation models offer a promising route to compress multi-modal physiological signals into compact representations of human health, with broad applications across sleep medicine, cardiology, neurology and other healthcare domains. Existing models have typically been trained with masked-reconstruction or contrastive objectives. However, masked reconstruction may be poorly suited to the stochastic nature of these signals, while contrastive approaches rely on positive-pair definitions despite the semantic invariances of physiological signals being poorly understood. In this work, we show that next-token prediction is a simple and scalable alternative. We develop Hypnos, a multi-modal sleep foundation model trained using eight different sensing modalities (e.g. EEG, ECG, respiratory signals) drawn from over 20,000 overnight polysomnography recordings. We tokenize each modality into streams of discrete tokens using residual vector quantization, then train a large auto-regressive RQ-Transformer to jointly predict the next token across all modalities in parallel. After training, Hypnos can be applied to continuous streams of sensor data from any subset of supported modalities, generating embeddings for downstream tasks. Across a range of benchmarks, Hypnos significantly outperforms existing foundation models. In sleep stage classification, we match the performance of strong supervised baselines on held-out test sets whilst using

100\times

less labelled data. Hypnos even generalises to daytime physiology, surpassing a dedicated ECG foundation model at detecting atrial fibrillation. Our results demonstrate that next-token prediction is a strong self-supervised objective for representation learning from multi-modal physiological signals.

Jonathan F. Carter, Lionel Tarassenko

Institute of Biomedical Engineering University of Oxford

Sleep Stage Classification Time Series Classification Self-Supervised Time Series Representation Learning Multimodal Pretraining Next-Token Prediction Multimodal Foundation Models+2

Jun 8, 2026cs.AI

AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models

Multimodal Foundation Models (MFMs) have made substantial progress, yet remain fragile in spatial reasoning over the physical world. A key bottleneck lies in their inability to transform local egocentric observations into a global allocentric spatial representation. To address this, we propose AlloSpatial, an agentic framework for allocentric spatial cognition in foundation models. AlloSpatial introduces World2Mind, a plug-and-play cognitive mapping sandbox that converts egocentric observations into structured allocentric priors, including Allocentric-Spatial Trees and route maps that support querying object topology, geometric relations, passability, and trajectories. To utilize these priors reliably under noisy reconstruction and ambiguous visual evidence, AlloSpatial introduces a Spatial Reasoning Harness for tool-use judgment, modality-decoupled cue collection, and geometry-semantic arbitration. We further internalize this process in Qwen3-VL through cold-start reinforcement learning with a harness-gated trajectory-level reward. Experiments on VSI-Bench and MindCube show that AlloSpatial improves proprietary models by 5%-18% in a training-free setting, while ASTs alone support strong spatial reasoning even when visual inputs are removed. The trained AlloSpatial agents further outperform larger general-purpose models and competitive spatial baselines, suggesting that structured allocentric representations, active tool use, and verifiable reasoning offer a promising route toward spatially capable foundation models.

Shouwei Ruan, Bin Wang, Zhenyu Wu +5

Institute of Artificial Intelligence, Beihang University · Huawei Noah’s Ark Lab · University of Science and Technology Beijing

VLM Reasoning Multimodal Foundation Models Spatial Reasoning

Jun 6, 2026cs.CV

Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning

Test-time Scaling (TTS) has emerged as a pivotal research direction for enhancing model performance by dynamically allocating computational resources during inference. Recent advancements have adapted this paradigm to Multimodal Foundation Models (MFMs), unlocking their potential in multimodal reasoning and generation. Despite rapid progress, the field lacks a systematic survey and unified theoretical framework to delineate the developmental landscape of multimodal TTS. To bridge this gap, we present the first comprehensive review of TTS research for MFMs, proposing a unified taxonomic framework that categorizes existing methodologies into three distinct strategies: sampling-based, feedback-based, and search-based approaches. We further summarize representative applications and benchmarks commonly utilized to evaluate multimodal TTS capabilities in generation and reasoning tasks. Finally, this survey discusses open challenges and outlines future research directions, providing a systematic roadmap for subsequent studies in this rapidly evolving field.

