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

Mar 1, 2026cs.CL

MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine

Biomedical multimodal assistants have the potential to unify radiology, pathology, and clinical-text reasoning, yet a critical deployment gap remains: top-performing systems are either closed-source or computationally prohibitive, precluding the on-premises deployment required for patient privacy and PHI compliance. We introduce MEDGPT-OSS, an open-weight, 20B-parameter generalist vision-language model designed to facilitate open research in clinical AI. Rather than relying on architectural complexity, MEDGPT-OSS pairs the GPT-oss language backbone with a visual front-end via a optimized, three-stage training curriculum. By progressively domain-adapting these modules through rigorous data curation and long-context multimodal alignment, we demonstrate that a 20B model can bridge the capacity gap. It successfully outperforms larger open medical models on out-of-distribution (OOD) multimodal reasoning and complex text-only clinical tasks. By unifying diverse modalities under a single instruction-following interface, MEDGPT-OSS maintains a parameter-efficient footprint fully compatible with commodity GPUs. We release the complete training recipe, open-weight checkpoints, and a rigorous evaluation harness to serve as a verifiable foundation for privacy-preserving, institution-specific clinical AI research.

Kai Zhang, Zhengqing Yuan, Cheng Peng +10

Department of Computer Science and Engineering, Lehigh University · Department of Computer Science and Engineering, University of Notre Dame · Department of Health Outcomes & Biomedical Informatics, University of Florida +3

Healthcare Multimodal Pretraining Medical VLMs Clinical Reasoning Multimodal Foundation Models

Feb 24, 2026cs.CV

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation

Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending prompts to both vision and text encoders across multiple transformer layers significantly boosts performance, it dramatically increases the number of trainable parameters, with state-of-the-art methods requiring millions of parameters and abandoning the parameter efficiency that makes prompt tuning attractive. In this work, we propose MMLoP (Multi-Modal Low-Rank Prompting), a framework that achieves deep multi-modal prompting with only 11.5K trainable parameters, comparable to early text-only methods like CoOp. MMLoP parameterizes vision and text prompts at each transformer layer through a low-rank factorization that constrains prompts to a compact subspace, providing parameter efficiency while motivating the need for our complementary regularization components. To further close the accuracy gap with state-of-the-art methods, we introduce three complementary components: a self-regulating consistency loss that anchors prompted representations to frozen zero-shot CLIP features at both the feature and logit levels, a uniform drift correction that removes the global embedding shift induced by prompt tuning to preserve class-discriminative structure, and a shared up-projection that couples vision and text prompts through a common low-rank factor to enforce cross-modal alignment. Extensive experiments across three benchmarks and 11 diverse datasets demonstrate that MMLoP achieves a highly favorable accuracy-efficiency tradeoff, outperforming the majority of existing methods including those with orders of magnitude more parameters, while achieving a harmonic mean of 79.70% on base-to-novel generalization. Code is available at https://github.com/sajjad-ucsb/MMLoP.

Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh +1

University of California, Santa Barbara · University of California, Los Angeles

Cross-Modal Learning Prompt Learning VLM Adaptation Multimodal Foundation Models Vision-Language Alignment Visual Prompt Learning

Feb 9, 2026cs.CL

UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Models

Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent textual and visual modalities are aligned. To investigate this question, we use reasoning-guided image generation as a diagnostic task, where models produce textual reasoning first and then generate images. We introduce UReason, a benchmark for evaluating reasoning-to-generation alignment in this paradigm, consisting of 2,000 human-curated and human-verified instances spanning five reasoning-intensive tasks: Code, Arithmetic, Spatial, Attribute, and Text. To enable controlled analysis, we develop an evaluation framework that compares direct generation, reasoning-guided generation, and decontextualized generation, which conditions only on the refined prompt extracted from reasoning. Across eight widely used open-source UMMs, while we find that reasoning-guided generation yields improvements over direct generation, somewhat surprisingly, decontextualized generation consistently outperforms reasoning-guided generation by a large margin. Our further analyses suggest that the intended visual semantics in textual reasoning are not reliably reflected in the generated images, despite their unified design and training. Overall, UReason serves as a practical litmus test for reasoning-to-generation alignment and provides a challenging benchmark for developing next-generation, more tightly aligned UMMs.

Cheng Yang, Chufan Shi, Bo Shui +7

University of California San Diego · University of Southern California · University of Illinois Urbana-Champaign +1

Unified Multimodal Models Image Generation Multimodal Reasoning Multimodal Foundation Models Multimodal Model Evaluation Multimodal Understanding

Jan 15, 2026cs.SD

HeartMuLa: A Family of Open Sourced Music Foundation Models

We present a family of open-source Music Foundation Models designed to advance large-scale music understanding and generation across diverse tasks and modalities. Our framework consists of four major components: (1) HeartCLAP, an audio-text alignment model; (2) HeartTranscriptor, a robust lyric recognition model optimized for real-world music scenarios; and (3) HeartCodec, a low-frame-rate (12.5 Hz) yet high-fidelity music codec tokenizer that captures long-range musical structure while preserving fine-grained acoustic details and enabling efficient autoregressive modeling; (4) HeartMuLa, an LLM-based song generation model capable of synthesizing high-fidelity music under rich, user-controllable conditions (e.g., textual style descriptions, lyrics, and reference audio). In addition, it provides two specialized modes: (i) fine-grained musical attribute control, which allows users to specify the style of different song sections (e.g., intro, verse, chorus) using natural language prompts; and (ii) short, engaging music generation, which is suitable as background music for short videos. Lastly, HeartMuLa improves significantly when scaled to 7B parameters. For the first time, we show that a Suno-level, commercial-grade system can be reproduced using academic-scale data and GPU resources. We expect these foundation models to serve as strong baselines for future research and to facilitate practical applications in multimodal content production.

