1 citations · 1 across the 8 of their papers we have counts for
7 papers · 1 filter
GroupMask: Layer-Adaptive Group-wise Sparsity for Semi-Structured LLM Pruning
Zhengao Li, Shuoqiu Li, Xiaofang Zhang +7
Semi-structured pruning compresses large language models (LLMs) while keeping a regular sparse structure, but the prevailing N:M pattern fixes the same local sparsity ratio in ever…
TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces
Dehai Min, Daoan Zhang, Yiming Zeng +13
An agent can complete a task while exhibiting undesirable behavior during execution. Developers need tests for the specific behaviors encountered in deployment, beyond fixed benchm…
SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning
Zhuochun Li, Yuelyu Ji, Yiming Zeng +1
Reinforcement learning-based knowledge distillation has the potential to transfer complex reasoning from teacher to student models, yet it currently faces a critical dilemma: resea…
MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation
Yiming Zeng, Lei Lu, Zexin Li +10
Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of large language models, but existing MoE-based PEFT methods typically improve capacity by storing multiple ful…
ConFL: Explainable Concurrent Fault Localization via Hierarchy-Guided LLM Reasoning
Shuai Shao, Dingbang Wang, Yiming Zeng +1
Localizing concurrent bugs from bug reports alone is challenging due to incomplete information, misleading program-entity mentions, and complex cross-thread interactions, causing e…
HyperFL: Query-Adaptive Representation Learning for Software Fault Localization
Shuai Shao, Yiming Zeng, Yu Zhao +1
Software fault localization identifies the code locations responsible for reported issues and is a fundamental step toward automated debugging and program repair. Recent retrieval-…
Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
Zhuochun Li, Yong Zhang, Ming Li +8
Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design. In th…