Zhong Li
10 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper identifies and characterizes 'guidance injection,' a stealthy attack vector that embeds adversarial operational narratives into autonomous coding agents' bootstrap guidance, demonstrating high success rates and evasion capabilities.
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 proposes $D^3$, a dynamic graph-constrained scheduling framework that optimizes LLM training order by modeling sample interactions as a dynamic influence graph.
The paper proposes DiReCT, a novel framework that treats data selection during LLM annealing as a constrained optimization problem based on the spectral geometry of the loss landscape, achieving state-of-the-art performance.
The paper introduces DiscourseFlip, a novel graph-guided attack that demonstrates how coordinated poisoning across a multi-topic query space can manipulate the overall opinion generated by black-box Retrieval-Augmented Generation (RAG) systems.
The paper introduces DiscourseFlip, a novel black-box, graph-guided attack that manipulates opinions across an entire multi-topic query network, demonstrating a significant leap in scope and effectiveness over existing RAG attack methods.
This paper proposes Gleam, a framework for efficient GPU sharing across local-area CUDA devices, reducing bandwidth overhead, improving API call latency, and ensuring context consistency.
This paper investigates the performance of various methods in reciprocity-based over-the-air split learning.
This paper studies the properties of Gaussian random wave fields on lattices and their implications for signal processing and communication systems.
This paper evaluates a simple inference-time scaling approach for large language model agents on complex tasks.