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

Jul 8, 2026cs.AI

Infinity-Parser2 Technical Report

We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarcity of faithfully annotated parsing corpora. Our contributions are threefold. First, we build a scalable synthesis engine, pairing a controllable rendering framework with an iterative refinement loop, and use it to construct and open-source Infinity-Doc2-5M: a 5-million-sample bilingual (Chinese/English) corpus spanning diverse document types, annotated with element bounding boxes, canonical content forms (Markdown, HTML, LaTeX, SMILES, structured charts), and full-page reading order. Second, we introduce a verifiable, multi-task reward system that enables Joint Reinforcement Learning across eight co-trained objectives (document parsing, layout analysis, table parsing, math formula parsing, chart parsing, chemical formula parsing, document VQA, and general multimodal understanding), unifying perception, structure, and reasoning in a single optimization signal. Third, we release two variants under a shared architecture: Infinity-Parser2-Flash, optimized for low-latency inference with a 3.68x throughput gain over Infinity-Parser-7B, and Infinity-Parser2-Pro, engineered for precision-critical settings. Infinity-Parser2-Pro reaches state-of-the-art 87.6% on olmOCR-Bench and 74.3% on ParseBench, surpassing DeepSeek-OCR-2, PaddleOCR-VL-1.5, and MinerU2.5, with strong generalization to charts, chemical formulas, and document VQA.

Zuming Huang, Jun Huang, Kexuan Ren +12

Synthetic Data Generation Multimodal Large Language Models Document Parsing Multi-Task RL Multimodal Foundation Models Multimodal Understanding

Jul 8, 2026cs.CV

MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models

Medicine is inherently multimodal, requiring clinicians to synthesize information across diverse data streams. Yet the development of multimodal foundation models is constrained by limited access to large-scale, high-quality clinical data. Although PubMed Central (PMC) offers a complementary source of expert-authored image-text data, existing PMC-derived resources remain limited in fidelity, reproducibility, and clinical validation. We introduce MedPMC, an automated, continuously updatable framework that transforms permissively licensed literature into high-fidelity infrastructure for medical multimodal models. Applied to 6.1 million PMC articles, MedPMC curated 11 million medical image-text pairs. Component evaluations showed strong performance for initial screening (F1 = 93.2), multi-panel figure detection (F1 = 96.5), figure separation (mAP = 89.8), caption separation and alignment (F1 = 81.4; ROUGE-L = 85.3), and medical figure classification (F1 = 96.5). Manual review by five annotators, three with medical training, found 95.3% of MedPMC images medically relevant, versus 19.7% in a prior PMC-derived dataset. Across 26 benchmarks spanning 11 specialties, a MedPMC-trained CLIP-style model improved average zero-shot AUC by 7.1 percentage points over the strongest architecture-matched biomedical CLIP baseline despite using fewer than half as many image-text pairs. As the vision encoder in a multimodal large language model, it improved medical visual question-answering by 1.9 and 16.9 percentage points across two benchmarks. In 10,524 Yale New Haven Health System dermatology photographs, it improved morphology-to-image retrieval Recall@5 by 11.7 percentage points. These findings show that high-fidelity literature curation strengthens medical multimodal foundation models across benchmark and clinical settings. We publicly release the framework, corpus, benchmarks, and pretrained models.

Hyunjae Kim, Dain Kim, Pan Xiao +25

Yale University, New Haven, CT, USA · Korea University, Seoul, South Korea · Washington University in St. Louis, St. Louis, MO, USA +4

Medical Imaging Foundation Models Training Data Curation Multimodal Pretraining Medical VLMs Multimodal Foundation Models Medical Image Benchmarks

Jul 7, 2026cs.NE

Do You Remember? Toward Memory-Centric Multimodal AI

Human memory is reconstructive, not a faithful recording. Current multimodal LLMs (MLLMs) lack this capability: they process images through a frozen visual encoder, produce a one-shot text output, and discard internal representations. We present DoYouRemember, a three-stage architecture introducing reconstructive memory into MLLMs: (1) a VQ-VAE compresses images into discrete visual tokens, (2) a LoRA-fine-tuned LLM jointly attends to visual and text tokens, and (3) a Diffusion Decoder reconstructs images from the LLM's hidden states. On 1,000 3D facial skin texture maps and 99,000 unlabeled facial images, we find that LLM hidden states contain approximately zero recoverable visual information -- the same Decoder producing clear reconstructions from VQ-VAE tokens (pre-LLM) produces pure noise from LLM hidden states (post-LLM), demonstrating that the LLM understands images but does not remember them. Training a shared memory matrix M under backpropagation systematically fails due to gradient cancellation (O(1/sqrt(N)) attenuation). We identify three root causes and show that local EMA updating resolves all three: each image updates only its top-8 slots out of 64, preserving inter-slot diversity. The resulting M (229K parameters, 16x compressed) approaches the VQ upper bound on unseen test images. Scaling to 1,024 slots surpasses it (LPIPS 0.056 vs. 0.071), as M's continuous representation avoids VQ quantization error. We unify these findings under an information-theoretic framework: memory is lossy compression, recall is decompression, and hallucination is an inherent property of lossy decompression rather than a defect.