Cong Wan, Ying He, Zhongzhan Huang +1

Sun Yat-sen University

Test-Time Scaling Multimodal Reasoning Multimodal Generation Multimodal Foundation Models Multimodal Learning

Jun 4, 2026cs.AI

TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models

Time series foundation models (TS-FMs) aim to learn generalizable temporal representations that can be adapted to a wide range of downstream tasks. In real-world multimodal settings, time series are frequently affected by temporal misalignment and partial modality missingness, where different modalities are observed at heterogeneous time scales or are partially absent. Existing approaches typically rely on naive imputation or masking strategies, which fail to account for cross-modal dependencies and often lead to misaligned or degraded representations. We propose TRACE, a conditional estimation paradigm for multimodal time series foundation model pipelines under missingness and irregular sampling, allowing incomplete target modalities to be systematically inferred from available auxiliary modalities. We evaluate TRACE on diverse multimodal benchmarks spanning healthcare and affective computing, including the MIMIC-IV clinical dataset and the CMU-MOSI and CMU-MOSEI benchmarks for multimodal sentiment analysis. Across a range of downstream prediction tasks and missing-modality settings, TRACE consistently outperforms prior multimodal fusion approaches, demonstrating improved robustness to severe modality missingness and more reliable cross-modal representations.

Ziwen Kan, Yishuo Chen, Kecheng Li +7

Department of Computer Science, University of Central Florida · Department of Computer Science, University of North Carolina at Chapel Hill

Irregular Time-Series Modeling Missing-Modality Learning Multimodal Foundation Models Multimodal Fusion Time-Series Foundation Models

Jun 4, 2026cs.MM

Beyond Generative Decoding: Discriminative Hidden-State Readout from a Native Omni-Modal LLM for Multimodal Sentiment Analysis

Multimodal sentiment analysis (MSA) infers human affect from language, acoustic, and visual signals. Recent methods increasingly adapt large multimodal models (LMMs) via generative readout: prompting the model to emit a sentiment score as a text string. While convenient, this ties continuous regression to discrete autoregressive decoding, incurring unmeasured costs. We revisit this readout mechanism and propose a discriminative formulation built on the Thinker module of a native omni-modal LLM (Qwen2.5-Omni-7B). Instead of text decoding, we map the final-layer hidden state of the last non-padding token to a continuous score via a lightweight regression head in a single forward pass. Using 4-bit quantization and low-rank adaptation (QLoRA), the entire 7B pipeline -- including video and audio processing -- trains on a single consumer GPU (RTX 5090, 32 GB) with 10-21 GB peak memory and 1.14% trainable parameters. Through a controlled comparison fixing the backbone, data, and LoRA configuration, we isolate the impact of the readout. On CMU-MOSI and CMU-MOSEI, our discriminative readout reaches state-of-the-art accuracy without task-specific feature engineering (MOSI: MAE 0.551, Corr 0.888; MOSEI: MAE 0.506, Corr 0.790) and exhibits strong multi-seed stability. In contrast, the generative readout -- even after equivalent supervised training -- more than doubles the mean absolute error, yields unparsable or out-of-range outputs (2.8% zero-shot), and suffers from higher latency. Modality ablations reveal a text-dominant regime on CMU-MOSI. Our findings indicate that how an LMM is read out is as consequential as how it is trained, demonstrating that a discriminative readout offers a more accurate, efficient, and reliable alternative for continuous MSA.

Bin Wen, Tien-Ping Tan

School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia.

Efficient Multimodal Inference Sentiment Analysis Multimodal Large Language Models Multimodal Sentiment Analysis Multimodal Foundation Models Multimodal Understanding

Jun 3, 2026cs.CV

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning

Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleaved image-text In-Context Demonstrations (ICDs) conditions the model to solve new tasks. Despite its flexibility, multimodal ICL incurs high inference latency and suffers from instability due to sensitivity to demonstration formatting, ordering, and content. To address these limitations, we propose Hyper-ICL, a lightweight, training-based framework for demonstration-free multimodal ICL that reconstructs demonstration effects directly without requiring ICDs at inference time. Hyper-ICL learns a parameter-efficient low-rank logit-level adapter that calibrates attention distributions to better match demonstration-induced attention redistribution. To capture how demonstration influence varies across queries, we introduce a query-adaptive modulation mechanism that adaptively controls intervention strength at token level across layers and heads based on the current query. Finally, we propose a layer-wise hyperbolic anchor distillation loss that aligns intermediate student features to a demonstration-conditioned teacher via Lorentz geodesic distance. This loss encourages the student to reconstruct the demonstration-query relationships induced by ICDs. Extensive experiments across six different multimodal benchmarks (including VQAv2, OK-VQA, and COCO Caption) demonstrate that Hyper-ICL consistently improves accuracy and stability over vanilla ICL and existing state-of-the-art methods.

