Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
RAPTOR: Ridge-Adaptive Logistic Probes
Ziqi Gao, Yaotian Zhu, Qingcheng Zeng +4
Probing studies what information is encoded in a frozen LLM's layer representations by training a lightweight predictor on top of them. Beyond analysis, probes are often used opera…
cs.LG2025
FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
Heming Zou, Yunliang Zang, Wutong Xu +2
Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models, but it suffers from parameter interference, resulting in suboptimal perfor…
cs.LG2025
Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
Xiaodan Li, Mengjie Wu, Yao Zhu +5
Large models (LMs) are powerful content generators, yet their open-ended nature can also introduce potential risks, such as generating harmful or biased content. Existing guardrail…