5 papers
What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom
Yan Ma, Weiyu Zhang, Tianle Li +3
Vision tool-use reinforcement learning (RL) can equip vision language models with visual operators such as crop-and-zoom and achieves strong performance gains, yet it remains uncle…
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Yan Ma, Linge Du, Xuyang Shen +7
Reinforcement learning (RL) is becoming an important direction for post-training vision-language models (VLMs), but public training methodologies for unified multimodal RL remain m…
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
SII-GAIR, Sand. ai, : +43
We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation. daVinci-MagiHuman jointly generates synchronized video and audio…
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
Yan Ma, Steffi Chern, Xuyang Shen +2
Reinforcement learning (RL) has recently shown strong potential in improving the reasoning capabilities of large language models and is now being actively extended to vision-langua…
Weak-to-Strong Reasoning
Yuqing Yang, Yan Ma, Pengfei Liu
When large language models (LLMs) exceed human-level capabilities, it becomes increasingly challenging to provide full-scale and accurate supervision for these models. Weak-to-stro…