Zixuan Hu

UltraHorizon: Benchmarking LLM-Agent Capabilities in Ultra Long-Horizon Scenarios

A Bias–Variance Tradeoff Perspective for Improving Test-Time Scaling

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent

LoRA Recycle: Towards Fine-Tuning-Free Visual Foundation Model via Double-Efficient Data-Free Meta-Learning