Xuguang Yu, Weigang Zheng, Minyue Yu

Memory-Augmented VLMs Multimodal Memory Memory-Augmented Language Models Neural Network Memorization Image Reconstruction Multimodal Large Language Models+3

Jul 7, 2026cs.CV

ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction remains largely implicit. Existing methods concatenate text and 3D tokens into a flat sequence and rely on self-attention, collapsing coarse structural cues and fine geometric details into one undifferentiated representation. We introduce ELSA3D, a unified 3D model that addresses this with elastic semantic anchoring, structuring language and geometric reasoning jointly along matched abstraction scales. ELSA3D represents geometry with a scale-aware octree tokenizer and introduces Anchor Tokens, sparse cross-modal units that select semantic cues, route them to the most relevant 3D scale, retrieve scale-specific geometric evidence, and write the fused signal back into the unified representation, keeping interaction sparse yet precise. A lightweight per-block router makes both computation and reasoning elastic, choosing which text tokens instantiate anchors at which geometric scale so that cross-modal capacity concentrates where alignment is most needed. ELSA3D achieves state-of-the-art performance across image-to-3D generation, text-to-3D generation, and 3D captioning, outperforming the strongest unified baseline while roughly halving FLOPs and inference latency relative to the non-elastic version of the same model.

Tianjiao Yu, Xinzhuo Li, Yifan Shen +4

University of Illinois Urbana-Champaign

3D Foundation Models Unified Multimodal Models Cross-Modal Attention Text-to-3D Generation Multimodal Foundation Models Vision-Language Alignment+1

Jul 7, 2026cs.CV

Vision as Unified Multimodal Generation

We formulate computer vision as unified multimodal generation, where heterogeneous visual tasks are expressed in the native text and image generation spaces of a unified multimodal model, without task-specific architectures. Under this formulation, SenseNova-Vision uses natural-language instructions and optional visual prompts to specify tasks, target regions or views, and decoding conventions, and generates responses as text for symbolic outputs, images for dense spatial predictions, or mixed text-and-image outputs for compositional tasks. To support large-scale training, we convert diverse computer vision annotations into instruction-response examples compatible with these generation spaces, resulting in the SenseNova-Vision Corpus, a computer-vision instruction-response corpus spanning text, image, and mixed targets. Starting from an off-the-shelf pretrained unified multimodal model, SenseNova-Vision is trained primarily on this corpus, with auxiliary multimodal data used as a capability-preserving mixture, and requires no task-specific prediction heads or architectural modifications. The resulting model covers a broad range of vision tasks, including detection, OCR, keypoint estimation, segmentation, depth estimation, surface normal prediction, point maps, and camera pose estimation, while supporting language-defined variants that combine category, color, region, and other visual cues. Experiments show that a single unified model can match leading task-specialized systems across structured visual understanding, dense geometric prediction, segmentation, and multi-view visual geometry. These results suggest unified multimodal generation as a scalable route for integrating computer vision capabilities into general-purpose foundation models. The model and corpus are publicly available.

Xiaoyang Han, Jianhua Li, Kewang Deng +14

SenseTime Research · Peking University · Shanghai Jiao Tong University +3

Unified Multimodal Models Multimodal Generation Multimodal Foundation Models Multimodal Understanding

Jul 6, 2026cs.CL

Unified Audio Intelligence Without Regressing on Text Intelligence

Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM. Audex adopts a simple unified design with a single Transformer decoder: audio inputs are encoded and projected into the text embedding space, while text tokens and quantized audio output tokens are treated uniformly during generation. This architecture enables strong audio-text fusion, seamless multimodal generation, and compatibility with standard LLM training and inference infrastructure. For training, we meticulously curate audio-text datasets comprising 157.4B audio tokens and 320.5B text tokens. We apply multi-stage supervised training on these datasets, followed by text-only Cascade RL and multi-domain on-policy distillation. Audex delivers state-of-the-art audio understanding, speech recognition and translation, text-to-speech, audio generation, and speech-to-speech generation, while preserving very compelling reasoning, alignment, knowledge, long-context, and agentic capabilities of its text-only LLM backbone with marginal or no regression. We release the model checkpoints to facilitate open research.

Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim +17

NVIDIA

TTS Synthesis Unified Multimodal Models Audio Understanding Audio-Language Models Automatic Speech Recognition Multimodal Foundation Models+1

Jul 4, 2026cs.AI

Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process

Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learning (RL) remains an open challenge. Existing approaches apply RL exclusively to text steps, relegating image generation to supervised surrogates, preventing policy gradients from propagating through the full interleaved trajectory across heterogeneous modalities. This leaves the potential of RL for UMMs largely untapped. In the paper, we introduce \textbf{BRAID} (\textbf{B}ridging inte\textbf{R}le\textbf{A}ved mult\textbf{I}-modal reasoning as a unified \textbf{D}ecision process), a simple framework that casts multi-turn text-image-text reasoning as a unified Markov decision process (MDP), enabling joint optimization of textual and visual generation via a single, principled RL objective. BRAID computes a shared trajectory-level advantage and propagates it coherently into both text tokens and image denoising paths, each optimized through its modality-native policy gradient mechanism. To further address long-horizon credit assignment, BRAID employs a vision-language model (VLM) judge that scores each intermediate image on its reasoning utility, supplying dense turn-level feedback to sharpen learning at critical visual branches. Experiments on spatial reasoning and visual perception benchmarks show that BRAID consistently outperforms various baselines, confirming that a unified MDP formulation with vision-thinking guidance is essential for effective multi-modal reasoning.

