α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Runjin Chen
Runjin Chen
4
papers
52
total citations
papers (4)
SEAL: Steerable Reasoning Calibration of Large Language Models for Free
COLM 2025
arXiv
41
citations
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment
COLM 2025
arXiv
5
citations
LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
COLM 2025
arXiv
5
citations
Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
ICML 2025
arXiv
1
citations