activity
20242026
collaborators

7 papers

cs.CL2026

SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization

Jinyang Wu, Changpeng Yang, Yuhao Shen +9

Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fa…

cs.CL2025

From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks

Changpeng Yang, Jinyang Wu, Yuchen Liu +9

Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each…

cs.CL2025

RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing

Ruihan Jin, Pengpeng Shao, Zhengqi Wen +4

The rapid advancements in large language models (LLMs) have led to the emergence of routing techniques, which aim to efficiently select the optimal LLM from diverse candidates to t…

cs.LG2025

Two-Stage Regularization-Based Structured Pruning for LLMs

Mingkuan Feng, Jinyang Wu, Siyuan Liu +7

The deployment of large language models (LLMs) is largely hindered by their large number of parameters. Structural pruning has emerged as a promising solution. Prior structured pru…

cs.CL2025

AStar: Boosting Multimodal Reasoning with Automated Structured Thinking

Jinyang Wu, Mingkuan Feng, Guocheng Zhai +7

Multimodal large language models excel across diverse domains but struggle with complex visual reasoning tasks. To enhance their reasoning capabilities, current approaches typicall…

cs.LG2025

DReSS: Data-driven Regularized Structured Streamlining for Large Language Models

Mingkuan Feng, Jinyang Wu, Shuai Zhang +5

Large language models (LLMs) have achieved significant progress across various domains, but their increasing scale results in high computational and memory costs. Recent studies ha…