Related papers: VisRef: Visual Refocusing while Thinking Improves …

The development of Multi-modal Large Language Models (MLLMs) enhances Large Language Models (LLMs) with the ability to perceive data formats beyond text, significantly advancing a range of downstream applications, such as visual question…

Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and…

Recent advances in reinforcement learning (RL) have strengthened the reasoning capabilities of vision-language models (VLMs). However, enhancing policy exploration to better scale test-time compute remains largely underexplored. In…

Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show…

Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable reasoning. This limitation is especially pronounced in tasks…

Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their…

Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that get correct answers by chance. We observe that better…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Recently DeepSeek R1 demonstrated how reinforcement learning with simple rule-based incentives can enable autonomous development of complex reasoning in large language models, characterized by the "aha moment", in which the model manifest…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic reasoning, and struggle with long-form video question…

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancing complex reasoning in large language models, and recent work extends RLVR to multimodal large language models (MLLMs). This transfer,…

While recent multimodal models have shown progress in vision-language tasks, small-scale variants still struggle with the fine-grained temporal reasoning required for video understanding. We introduce ReasonAct, a method that enhances video…

Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regions of interest (RoIs) by injecting cropped image patches or…

Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in…

Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling. While reinforcement…

While Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Vision-Language Models (LVLMs), most existing methods in multimodal reasoning neglect the critical role of visual perception within…

Traditional multimodal retrieval systems rely primarily on bi-encoder architectures, where performance is closely tied to embedding dimensionality. Recent work, Think-Then-Embed (TTE), shows that incorporating multimodal reasoning to elicit…

Vision-Language Models (VLMs) have achieved remarkable progress across tasks such as visual question answering and image captioning. Yet, the extent to which these models perform visual reasoning as opposed to relying on linguistic priors…