Cheng Liu

This paper provides the first comprehensive, end-to-end survey dedicated to the security of Retrieval-Augmented Generation (RAG) systems, systematically mapping threats, defenses, and benchmarks across the entire pipeline.

This paper evaluates the vulnerability of Fully Homomorphic Encryption (FHE) computation to silent data corruption (SDC) using large-scale fault-injection experiments and theoretical analysis.

TrajGuard is a novel, training-free defense framework that detects jailbreaks by monitoring the progressive risk signals embedded in the hidden-state trajectories of tokens during the LLM decoding process, achieving a high defense rate with low latency.

The paper introduces MOV-Bench, a challenging benchmark for multi-hop audio-visual reasoning, and proposes AOP-Agent, an agentic framework that significantly improves open-source Omni-LLMs' ability to perform active cross-modal perception.

FT-Pilot is a novel GNN-guided LLM framework that automatically rewrites RTL code to harden digital circuits against soft errors, providing an efficient, automated path for reliability optimization.

The paper introduces LLMSurgeon, a framework that estimates the domain-level data mixture of a Large Language Model (LLM) using only generated text, thereby providing a post-hoc method to audit the model's 'digital DNA'.

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training and rollout.

The paper introduces pause-and-think-T, a reasoning-centric dataset and benchmark that enables compact Vision-Language Models to perform visually grounded, context-aware action suggestion, matching large models like GPT-4o.

The JAMEL framework addresses the challenge of effective exploration in open-ended environments by jointly training agent memory and exploration policies using natural, novelty-driven signals.

The paper introduces OpAI-Bench, a novel benchmark designed to study how AI authorship signals evolve and accumulate during the progressive co-editing process between humans and AI.