Zican Hu, Xuyang Hu, Yiming Liu +10

Nanjing University · Shanghai AI Laboratory · Tsinghua University +5

Unified Multimodal Models Multimodal Reasoning Multimodal Optimization Multimodal Generation Multimodal Foundation Models RL for VLMs+1

Jul 4, 2026cs.CV

Attending to Multimodal Generation One Token at a Time

Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic information in an evolving context. Prior work on interpretability has focused on individual layers and circuits (where), leaving the token-level dynamics of multimodal computation during generation (when) underexplored. We address this gap and study attention shifts as per semantic role; tracking model attention to image, text, instruction, and previously generated tokens, One Token at a Time (OTaT). We introduce multimodal tasks that require explicit switching between visual and textual context within a single response. Across two mainstream model families and four open-weight MLLMs of varying sizes, we establish consistent patterns: attention to image peaks at tokens requiring image-derived information, instruction tokens are revisited during task transitions, and attention to previously generated tokens increases as the generation progresses. Causal attention blocking interventions validate the functional role of these trends. We profile model behavior under disrupted attention and observe responses falling back to language priors, or exhibiting cross-modal leakage, denial, or recovery. Finally, informed of the attention dynamics through our novel analysis, we propose a simple test-time intervention to boost attention to the relevant modality at the right time, significantly improving multimodal task performance.

Varun Gupta, Vineet Gandhi, Makarand Tapaswi

CVIT, IIIT Hyderabad

Multimodal Large Language Models Multimodal Generation Multimodal Foundation Models Multimodal Model Interpretability Multimodal Understanding

Jul 3, 2026cs.CV

WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling

World models aim to capture environment dynamics in ways that support perception, reasoning, and action, and have recently become a central direction in Vision-Language-Action-World (VLAW) modeling. Meanwhile, unified vision-language models have demonstrated strong multimodal generation capabilities, yet their potential as world models remains underexplored. In this work, we introduce \texttt{WorldBagel}, a unified VLAW framework built on BAGEL, a modern multimodal unified model, and use it to systematically investigate the role of unification in world modeling. Across multi-task robotic manipulation and cross-domain experiments, \texttt{WorldBagel} consistently outperforms task-specific alternatives and learns action representations that are more structured and semantically aligned with visual and linguistic context. Experiments on LIBERO, Language Table, and Franka show that unification is not only an architectural convenience, but also a key factor in learning effective VLAW models, leading to consistent empirical gains and deeper insights into multimodal world modeling. Code and model checkpoints will be released upon acceptance.

Zelin Zhao, Min Shi, Bo Yuan +5

Georgia Institute of Technology

World Models for Robotics Unified Multimodal Models Robotic Manipulation Vision-Language-Action Models Multimodal Foundation Models

Jul 3, 2026cs.LG

OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models

Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost. Existing audio-visual token compression methods often rely on unimodal guidance, overlooking the temporal locality of query-relevant evidence in audio-visual inputs and implicitly assuming that the two modalities share a temporally aligned information density distribution. We propose \textbf{OmniFocus}, a training-free query-guided token compression method for OmniLLMs that performs independent importance estimation for video and audio, enabling a modality-symmetric compression design that preserves modality-specific salient evidence while maintaining audio-visual alignment, thereby mitigating the modality bias issue that can arise from unimodal-guided compression. Experiments on the Qwen2.5-Omni model family across four audio-visual benchmarks show that OmniFocus maintains strong compressed performance at low token retention ratios and outperforms existing baselines on several major benchmark scores at 25% token retention. On DailyOmni with Qwen2.5-Omni-7B at 25% token retention, OmniFocus maintains 59.40 accuracy while delivering up to 1.38

\times

prefill speedup relative to the full-token baseline, highlighting a favorable practical accuracy-efficiency trade-off.

Shijie Cao, Qingyu Zhang, Boxi Yu +6

School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Limerick +1

Efficient Multimodal Inference Multimodal Large Language Models Multimodal Token Compression Multimodal Foundation Models Multimodal Understanding

Jul 2, 2026cs.CL

Gemma 4 Technical Report

We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures, ranging from 2.3B to 31B parameters. Alongside improved vision and audio encoders for all model sizes, we propose a unified, encoder-free architecture for our 12B model, which ingests raw audio and image patches. Furthermore, we integrate a thinking mode, enabling Gemma models to generate reasoning traces prior to responding. We improve inference speed, memory, and compute efficiency, as well as long-context abilities through critical design choices. Gemma 4 establishes a leap in performance across STEM, multimodal, and long-context benchmarks, and rivals larger, frontier open models in human-rated tasks.

Gemma Team, Sherif El Abd, Vaibhav Aggarwal +298

Efficient Multimodal Inference Unified Multimodal Models Long-Context Language Model Inference Multimodal Large Language Models Multimodal Reasoning Open-Weight Language Models+2

Jul 2, 2026cs.AI

Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails

Multimodal large language models must continually adapt to evolving tasks and domains, yet standard continual learning metrics mainly measure whether old answers remain correct, leaving the stability of multimodal grounding largely unexamined. We study this overlooked failure mode and ask whether a continually adapted MLLM can preserve not only what it answers, but also how it uses visual, textual, OCR, chart, and document evidence. We identify \emph{hidden evidence-use forgetting}, where answer accuracy is retained while the model silently shifts toward different or less grounded evidence channels, and propose \textsc{RCL}, a replay-free reliance-constrained continual learning framework. \textsc{RCL} freezes the previous checkpoint as a behavioral reference, estimates teacher and student evidence-reliance profiles through counterfactual channel interventions, and jointly optimizes task learning, prediction preservation, and reliance preservation without adding inference-time cost. Across CoIN, COAST, MCITlib, and an evidence-sensitive multimodal stream, \textsc{RCL} consistently improves final performance and reduces forgetting over replay-free, PEFT, routing, and memory-assisted baselines, while substantially lowering modality reliance drift, dominant evidence flips, and hidden forgetting rates. These results suggest that robust continual multimodal learning requires preserving the evidence path behind correct answers, not merely the answers themselves.

