Xi Yang

ianyeung's activity

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

upvoted a paper 1 day ago

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration

Paper • 2605.31039 • Published 5 days ago • 34

upvoted 2 papers 4 days ago

SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control

Paper • 2605.27891 • Published 7 days ago • 6

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Paper • 2605.30263 • Published 6 days ago • 53

liked a dataset 5 days ago

facebook/sam-3d-body-dataset

Viewer • Updated Nov 19, 2025 • 5.66M • 590 • 56

liked a model 6 days ago

meituan-longcat/LongCat-Video-Avatar-1.5

Updated 1 day ago • 174 • 476

liked a dataset 7 days ago

SingleBicycle/4KLSDB

Viewer • Updated 7 days ago • 406k • 4.43k • 3

upvoted a paper 8 days ago

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

Paper • 2605.21573 • Published 14 days ago • 107

upvoted 5 papers 14 days ago

LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs

Paper • 2605.17260 • Published 17 days ago • 25

KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration

Paper • 2605.14278 • Published 20 days ago • 37

AI for Auto-Research: Roadmap & User Guide

Paper • 2605.18661 • Published 16 days ago • 67

Lance: Unified Multimodal Modeling by Multi-Task Synergy

Paper • 2605.18678 • Published 16 days ago • 78

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Paper • 2605.18739 • Published 16 days ago • 112

liked a model 16 days ago

bytedance-research/Lance

Any-to-Any • Updated 5 days ago • 3.19k • 1.01k

upvoted 2 papers 18 days ago

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models

Paper • 2605.15055 • Published 20 days ago • 19

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Paper • 2605.15141 • Published 20 days ago • 93

upvoted a paper 19 days ago

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published 21 days ago • 101

upvoted 2 papers 20 days ago

World Action Models: The Next Frontier in Embodied AI

Paper • 2605.12090 • Published 22 days ago • 67

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Paper • 2605.12500 • Published 22 days ago • 191

liked a model 21 days ago

lightx2v/Wan2.2-Distill-Models

Updated Apr 20 • 25.6k • 129

liked a model 22 days ago

AIDC-AI/Ovis-Image-7B

Text-to-Image • Updated 18 days ago • 270 • • 207