8 papers
DRIFT: Refining Instruction Data via On-Policy Data Attribution
Zefan Wang, Lincheng Li, Tianyu Yu +1
Optimizing the training data distribution for Supervised Fine-Tuning (SFT) dictates the capability of Large Language Models (LLMs). While existing data curation methods excel at ac…
Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning
Fanhu Zeng, Zhicong Luo, Zefan Wang +3
Visual reasoning through reinforcement learning with verifiable rewards (RLVR) has achieved remarkable progress. However, when dealing with multi-source inputs, existing approaches…
GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
Fengxiang Wang, Mingshuo Chen, Yueying Li +11
Ultra-high-resolution (UHR) remote sensing (RS) imagery offers valuable data for Earth observation but pose challenges for existing multimodal foundation models due to two key bott…
Process Reinforcement through Implicit Rewards
Ganqu Cui, Lifan Yuan, Zefan Wang +22
Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in ta…
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
Tianyu Yu, Zefan Wang, Chongyi Wang +31
Multimodal Large Language Models (MLLMs) are undergoing rapid progress and represent the frontier of AI development. However, their training and inference efficiency have emerged a…
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
Shangzhan Li, Zefan Wang, Ye He +8
Kernel development in deep learning requires optimizing computational units across hardware while balancing memory management, parallelism, and hardware-specific optimizations thro…