collaborators

10 papers

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.AI2026

Language-based Trial and Error Falls Behind in the Era of Experience

Haoyu Wang, Guozheng Ma, Shugang Cui +7

While Large Language Models (LLMs) excel in language-based agentic tasks, their applicability to unseen, nonlinguistic environments (e.g., symbolic or spatial tasks) remains limite…

cs.AI2026

Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System

Yanming Li, Xuelin Zhang, WenJie Lu +11

Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving complex problems. However, training…

cs.CL2026

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning

Liang Chen, Xueting Han, Li Shen +2

Supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) are two widely used post-training paradigms for improving the reasoning ability of large lang…

cs.CV2025

DeContext as Defense: Safe Image Editing in Diffusion Transformers

Linghui Shen, Mingyue Cui, Xingyi Yang

In-context diffusion models allow users to modify images with remarkable ease and realism. However, the same power raises serious privacy concerns: personal images can be easily ma…

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,…