Qianyu Chen, Canran Xiao, Runxuan Tang

1Nanyang Technological University · 2Shenzhen Campus of Sun Yat-sen University

Multimodal Grounding Multimodal Foundation Models Continual Learning for VLMs Multimodal Understanding

Jul 2, 2026cs.AI

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time. We study fixed-footprint continual adaptation: the deployed adaptation state is kept under a fixed memory budget, while the backbone model is left unchanged and task-specific updates are externalized. We propose InduceKV, a retrieval-based method that stores each selected training prefix as an attention-ready memory entry, consisting of a frozen retrieval key and compact layerwise key--value (KV) payloads that can be appended to the model's self-attention cache. Under a strict memory budget, InduceKV constructs a compact inducing set through bilevel selection: a lightweight calibration is fit for retrieval, while the selected memory balances current-task likelihood, anchor-based retention, and coverage in the frozen retrieval space. Across task-incremental instruction tuning, continual VQA, domain-incremental adaptation, and lifelong multimodal instruction tuning, InduceKV consistently improves over PEFT, MoE, replay, and prompt-retrieval baselines under matched memory budgets. We further report backbone-matched, stage-1 CoIN, compute-matched, and scalability diagnostics, showing that the gains are not due to a stronger backbone, replay alone, or an unbounded candidate pool.

Qianyu Chen, Ziteng Feng, Canran Xiao +1

1Nanyang Technological University · University of Science and Technology of China · 3Shenzhen Campus of Sun Yat-sen University

Continual Learning for LLMs Memory-Efficient Fine-Tuning Memory-Augmented Language Models VLM Adaptation KV Caching Multimodal Large Language Models+2

Jul 1, 2026cs.CV

Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning

Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuance. A promising alternative is continuous latent reasoning, where the goal is to discover implicit reasoning pathways that bridge the multimodal query and the final answer. However, this introduces a severe train-inference mismatch: a training-time posterior, conditioned on the ground-truth answer, can exploit answer-dependent shortcuts. Standard variational training then forces the inference-time prior to mimic a posterior that has access to information unavailable at test time, leading to poor performance. To address this, we propose Asymmetric Mutual Variational Learning (AMVL), a framework that resolves this mismatch via a bidirectional calibration objective. A forward KL divergence trains the target-agnostic prior to match the posterior, while a novel reverse KL divergence simultaneously regularizes the posterior, preventing it from collapsing into inference-incompatible regions and mitigating this ``answer leakage''. We provide theoretical analysis formalizing this leakage as prior contamination and prove that our dual-KL objective reduces it. We instantiate AMVL in a latent-integrated MLLM and show that it consistently outperforms strong discrete and latent-reasoning baselines, improving the average score on the complex BLINK benchmark by +10.83 and achieving gains of up to +32.00 on individual reasoning tasks, with analyses confirming improved latent-space stability.

Shijie Li, Yilin Gao, Siyuan Yang +7

Shanghai Jiao Tong University · Ant Group

Multimodal Large Language Models Latent Visual Reasoning Continuous Latent Reasoning Multimodal Foundation Models Variational Inference Latent Reasoning+1

Jul 1, 2026cs.CV

Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs

Touch supplies the physical grounding needed to perceive intrinsic material properties, such as friction and compliance, that vision alone often cannot resolve. Recent efforts for equipping multimodal LLMs with this tactile sense, however, expose a zero-sum trade-off: the limited parameter budget of compact models forces a choice between acquiring the new sensory modality and preserving the established vision-language reasoning. We present Splash, a mask-isolated tactile alignment learning framework for MLLMs. Splash quantifies the significance of each pretrained parameter, and partitions the parameter space into a dormant and critical subspace. While the frozen critical subspace acts as a stable anchor to safeguard general visual knowledge, Splash updates the isolated dormant subspace to internalize tactile alignment towards LLMs. This selective, non-destructive expansion effectively prevents catastrophic forgetting and ensures non-destructive modality expansion. Extensive experiments show that Splash effectively achieves tactile reasoning without additional inference overhead in the LLM part, demonstrating state-of-the-art performance on visuo-tactile benchmarks, including SSVTP, TVL, and TacQuad, while preserving its original general-purpose capabilities.

