Related papers: Beyond Perceptual Shortcuts: Causal-Inspired Debia…

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…

Video large language models (Video LLMs) achieve strong benchmark accuracy, yet often answer video questions through shortcuts such as single-frame cues and language priors rather than by tracking spatiotemporal dynamics. This issue is…

DeepSeek-R1-Zero has successfully demonstrated the emergence of reasoning capabilities in LLMs purely through Reinforcement Learning (RL). Inspired by this breakthrough, we explore how RL can be utilized to enhance the reasoning capability…

While recent advances in reinforcement learning have significantly enhanced reasoning capabilities in large language models (LLMs), these techniques remain underexplored in multi-modal LLMs for video captioning. This paper presents the…

Large language models (LLMs) tackle complex tasks by generating long chains of thought or "reasoning traces" that act as latent variables in the generation of an output given a query. A model's ability to generate such traces can be…

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward…

Visual understanding is inherently intention-driven - humans selectively focus on different regions of a scene based on their goals. Recent advances in large multimodal models (LMMs) enable flexible expression of such intentions through…

Recent advances in video generation have enabled the synthesis of videos with strong temporal consistency and impressive visual quality, marking a crucial step toward vision foundation models. To evaluate these video generation models,…

The "Reason-Then-Respond" paradigm, enhanced by Reinforcement Learning, has shown great promise in advancing Multimodal Large Language Models. However, its application to the video domain has led to specialized models that excel at either…

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…

Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-language models (VLMs). However, its outcome-level supervision is too coarse to diagnose and…

Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual…

While Chain-of-Thought (CoT) significantly enhances the performance of Large Language Models (LLMs), explicit reasoning chains introduce substantial computational redundancy. Recent latent reasoning methods attempt to mitigate this by…

Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short…

Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning over uniformly sampled frames, which weakens temporal localization and leads to substantial…

Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs across various applications. While supervised fine-tuning…

Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning with rule-based rewards.…

Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still struggles to achieve reliable spatio-temporal grounding…

Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, our initial experiments reveal that incorporating a thinking…

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection,…