Dongchao Yang, Yuxin Xie, Yuguo Yin +26

Text-to-Music Generation Neural Audio Codecs Controllable Music Generation Audio Understanding Audio-Language Models Multimodal Foundation Models

Jan 12, 2026cs.CV

CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation

Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasoning remains unstable. Repeated sampling over the same input often produces divergent reasoning trajectories and inconsistent final predictions. To address this, we introduce two complementary approaches inspired by test-time scaling: (1) CASHEW, an inference-time framework that stabilizes reasoning by iteratively aggregating multiple candidate trajectories into higher-quality reasoning traces, with explicit visual verification filtering hallucinated steps and grounding reasoning in visual evidence, and (2) CASHEW-RL, a learned variant that internalizes this aggregation behavior within a single model. CASHEW-RL is trained using Group Sequence Policy Optimization (GSPO) with a composite reward that encourages correct answers grounded in minimal yet sufficient visual evidence, while adaptively allocating reasoning effort based on task difficulty. This training objective enables robust self-aggregation at inference. Extensive experiments on 13 image understanding, video understanding, and video reasoning benchmarks show significant performance improvements, including gains of up to +26.2 percentage points on ScienceQA and +9.1 percentage points on EgoSchema.

Chaoyu Li, Fei Tao, Pooyan Fazli

Arizona State University · NewsBreak

Test-Time Scaling for VLMs Test-Time Scaling Video Reasoning VLM Reasoning Visually Grounded Reasoning Multimodal Foundation Models+2

Jan 11, 2026cs.CV

CLIMP: Contrastive Language-Image Mamba Pretraining

Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and scales quadratically with resolution. To address these limitations, We present CLIMP, the first fully Mamba-based contrastive vision-language model that replaces both the vision and text encoders with Mamba. The new architecture encodes sequential structure in both vision and language, with VMamba capturing visual spatial inductive biases, reducing reliance on spurious correlations and producing an embedding space favorable for cross-modal retrieval and out-of-distribution robustness-surpassing OpenAI's CLIP-ViT-B by 7.5% on ImageNet-O. CLIMP naturally supports variable input resolutions without positional encoding interpolation or specialized training, achieving up to 6.6% higher retrieval accuracy at 16x training resolution while using 5x less memory and 1.8x fewer FLOPs. The autoregressive text encoder further overcomes CLIP's fixed context limitation, enabling dense captioning retrieval. Our findings suggest that Mamba exhibits advantageous properties for vision-language learning, making it a compelling alternative to Transformer-based CLIP.The code and models are publicly available at https://github.com/NimrodShabtay/CLIMP}

Nimrod Shabtay, Itamar Zimerman, Eli Schwartz +1

Tel-Aviv University · IBM Research

Cross-Modal Learning VLM Robustness Mamba Vision-Language Retrieval Multimodal Foundation Models Multimodal Contrastive Learning+1

Jan 10, 2026cs.CV

BabyVision: Visual Reasoning Beyond Language

While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.

Liang Chen, Weichu Xie, Yiyan Liang +27

1UniPat AI · 6Peking University · 3Alibaba Group +8

VLM Evaluation Visual Reasoning Multimodal Large Language Models Modality Gap in VLMs Visually Grounded Reasoning Multimodal Foundation Models+1

Dec 16, 2025cs.CL

Parameter Efficient Multimodal Instruction Tuning for Romanian Vision Language Models

Focusing on low-resource languages is an essential step toward democratizing generative AI. In this work, we contribute to reducing the multimodal NLP resource gap for Romanian. We translate the widely known Flickr30K dataset into Romanian and further extend it for visual question answering by leveraging open-source LLMs. We demonstrate the usefulness of our datasets by fine-tuning open-source VLMs on Romanian visual question answering. We select VLMs from three widely used model families: LLaMA 3.2, LLaVA 1.6, and Qwen2. For fine-tuning, we employ the parameter-efficient LoRA method. Our models show improved Romanian capabilities in visual QA, as well as on tasks they were not trained on, such as Romanian image description generation. The seven-billion-parameter Qwen2-VL-RoVQA obtains top scores on both tasks, with improvements of +2.29% and +4.45% in BERTScore F1 on VQA and captioning, respectively, over its original version. Finally, the models show substantial reductions in grammatical errors compared to their original forms, indicating improvements not only in language understanding but also in Romanian fluency.

