2 papers
cs.LG2026
GSS: Gated Subspace Steering for Selective Memorization Mitigation in LLMs
Xuanqi Zhang, Haoyang Shang, Xiaoxiao Li
Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply…
cs.CV2024
LLEMamba: Low-Light Enhancement via Relighting-Guided Mamba with Deep Unfolding Network
Xuanqi Zhang, Haijin Zeng, Jinwang Pan +2
Transformer-based low-light enhancement methods have yielded promising performance by effectively capturing long-range dependencies in a global context. However, their elevated com…