相关论文: OmniDiagram: Advancing Unified Diagram Code Genera…

DeepSeek-R1 has demonstrated powerful reasoning capabilities in the text domain through stable reinforcement learning (RL). Recently, in the multimodal domain, works have begun to directly apply RL to generate R1-like free-form reasoning…

Knowledge-Based Visual Question Answering (KB-VQA) requires models to answer questions about an image by integrating external knowledge, posing significant challenges due to noisy retrieval and the structured, encyclopedic nature of the…

Large language models can generate executable code for educational animations, but the resulting renders often exhibit visual defects, including element overlap, misalignment, and broken animation continuity. These defects cannot be…

Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose…

Recent large multimodal models (LMMs) have made rapid progress in visual grounding, document understanding, and diagram reasoning tasks. However, their ability to convert Printed Circuit Board (PCB) schematic diagrams into machine-readable…

Using vision-language models (VLMs) as reward models in reinforcement learning holds promise for reducing costs and improving safety. So far, VLM reward models have only been used for goal-oriented tasks, where the agent must reach a…

Designing a single model to address multiple tasks has been a long-standing objective in artificial intelligence. Recently, large language models have demonstrated exceptional capability in solving different tasks within the language…

Vision-language models (VLMs) have shown promise in graph structure understanding, but remain limited by input-token constraints, facing scalability bottlenecks and lacking effective mechanisms to coordinate textual and visual modalities.…

Visual retrieval-augmented generation (VRAG) augments vision-language models (VLMs) with external visual knowledge to ground reasoning and reduce hallucinations. Yet current VRAG systems often fail to reliably perceive and integrate…

Image-to-code generation tests whether a vision-language model (VLM) can recover the structure of an image enough to express it as executable code. Existing benchmarks either focus on narrow visual domains, depend on paired executable…

While humans perceive the world through diverse modalities that operate synergistically to support a holistic understanding of their surroundings, existing omnivideo models still face substantial challenges on audio-visual understanding…

Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the…

While multimodal large language models have advanced across text, image, and audio, personalization research has remained primarily vision-language, with unified omnimodal benchmarking that jointly covers text, image, and audio still…

Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions through shortcuts or prior familiarity with a chart based on their own background…

Automatically generating training supervision for embodied tasks is crucial, as manual designing is tedious and not scalable. While prior works use large language models (LLMs) or vision-language models (VLMs) to generate rewards, these…

Graph Retrieval-Augmented Generation (GraphRAG) has shown great effectiveness in enhancing the reasoning abilities of LLMs by leveraging graph structures for knowledge representation and modeling complex real-world relationships. However,…

We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets. We have developed a strong and robust question engine that leverages scene…

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…

End-to-end autonomous driving models based on Vision-Language-Action (VLA) architectures have shown promising results by learning driving policies through behavior cloning on expert demonstrations. However, imitation learning inherently…

Long Chain-of-Thought (LCoT), achieved by Reinforcement Learning with Verifiable Rewards (RLVR), has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs). However, reasoning in current LLMs is primarily…