← Search

Fanyi Zeng

2 accepted papers

2026

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation

AAAI 2026technical

Layer pruning is a viable technique for compressing large language models while achieving acceleration proportional to the pruning ratio. In this work, we identify that removing any layer induces a magnitude gap in hidden states, and demonstrate that a simple compensation operation leads to superior

Cited by 0SourcePDFScholar
2025

Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement Learning

UAI 2025

Offline reinforcement learning (RL) heavily relies on the coverage of pre-collected data over the target policy’s distribution. Existing studies aim to improve data-policy coverage to mitigate distributional shifts, but overlook security risks from insufficient coverage, and the single-step analysis

Cited by 0SourcePDFScholar