Related papers: Visual Attention Reasoning via Hierarchical Search…

Recent advancements in long chain-of-thought (CoT) reasoning, particularly through the Group Relative Policy Optimization algorithm used by DeepSeek-R1, have led to significant interest in the potential of Reinforcement Learning with…

Reinforcement Learning has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet the resulting policies remain brittle against real-world visual degradations such as blur, compression artifacts,…

Medical vision-language models (VLMs) excel at image-text understanding but typically rely on a single-pass reasoning that neglects localized visual cues. In clinical practice, however, human experts iteratively scan, focus, and refine the…

Despite progress in Large Vision-Language Models (LVLMs), their capacity for visual reasoning is often limited by the binding problem: the failure to reliably associate perceptual features with their correct visual referents. This…

Recent advancements in Large Vision-Language Models have showcased remarkable capabilities. However, they often falter when confronted with complex reasoning tasks that humans typically address through visual aids and deliberate,…

Recently, Multimodal Large Language Models (MLLMs) have made rapid progress, particularly in enhancing their reasoning capabilities. However, existing reasoning benchmarks still primarily assess language-based reasoning, often treating…

Although Multimodal Large Language Models (MLLMs) have demonstrated increasingly impressive performance in chart understanding, most of them exhibit alarming hallucinations and significant performance degradation when handling non-annotated…

Self-consistency methods are the core technique for improving the reasoning reliability of multimodal large language models (MLLMs). By generating multiple reasoning results through repeated sampling and selecting the best answer via…

Visual retrieval-augmented generation (VRAG) augments vision-language models (VLMs) with external visual knowledge to ground reasoning and reduce hallucinations. Yet current VRAG systems often fail to reliably perceive and integrate…

Effectively retrieving, reasoning and understanding visually rich information remains a challenge for RAG methods. Traditional text-based methods cannot handle visual-related information. On the other hand, current vision-based RAG…

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…

Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that…

Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models (MLLMs). While vision-centric post-training is crucial for…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…

Recent breakthroughs in reasoning language models have significantly advanced text-based reasoning. On the other hand, Multi-modal Large Language Models (MLLMs) still lag behind, hindered by their outdated internal LLMs. Upgrading these…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Medical vision-language models (VLMs) show strong performance on radiology tasks but often produce fluent yet weakly grounded conclusions due to over-reliance on a dominant modality. We introduce a context-aligned reasoning framework that…

Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to use tools for verification, limiting their reliability on…

Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations. While hallucinations are well-studied, the exact causes behind them remain underexplored. In this…

Building on recent advances in language-based reasoning models, we explore multimodal reasoning that integrates vision and text. Existing multimodal benchmarks primarily test visual extraction combined with text-based reasoning, lacking…