Zihan Li
6 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.
This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preservation.
The paper introduces Plan, a structured agentic behavior that decomposes multi-hop questions into ordered sub-questions before retrieval, and proposes a self-bootstrapping paradigm to train it without relying on model distillation.
The paper introduces MemCog, a Memory-as-Cognition system that integrates memory access directly into the reasoning process, significantly improving agent performance, especially in proactive memory retrieval tasks.
The paper introduces PIGMENT, a physics-informed foundation model that enables reliable quantitative mapping of brain microstructure from extremely sparse or challenging diffusion MRI scans.
The paper proposes DySCo, a dynamic trust-aware sparse consensus mechanism, to efficiently manage communication in multi-agent LLM systems by selectively connecting agents based on real-time value, thus reducing overhead while maintaining critical cross-validation.
Papers
Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus
The paper proposes DySCo, a dynamic trust-aware sparse consensus mechanism, to efficiently manage communication in multi-agent LLM systems by selectively connecting agents based on real-time value, th…