xichen

xichenhku's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 8 papers about 1 month ago

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

Paper • 2506.14574 • Published Jun 17 • 1

ROSE: Remove Objects with Side Effects in Videos

Paper • 2508.18633 • Published Aug 26 • 7

Animate-X++: Universal Character Image Animation with Dynamic Backgrounds

Paper • 2508.09454 • Published Aug 13

Factuality Matters: When Image Generation and Editing Meet Structured Visuals

Paper • 2510.05091 • Published Oct 6 • 19

From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models

Paper • 2510.05095 • Published Oct 6 • 1

Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents

Paper • 2510.06214 • Published Oct 7 • 1

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

Paper • 2510.13809 • Published Oct 15 • 37

PICABench: How Far Are We from Physically Realistic Image Editing?

Paper • 2510.17681 • Published Oct 20 • 62

authored a paper 5 months ago

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning

Paper • 2506.22434 • Published Jun 27 • 10

authored 3 papers 6 months ago

ObjectMover: Generative Object Movement with Video Prior

Paper • 2503.08037 • Published Mar 11 • 5

PlayerOne: Egocentric World Simulator

Paper • 2506.09995 • Published Jun 11 • 34

LayerFlow: A Unified Model for Layer-aware Video Generation

Paper • 2506.04228 • Published Jun 4 • 13

authored 3 papers 11 months ago

MangaNinja: Line Art Colorization with Precise Reference Following

Paper • 2501.08332 • Published Jan 14 • 61

LogoSticker: Inserting Logos into Diffusion Models for Customized Generation

Paper • 2407.13752 • Published Jul 18, 2024

VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control

Paper • 2501.01427 • Published Jan 2 • 54

authored 2 papers 12 months ago

FashionComposer: Compositional Fashion Image Generation

Paper • 2412.14168 • Published Dec 18, 2024 • 16

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

Paper • 2412.07774 • Published Dec 10, 2024 • 30

authored 3 papers over 1 year ago

Zero-shot Image Editing with Reference Imitation

Paper • 2406.07547 • Published Jun 11, 2024 • 33

Wear-Any-Way: Manipulable Virtual Try-on via Sparse Correspondence Alignment

Paper • 2403.12965 • Published Mar 19, 2024 • 2

OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

Paper • 2309.00616 • Published Sep 1, 2023 • 1