George-Andrei Dima, Răzvan-Alexandru Smădu, Dumitru-Clementin Cercel

National University of Science and Technology POLITEHNICA Bucharest, Bucharest, Romania

Visual Question Answering Image Captioning Vision-Language Models VLM Adaptation Multimodal Foundation Models

Oct 24, 2025cs.AI

OpenPhone: Mobile Agentic Foundation Models

With the advancement of multimodal large language models (MLLMs), building GUI agent systems has become an increasingly promising direction--especially for mobile platforms, given their rich app ecosystems and intuitive touch interactions. Yet mobile GUI agents face a critical dilemma: truly on-device models (4B or smaller) lack sufficient performance, while capable models (starting from 7B) are either too large for mobile deployment or prohibitively costly (e.g., cloud-only closed-source MLLMs). To resolve this, we propose OpenPhone, a mobile GUI agent system that leverages device-cloud collaboration to tap the cost-efficiency of on device models and the high capability of cloud models, while avoiding their drawbacks. Specifically, OpenPhone enhances Qwen2.5-VL-3B via two-stage SFT->GRPO training on synthetic GUI data for strong decision-making, integrates an efficient long-reasoning and memory management mechanism to utilize historical interactions under tight resources, and defaults to on-device execution--only escalating challenging subtasks to the cloud via real-time complexity assessment. Experiments on the online AndroidLab benchmark and diverse apps show OpenPhone matches or nears larger models, with a significant reduction in cloud costs.

Yangqin Jiang, Chao Huang

The University of Hong Kong

On-Device Language Model Inference GUI Agents Mobile GUI Agents LLM Agent Training Multimodal Foundation Models

Oct 20, 2025cs.SE

From Charts to Code: A Hierarchical Benchmark for Multimodal Models

We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse real-world scenarios and progressively increasing task difficulty. It consists of three levels: Level 1 (Chart Reproduction) reproduces charts from a reference figure and user query; Level 2 (Chart Editing) involves complex modifications such as changing chart types or adding elements; and Level 3 (Long-Table to Chart Generation) requires models to transform long, information-dense tables into faithful charts following user instructions. To our knowledge, this is the first hierarchical benchmark that reflects practical chart2code usage while systematically scaling task complexity. In total, Chart2Code contains 2,023 tasks across 22 chart types, paired with multi-level evaluation metrics that assess both code correctness and the visual fidelity of rendered charts. We benchmark 25 state-of-the-art (SoTA) LMMs, including both proprietary and the latest open-source models such as GPT-5, Qwen2.5-VL, InternVL3/3.5, MiMo-VL, and Seed-1.6-VL. Experimental results demonstrate that even the SoTA model GPT-5 averages only 0.57 on code-based evaluation and 0.22 on chart-quality assessment across the editing tasks, underscoring the difficulty of Chart2Code. We anticipate this benchmark will drive advances in multimodal reasoning and foster the development of more robust and general-purpose LMMs. Our code and data are available on Chart2Code.

Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu +8

CSU-JPG, Central South University · National University of Singapore · Nanyang Technological University

Data Visualization Code Generation Code Generation Evaluation Multimodal Foundation Models Chart Understanding Multimodal Model Evaluation+1

Oct 14, 2025cs.CV

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a model's strong visual understanding often fails to transfer to visual generation: it may correctly judge prompt-image alignment while failing to generate a faithful image from the same prompt. This raises a compelling question: Can a model improve itself by using its understanding module to reward its generation module? We introduce SRUM, a self-rewarding post-training framework directly applicable to existing UMMs of various designs. SRUM creates a feedback loop where the model's own understanding module acts as an internal ``evaluator'', providing corrective signals to improve generation without additional human-labeled data or external reward models. To provide comprehensive feedback, SRUM uses a global-local dual reward system: a \textbf{global reward} ensures overall visual semantics and layout, while a \textbf{local reward} refines fine-grained, object-level fidelity. SRUM shows strong generalization, boosting performance on T2I-CompBench from 82.18 to \textbf{88.37} and on T2I-ReasonBench from 43.82 to \textbf{46.75}. Overall, our work establishes a powerful paradigm for enabling a UMM's understanding module to guide and enhance its own generation via self-rewarding.

Weiyang Jin, Yuwei Niu, Jiaqi Liao +4

HKU MMLab · The University of Hong Kong · Shenzhen Loop Area Institute +2

Unified Multimodal Models T2I Generation Generative Modeling Multimodal Reward Modeling RL for Image Generation Multimodal Foundation Models

Sep 28, 2025cs.CV

HunyuanImage 3.0 Technical Report

We present HunyuanImage 3.0, a native multimodal model that unifies multimodal understanding and generation within an autoregressive framework, with its image generation module publicly available. The achievement of HunyuanImage 3.0 relies on several key components, including meticulous data curation, advanced architecture design, a native Chain-of-Thoughts schema, progressive model pre-training, aggressive model post-training, and an efficient infrastructure that enables large-scale training and inference. With these advancements, we successfully trained a Mixture-of-Experts (MoE) model comprising over 80 billion parameters in total, with 13 billion parameters activated per token during inference, making it the largest and most powerful open-source image generative model to date. We conducted extensive experiments and the results of automatic and human evaluation of text-image alignment and visual quality demonstrate that HunyuanImage 3.0 rivals previous state-of-the-art models. By releasing the code and weights of HunyuanImage 3.0, we aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant multimodal ecosystem. All open source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanImage-3.0

Tencent Hunyuan Foundation Model Team

Tencent Hunyuan Foundation Model Team

Unified Multimodal Models Autoregressive Image Generation Multimodal Foundation Models