Niloufar Alipour Talemi, Hossein Kashiani, Fatemeh Afghah

Holcombe Department of Electrical and Computer Engineering, Clemson University, Clemson, United States.

Efficient Multimodal Inference Multimodal ICL Multimodal Large Language Models In-Context Learning Attention Mechanisms Multimodal Foundation Models+2

Jun 3, 2026cs.CV

Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models

Foundation models have driven rapid progress in computer vision, yet the two dominant paradigms, vision-language foundation models (VLMs) and vision-only foundation models (VFMs), remain only partially compatible. VLMs offer language-grounded semantic alignment but are often visually coarse, while VFMs learn discriminative perceptual geometry but lack semantic grounding. We propose GPUA (Geometry-Preserving Unsupervised Alignment), a framework that integrates the complementary strengths of VFMs and VLMs. Inspired by cross-lingual alignment, GPUA treats VFM features as a visual language and learns an orthogonal mapping that translates the VFM space into the VLM semantic space, preserving geometry and narrowing the modality gap without labels or model parameter updates. GPUA is task-agnostic and requires only feature-level access to pretrained models. Experiments across diverse benchmarks demonstrate improved cross-model compatibility and strong gains in downstream zero-shot recognition and segmentation with negligible overhead. Code is available at https://github.com/Yuteam14/GPUA

Shuwen Yu, Zhanxuan Hu, Yi Zhao +2

Yunnan Normal University, Kunming, China · Kunming University of Science and Technology, Kunming, China

Cross-Modal Representation Learning Vision Foundation Model Adaptation Cross-Modal Feature Matching Multimodal Foundation Models Vision-Language Alignment

Jun 3, 2026cs.CV

Frames2LoRA: Parametric Video Internalization for Vision-Language Models

Processing video in vision-language models is expensive: each frame occupies hundreds of tokens, and inference cost scales with every frame and every repeated query. We introduce Frames2LoRA, a method for parametric video internalization. A perceiver hypernetwork reads the intermediate representations produced layer-by-layer as a frozen VLM encodes a video, and generates a Low-Rank Adaptation (LoRA) adapter in a single forward pass. Unlike standard LoRA fine-tuning, which requires iterative gradient updates, Frames2LoRA predicts these weights directly from the video. Trained for SmolVLM2 500M and 2.2B on video summarization and captioning, Frames2LoRA enables the same frozen VLM to answer queries from the adapter alone, with zero visual tokens in its context at query time. Frames2LoRA is statistically non-inferior and equivalent to direct video-in-context inference across all five captioning benchmarks at both model scales, and across seven of eight video question answering benchmark-scale pairings. Although trained only on 12 frames at 384px, it remains stable up to 1,024 frames and 1024px, where direct video-in-context inference often degenerates. Across this sweep, it reduces answer-time visual-token load by up to 1,500x and query TTFT by 6-80x, while preserving video-faithful outputs. We also find that independently generated adapters for non-overlapping video segments can compose in rank space, suggesting a path toward chunked long-video internalization.

Manan Suri, Sarvesh Baskar, Dinesh Manocha

University of Maryland, College Park

VLM Adaptation Efficient VLM Inference Low-Rank Adaptation Multimodal Foundation Models

Jun 3, 2026cs.LG

Differentiable Efficient Operator Search

Efficient multimodal foundation models often rely on manually designed token-reduction operators, such as pruning, merging, pooling, and adaptive reweighting. Although these operators appear different, we show that they can be interpreted as distinct regimes of a shared operator space. Based on this view, we introduce Efficient Operator Search, a differentiable framework that jointly searches where to reduce tokens, how many tokens to retain, and how reduced token information should be processed. The proposed search space parameterizes layer activation, retention budget, and operator behavior, while the search policy optimizes task performance under one-sided budget and cost constraints. This formulation recovers representative hand-designed baselines as special cases and further discovers hybrid operators beyond isolated manual designs. Experiments on multimodal benchmarks show that the searched operators achieve competitive accuracy-efficiency trade-offs, especially under aggressive visual-token reduction. These results suggest that efficient multimodal inference can be reframed from manual operator design to differentiable operator search.

