Adam Lee

Abecid's activity

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

upvoted a paper about 1 hour ago

Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds

Paper • 2610.27999 • Published 2 days ago • 177

upvoted a paper about 7 hours ago

SolarRenderer: Few-Step Generative Reference Rendering

Paper • 2610.28630 • Published 2 days ago • 43

upvoted a paper 1 day ago

Can Visual Generation Expand What Unified Multimodal Models Know?

Paper • 2610.21459 • Published 7 days ago • 31

published a model 5 days ago

Abecid/DeXplicit

Image-to-Video • Updated 5 days ago

updated a model 5 days ago

Abecid/DeXplicit

Image-to-Video • Updated 5 days ago

upvoted a paper 5 days ago

Player-1: Learning to Play from Synthetic Experience

Paper • 2610.20584 • Published 8 days ago • 349

upvoted a paper 6 days ago

FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching

Paper • 2610.17552 • Published 9 days ago • 45

upvoted a paper 12 days ago

MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers

Paper • 2610.06801 • Published 17 days ago • 46

upvoted 2 papers 13 days ago

GRACE: Generation-aware latent compression for efficient video generation

Paper • 2610.10524 • Published 15 days ago • 91

SGF+: Decoupling Gradient Flows for Autoregressive Video Generation

Paper • 2610.10429 • Published 15 days ago • 61

upvoted a paper 16 days ago

Octrees as an Explicit 3D Language

Paper • 2610.02388 • Published 21 days ago • 17

upvoted a paper 19 days ago

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Paper • 2609.37200 • Published 23 days ago • 141

upvoted a paper 20 days ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 23 days ago • 549

upvoted a paper 23 days ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 27 days ago • 139

liked a model 24 days ago

facebook/dinov3-vitb16-pretrain-lvd1689m

Image Feature Extraction • 85.7M • Updated Aug 19, 2025 • 472k • 473

upvoted 5 papers about 1 month ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published Sep 17 • 142

What Does Privileged Information Add to On-Policy Self-Distillation?

Paper • 2609.20612 • Published Sep 17 • 36

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

Paper • 2609.11638 • Published Sep 10 • 328

Discovery Foundation Models: Toward Open-Ended Discovery Intelligence

Paper • 2609.15973 • Published Sep 14 • 33

Programmable World Model

Paper • 2609.10540 • Published Sep 9 • 92