Adam Lee

Abecid's activity

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

upvoted 2 papers 2 days ago

Generative Modeling via Drifting

Paper • 2602.04770 • Published Feb 4 • 6

PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation

Paper • 2605.14269 • Published 6 days ago • 7

liked a model 2 days ago

facebook/VGGT-Omega

Updated 5 days ago • 64

upvoted a paper 2 days ago

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO

Paper • 2605.15190 • Published 6 days ago • 12

upvoted a paper 3 days ago

Normalizing Trajectory Models

Paper • 2605.08078 • Published 12 days ago • 14

upvoted 2 papers 4 days ago

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

Paper • 2605.15141 • Published 6 days ago • 88

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published 6 days ago • 76

upvoted 2 papers 5 days ago

RigidFormer: Learning Rigid Dynamics using Transformers

Paper • 2605.09196 • Published 11 days ago • 14

Asymmetric Flow Models

Paper • 2605.12964 • Published 7 days ago • 21

upvoted a paper 6 days ago

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

Paper • 2605.13724 • Published 7 days ago • 95

upvoted a paper 8 days ago

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published 13 days ago • 185

upvoted a paper 10 days ago

Generative Modeling with Orbit-Space Particle Flow Matching

Paper • 2605.02222 • Published 16 days ago • 9

upvoted a paper 11 days ago

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation

Paper • 2605.06376 • Published 13 days ago • 26

upvoted a paper 14 days ago

ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models

Paper • 2405.13729 • Published 21 days ago • 13

upvoted a paper 15 days ago

Map2World: Segment Map Conditioned Text to 3D World Generation

Paper • 2605.00781 • Published 19 days ago • 25

upvoted a paper 16 days ago

UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

Paper • 2605.00658 • Published 19 days ago • 82

upvoted a paper 17 days ago

PhyCo: Learning Controllable Physical Priors for Generative Motion

Paper • 2604.28169 • Published 20 days ago • 13

upvoted 3 papers 22 days ago

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

Paper • 2604.21689 • Published 27 days ago • 25

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

Paper • 2604.24764 • Published 23 days ago • 118

Video Analysis and Generation via a Semantic Progress Function

Paper • 2604.22554 • Published 26 days ago • 63