Xiaohuan Pei, Jiyuan Zhang, Yuanfan Guo +4

1The University of Sydney · 2ByteDance · 3Shanghai Jiao Tong University +1

Efficient Multimodal Inference Multimodal Token Compression Multimodal Foundation Models Multimodal Learning

Jun 2, 2026cs.LG

KODA: Contrastive Representation Comparison and Alignment for Vision-Language Foundation Models

Vision-language foundation models such as CLIP and SigLIP provide widely used representations for multimodal learning systems. While these models are typically compared through downstream performance, such evaluations often do not explain how their representations differ structurally. In this work, we study this problem through the task of Contrastive Embedding Clustering: identifying sample subsets that are weakly clustered under one representation but strongly clustered under another. We propose \emph{Kernel Optimization for Discrepancy Analysis (KODA)}, a kernel-based framework for contrastive representation comparison and alignment. KODA constructs unified multimodal kernels through modality-wise kernel composition and formulates discrepancy discovery as a constrained optimization problem that searches for coherent structures in one representation while suppressing coherence in a reference representation. This yields interpretable discrepancy directions associated with specific sample subsets and modality interactions. To scale KODA to large vision-language datasets, we develop randomized low-dimensional approximations of joint kernels using random projections, including Random Fourier Features for shift-invariant kernels. Empirically, KODA identifies consistent and interpretable discrepancy structures across vision-language representations and provides sample subsets for representation alignment. The code is available at https://github.com/yokiwuuu/KODA.

Youqi Wu, Mohammad Jalali, Farzan Farnia

Department of Computer Science and Engineering, The Chinese University of Hong Kong.

Kernel Methods Multimodal Foundation Models Vision-Language Alignment

Jun 2, 2026cs.CV

Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs

As foundation models scale toward fusing more heterogeneous visual streams, understanding how diverse encoders interact under joint training becomes a prerequisite for principled design. Yet large vision-language models (LVLMs) currently lack the tools to do so, and parameter-efficient encoder configurations remain hard to identify before training. To re-examine encoder roles under joint training, on the 16-benchmark Cambrian-1 suite we retrain and evaluate all 31 non-empty subsets of five common vision encoders under a unified pipeline (~20k GPU-hours total), and report three findings. First, retraining each subset from scratch reveals encoder rankings that differ from those obtained by masking encoders on a fixed checkpoint, including which encoder ranks first overall. Second, we decompose each encoder's contribution into two axes, Capacity, the score an encoder reaches on its own, and Necessity, the drop when it is removed from the full pool. The two axes are not interchangeable. Pairing the two highest-Capacity encoders is suboptimal, while pairing a high-Capacity anchor with an adaptive complement matches the full five-encoder model. Adding further encoders beyond this pair yields only marginal gains. Third, at fixed parameter count, per-encoder pre-projector effective rank explains the residual score variation. The strongest pairs combine an anchor whose rank survives joint training with a complement whose rank expands under it, suggesting that higher-rank, less-collapsed projector inputs correspond to a more favorable optimization regime at the encoder-projector interface. Together, the Capacity-Necessity decomposition and the pre-projector rank analysis, along with comprehensive evaluation through retraining, expose a methodological gap in multi-encoder LVLM design, and offer concrete primitives for closing it.

Wei Ding, Yudong Zhang, Ruobing Xie +3

Tsinghua University Beijing, China · Tsinghua University, Tencent Beijing, China · University of Science and Technology Beijing Beijing, China

VLM Evaluation Vision-Language Models Large Vision-Language Models Multimodal Foundation Models

Jun 2, 2026cs.CV

Investigating Adversarial Robustness of Multi-modal Large Language Models

Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e.g., CLIP) substantially expands the attack surface, making these models vulnerable to visual adversarial perturbations. Prior defenses typically preserve compatibility with pretrained MLLMs by enforcing strict alignment to CLIP's original embedding space during adversarial fine-tuning; while practical, this constraint fundamentally limits achievable robustness. We present a systematic investigation of adversarial robustness in MLLMs. We first introduce a diagnostic CLIP-alignment protocol that predicts, prior to full MLLM training, which robust vision encoders will transfer effectively to the multimodal setting, revealing that large-scale multimodal adversarial pretraining, rather than unimodal scale alone, is the critical factor for strong robustness transfer. Integrating such encoders into MLLMs via end-to-end multimodal training yields average gains of 28 CIDEr points on captioning and 11.7% VQA accuracy under strong adversarial attacks compared to constrained plug-and-play baselines. We further show that adversarial training applied directly to a standard non-robust MLLM degrades both clean and adversarial performance, establishing robust visual representations as a strict prerequisite, while end-to-end adversarial training from a robust backbone delivers additional gains of 1.9 CIDEr points and 4.3% VQA accuracy. Beyond training-time defenses, lightweight test-time visual stochastic transformations serve as an effective black-box defense for non-robust MLLMs, elevating adversarial performance from near-zero to levels comparable with robust models. Finally, we show that our robust models substantially reduce toxic generation under white-box visual jailbreak attacks. Code and pretrained weights will be released publicly.