Sep 28, 2025cs.CV

LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models

Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. Post-training quantization (PTQ) has successfully compressed language models to as low as 1-bit precision, its effectiveness for multimodal LLMs (MLLMs) remains unexplored. In this paper, we present the first method for ultra-low-bit (<4-bit) quantization of MLLMs. Our analysis reveals that multimodal tokens and intermediate layer activations produced by them exhibit significantly higher entropy compared to text tokens, indicating greater functional complexity that makes MLLMs less tolerant to ultra-low bit quantization. However, this entropy varies significantly across layers, with some layers producing lower-entropy activation distributions that we empirically show can better tolerate ultra-low bit quantization. Existing PTQ methods optimize weight quantization within each layer but apply the same target precision uniformly, ignoring this variation in complexity across layers. Building on this insight, we propose LUQ: Layerwise Ultra-Low Bit Quantization, which characterizes each transformer layer's functional complexity via its output activation entropy and selectively applies ultra-low bit quantization to layers encoding simpler, more compressible functions. We also show that multimodal calibration (image and text tokens) boosts VQA performance in the ultra-low bit regime. Evaluated on LLaVA-1.5 and Qwen-2.5-VL across 9 VQA benchmarks, LUQ models use 40% and 31% less memory than their 4-bit counterparts while exhibiting less than 10% degradation on MME.

Shubhang Bhatnagar, Andy Xu, Kar-Han Tan +1

University of Illinois Urbana-Champaign · Work done as an intern at HP Inc. · University of California, Los Angeles +1

Mixed-Precision Quantization LLM Quantization VLM Quantization Multimodal Large Language Models Multimodal Foundation Models Post-Training Quantization+1

Sep 23, 2025cs.CV

Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation. Unlike existing multimodal MDMs such as MMaDa and Muddit which only support simple image-level understanding tasks and low-resolution image generation, Lavida-O presents a single framework that enables image-level understanding, object grounding, image editing, and high-resolution (1024px) text-to-image synthesis. Lavida-O incorporates a novel Elastic Mixture-of-Transformers (Elastic-MoT) architecture that couples a lightweight generation branch with a larger understanding branch, supported by token compression, universal text conditioning and stratified sampling for efficient and high-quality generation. Lavida-O further incorporates planning and iterative self-reflection in image generation and editing tasks, seamlessly boosting generation quality with its understanding capabilities. Lavida-O achieves state-of-the-art performance on a wide range of benchmarks including RefCOCO object grounding, GenEval text-to-image generation, and ImgEdit image editing, outperforming existing autoregressive models and continuous diffusion models such as Qwen2.5-VL and FluxKontext-dev, while offering considerable speedup at inference. These advances establish Lavida-O as a new paradigm for scalable multimodal reasoning and generation.

Shufan Li, Jiuxiang Gu, Kangning Liu +4

Adobe · UCLA

Masked Diffusion Models Unified Multimodal Models Multimodal Foundation Models Diffusion-Based Image Editing T2I Diffusion Models Diffusion Models+2

Sep 8, 2025cs.CV

Reconstruction Alignment Improves Unified Multimodal Models

Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image-text pairs (or sequences) whose captions are typically sparse and miss fine-grained visual details, even when they use hundreds of words to describe a simple image. We introduce Reconstruction Alignment (RECA), a resource-efficient post-training method that leverages visual understanding encoder embeddings as dense "text prompts", providing rich supervision without captions. Concretely, RECA conditions a UMM on its own visual understanding embeddings and optimizes it to reconstruct the input image with a self-supervised reconstruction loss, thereby realigning understanding and generation. Despite its simplicity, RECA is broadly applicable: across autoregressive, masked-autoregressive, and diffusion-based UMMs, it consistently improves generation and editing fidelity. With only 27 GPU hours, post-training with RECA substantially improves image generation performance on GenEval (0.73

\rightarrow

0.90) and DPGBench (80.93

\rightarrow

88.15), while also boosting editing benchmarks (ImgEdit 3.38

\rightarrow

3.75, GEdit 6.94

\rightarrow

7.27). Notably, RECA surpasses much larger open-source models and applies broadly across diverse UMM architectures, establishing it as an efficient and general post-training alignment strategy for UMMs.

Ji Xie, Trevor Darrell, Luke Zettlemoyer +1

1UC Berkeley · University of Washington · 3Duke University

Unified Multimodal Models Cross-Modal Alignment Multimodal Generation Multimodal Foundation Models Multimodal Understanding

Aug 19, 2025cs.CL

VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark

We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) interpret and reason over visual and textual information beyond English. VMMU consists of 2.5k multimodal questions across 7 tasks, covering a diverse range of problem contexts, including STEM problem solving, data interpretation, rule-governed visual reasoning, and abstract visual reasoning. All questions require genuine multimodal integration, rather than reliance on text-only cues or OCR-based shortcuts. We evaluate a diverse set of state-of-the-art proprietary and open-source VLMs on VMMU. Despite strong Vietnamese OCR performance, proprietary models achieve only 66% mean accuracy. Further analysis shows that the primary source of failure is not OCR, but instead multimodal grounding and reasoning over text and visual evidence. Code and data are available at https://vmmu-bench.github.io/

Vy Tuong Dang, An Vo, Emilio Villa-Cueva +4

KAIST · MBZUAI

VLM Evaluation Multimodal Reasoning Multilingual VLM Evaluation Vision-Language Grounding Visually Grounded Reasoning Multimodal Foundation Models+2

Aug 17, 2025cs.CV

Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping

Connecting pretrained vision and language models usually involves projecting image features into the language model's input space. Inverse-LLaVA reverses this mapping within decoder attention: language states are projected to the visual feature dimension, and modality-specific maps produce residual query, key, and value updates. Fusion and low-rank adaptation (LoRA) learn jointly from 665K visual instructions, with frozen backbones and no separate alignment stage. Across nine primary benchmark evaluations, the final 7B model approaches two-stage LLaVA-1.5 on several tasks. It scores 78.45% on VQAv2 versus 79.13% for official LLaVA-LoRA, and 50.96% versus 48.56% on VizWiz; TextVQA is lower at 56.96% versus 58.47%. Controlled studies examine fusion components, insertion depth, visual features, and language-model size. Representation analysis shows that the text maps preserve much of the pairwise similarity ordering while changing its geometric spread. Additional paired supervision improves celebrity recognition, while instruction replay repairs caption-induced answer-format failures. Analytical cost expressions and fixed-work profiles separate the additional fusion computation from the omitted alignment stage. These findings establish text-to-vision attention fusion as a practical alternative for instruction-only multimodal adaptation.

