collaborators

6 papers

cs.CR2026

How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment

Guang Yang, Fengchen Liu, Alex Wang +2

State-aligned distortion has been documented in China-origin text-based large language models (LLMs), but whether, and in what form, it arises in multimodal systems has not been sy…

cs.CR2026

GLID: Gated Local Intrinsic Dimension Repairs the Blind Spots of Face-Forgery Detectors

Guang Yang, Fengchen Liu

Fine-tuned foundation-model detectors dominate face-forgery benchmarks, yet they stay blind to generator families absent from training. We present GLID, a detector that repairs thi…

cs.AI2026

MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection

Zhewen Tan, Yilun Yao, Huiyan Jin +9

Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizon task execution. However, t…

cs.AI2026

Echo: Learning from Experience Data via User-Driven Refinement

Hande Dong, Xiaoyun Liang, Jiarui Yu +15

Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions bet…

cs.CR2026

Asking Back: Interaction-Layer Antidistillation Watermarks

Guang Yang, Amir Ghasemian, Fengchen Liu +3

Detecting unauthorized knowledge distillation from a deployed LLM API is hard because the defender controls neither the attacker's training pipeline nor the next-token logits. Exis…

cs.CL2024

Aggregated Knowledge Model: Enhancing Domain-Specific QA with Fine-Tuned and Retrieval-Augmented Generation Models

Fengchen Liu, Jordan Jung, Wei Feinstein +2

This paper introduces a novel approach to enhancing closed-domain Question Answering (QA) systems, focusing on the specific needs of the Lawrence Berkeley National Laboratory (LBL)…