6 papers · 1 filter
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
He Du, Qiming Ge, Jiakai Hu +18
We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented…
How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
Zixian Huang, Kaichen Yang, Xu Huang +6
A widely adopted strategy for model enhancement is to use synthetic data generated by a stronger model for supervised fine-tuning (SFT). However, for emerging reasoning models like…
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design
Xu Guo, Qiming Ge, Jian Tong +8
Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (M…
Pre-Trained Policy Discriminators are General Reward Models
Shihan Dou, Shichun Liu, Yuming Yang +19
We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guidi…
Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law
Qiming Ge, Shuhao Xing, Songyang Gao +8
Scaling law builds the relationship between training computation and validation loss, enabling researchers to effectively predict the loss trending of models across different level…
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data
Han Xia, Songyang Gao, Qiming Ge +3
Reinforcement Learning from Human Feedback (RLHF) has proven effective in aligning large language models with human intentions, yet it often relies on complex methodologies like Pr…