Hashmat Shadab Malik, Muzammal Naseer, Salman Khan

Mohamed Bin Zayed University of AI, UAE · Khalifa University, UAE · Australian National University, Australia

Adversarial Training VLM Robustness Adversarial Attacks on VLMs Adversarial Robustness Multimodal Large Language Models Multimodal Foundation Models

Jun 2, 2026cs.CV

Attend to Anything: Foundation Model for Unified Human Attention Modeling

Existing human attention (saliency) modeling methods persist as highly fragmented across modalities, scenes, and task formulations. Consequently, even with increasing model capacity and data scale, current models predominantly remain scene-dependent and task-specific, failing to practically generalize in real-world applications. To address the fundamental limitations, we present the Attend to Anything Model (AAM), a multi-modal foundation model that unifies attention modeling across various image, video, and audio-visual tasks and scenes. AAM reformulates attention as a cognitive entailment relationship organized in a general-to-specific hierarchy, implemented through language prompts with hierarchical embeddings in hyperbolic space. Furthermore, to unify static image and dynamic video attention, we adopt a fluid-dynamics perspective, formulating video-frame attention as a diffusive temporal evolution governed by the Fokker--Planck equation. Extensive experiments on 16 benchmarks demonstrate that AAM consistently outperforms state-of-the-art methods by an average of 6% across various scenarios, while achieving approximately a 4

\times

speedup in video inference. Overall, these results demonstrate that AAM provides a principled foundation for future research on attention and saliency-related tasks. The dataset and code will be available at https://github.com/wz-zhao/Attend-to-Anything.

Wenzhuo Zhao, Ronghao Xian, Keren Fu +1

College of Computer Science, Sichuan University, Chengdu, 610065, China · National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, 610065, China

Visual Attention Unified Multimodal Models Visual Saliency Multimodal Foundation Models

Jun 1, 2026cs.CV

Cosmos 3: Omnimodal World Models for Physical AI

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI -- effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3.

NVIDIA, :, Aditi +293

Unified Multimodal Models World Models Multimodal Generation Vision-Language-Action Models Multimodal Foundation Models Embodied World Models+1

Jun 1, 2026cs.CV

AdaCodec: A Predictive Visual Code for Video MLLMs

Video is temporally redundant: adjacent frames usually share most objects, background, and layout. Yet existing video multimodal large language models (video MLLMs) usually encode each sampled frame as an independent RGB image, causing visual tokens to repeat content already present in earlier frames. This suggests a more direct video interface: send a full reference frame only when the scene cannot be predicted well from prior context, and otherwise transmit a compact description of inter-frame changes. We call this interface a \emph{predictive visual code}, and instantiate it for video MLLMs as \textbf{AdaCodec}. AdaCodec spends full visual tokens on a reference frame only when its conditional predictive cost is high; otherwise, it encodes inter-frame changes, including motion and prediction residuals, as compact P-tokens. Across all eleven benchmarks, AdaCodec improves over the Qwen3-VL-8B per-frame RGB baseline at a matched visual-token budget. Even at

1/7

the budget, AdaCodec with 32k tokens surpasses the 224k baseline on all long-video benchmarks; on five general-video benchmarks, it raises the average score while substantially cutting time-to-first-token from 9.26s to 1.62s.

