Yunzhe Qi

Influence-Preserving Proxies for Gradient-Based Data Selection in LLM FineTuning

AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning

Auto-regressive In-context Demonstration Selection

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning

Automatic Task-aware Instruction Optimizer for Black-box LLMs

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

Robust Watermarking for Diffusion Models: A Unified Multi-Dimensional Recipe