Xuhui Zhan, Tyler Derr

Data Science Institute, Vanderbilt University, 2201 West End Ave, Nashville, 37235, Tennessee, United States. · Computer Science Department, Vanderbilt University, 2201 West End Ave, Nashville, 37235, Tennessee, United States.

Cross-Modal Learning Cross-Modal Representation Learning Cross-Modal Alignment Multimodal Large Language Models Multimodal Reasoning Multimodal Foundation Models+1

Jul 21, 2025cs.CV

Position: Reasoning After Perception Means Reasoning Without Vision

A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language reasoning (e.g., chain-of-thought, in-context learning, or external tools). We challenge this assumption. We argue that for a broad class of visual tasks hard to specify in language, failures stem from a structural fatality where the temporal decision of \textit{when} to reason strictly dictates the spatial constraint of \textit{where} reasoning takes place. When visual reasoning is deferred to language generation, current architectures do not merely delay computation; they displace it from the continuous visual representation to a discrete textual space. Consequently, the sequential

Perception-then-Reasoning'' paradigm degenerates perception into a passive, one-off feature encoding process, rendering it functionally equivalent to

Reasoning-in-Text-Space'', where task-critical spatial signals are collapsed before reasoning begins. We substantiate this claim with the Turing Eye Test (TET): tasks that must be resolved in \emph{visual space} and are hard to verbalize; results show text-only reasoning cannot remedy these perceptual failures. Our findings suggest rethinking the architectural divide: shifting from reasoning \textit{about} perception to reasoning \textit{within} perception. This facilitates actively reasoning-driven perception that operates directly on pixel-level visual representations, rather than within a collapsed textual space.

Hongcheng Gao, Zihao Huang, Jingyi Tang +12

Tsinghua University · BIT · Peking University +6

Visual Reasoning VLM Reasoning Visually Grounded Reasoning Multimodal Foundation Models Active Visual Perception Multimodal Understanding

Jun 23, 2025cs.IR

Can Argus Judge Them All? Comparing VLMs Across Domains

Vision-Language Models (VLMs) are increasingly used in industry VLM applications such as retrieval systems, content generation platforms, and decision-support workflows, where model selection is commonly guided by benchmark rankings. These rankings are largely determined by retrieval, captioning, and reasoning downstream tasks; however, models with similar task performance often show substantially different behavior across datasets. This creates a Capability-Reliability Gap between benchmark performance and observed model stability. We present ARGUS-EVAL, a capability-reliability-oriented evaluation framework for VLMs that characterizes model behavior through Benchmark Capability P(M), Cross-Dataset Consistency CDC(M), Robustness Retention RR(M), and Efficiency E(M). We evaluate CLIP, BLIP, LXMERT, Gemma-3-4B, and Qwen-2.5VL-3B-Instruct across retrieval, captioning, and reasoning downstream tasks. The results reveal notable differences between capability-oriented and reliability-oriented rankings. Qwen-2.5VL-3BInstruct achieves the strongest overall capability (R@1 = 82.7%, BLEU-4 = 47.2%, CIDEr = 141.6, CDC = 0.91), whereas CLIP records the lowest latency (31 ms) and memory footprint (0.9 GB).

Harsh Joshi, Gautam Siddharth Kashyap, Rafiq Ali +5

Bharati Vidyapeeth, New Delhi, India · Macquarie University, Sydney, Australia · DSEU-Okhla, New Delhi, India +3

VLM Evaluation VLM Robustness Multimodal Foundation Models Cross-Dataset Generalization

Jun 8, 2025cs.CL

Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in understanding common visual elements, largely due to their large-scale datasets and advanced training strategies. However, their effectiveness in medical applications remains limited due to the inherent discrepancies between data and tasks in medical scenarios and those in the general domain. Concretely, existing medical MLLMs face the following critical limitations: (1) limited coverage of medical knowledge beyond imaging, (2) heightened susceptibility to hallucinations due to suboptimal data curation processes, (3) lack of reasoning capabilities tailored for complex medical scenarios. To address these challenges, we first propose a comprehensive data curation procedure that (1) efficiently acquires rich medical knowledge data not only from medical imaging but also from extensive medical texts and general-domain data; and (2) synthesizes accurate medical captions, visual question answering (VQA), and reasoning samples. As a result, we build a multimodal dataset enriched with extensive medical knowledge. Building on the curated data, we introduce our medical-specialized MLLM: Lingshu. Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities progressively. Besides, we preliminarily explore the potential of applying reinforcement learning with verifiable rewards paradigm to enhance Lingshu's medical reasoning ability. Additionally, we develop MedEvalKit, a unified evaluation framework that consolidates leading multimodal and textual medical benchmarks for standardized, fair, and efficient model assessment. We evaluate the performance of Lingshu on three fundamental medical tasks, multimodal QA, text-based QA, and medical report generation. The results show that Lingshu consistently outperforms the existing open-source multimodal models on most tasks ...

