activity
20232026
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Mingyue Cui, Linghui Shen, Xingyi Yang

Sparse Autoencoders (SAEs) decompose residual-stream activations into interpretable features. Recent latent-space defenses increasingly rely on these decompositions, assuming that…

cs.LG2025

Provably Robust Adaptation for Language-Empowered Foundation Models

Yuni Lai, Xiaoyu Xue, Linghui Shen +5

Language-empowered foundation models (LeFMs), such as CLIP and GraphCLIP, have transformed multimodal learning by aligning visual (or graph) features with textual representations,…

cs.LG2025

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

Liang Chen, Xueting Han, Li Shen +2

Harmful fine-tuning (HFT), performed directly on open-source LLMs or through Fine-tuning-as-a-Service, breaks safety alignment and poses significant threats. Existing methods aim t…

cs.LG2025

Exploration by Random Distribution Distillation

Zhirui Fang, Kai Yang, Jian Tao +4

Exploration remains a critical challenge in online reinforcement learning, as an agent must effectively explore unknown environments to achieve high returns. Currently, the main ex…

cs.LG2025

PEARL: Towards Permutation-Resilient LLMs

Liang Chen, Li Shen, Yang Deng +3

The in-context learning (ICL) capability of large language models (LLMs) enables them to perform challenging tasks using provided demonstrations. However, ICL is highly sensitive t…

cs.LG2025

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing

Kunfeng Lai, Zhenheng Tang, Xinglin Pan +7

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation…