7 papers
Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
Baicheng Chen, Zheyuan Liu, Jingyu Zhang +4
Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations rather than model parameters alo…
Controllable Molecular Generative Foundation Models
Yihan Zhu, Yuhan Liu, Weijiang Li +2
Despite the success of foundation models in language and vision, molecular graph generation still lacks a unified framework for heterogeneous design tasks with reliable controllabi…
3DEditSafe: Defending 3D Editing Pipelines from Unsafe Generation
Nicole Meng, Zheyuan Liu, Meng Jiang +1
Recent advances in 3D generative editing, particularly pipelines based on 3D Gaussian Splatting (3DGS), have achieved high-fidelity, multi-view-consistent scene manipulation from t…
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
Diancheng Kang, Zheyuan Liu, Ningshan Ma +3
Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful…
Dual-Space Smoothness for Robust and Balanced LLM Unlearning
Han Yan, Zheyuan Liu, Meng Jiang
As large language models evolve, Machine Unlearning has emerged to address growing concerns around user privacy, copyright infringement, and overall safety. Yet state-of-the-art (S…
Incorporating Rather Than Eliminating: Achieving Fairness for Skin Disease Diagnosis Through Group-Specific Expert
Gelei Xu, Yuying Duan, Zheyuan Liu +5
AI-based systems have achieved high accuracy in skin disease diagnostics but often exhibit biases across demographic groups, leading to inequitable healthcare outcomes and diminish…