Weiwen Xu, Hou Pong Chan, Long Li +15

LASA Team · DAMO Academy, Alibaba Group

Medical Report Generation Multimodal Pretraining Multimodal QA Multimodal Reasoning Medical VLMs Multimodal Foundation Models+2

May 22, 2025cs.CV

Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding

In this work, we propose Dimple, the first Discrete Diffusion Multimodal Large Language Model (DMLLM). We observe that training with a purely discrete diffusion approach leads to significant training instability, suboptimal performance, and severe length bias issues. To address these challenges, we design a novel training paradigm that combines an initial autoregressive phase with a subsequent diffusion phase. This approach yields the Dimple-7B model, trained on the same dataset and using a similar training pipeline as LLaVA-NEXT. Dimple-7B ultimately surpasses LLaVA-NEXT in performance by 3.9%, demonstrating that DMLLM can achieve performance comparable to that of autoregressive models. To improve inference efficiency, we propose a decoding strategy termed confident decoding, which dynamically adjusts the number of tokens generated at each step, significantly reducing the number of generation iterations. In autoregressive models, the number of forward iterations during generation equals the response length. With confident decoding, however, the number of iterations needed by Dimple is even only

\frac{\text{response length}}{3}

. We also re-implement the prefilling technique in autoregressive models and demonstrate that it does not significantly impact performance on most benchmark evaluations, while offering a speedup of 1.5x to 7x. Additionally, we explore Dimple's capability to precisely control its response using structure priors. These priors enable structured responses in a manner distinct from instruction-based or chain-of-thought prompting, and allow fine-grained control over response format and length, which is difficult to achieve in autoregressive models. Overall, this work validates the feasibility and advantages of DMLLM and enhances its inference efficiency and controllability. Code and models are available at https://github.com/yu-rp/Dimple.

Runpeng Yu, Xinyin Ma, Xinchao Wang

National University of Singapore

Multimodal Large Language Models LLM Inference Acceleration Diffusion Language Model Decoding Multimodal Foundation Models Diffusion Language Models

May 22, 2025cs.CV

LaViDa: A Large Diffusion Language Model for Multimodal Understanding

Modern Vision-Language Models (VLMs) can solve a wide range of tasks requiring visual reasoning. In real-world scenarios, desirable properties for VLMs include fast inference and controllable generation (e.g., constraining outputs to adhere to a desired format). However, existing autoregressive (AR) VLMs like LLaVA struggle in these aspects. Discrete diffusion models (DMs) offer a promising alternative, enabling parallel decoding for faster inference and bidirectional context for controllable generation through text-infilling. While effective in language-only settings, DMs' potential for multimodal tasks is underexplored. We introduce LaViDa, a family of VLMs built on DMs. We build LaViDa by equipping DMs with a vision encoder and jointly fine-tune the combined parts for multimodal instruction following. To address challenges encountered, LaViDa incorporates novel techniques such as complementary masking for effective training, prefix KV cache for efficient inference, and timestep shifting for high-quality sampling. Experiments show that LaViDa achieves competitive or superior performance to AR VLMs on multi-modal benchmarks such as MMMU, while offering unique advantages of DMs, including flexible speed-quality tradeoff, controllability, and bidirectional reasoning. On COCO captioning, LaViDa surpasses Open-LLaVa-Next-8B by +4.1 CIDEr with 1.92x speedup. On bidirectional tasks, it achieves +59% improvement on Constrained Poem Completion. These results demonstrate LaViDa as a strong alternative to AR VLMs. Code and models will be released in the camera-ready version.

Shufan Li, Konstantinos Kallidromitis, Hritik Bansal +7

1UCLA · 2Panasonic AI Research · 4Salesforce Research +1

Vision-Language Models Efficient VLM Inference Controllable Text Generation Multimodal Foundation Models Diffusion Language Models Multimodal Diffusion Models+1

May 16, 2025cs.CV

HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation

Although recent large multimodal models (LMMs) show impressive progress on vision language tasks, their alignment with human centered (HC) principles such as fairness, ethics, inclusivity, empathy, and robustness is often overlooked. Existing LMM benchmarks are largely accuracy-agnostic. We present HumaniBench, a unified framework for characterizing HC alignment across realistic, socially grounded visual contexts. It contains 32,000 expert-verified image-question pairs from real-world news imagery, each mapped to one or more HC principles through explicit metrics. Comparing 15 state of the art LMMs reveals consistent trade -offs: proprietary systems lead on ethics, reasoning, and empathy, while open-source models show superior visual grounding and resilience. All models show persistent gaps in fairness and multilingual inclusivity. Chain-of-thought prompting and test-time scaling yield 8to 12 % gains on several HC dimensions. HumaniBench enables fine-grained analysis of alignment trade-offs not captured by conventional multimodal benchmarks. https://vectorinstitute.github.io/humanibench/

Shaina Raza, Aravind Narayanan, Vahid Reza Khazaie +6

Vector Institute for Artificial Intelligence, Toronto, Canada · University of Central Florida, Orlando, USA

Algorithmic Fairness Multimodal Large Language Models Multimodal Foundation Models Multimodal Model Evaluation Multimodal Understanding