Yoonhyung Park, Minji Kim, Sungwon Moon +1

Division of Artificial Intelligence & Software, Ewha Womans University

Visuo-Tactile Representation Learning Multimodal Large Language Models Multimodal Foundation Models Continual Learning for VLMs Parameter-Efficient Fine-Tuning Multimodal Understanding

Jul 1, 2026cs.CV

Rosetta: Composable Native Multimodal Pretraining

Achieving true artificial general intelligence requires foundation models capable of integrating new modalities without forgetting prior knowledge. However, accommodating continuous generative objectives alongside discrete understanding tasks causes severe gradient conflicts. Existing architectures, including standard Mixture-of-Experts (MoE), are highly susceptible to representation overwriting. Even structurally partitioned paradigms like Mixture-of-Transformers (MoT) remain vulnerable to catastrophic forgetting, severely impeding multimodal scalability. In this work, we introduce Rosetta, a composable native multimodal pretraining framework designed for seamless and non-destructive modality expansion. Rosetta adopts a modular paradigm where core foundational knowledge is preserved within global shared experts, while modality-specific capabilities are distributed across plug-and-play experts. To guarantee non-destructive composition, we propose Momentum-Anchored Orthogonal Projection (MAOP). MAOP leverages the optimizer's momentum state as an implicit semantic anchor, selectively neutralizing conflicting gradient components from new modalities while preserving synergistic updates. Extensive evaluations demonstrate that, while standard MoE and MoT architectures suffer catastrophic forgetting of previously acquired knowledge, Rosetta robustly preserves established language and visual understanding. Furthermore, it delivers superior image generation and unlocks cross-modal synergy, paving the way for truly composable and unified multimodal foundation models. To facilitate further multimodal research, we release our code and checkpoints to the community. Project page at https://rosetta-lmm.github.io/.

Xiangyue Liu, Zijian Zhang, Miles Yang +3

HKUST · Tencent Hunyuan

Unified Multimodal Models Multimodal Pretraining Multimodal Generation Gradient Projection Multimodal Foundation Models Continual Learning for VLMs+2

Jun 30, 2026cs.CV

Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners

Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we present DeCoDe, a simple yet effective technique that enables off-the-shelf MLLMs to act as strong few-shot classifiers without any additional training. Our approach builds on the idea of few-shot classification as a set of pairwise image comparisons, decomposing the task into a set of binary decisions. Given a query image and a support image from a candidate class, the MLLM is prompted to decide whether the two images depict the same class. The logit corresponding to an affirmative response is then used as a similarity score to assign the query image to the most likely class. While this already yields good results, we show that providing additional high-level information, such as the data domain, to the model further improves performance. Our evaluation provides an extensive analysis of various inference variants on a suite of twelve datasets, six established and six newly curated few-shot benchmarks spanning across diverse domains. The results show that the proposed simple decomposition technique can turn off-the-shelf MLLMs into powerful few-shot learners, significantly outperforming current state-of-the-art few-shot methods on both standard and novel domains. Code is available at https://github.com/yunhanwang1105/DeCoDe.

Yunhan Wang, Eshika Khandelwal, Edson Araujo +3

Tuebingen AI Center, University of Tuebingen, Germany

Multimodal Large Language Models Few-Shot Prompting Multimodal Foundation Models Few-Shot Image Classification

Jun 30, 2026cs.LG

FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning

Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-centric and modality-centric tasks. In practice, however, such multimodal graphs are often distributed across decentralized clients, where raw contents and local structures cannot be centrally shared due to privacy constraints. This motivates federated multimodal graph foundation learning, which requires not only transferable representation learning but also intrinsic semantic traceability under strict data isolation. Existing methods usually exchange or store knowledge through parameters, prototypes, embeddings, or compact codebooks, which support optimization and transfer but do not explicitly expose how modality evidence, node semantics, and topology context jointly support predictions. To bridge this gap, we propose FedLAB, a traceable semantic codebook framework that organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context. FedLAB further refines these trace units through federated semantic barycenter pre-training while keeping raw multimodal contents and graph structures local. Extensive experiments on 10 benchmarks and 6 downstream tasks show that FedLAB improves over state-of-the-art baselines by up to 7.53%, while preserving a native semantic trace interface.

Zekai Chen, Kairui Yang, Xuaner Chen +4

Beijing Institute of Technology, Beijing, China

Multimodal Federated Learning Representation Learning Federated Graph Learning Graph Foundation Models Multimodal Foundation Models Multimodal Model Interpretability

Jun 30, 2026cs.CV

CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts

Chain-of-thought (CoT) reasoning has enabled multi-modal large language models (MLLMs) to tackle complex visual reasoning tasks by generating explicit intermediate reasoning steps in natural language. However, this text-based reasoning paradigm is inherently slow at inference time with even thousands of tokens and fundamentally constrained by the expressiveness of natural language. In this paper, we propose CoLT, (Chain of Latent Thoughts), a novel framework that teaches multi-modal models to reason through a chain of latent thought representations instead of verbose text tokens, which can perform thinking with as few as 3 steps. Naively forcing the model to think with latent states easily produces meaningless semantics and makes training unstable. To effectively regulate the latent reasoning process, we introduce a lightweight external decoder that provides step-level supervision for each latent reasoning step in two complementary directions: a forward mode that decodes latent thoughts into the textual reasoning of the next step, and a backward mode that aligns decoder hidden states with the model's latent thoughts given preceding textual context. We further incorporate internal supervision that encourages coherent step-by-step latent transitions. The decoder and internal supervision are removed during inference to maintain high efficiency of latent reasoning. Extensive experiments on eight benchmarks demonstrate that CoLT not only outperforms existing latent reasoning methods such as CODI and SIM-CoT, but also surpasses latent visual reasoning approaches that rely on auxiliary images with costly annotation requirements. Compared to text CoT methods, CoLT can notably reduce the inference time by 10.1

\times

and text decoding time by 22.6

\times

. Code is released at https://github.com/hulianyuyy/CoLT.

