8 papers
Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs
Zeyuan Yang, Zhuohao Chen, Jiaben Chen +3
Reinforcement learning has brought strong gains to language model reasoning, but its improvements on visual tasks remain less consistent. One difficulty is that visual task failure…
Multimodal Thinking with Renderable Programs
Sunli Chen, Ding Zhong, Ziqiao Ma +6
Current vision-language models (VLMs) excel at visual content understanding and text-based reasoning, yet their structure limits the advancement of incorporating images into the re…
UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation
Zeyuan Yang, Hao-Wei Chen, Xueyang Yu +5
Recent years have seen remarkable progress in unified vision-language models handling both multimodal understanding and generation within a single architecture. While autoregressiv…
Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
Zeyuan Yang, Xueyang Yu, Delin Chen +2
Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand v…
Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering
Guangtao Zeng, Maohao Shen, Delin Chen +8
Language models (LMs) perform well on standardized coding benchmarks but struggle with real-world software engineering tasks such as resolving GitHub issues in SWE-Bench, especiall…
Scaling Autonomous Agents via Automatic Reward Modeling And Planning
Zhenfang Chen, Delin Chen, Rui Sun +2
Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step deci…
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
Maohao Shen, Guangtao Zeng, Zhenting Qi +7
Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains. Recent studies have shown that increasing test-time computation enhances LL…
VCA: Video Curious Agent for Long Video Understanding
Zeyuan Yang, Delin Chen, Xueyang Yu +2
Long video understanding poses unique challenges due to their temporal complexity and low information density. Recent works address this task by sampling numerous frames or incorpo…