May 15, 2025cs.LG

ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset

Conventional forecasting methods are trained end-to-end on unimodal time series, which limits their ability to exploit textual information and undermines their generalization in data-scarce scenarios. Recently, large language models (LLMs) and time series foundation models (TSFMs) have demonstrated powerful capabilities in complex textual reasoning and zero-shot temporal modeling, respectively. Integrating these strengths to construct a multimodal time series foundation model that jointly leverages temporal and textual information for zero-shot future inference has emerged as a promising research direction. However, the scarcity of large-scale, high-quality multimodal datasets remains a fundamental obstacle. To address this challenge, we propose ChronoSteer, a decoupled agentic framework that learns cross-modal alignment from synthetic paired supervision. Specifically, a pretrained LLM first converts textual events into revision instructions that steer the initial unimodal prediction produced by a frozen TSFM. These revision instructions form an intermediate instruction space that bridges the semantic gap between text and time series while fully leveraging pretrained knowledge. Technically, the instructions are discretized into a compact codebook of instruction anchors, effectively mitigating semantic divergence while reducing the cost of dataset construction. Finally, we adopt a two-stage training strategy to recover the fine-grained magnitude information lost during discretization. Furthermore, we release a leakage-controlled multimodal benchmark constructed with temporal separation and textual context available before the prediction window. When paired with an LLM and trained on synthetic cross-modal alignment data, ChronoSteer achieves a 25.8% improvement in zero-shot prediction accuracy over its unimodal backbone, and outperforms prior state-of-the-art unimodal and multimodal ...

Chengsen Wang, Qi Qi, Zhongwen Rao +2

Beijing University of Posts and Telecommunications · Huawei Noah’s Ark Lab

Cross-Modal Learning Multivariate Time Series Forecasting Zero-Shot Time Series Forecasting Cross-Modal Alignment Multimodal Foundation Models Time-Series Foundation Models

Feb 13, 2025cs.CV

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Large Multimodal Models (LMMs) exhibit shortfalls when interpreting images and, by some measures, have poorer spatial cognition than young children or animals. Despite this, they attain high scores on many popular visual benchmarks, with headroom rapidly eroded by model progress. This creates a need for difficult benchmarks that remain relevant for longer. We introduce ZeroBench - a lightweight visual reasoning benchmark curated using adversarial filtering to be "impossible" for frontier LMMs at its original release, with initial SotA scores of 0% pass@1 and pass^5. We track progress on ZeroBench over the subsequent year, observing SotA reaching 6% pass^5 and 19% pass@5, indicating the potential longevity of the benchmark. We evaluate 46 LMMs on ZeroBench, compare performance to a human baseline, analyse strengths and weaknesses, chart a year of progress in visual capabilities, and publicly release ZeroBench at https://zerobench.github.io.

Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma +31

University of Cambridge

Visual Reasoning VLM Reasoning Visually Grounded Reasoning Multimodal Foundation Models Multimodal Model Evaluation Multimodal Understanding

Feb 11, 2025cs.CV

Histopathology Multi-modal Embedding for Pathology Composed Retrieval

To overcome the black-box nature of predictive AI and the hallucination risks of generative models, retrieval-based models offer an interpretable, evidence-based paradigm for pathology clinical workflow. However, real-world clinical queries are inherently interleaved (e.g., pathology images and text). Current dual-encoders suffer from an \textbf{Architectural Mismatch}, lacking the mechanism to fuse such composed queries. To address this, we formalize the task of Pathology Composed Retrieval (PCR). While Multimodal Large Language Models (MLLMs) offer deep-fusion capabilities, directly applying them exposes a \textbf{Task Mismatch} and a \textbf{Domain Mismatch}. To resolve these challenges, we propose HOMIE, a model-agnostic adaptation framework that transforms any generative MLLM into a specialized pathology retrieval expert. Evaluated on our newly introduced PCR Benchmark, a lightweight 2B-parameter HOMIE variant substantially outperforms existing paradigms, surpassing specialized 7B pathology MLLMs and dual-encoders by large margins on composed retrieval, while maintaining strong performance on traditional simple retrieval. The project page is available at https://qfchou.github.io/HOMIE_page/.

Qifeng Zhou, Wenliang Zhong, Thao M. Dang +4

The University of Texas at Arlington, Arlington TX 76010, USA

Computational Pathology Healthcare Multimodal Large Language Models Multimodal Foundation Models Composed Image Retrieval

Oct 19, 2024cs.CL

MultiViewDx: Evidence-Linked Multi-View Clinical Diagnosis

Medical multimodal large language models (MLLMs) can perform well on existing medical visual question answering (MedVQA) benchmarks, but their training data often does not match clinical diagnosis. Most supervision is organized around isolated images or short QA pairs, leaving two structures weakly specified: how evidence leads to a decision, and how views, series, modalities, and patient context from the same case are linked. We introduce MultiViewDx, a partly physician-validated multimodal instruction dataset for evidence-linked multi-view medical imaging diagnosis. MultiViewDx uses the clinical case as the supervision unit. It links imaging studies with patient context, normalizes heterogeneous reports into an evidence-linked workflow (evidence -> findings -> differential discussion -> diagnosis), and uses a unified image-text retriever to constrain instruction synthesis to source-supported evidence. It covers X-ray, CT, MRI, ultrasound, histopathology, and other clinical visual sources. We fine-tune MultiViewDx-8B-AN and evaluate it on both existing MedVQA benchmarks and real-world case-based diagnostic reasoning. Across four MedVQA benchmarks, it achieves the best average accuracy among compared systems (79.0%), outperforming HuatuoGPT-Vision-34B (66.7%) and Claude3-Opus (55.7%). Beyond MedVQA, on JAMA Clinical Challenge cases, it receives the strongest overall rating under a physician-designed rubric for key clinical points, diagnostic inference, and evidence grounding. Controlled ablations and clinician evaluation show that both case-level multi-view organization and evidence-linked reasoning targets contribute to the gain.

