Related papers: DeepEyes: Incentivizing "Thinking with Images" via…

Agentic multimodal models should not only comprehend text and images, but also actively invoke external tools, such as code execution environments and web search, and integrate these operations into reasoning. In this work, we introduce…

Accurate medical diagnosis often involves progressive visual focusing and iterative reasoning, characteristics commonly observed in clinical workflows. While recent vision-language models demonstrate promising chain-of-thought (CoT)…

General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on…

Vision language models (VLMs) are increasingly capable of reasoning over images, but robust visual reasoning often requires re-grounding intermediate steps in the underlying visual evidence. Recent approaches typically rely on external…

Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these multi-modal models cannot distinguish…

We present Thinking with Generated Images, a novel paradigm that fundamentally transforms how large multimodal models (LMMs) engage with visual reasoning by enabling them to natively think across text and vision modalities through…

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…

Multimodal Large Language Models (MLLMs) exhibit impressive performance across various visual tasks. Subsequent investigations into enhancing their visual reasoning abilities have significantly expanded their performance envelope. However,…

Recent advances in large Vision-Language Models (VLMs) have exhibited strong reasoning capabilities on complex visual tasks by thinking with images in their Chain-of-Thought (CoT), which is achieved by actively invoking tools to analyze…

Models capable of "thinking with images" by dynamically grounding their reasoning in visual evidence represent a major leap in multimodal AI. However, replicating and advancing this ability is non-trivial, with current methods often trapped…

Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…

The "thinking with images" paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of-thought to image-interactive reasoning. By invoking visual tools or generating intermediate…

Multimodal Large Language Models (MLLMs) often struggle to accurately perceive fine-grained visual details, especially when targets are tiny or visually subtle. This challenge can be addressed through semantic-visual information fusion,…

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…

Successful and effective communication between humans and AI relies on a shared experience of the world. By training solely on written text, current language models (LMs) miss the grounded experience of humans in the real-world -- their…

Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise. While recent works have attempted to adapt DeepSeek-R1-style reinforcement learning (RL)…

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced reasoning capabilities in Large Language Models. However, adapting RLVR to multimodal domains suffers from a critical \textit{perception-reasoning decoupling}.…

Reinforcement Learning Finetuning (RFT) has significantly advanced the reasoning capabilities of large language models (LLMs) by enabling long chains of thought, self-correction, and effective tool use. While recent works attempt to extend…

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…

Deep learning based data-driven approaches have been successfully applied in various image understanding applications ranging from object recognition, semantic segmentation to visual question answering. However, the lack of knowledge…