Related papers: Reward Design for Physical Reasoning in Vision-Lan…
While chain-of-thought (CoT) reasoning has substantially improved multimodal large language models (MLLMs) on complex reasoning tasks, existing approaches largely rely on long textual reasoning trajectories and provide limited mechanisms…
Recent advances in vision-language models (VLMs) have demonstrated strong generalization in natural image tasks. However, their performance often degrades on unmanned aerial vehicle (UAV)-based aerial imagery, which features high…
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 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 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…
Visual reasoning abilities play a crucial role in understanding complex multimodal data, advancing both domain-specific applications and artificial general intelligence (AGI). Existing methods enhance Vision-Language Models (VLMs) through…
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…
Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT)…
Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool use scenarios. Recent advancements in reinforcement…
Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) because it can perform fine-grained evaluation of the reasoning steps of generated content. However, most PRMs lack long-term reasoning and deep…
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…
When faced with complex problems, we tend to engage in slower, more deliberate thinking. In contrast, for simple questions we give quick, intuitive responses. This dual-system thinking approach allows us to allocate cognitive resources…
Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image…
Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack…
Vision Language Models exhibit impressive performance for various tasks, yet they often lack the sophisticated situational reasoning required for complex decision-making. This paper shows that VLMs can achieve surprisingly strong…
Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the…
The diagnosis of pathological images is often limited by expert availability and regional disparities, highlighting the importance of automated diagnosis using Vision-Language Models (VLMs). Traditional multimodal models typically emphasize…
Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce. Recent open-source work like DeepSeek-R1 demonstrates…
This paper investigates Reinforcement Learning (RL) approaches to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Although RL algorithms such as Group Relative Policy…
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…