Yichen Li
6 papers · Latest:
Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs
AugMP is a novel graph representation learning strategy to manipulate federated fine-tuning of LLMs, reducing accuracy and evading defenses.
CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers
CoCoReviewBench is a new benchmark for AI reviewers, focusing on completeness and correctness by curating 3,900 papers with expert annotations.
FingerEye: Continuous and Unified Vision-Tactile Sensing for Dexterous Manipulation
FingerEye is a novel sensor providing continuous vision-tactile feedback for dexterous manipulation, enabling seamless pre-contact to post-contact perception.
Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing
This paper proposes Cascaded Code Editing, combining large models for edit sketch generation and small models for efficient application.
TypeScript Repository Indexing for Code Agent Retrieval
A new TypeScript parser for ABCoder improves code indexing efficiency for LLM agents by using the TypeScript Compiler API.
Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective
This paper reveals how BPE tokenization creates a "gibberish bias" in Code LLMs, making certain high-entropy secrets easier to memorize and leak.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.