Haowen Hou, Zhen Huang, Zheming Liang +8

Shanghai Jiao Tong University · Shanghai Innovation Institute

Predictive Coding Efficient VLM Inference Visual Tokenization Video-Language Models Multimodal Foundation Models Video Token Compression+2

May 31, 2026cs.AI

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition

Understanding modality interaction in multimodal large language models (MLLMs) is central to reliable deployment. We introduce Partial Information Decomposition (PID) as a decision-level framework that separates unique, redundant, and synergistic contributions of sensory and linguistic inputs, beyond representation alignment and outcome-based evaluation. Across vision--language benchmarks, PID reveals recurring modality-use profiles: reasoning and grounding-oriented tasks tend to exhibit high synergy, whereas expert and knowledge-oriented tasks show stronger language-unique reliance. These profiles generalize across model families and predict sensitivity to modality-level interventions. We further extend PID to tri-modal systems with Sensory PID, treating language as a control variable to decompose video--audio information gain. Applied to omni-modal models, Sensory PID reveals a sensory synergy bottleneck dominated by visual information even on audio--visual fusion tasks. Finally, PID-guided reweighting provides initial evidence for improving multimodal reasoning and grounding performance.

Wanlong Fang, Tianle Zhang, Wen Tao +1

College of Computing and Data Science, Nanyang Technological University, Singapore · Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore · Centre of AI in Medicine (C-AIM), Nanyang Technological University, Singapore

Multimodal Grounding Multimodal Large Language Models Multimodal Reasoning Multimodal Foundation Models Multimodal Model Interpretability Multimodal Fusion+1

May 30, 2026cs.CL

MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models

This work presents MLLM-Microscope, a novel system designed for analyzing the hidden representations within Multimodal Large Language Models (MLLMs). Our system evaluates the linearity, intrinsic dimension, and anisotropy of multimodal token embeddings across transformer layers. Utilizing the ScienceQA dataset, we evaluate two state-of-the-art MLLMs, LLaVA-NeXT and OmniFusion. We find that both the main and residual streams for tokens of both modalities exhibit highly linear behaviors across transformer layers. However, LLaVA-NeXT's image tokens reveal a slight decline in linearity, whereas OmniFusion's remain consistent. Image token dimensions in OmniFusion remain consistently higher across layers compared to LLaVA-NeXT. Also, the OmniFusion's anisotropy is observed to stay consistently low throughout the layers. These findings suggest that the inner workings of MLLMs highly depend on the nature of modality fusion performed before passing the token sequence into LLM. This and other new potential insights obtainable from our system are surely capable of enhancing our understanding of the inner workings of MLLMs, informing future model design and optimization.

Ravil Mussabayev, Rustam Mussabayev

Satbayev University

Representation Geometry Multimodal Large Language Models VLM Interpretability Multimodal Embedding Multimodal Foundation Models Multimodal Model Interpretability+1

May 29, 2026cs.CV

Zamba2-VL Technical Report

We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with a small number of shared transformer blocks. Across a broad range of image understanding, reasoning, OCR, grounding, and counting benchmarks, Zamba2-VL is competitive with leading Transformer-based open-weight VLMs of comparable scale, including the Molmo2, Qwen3-VL, and InternVL3.5 families, and substantially outperforms prior SSM-based and hybrid VLMs such as VL-Mamba, Cobra, and mmMamba. Inheriting the near-linear prefill compute and small, near-constant recurrent state of its Zamba2 backbone, Zamba2-VL delivers roughly an order of magnitude lower time-to-first-token (TTFT) than these Transformer baselines at matched parameter scale, with the efficiency gap most pronounced at the smaller 1.2B and 2.7B scales most relevant to on-device and edge deployment. We release three models -- 1.2B, 2.7B, and 7B -- together with inference code at https://huggingface.co/collections/Zyphra/zamba2-vl.

Hassan Shapourian, Kasra Hejazi, Olabode M. Sule +1

Zyphra, San Francisco, CA

Vision-Language Models Efficient VLM Inference Multimodal Foundation Models

May 29, 2026cs.CV

Representation Forcing for Bottleneck-Free Unified Multimodal Models

Unified multimodal models (UMMs) aim to handle perception and generation in a single model. Yet existing UMMs still rely on a frozen, separately pretrained VAE for image generation, imposing a structural bottleneck. Naively removing it introduces a quality gap, as the model must learn both high-level structure and low-level details from raw pixels. In this paper, we propose Representation Forcing (RF), a technique that closes this gap by making representation prediction a native capability of the model. Concretely, RF forces the decoder to autoregressively predict visual representations as intermediate tokens before pixels; these tokens then stay in context to guide pixel diffusion within the same backbone. By turning representations from perception outputs into generation targets, RF eliminates the need for any external generative latent space. We find that RF benefits both understanding and generation. On image generation, our pixel-space model with RF matches state-of-the-art VAE-based unified models. On image understanding, pixel-space RF generally outperforms its VAE-based variant. Together, these results offer an effective step toward end-to-end, bottleneck-free UMMs.

