Ye Wang

11

Papers

167

Total Citations

Papers (11)

When Attention Sink Emerges in Language Models: An Empirical View

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models

OmniStyle: Filtering High Quality Style Transfer Data at Scale

SigStyle: Signature Style Transfer via Personalized Text-to-Image Models

A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

MotionCtrl: A Real-time Controllable Vision-Language-Motion Model

LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs

Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage

MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models