Related papers: MJ1: Multimodal Judgment via Grounded Verification

Multimodal LLMs often produce fluent yet unreliable reasoning, exhibiting weak step-to-step coherence and insufficient visual grounding, largely because existing alignment approaches supervise only the final answer while ignoring the…

Models capable of "thinking with images" by dynamically grounding their reasoning in visual evidence represent a major leap in multimodal AI. However, replicating and advancing this ability is non-trivial, with current methods often trapped…

We address the problem of phrase grounding by lear ing a multi-level common semantic space shared by the textual and visual modalities. We exploit multiple levels of feature maps of a Deep Convolutional Neural Network, as well as…

Recently, the role of LLM-as-judge in evaluating large language models has gained prominence. However, current judge models suffer from narrow specialization and limited robustness, undermining their capacity for comprehensive evaluations.…

Multimodal large language models (MLLMs) have advanced perception across text, vision, and audio, yet they often struggle with structured cross-modal reasoning, particularly when integrating audio and visual signals. We introduce…

Recent video multimodal large language models achieve impressive results across various benchmarks. However, current evaluations suffer from two critical limitations: (1) inflated scores can mask deficiencies in fine-grained visual…

We introduce V-tableR1, a process-supervised reinforcement learning framework that elicits rigorous, verifiable reasoning from multimodal large language models (MLLMs). Current MLLMs trained solely on final outcomes often treat visual…

Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…

Recent advances in generative AI have significantly enhanced the realism of multimodal media manipulation, thereby posing substantial challenges to manipulation detection. Existing manipulation detection and grounding approaches…

Recent advances in Vision-Language Models (VLMs) have improved performance in multi-modal learning, raising the question of whether these models truly understand the content they process. Crucially, can VLMs detect when a reasoning process…

The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle…

Large language models have achieved remarkable success on final-answer mathematical problems, largely due to the ease of applying reinforcement learning with verifiable rewards. However, the reasoning underlying these solutions is often…

According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language models (LLMs). However, in the multimodal (MM) domain, there is…

Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific…

Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences. However, their ability to follow diverse, fine-grained…

Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able to synthesize vision-centric problems spanning diverse levels…

Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while…

Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hallucination, attention leakage, and failures in object…

Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions, yet existing methods typically rely on memorizing isolated artifacts and struggle with imperceptible manipulation…

Instruction tuning of large vision-language models (LVLMs) increasingly depends on massive multimodal corpora, yet these datasets contain samples with substantial redundancy, low visual dependency, and highly imbalanced coverage of…