Yuqing Wang, Zhijie Lin, Ceyuan Yang +10

University of Hong Kong · ByteDance Seed · The Chinese University of Hong Kong +2

Unified Multimodal Models Conditional Image Generation Multimodal Generation Diffusion-Based Image Generation Multimodal Foundation Models

May 29, 2026cs.CV

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning

With the rapid advancement of large multimodal models (LMMs), inference-time overhead has become a key bottleneck for real-world deployment. Existing methods typically prune visual tokens at prefill, assuming the required visual evidence remains static during reasoning. However, we empirically show that visual evidence is strongly step-dependent: only a sparse subset of visual tokens is critical at each decoding step, and the critical set evolves across reasoning. Furthermore, we identify a coupled bottleneck where redundant visual context can steer the model toward query-irrelevant regions, lengthening the reasoning trace. Guided by these insights, we propose VisionPulse, a step-wise visual token pruning framework during reasoning. VisionPulse computes a lightweight visual attention mass to estimate the step-wise retention budget by exploiting its strong positive correlation with LMMs' effective visual token usage and retain only the most critical tokens under this budget. By enforcing visual sparsity during reasoning, VisionPulse filters redundant visual context while preserving relevant visual evidence, shortening reasoning traces naturally. Extensive experiments show that VisionPulse only retains 5% of visual tokens per step with reasoning traces shortened by 11.2%, while keeping accuracy almost unchanged.

Hengbo Xu, Shengjie Jin, Yanbiao Ma +1

Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China.

Efficient Multimodal Inference Visual Attention Multimodal Reasoning VLM Reasoning Multimodal Foundation Models Visual Token Pruning+1

May 29, 2026cs.CL

"Înţelegi Româneşte?'' A Recipe for Romanian Vision-Language Models

Vision-Language Models (VLMs) largely follow the text-only LLM trajectory, excelling on English benchmarks but sharply degrading on low-resource languages, where neither large-scale image-text corpora nor culturally grounded evaluations exist. We present a systematic study of building a language-specific VLM for Romanian, covering the full pipeline from data construction to architectural choices. We translate established English VLM training and evaluation corpora into Romanian, applying machine translation to textual annotations and to in-image text, preserving visual grounding while adapting the textual content. Using this data, we train and ablate a series of VLMs to isolate the contribution of (i) vision backbones of varying scale and pretraining, (ii) language backbones from multilingual to Romanian-adapted LLMs, and (iii) OCR-style image-text data. We further curate HoraVQA, a culturally native evaluation set grounded in Romanian everyday scenes. Romanian-adapted VLMs consistently outperform their same-sized counterparts and, across all evaluated benchmarks, even surpass models from the next larger size category.

Mihai Masala, Marius Leordeanu, Mihai Dascalu +1

National University of Science and Technology POLITEHNICA Bucharest, Romania

VLM Evaluation Vision-Language Models VLM Adaptation Multimodal Foundation Models Vision-Language Pretraining

May 29, 2026cs.CV

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration

Real-world image restoration (IR) is bottlenecked by the scarcity of high-quality paired training data. Synthetic datasets are abundant but often fail to model real-world degradations, while real-world paired datasets are expensive and difficult to capture. As a result, IR models trained on these datasets show limited generalization in real-world scenarios. In this work, we propose Generative Ground Truth (GGT) by using generative multimodal foundation models (MFMs) to produce high-quality (HQ) targets from real-world low-quality (LQ) images. We first conduct a systematic evaluation of nine state-of-the-art MFMs, including Nano-Banana-2 and GPT-Image-2, on images of various scenes and degradation types. The results demonstrate that Nano-Banana-2 with VLM-based adaptive prompting shows the highest capability to synthesize perceptually realistic and content-faithful HQ targets, which can serve as the GGT for the LQ input. We then employ Nano-Banana-2 to build a GGT synthesis pipeline, which involves multi-stage quality control to ensure data reliability, and construct GGT-100K, an LQ-HQ paired dataset comprising 103,707 training pairs and covering diverse scenes and complex real-world degradations. A test set of 500 image pairs is also established. Extensive experiments show that GGT-100K consistently improves the real-world generalization of a wide range of IR models, with particularly strong benefits for finetuning generative models for IR tasks. Our results suggest that MFMs can serve as practical tools for restoration-oriented data generation, and GGT-100K is a useful resource to expand the generalization boundaries of real-world IR models.

