Related papers: See, Think, Learn: A Self-Taught Multimodal Reason…

Vision-language-action models (VLAs) have shown potential in leveraging pretrained vision-language models and diverse robot demonstrations for learning generalizable sensorimotor control. While this paradigm effectively utilizes large-scale…

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…

In this paper, we address the challenging task of multimodal reasoning by incorporating the notion of ``slow thinking'' into multimodal large language models (MLLMs). Our core idea is that models can learn to adaptively use different levels…

Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to…

We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the…

Humans are born with vision-based 4D spatial-temporal intelligence, which enables us to perceive and reason about the evolution of 3D space over time from purely visual inputs. Despite its importance, this capability remains a significant…

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive…

The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the…

Compositional reasoning remains a persistent weakness of modern vision language models (VLMs): they often falter when a task hinges on understanding how multiple objects, attributes, and relations interact within an image. Multiple research…

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…

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…

In recent years, large language models (LLMs) have demonstrated significant potential in complex reasoning tasks like mathematical problem-solving. However, existing research predominantly relies on reinforcement learning (RL) frameworks…

Vision-language models (VLMs) are widely assumed to exhibit in-context learning (ICL), a property similar to that of their language-only counterparts. While recent work suggests VLMs can perform multimodal ICL (MM-ICL), studies show they…

Visual reasoning is challenging, requiring both precise object grounding and understanding complex spatial relationships. Existing methods fall into two camps: language-only chain-of-thought approaches, which demand large-scale (image,…

Recent developments have enabled Large Language Models (LLMs) to engage in complex reasoning tasks through deep thinking. However, the capacity of reasoning has not been successfully transferred to non-high-resource languages due to…

The video reasoning ability of multimodal large language models (MLLMs) is crucial for downstream tasks like video question answering and temporal grounding. While recent approaches have explored text-based chain-of-thought (CoT) reasoning…

Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, most existing large language models (LLMs) treat the reasoning and verification as…

Recent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing frameworks treat visual actions as optional tools, boosting…

Vision-language tracking has received increasing attention in recent years, as textual information can effectively address the inflexibility and inaccuracy associated with specifying the target object to be tracked. Existing works either…

Large Language Models (LLMs) have shown remarkable performance on complex reasoning tasks, especially when equipped with long chain-of-thought (CoT) reasoning. However, eliciting long CoT typically requires large-scale reinforcement…