Showing 2026 · cs.LGShow all
2 papers · 2 filters
cs.LG2026
CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning
Zhiren Gong, Zihao Zeng, Zijie Wang +3
Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups. Most training-free…
cs.LG2026
Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits
Zhiren Gong, He Lu, Zihao Zeng +6
Mechanistic interpretability seeks to explain transformer behavior through circuits: sets of internal components that causally support a behavior. However, self-repair creates a bl…