Yuying Ge

15

Papers

16

Total Citations

Papers (15)

GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers

Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation

AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction

SEED-Bench: Benchmarking Multimodal Large Language Models

ViT-Lens: Towards Omni-modal Representations

DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images

Parser-Free Virtual Try-On via Distilling Appearance Flows

Bridging Video-Text Retrieval With Multiple Choice Questions

All in One: Exploring Unified Video-Language Pre-Training

Learning Transferable Spatiotemporal Representations From Natural Script Knowledge

Policy Adaptation From Foundation Model Feedback

MILES: Visual BERT Pre-training with Injected Language Semantics for Video-Text Retrieval

Disentangled Cycle Consistency for Highly-Realistic Virtual Try-On

Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

JourneyDB: A Benchmark for Generative Image Understanding