7 papers
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…
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…
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…
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…
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…
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…