Lianyu Hu, Shengqian Qin, Zeqin Liao +4

Nanyang Technological University, Singapore · Shanghai Jiao Tong University, China · NKIARI, Shenzhen Futian, China +2

Efficient Multimodal Inference Efficient Language Model Reasoning Latent Visual Reasoning Multimodal CoT Reasoning Multimodal Foundation Models Multimodal Understanding+1

Jun 30, 2026cs.CV

Rethinking Foundation Model Collaboration: Enhancing Specialized Models through Proxy Task Reasoning

Foundation models are increasingly integrated into embodied intelligence systems, but directly assigning them structured prediction tasks requires precise geometric and numerical estimation, where specialized models often remain stronger. This capability mismatch raises a key question: should foundation models replace task-specific predictors, or should they collaborate through tasks better aligned with their strengths? We propose FAT, a foundation-model-augmented task-specific reasoning framework that treats collaboration as task decomposition rather than model replacement. FAT decomposes structured prediction into specialist prediction, information-space reconstruction, and foundation-model proxy reasoning. The specialist generates geometrically and physically valid hypotheses in the native output space, while the foundation model performs a bounded proxy task, such as selection or verification, over reconstructed multimodal candidates. We instantiate this principle as ProxySelect with a vision--language model. Across 2D object detection, 3D object detection, trajectory prediction, and semantic segmentation, ProxySelect consistently improves specialized baselines and substantially outperforms direct foundation-model regression at lower computational cost. These results suggest a general collaboration principle: specialized models preserve task-specific structure, while foundation models refine their hypotheses through contextual proxy reasoning.

Hongyi Lin, Yang Liu, Jinhua Zhao +1

School of Vehicle and Mobility, Tsinghua University, Beijing, China · Department of Urban Studies and Planning, Massachusetts Institute of Technology, Cambridge, MA, USA

VLM Reasoning Multimodal Foundation Models Structured Prediction

Jun 29, 2026cs.CV

Orca: The World is in Your Mind

We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-Prediction modeling, offering a unified state-transition modeling route toward understanding, predicting, and acting upon the world. Orca learns through two complementary paradigms: unconscious learning captures dense natural state transitions from continuous videos, and conscious learning models sparse meaningful state transitions by language-described events and VQA supervision. For pre-training, we construct a large-scale world-learning inventory data, including 125K hours of video data and 160M event annotations. After pre-training, Orca learns a unified world latent space. To examine whether the learned latent supports downstream, we evaluate it by three representative downstream readouts: text generation, image prediction, and embodied action generation. Orca's backbone is frozen, and only the lightweight modality-specific decoders are trainable. Experiments show the scalability of the proposed paradigm and verify that stronger world latent enables stronger downstream readouts. Orca outperforms similar-sized specialized baselines. These results show that Orca, as a general world foundation model, presents a promising approach to understanding, predicting, and acting upon the world. Finally, we discuss the current limitations, aiming to provide useful insights and inspiration for the community.

Yihao Wang, Yuheng Ji, Mingyu Cao +54

World Model Learning Multimodal Pretraining Latent World Models Multimodal Foundation Models Embodied World Models Multimodal Understanding

Jun 29, 2026cs.CV

Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning

Inductive biases steer learning toward generalizable solutions by encoding task structure. In this work, we identify a crucial missing bias in MLLMs: cross-view consistency, \textit{i.e.}, semantically invariant views of the same instance should lead to the same answer. Standard reinforcement learning with verifiable rewards (RLVR) objectives do not impose this constraint, but instead assign pointwise rewards to each visual input. Even with data augmentation (DA), transformed views are typically rewarded independently, providing little signal once within-view rewards saturate. We propose \textbf{ConsistRoll}, a simple but effective method that injects cross-view consistency into RLVR training by reusing the group-sampling mechanism of GRPO. Specifically, ConsistRoll places original and semantically invariant transformed views in the same generation group, and assigns a joint reward only when paired completions are both correct and consistent. In this way, ConsistRoll turns consistency into an online credit-assignment signal, \textbf{without extra generation overhead and annotations}. Theoretically, we show that cross-view consistency is a valid inductive bias, and ConsistRoll introduces a cross-view correction term absent from DA, penalizing view dependence and alleviating advantage collapse. Comprehensive benchmarks across math, general-purpose, hallucination domains confirm that ConsistRoll achieves robust improvements in multimodal reasoning.

Xin Zou, Haolin Deng, Yibo Yan +6

HKUST (GZ) · HKUST · UIC +1

Multi-View Consistency Multimodal Robustness Multimodal Large Language Models Multimodal Reasoning Reinforcement Learning with Verifiable Rewards Multimodal Foundation Models+1

Jun 29, 2026cs.CV

Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation

Multimodal Large Language Models (MLLMs) are prone to hallucination as their generation preferences are insufficiently calibrated to visual evidence, causing them to fall back on linguistic priors, rather than faithful grounding. In this work, we start from an empirical observation: when query-relevant visual evidence is explicitly strengthened using the model's own attention, generation becomes more accurate, suggesting that many failures do not arise solely from missing perception, but from an insufficient tendency to trust the evidence the model has already attended to. Motivated by this finding, we propose Oriented Pickup Preference Optimization (\texttt{OPPO}), an evidence-aware alignment objective that learns preferences over the strength of visual evidence, rather than only response quality. Concretely, \texttt{OPPO} contrasts the same faithful response under stronger, anchored, weaker-evidence views, turning naive visual preference into ordered visual-evidence alignment. We further combine this objective with fine-grained span-level and token-level regularization to stabilize the training. Besides, we provide a theoretical analysis showing that ordered evidence margins induce a positive lower bound on local visual sensitivity. Extensive evaluations across hallucination and general-purpose benchmarks demonstrate that \texttt{OPPO} consistently outperforms baseline methods.

