Related papers: TangramSR: Can Vision-Language Models Reason in Co…

Natural language can offer a concise and human-interpretable means of specifying reinforcement learning (RL) tasks. The ability to extract rewards from a language instruction can enable the development of robotic systems that can learn from…

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address…

Recent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time. In contrast, humans leverage the metacognitive model with memory,…

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…

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for…

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Recently, newly developed Vision-Language Models (VLMs), such as OpenAI's o1, have emerged, seemingly demonstrating advanced reasoning capabilities across text and image modalities. However, the depth of these advances in language-guided…

Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already demonstrated impressive capabilities in common visual…

Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs), but often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers during…

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference…

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…

Understanding visual degradations is a critical yet challenging problem in computer vision. While recent Vision-Language Models (VLMs) excel at qualitative description, they often fall short in understanding the parametric physics…

Multi-modal Large Language Models (MLLMs) have advanced greatly in general tasks. However, they still face challenges in geometric reasoning, a task that requires synergistic integration of visual recognition proficiency and complex…

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…

Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs). Yet, its efficacy in training vision-language model (VLM) agents for goal-directed…

Vision-Language(-Action) Models (VLMs) are increasingly applied to interactive environments, yet existing benchmarks often overlook the complex physical reasoning required for point-and-click puzzle games. This paper introduces…

Tool use, such as web search, has become a standard capability even in freely available large language models (LLMs). However, existing benchmarks evaluate temporal reasoning mainly in static, non-tool-using settings, which poorly reflect…

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…

The advancement of embodied intelligence is accelerating the integration of robots into daily life as human assistants. This evolution requires robots to not only interpret high-level instructions and plan tasks but also perceive and adapt…

While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual reasoning introduces added complexity by requiring models to direct visual attention,…