Junda Wang, Zonghai Yao, Yujan Ting +5

United Imaging Intelligence, MA, USA · Manning College of Information and Computer Sciences, University of Massachusetts Amherst, MA, USA · Department of Medicine, University of Massachusetts Medical School, Worcester, MA, USA +1

Healthcare Medical Image Analysis Medical VQA Medical Image Grounding Multimodal Foundation Models Multimodal Instruction Tuning+1

Jul 16, 2024cs.CV

VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models

We present VLMEvalKit: an open-source toolkit for evaluating large multi-modality models based on PyTorch. The toolkit aims to provide a user-friendly and comprehensive framework for researchers and developers to evaluate existing multi-modality models and publish \textbf{reproducible} evaluation results. In VLMEvalKit, we implement over 450+ large multi-modality model configurations, including both proprietary APIs and open-source models, and support 330+ benchmarks across diverse multi-modal benchmarks. By implementing a single interface, new models can be easily added to the toolkit, while the toolkit automatically handles the remaining workloads, including data preparation, distributed inference, prediction post-processing, and metric calculation. VLMEvalKit has also evolved to a broader evaluation suite spanning video/audio, document understanding, GUI grounding, spatial reasoning, safety, scientific reasoning, and multi-turn dialogue. Based on the evaluation results obtained with the toolkit, we host the OpenVLM Leaderboard, a comprehensive leaderboard to track the progress of multi-modality learning research. The toolkit is released on https://github.com/open-compass/VLMEvalKit and is actively maintained.

Haodong Duan, Xinyu Fang, Junming Yang +41

VLM Evaluation LLM Evaluation Multimodal Foundation Models Multimodal Model Evaluation Multimodal Understanding

Date pendingcs.CV

ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation

We present ABACUS, a unified vision-language model that jointly addresses object counting, crowd counting, referring-expression counting, and count-faithful image generation within a single 3B-parameter model. ABACUS introduces three contributions: density-aware adaptive zooming paired with an objectness map from multi-head self-attention decomposition to spatially ground count predictions; a boundary-aware count policy trained via GRPO with nested local, boundary, and global rewards to eliminate over- and undercounting at crop boundaries; and a cycle-consistent GRPO strategy in which the frozen understanding branch scores generated candidates on count-deviation and aesthetic quality, closing the understanding-generation synergy gap without any external critic or annotation. ABACUS achieves state-of-the-art results across seven benchmarks spanning object counting (FSC-147, CARPK), crowd counting (ShanghaiTech A/B), referring-expression counting (REC-8K), count-faithful generation (CoCoCount, T2I-CompBench, GenEval), and count reasoning (CountQA), surpassing both task-specific specialists and larger generalist models. Project page is at https://mondalanindya.github.io/pages/ABACUS.

Anindya Mondal, Sauradip Nag, Anjan Dutta

University of Surrey, United Kingdom & Simon Fraser University, Canada · University of Surrey, United Kingdom

VLM Adaptation Crowd Counting Object Counting Multimodal Foundation Models Controllable Image Generation RL for VLMs

Date pendingcs.CV

Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap

Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesizes code, or imagines new imagery, each at the cost of a tool protocol, brittle code, or an expensive training pipeline. A fourth route makes vision dynamic without generating anything, by retrieving labeled exemplar images and reasoning over them, yet it remains underexplored despite being train-free. We present ReVisIT, a train-free framework that realizes this retrieval-based route by treating each retrieved image-label pair as a unit of visual thought. ReVisIT combines structured class definitions, per-query multimodal retrieval of exemplars, and alternating user/assistant injection of those exemplars before joint multi-attribute decoding, and degrades gracefully to whichever components a task admits. On VL-ICL Bench Fast Open MiniImageNet, Qwen3-VL-30B-A3B with ReVisIT reaches 98.5% at 4-shot, statistically indistinguishable from the 72B LLaVA-OneVision SOTA (98.7%) on this near-saturated task at about 1/2.4 the parameters, while the same backbone without the scaffold sits at chance. The turns layer alone adds 26.1 points to GPT-4.1 on free-form concept induction (Bongard-OpenWorld), and the full stack yields a 4-6 point macro gain across three backbones on MAAC-Bench, a new license-clean 27-class, 5-attribute benchmark, significant by paired bootstrap on the curator-derived attributes. Component analysis shows that retrieval-plus-turns is the universal lever while structured definitions are need-adaptive, and that 83% of the retrieval gain comes from retrieval quality rather than from the presence of exemplars. MAAC-Bench is released with a rubric-grounded LLM verification protocol that replaces author spot-check on subjective attributes.

Bingchen Huang, Zhiling Wang, Yifu Chen +1

Meituan

Multimodal RAG Multimodal ICL In-Context Learning VLM Reasoning Visually Grounded Reasoning Multimodal Foundation Models