Adam Lee

Abecid's activity

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

upvoted a paper about 24 hours ago

PhyCo: Learning Controllable Physical Priors for Generative Motion

Paper • 2604.28169 • Published 4 days ago • 10

upvoted 2 papers 6 days ago

StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition

Paper • 2604.21689 • Published 11 days ago • 24

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published 7 days ago • 115

upvoted 2 papers 7 days ago

Video Analysis and Generation via a Semantic Progress Function

Paper • 2604.22554 • Published 10 days ago • 63

Building a Precise Video Language with Human-AI Oversight

Paper • 2604.21718 • Published 12 days ago • 15

upvoted 2 papers 10 days ago

Fine-Tuning Diffusion Models via Intermediate Distribution Shaping

Paper • 2510.02692 • Published Mar 3 • 1

Seeing Fast and Slow: Learning the Flow of Time in Videos

Paper • 2604.21931 • Published 11 days ago • 19

upvoted 2 papers 11 days ago

MultiWorld: Scalable Multi-Agent Multi-View Video World Models

Paper • 2604.18564 • Published 14 days ago • 44

UniMesh: Unifying 3D Mesh Understanding and Generation

Paper • 2604.17472 • Published 15 days ago • 11

liked a model 11 days ago

ByteDance/Hyper-SD

Text-to-Image • Updated Dec 5, 2024 • 46.5k • • 1.34k

upvoted a paper 13 days ago

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

Paper • 2604.18168 • Published 14 days ago • 97

upvoted a paper 14 days ago

Elucidating the SNR-t Bias of Diffusion Probabilistic Models

Paper • 2604.16044 • Published 17 days ago • 74

upvoted 2 papers 16 days ago

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

Paper • 2604.15311 • Published 18 days ago • 12

Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

Paper • 2604.10949 • Published 21 days ago • 40

upvoted a paper 17 days ago

OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation

Paper • 2604.11804 • Published 21 days ago • 71

upvoted a paper 18 days ago

LPM 1.0: Video-based Character Performance Model

Paper • 2604.07823 • Published 25 days ago • 77

liked 2 models 18 days ago

tencent/HY-World-2.0

Image-to-3D • Updated 12 days ago • 3.43k • 637

nvidia/Lyra-2.0

Image-to-3D • Updated 11 days ago • 2.38k • 297

upvoted a paper 19 days ago

Rethinking the Diffusion Model from a Langevin Perspective

Paper • 2604.10465 • Published 22 days ago • 15

upvoted a paper 26 days ago

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Paper • 2510.05684 • Published Oct 7, 2025 • 146