Xinchi Qiu

Hallucination Reduction with CASAL: Contrastive Activation Steering for Amortized Learning

MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates

DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation Models

Preserving Ignorance Awareness in LLM Fine-Tuning

DEPT: Decoupled Embeddings for Pre-training Language Models

LLM Unlearning via Neural Activation Redirection