12 papers
LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation
Tankun Li, Zhi Chen, Yaohua Tang
Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities. To bypass the heavy memory footprint of critic n…
TCPO: Turn-Level Credit Policy Optimization
Sicong Liao, Zhi Chen, Yaohua Tang
Verifier-guided reinforcement learning has become a powerful paradigm for improving LLM reasoning. In multi-turn settings, models receive a verifier score after each turn and itera…
Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold
Songshuo Lu, Zhi Chen, Yaohua Tang
The paper proposes an expand‑then‑compress framework that builds a diverse set of RL‑trained teacher models and then distills them into a single student model, improving reasoning,…
MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU
Kun Cheng, Songshuo Lu, Sicong Liao +7
Native GPU kernel generation turns high-level tensor programs into executable, efficient low-level code. Existing Large Language Models (LLMs) struggle with this task, while execut…
ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting
Luchao Wang, Kaimin Liao, Qian Ren +3
A converged 3D Gaussian Splatting (3DGS) model may approximate the target scene while remaining poorly parameterized for further optimization. We identify this failure mode as \emp…
LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning
Yubin Wu, Zicheng Cai, Liping Ning +4
Developing lightweight, on-device vision-language GUI agents is essential for efficient cross-platform automated interaction. However, current on-device agents are constrained by l…