8 papers
Skip-Connected Policy Optimization for Implicit Advantage
Fengwei Teng, Jinyi Bai, Xinhao Yao +3
Group Relative Policy Optimization (GRPO) has proven effective in RLVR by using outcome-based rewards. While fine-grained dense rewards can theoretically improve performance, we re…
GRIP: Geometric Refinement and Adaptive Information Potential for Data Efficiency
Changhao Wang, Jiaolong Yang, Xinhao Yao +7
The performance of Large Language Models (LLMs) is increasingly governed by data efficiency rather than raw scaling volume. However, existing selection methods often decouple globa…
UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining
Changhao Wang, Yunfei Yu, Xinhao Yao +5
The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure…
Beyond the Black Box: A Survey on the Theory and Mechanism of Large Language Models
Zeyu Gan, Ruifeng Ren, Wei Yao +9
The rapid emergence of Large Language Models (LLMs) has precipitated a profound paradigm shift in Artificial Intelligence, delivering monumental engineering successes that increasi…
The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
Xinhao Yao, Lu Yu, Xiaolin Hu +4
The ongoing debate on whether reinforcement learning with verifiable rewards (RLVR) expands or shrinks the reasoning capabilities of large language models (LLMs) remains unresolved…
MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core
Dennis Liu, Zijie Yan, Xin Yao +15
Mixture of Experts (MoE) models enhance neural network scalability by dynamically selecting relevant experts per input token, enabling larger model sizes while maintaining manageab…