Urodoc Oncall

UDCAI's activity

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

upvoted 2 papers 2 days ago

On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

Paper • 2603.28762 • Published 3 days ago • 22

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Paper • 2603.27027 • Published 6 days ago • 136

upvoted 2 papers 3 days ago

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

Paper • 2603.28342 • Published 3 days ago • 19

ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks

Paper • 2603.27862 • Published 4 days ago • 24

upvoted 2 papers 4 days ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Paper • 2603.25716 • Published 7 days ago • 147

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

Paper • 2603.25730 • Published 7 days ago • 46

upvoted 2 papers 6 days ago

Voxtral TTS

Paper • 2603.25551 • Published 7 days ago • 56

PixelSmile: Toward Fine-Grained Facial Expression Editing

Paper • 2603.25728 • Published 7 days ago • 116

upvoted a paper 7 days ago

6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models

Paper • 2603.18742 • Published 14 days ago • 10

upvoted a paper 8 days ago

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation

Paper • 2603.23500 • Published 9 days ago • 35

upvoted a paper 9 days ago

TrajLoom: Dense Future Trajectory Generation from Video

Paper • 2603.22606 • Published 10 days ago • 5

upvoted 5 papers 10 days ago

Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels

Paper • 2603.22276 • Published 10 days ago • 13

Manifold-Aware Exploration for Reinforcement Learning in Video Generation

Paper • 2603.21872 • Published 10 days ago • 33

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published 10 days ago • 120

Versatile Editing of Video Content, Actions, and Dynamics without Training

Paper • 2603.17989 • Published 15 days ago • 16

Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders

Paper • 2603.19209 • Published 14 days ago • 5

upvoted a paper 14 days ago

3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model

Paper • 2603.18524 • Published 15 days ago • 58

upvoted 2 papers 15 days ago

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published 16 days ago • 135

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

Paper • 2603.15726 • Published 17 days ago • 184

upvoted a paper 17 days ago

ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer

Paper • 2603.15478 • Published 17 days ago • 24