Xin Zou, Haolin Deng, Yibo Yan +5

HKUST (GZ) · HKUST · OPPO AI Center

Multimodal Large Language Models Multimodal Hallucination Visually Grounded Reasoning Visual Grounding Multimodal Foundation Models VLM Hallucination Mitigation+1

Jun 28, 2026cs.CV

MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein

Multimodal Large Language Models (MLLMs) inherit rich relational priors from their language backbones, yet often fail when asked to apply these relationships in visual contexts. We trace this failure to a structural blind spot: projection-based alignment trains each visual token to carry the right semantics, but never asks whether the relationships between concepts survive the crossing from language to vision. To address this, we propose MIRROR (Mapping Inter-concept Relations from language to visual Representation via Optimal-transport-based Regularization), a geometric regularization framework that transfers relational priors from language to vision by exploiting the rich relational structure encoded in language representations. Specifically, we derive a surrogate loss from the proposed Semi-Inverse Gromov-Wasserstein (SI-GW) problem, an inverse geometric problem that aligns visual representations with language-derived relational priors. We show that this formulation admits a unique closed-form solution that prescribes the ideal visual relational structure implied by language geometry and cross-modal coupling. The structure of the formulation also enables efficient computation, making it applicable to long token sequences. Applying SI-GW inside decoder-only Transformers requires careful design. We introduce targeted strategies at the layer, head, and token levels to ensure stable extraction without additional parameters or inference cost. MIRROR improves relational consistency while preserving performance on general vision-language tasks.

Hong-Han Wang, Yuntao Wang, Hu Ding

University of Science and Technology of China, Hefei, China

Large Vision-Language Models VLM Reasoning Modality Gap in VLMs Multimodal Foundation Models Vision-Language Alignment Optimal Transport+1

Jun 27, 2026cs.AI

COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models

Composition is a high-level visual intent that governs where subjects are placed and how a scene is organized, yet current unified multimodal models remain unreliable at fine-grained composition recognition and struggle to turn such intent into controllable generation. We present COMPASS, the first unified multimodal framework that grounds composition-intent control in a single system spanning both composition perception and composition-guided generation, with a shared expert token

τ_c

as the central intent anchor. On the perception side, COMPASS injects composition expertise into an MoE backbone in a minimally invasive manner and distills the inferred intent into

τ_c

. On the generation side, COMPASS reuses

τ_c

as a global conditioning signal that steers the denoising trajectory, effectively converting passive composition analysis into explicit layout control. To support systematic instruction-following composition learning and evaluation at scale, we construct Comp-11, a large-scale dataset with an 11-class taxonomy and reasoning-augmented annotations. Extensive experiments show that COMPASS substantially improves category-level composition understanding and delivers more composition-consistent, prompt-faithful generation than strong baselines.

Ziqi Zhou, Weize Quan, Mining Tan +6

University of Edinburgh, United Kingdom · State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, China · University of Chinese Academy of Sciences, China +1

Multimodal Grounding Unified Multimodal Models Compositional Image Generation Compositional T2I Generation Multimodal Foundation Models Multimodal Understanding

Jun 26, 2026cs.CV

ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval

Adapting a foundation vision-language encoder to a specialized retrieval task creates a fundamental tradeoff: gains on the target distribution come at the cost of the foundation model's broad generalization, and fashion retrieval is a stringent instance of this problem. We present ZooClaw-FashionSigLIP2, a fashion-specialized SigLIP2-base model that resolves this tradeoff with a simple recipe -- full fine-tuning with knowledge distillation on curated in-domain data, followed by \wiseft~\citep{wortsman2022wiseft} weight interpolation with the base model -- and outperforms LoRA, larger backbones (up to 1B parameters), and external training data. Under fair evaluation, ZooClaw-FashionSigLIP2 outperforms all baselines on every benchmark in our suite. In addition, we release ZooClaw-Fashion, a new high-quality fashion retrieval benchmark, and a systematic quality analysis of widely-used benchmarks that exposes and mitigates structural biases in their public ground truth. We open-source the model weights and all evaluation artifacts to facilitate future research.

