Xiaofei He

Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model

How Do Language Models Speak Languages? A Case Study on Unintended Code-Switching

SyncKV: A Syncopated Scheduling Approach to KV Cache Compression for Efficient Long-Context LLM Inference

Self-Supervised Direct Preference Optimization for Text-to-Image Diffusion Models

Depth Any Video with Scalable Synthetic Data

SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement

Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach

Large Language Models Can Be More Robust Multiple Choice Selectors Through Attention Intervention

Interpretable Analysis and Reasoning Enhancement for LLMs via Cross-Generation Reasoning Trees

LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models

MatchMask: Mask-Centric Generative Data Augmentation for Label-Scarce Semantic Segmentation

SciPIP: An LLM-based Scientific Paper Idea Proposer