7 papers
Distilled Reinforcement Learning for LLM Post-training
Chen Wang, Zhaochun Li, Jionghao Bai +4
Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL)…
Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment
Chunyu Hu, Tianyin Liao, Ge Lan +4
The paper introduces GTAlign, a simple framework that aligns graph structures to tabular representations, enabling a text-free Graph Foundation Model that uses community-guided con…
SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
Chen Wang, Zhaochun Li, Jionghao Bai +3
Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entro…
Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training
Chen Wang, Hexuan Deng, Yining Zhang +5
Reinforcement learning with verifiable rewards improves LLM reasoning but often induces overthinking, where models generate unnecessarily long reasoning traces. Existing methods ma…
A Two-Stage GPU Kernel Tuner Combining Semantic Refactoring and Search-Based Optimization
Qiuyi Qu, Yicheng Sui, Yufei Sun +5
GPU code optimization is a key performance bottleneck for HPC workloads as well as large-model training and inference. Although compiler optimizations and hand-written kernels can…
Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off
Zhaochun Li, Chen Wang, Jionghao Bai +4
The exploration-exploitation (EE) trade-off is a central challenge in reinforcement learning (RL) for large language models (LLMs). With Group Relative Policy Optimization (GRPO),…