相关论文: Leveraging Latent Visual Reasoning in Silence

When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For…

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies…

Latent reasoning enables reasoning over continuous hidden states rather than explicit tokens, avoiding the language bottleneck and inference overhead of chain-of-thought for medical VQA. However, existing methods suffer from modality…

Reinforcement learning (RL) has emerged as a promising approach for eliciting reasoning chains before generating final answers. However, multimodal large language models (MLLMs) generate reasoning that lacks integration of visual…

Reinforcement learning (RL) with verifiable rewards has become a standard post-training stage for boosting visual reasoning in vision-language models, yet it remains unclear what capabilities RL actually improves compared with supervised…

Large Language Models (LLMs), despite being trained on text alone, surprisingly develop rich visual priors. These priors allow latent visual capabilities to be unlocked for vision tasks with a relatively small amount of multimodal data, and…

Recent large vision-language models (LVLMs) have demonstrated impressive reasoning ability by generating long chain-of-thought (CoT) responses. However, CoT reasoning in multimodal contexts is highly vulnerable to visual hallucination…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when observations contain action-correlated distractors, often…

Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and…

Vision-Language Models (VLMs) often suffer from visual hallucinations: generating things that are not consistent with visual inputs and language shortcuts, where they skip the visual part and just rely on text priors. These issues arise…

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…

The spatial reasoning task aims to reason about the spatial relationships in 2D and 3D space, which is a fundamental capability for Visual Question Answering (VQA) and robotics. Although vision language models (VLMs) have developed rapidly…

Latent reasoning models (LRMs) have attracted significant research interest due to their low inference cost (relative to explicit reasoning models) and theoretical ability to explore multiple reasoning paths in parallel. However, these…

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…

Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer…

Reward feedback learning (ReFL) has proven effective for aligning image generation with human preferences. However, its extension to video generation faces significant challenges. Existing video reward models rely on vision-language models…

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…

Enhancing the multimodal reasoning capabilities of Multimodal Large Language Models (MLLMs) is a challenging task that has attracted increasing attention in the community. Recently, several studies have applied Reinforcement Learning with…

Video reasoning, the task of enabling machines to infer from dynamic visual content through multi-step logic, is crucial for advanced AI. While the Chain-of-Thought (CoT) mechanism has enhanced reasoning in text-based tasks, its application…