Siqiao Xue, Chunxue Xu

VLM Robustness VLM Adaptation Image-Text Retrieval Multimodal Foundation Models

Jun 25, 2026cs.CV

Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards

Most unified large multimodal models (LMMs) that support both visual understanding and image generation still rely on curated post-training supervision, such as human annotations, preference labels, or external reward models. We ask whether a unified LMM can improve both abilities autonomously using only unlabeled images. We propose a self-evolving training framework with three internal roles: a Proposer that generates visual questions, a Solver that answers and evaluates them, and a Generator that synthesizes images. Training uses only self-derived consistency signals, without human annotations, preference labels, or task-trained external reward/judge models. To stabilize learning, we introduce Solver Token Entropy (STE), a continuous difficulty signal based on token-level prediction uncertainty that remains useful even when sample-level consistency becomes unreliable. For image generation, we design a multi-scale internal evaluation scheme that combines question-answer fidelity scoring with cycle-consistent captioning. This creates a solver-mediated coupling, where better visual understanding enables more reliable generation assessment and stronger internal training signals. The framework preserves the same role decomposition, reward logic, and training schedule across diffusion-based BLIP3o, rectified-flow BAGEL, and autoregressive VARGPT-v1.1 architectures, requiring only each backbone's native prompting and generation interface. Across eight understanding metrics, our method consistently improves over the corresponding base models. On BAGEL, it achieves a

+3.5\%

absolute gain on MMMU and improves GenEval image generation performance from

82\%

to

85\%

. Code and models are publicly released.

Ritesh Thawkar, Shravan Venkatraman, Omkar Thawakar +5

1Mohamed bin Zayed University of Artificial Intelligence · 4Linköping University · 3Australian National University +1

Unified Multimodal Models Multimodal Generation Multimodal Foundation Models Image Generation Evaluation Multimodal Learning Multimodal Understanding

Jun 25, 2026cs.CV

Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and Generation

Unified multimodal models capable of both understanding and generation have achieved remarkable strides. However, despite their unified designs, existing evaluations typically assess understanding and generation capabilities in isolation, overlooking the synergy between comprehension and generation. To bridge this gap, we introduce Unison, a comprehensive benchmark comprising 2,169 high-quality unified task samples, designed to evaluate joint understanding and generation in unified multimodal models. Unison offers three key strengths: 1) Comprehensive Dimensions: Unison encompasses internal consistency, understanding-guided generation, generation-guided understanding, and mutual enhancement to enable holistic evaluation. 2) Diagnostic Evaluation: it provides both unified and decoupled tracks for understanding and generation, allowing fine-grained attribution of failure modes and quantitative analysis of the gains from unified modeling. 3) Human Alignment: we also introduce Unison-Judge, an evaluation model well aligned with human judgments to ensure reliable assessment. Based on systematic evaluations of state-of-the-art models on Unison, we uncover critical limitations in current unified multimodal systems and highlight promising directions for future research. Codes, Unison and Unison-Judge are publicly available at https://github.com/FudanCVL/Unison.

Jinyu Liu, Xincheng Shuai, Henghui Ding +1

Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China · Shanghai Key Laboratory of Multimodal Embodied AI, Shanghai, China · Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China

Unified Multimodal Models Multimodal Foundation Models Multimodal Model Evaluation Multimodal Learning Multimodal Understanding

Jun 25, 2026cs.CV

ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP

CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applications increasingly demand visually grounded commonsense inference and compositional reasoning, it remains unclear whether CLIP-style encoders can support such reasoning without architectural changes. To address this, we present ReasonCLIP-58M, a continual pretraining framework that integrates large-scale reasoning supervision into CLIP-style models through our two-stage strategy, which progressively integrates reasoning signals while preserving descriptive alignment, followed by category-structured reasoning supervision. To support this framework, we construct two complementary datasets and a benchmark: ReasonLite-42M, with open-form, visually verifiable reasoning captions; ReasonPro-16M, with category-specific reasoning supervision; and RCLIP-Bench for diagnostic evaluation of visually grounded reasoning. We train a family of ReasonCLIP that improves visually grounded commonsense and compositional reasoning while also enhancing zero-shot retrieval performance. As a drop-in visual encoder for multimodal large language models such as LLaVA-NeXT, ReasonCLIP delivers consistent gains without additional inference cost, demonstrating that structured reasoning supervision enhances the expressive capacity of CLIP-style visual representations. All datasets, models, and training code are available at https://github.com/RISys-Lab/ReasonCLIP.

Sicheng Zhang, Muzammal Naseer, Binzhu Xie +5

Khalifa University · University of Western Australia · The Chinese University of Hong Kong +2

Compositional Reasoning Multimodal Reasoning VLM Reasoning Visually Grounded Reasoning Multimodal Foundation Models Continual Learning for VLMs+1

Jun 24, 2026cs.AI

iFLYTEK-Embodied-Omni Technical Report

General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will evolve, and produce precise control actions over extended horizons. Existing approaches typically specialize in visual-language reasoning, video-based world modeling, or action generation, while cascaded pipelines that first synthesize future observations and then infer actions can introduce interface bottlenecks and compound prediction errors. We present iFLYTEK-Embodied-Omni, a unified multimodal foundation model that jointly models vision(videos and images), language, and action within a single Omni framework. Its modality-specific visual-language, video-generation, and action-generation components communicate through shared multimodal self-attention. This design establishes brain-cerebellum collaboration: the vision-language modeland video generation model form a high-level brain for instruction understanding, task planning, progress tracking, and future visual-state prediction, whereas the action generation modelserves as a low-level cerebellum that directly converts planned subgoals and shared multimodal context into executable action chunks. To develop these capabilities, we combine action-annotated and action-free embodied videos from human demonstrations and robot interactions with embodied reasoning, embodied perception, and general-purpose image-text data to construct a comprehensive dataset. We further adopt a four-stage strategy that progressively trains the VLM, VGM, and AGM before jointly fine-tuning the complete model.

Yuan Zhang, Jingfei Ni, Guanchen Lu +12

1iFLYTEK · University of Science and Technology of China · 2LindenBot

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