Related papers: Learning to Think Fast and Slow for Visual Languag…

When applying reinforcement learning--typically through GRPO--to large vision-language model reasoning struggles to effectively scale reasoning length or generates verbose outputs across all tasks with only marginal gains in accuracy. To…

Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning (RL), typically Group Relative Policy Optimization (GRPO), these models are able to solve complex tasks such as mathematics and…

Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference. However, applying elaborate reasoning for all queries often results in…

The dual thinking framework considers fast, intuitive, and slower logical processing. The perception of dual thinking in vision requires images where inferences from intuitive and logical processing differ, and the latter is under-explored…

Human cognition is theorized to operate in two modes: fast, intuitive System 1 thinking and slow, deliberate System 2 thinking. While current Large Reasoning Models (LRMs) excel at System 2 thinking, their inability to perform fast thinking…

Despite tremendous recent advances in large model reasoning ability, vision-language models (VLMs) still struggle with detailed visual reasoning, especially when compute resources are limited. To address this challenge, we draw inspiration…

Recently, slow-thinking reasoning systems, built upon large language models (LLMs), have garnered widespread attention by scaling the thinking time during inference. There is also growing interest in adapting this capability to multimodal…

Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\textbf{VRMs}). owever, such transfer faces critical…

Learning general-purpose reasoning capabilities has long been a challenging problem in AI. Recent research in large language models (LLMs), such as DeepSeek-R1, has shown that reinforcement learning techniques like GRPO can enable…

Reinforcement Learning (RL) has proven to be an effective post-training strategy for enhancing reasoning in vision-language models (VLMs). Group Relative Policy Optimization (GRPO) is a recent prominent method that encourages models to…

Multimodal large language models (MLLMs) still struggle with complex reasoning tasks in Visual Question Answering (VQA). While current methods have advanced by incorporating visual prompts, our study uncovers critical limitations: these…

While recent large vision-language models (VLMs) have improved generalization in vision-language navigation (VLN), existing methods typically rely on end-to-end pipelines that map vision-language inputs directly to short-horizon discrete…

Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thinking approaches often lead to overthinking, where models…

Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs. Recently, this paradigm has been extended to multimodal tasks, leading to the development of diffusion multimodal large language…

Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…

Reinforcement learning with verifiable rewards (RLVR) has significantly advanced the reasoning ability of vision-language models (VLMs). However, the inherent text-dominated nature of VLMs often leads to insufficient visual faithfulness,…

A major drawback of reasoning models is their excessive token usage, inflating computational cost, resource demand, and latency. We show this verbosity stems not from deeper reasoning but from reinforcement learning loss minimization when…

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…

Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visual perception with language reasoning. However, they often suffer from overthinking, producing unnecessarily long reasoning…

Recent work on enhancing the reasoning abilities of large language models (LLMs) has introduced explicit length control as a means of constraining computational cost while preserving accuracy. However, existing approaches rely on…