Xiangtao Kong, Jixin Zhao, Lingchen Sun +2

The Hong Kong Polytechnic University · OPPO Research Institute

Synthetic Data Augmentation Image Restoration Multimodal Foundation Models

May 28, 2026cs.CL

Your Multimodal Speech Model Says I Have a Face for Radio

As large neural models have become better at language tasks, researchers are increasingly building multi- and omnimodal models that handle more modalities of data. One example is the expansion of speech recognition models to audio-visual data for noise mitigation and multimodal subtitling. While performance and bias have been studied extensively in the single-modality regime, it is unknown how new modalities affect this, even though they produce biases in humans. We therefore propose the first bias evaluation of multimodal speech recognition, where we create videos pairing different faces with the same audio, and measure changes in speech transcription accuracy. We find large quality-of-service differences across mWhisper-Flamingo and Gemini models, with drops of up to 4.05 word error rate points, across self-declared gender, ethnicity, and their intersection. Our findings point to a priority for developers to evaluate, fix, and communicate such limitations, as providing more signals through additional modalities is not necessarily better, and may even lead to biased outcomes.

Maya K. Nachesa, Vlad Niculae, Vagrant Gautam

Language Technology Lab University of Amsterdam · Heidelberg Institute for Theoretical Studies

ASR Evaluation Demographic Bias in ASR Automatic Speech Recognition Audio-Visual Speech Recognition Multimodal Foundation Models Multimodal Model Evaluation+2

May 28, 2026cs.CV

Archon: A Unified Multimodal Model for Holistic Digital Human Generation

Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visual content, remains an open challenge. In this paper, we present Archon, a fully pretrained, human-centric unified multimodal model for holistic avatar generation. Archon unifies seven modalities with modality-specific tokenizers, and a native autoregressive unified multimodal model pretrained on synchronized modalities and 72 diverse tasks to model holistic joint distributions. To address the token explosion challenge in high-fidelity talking videos, we introduce a memory-efficient semantic video reparameterization, achieving 4x token reduction while preserving fine-grained dynamics, coupled with a semantic-driven video diffusion decoder. We further propose a "Thinking in Modality" that decomposes ambiguous cross-modal tasks into stepwise thinking in an alternative chain of modality, progressively enhancing fidelity and controllability. Extensive experiments demonstrate that Archon achieves superior or comparable performance across diverse digital human generation tasks, validating the effectiveness of our unified framework. Project page: https://zju3dv.github.io/archon/.

Chong Bao, Shichen Liu, Lijun Yu +9

State Key Lab of CAD&CG, Zhejiang University · Google · The work was done during an internship at Google. +1

Unified Multimodal Models Multimodal Pretraining Human Avatar Animation Multimodal Generation Multimodal Foundation Models

May 28, 2026cs.AI

ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for Zero-Shot Traffic Signal Control

Reinforcement learning (RL) has shown promise in traffic signal control (TSC). However, its reliance on predefined states limits responsiveness to observable open-world events that are absent from training data. IoT-enabled intersections provide heterogeneous observations from roadside sensors and cameras, creating opportunities to improve RL adaptability to such events. To this end, we propose ReasonLight, a multimodal foundation model-enhanced RL framework for zero-shot TSC. ReasonLight integrates three sources of information: structured traffic measurements, multi-view camera observations, and candidate phase decisions from a pre-trained RL controller. Given an RL-proposed phase, ReasonLight extracts visual semantics from multi-view images and aligns them with compact sensor-derived scene descriptions. This alignment enables a semantic-guided refinement module to either preserve or adjust the proposed action according to traffic rules and event semantics. To ensure operational reliability, refined actions are constrained by the set of available phases. Any invalid decision is rejected, and the system falls back to the original RL action. We evaluate ReasonLight on two types of rare events not seen during RL training: emergency vehicle priority and temporary traffic regulation. Experimental results show that ReasonLight achieves zero-shot adaptation without retraining. It reduces emergency vehicle waiting time by up to 88.7% compared with the RL-only backbone while preserving comparable routine traffic performance.

Aoyu Pang, Maonan Wang, Yuejiao Xie +3

School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China · Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong · Shanghai AI Laboratory, Shanghai, China +1

RL Control Intelligent Transportation Systems Traffic Signal Control Multimodal Foundation Models