Urodoc Oncall

UDCAI's activity

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

upvoted a paper about 9 hours ago

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning

Paper • 2604.04746 • Published 2 days ago • 48

upvoted 2 papers 1 day ago

Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents

Paper • 2604.04979 • Published 6 days ago • 4

MedGemma 1.5 Technical Report

Paper • 2604.05081 • Published 4 days ago • 9

upvoted a paper 3 days ago

Self-Distilled RLVR

Paper • 2604.03128 • Published 7 days ago • 145

upvoted 4 papers 10 days ago

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

Paper • 2603.28762 • Published 10 days ago • 25

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Paper • 2603.27027 • Published 13 days ago • 141

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

Paper • 2603.28342 • Published 11 days ago • 26

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

Paper • 2603.27862 • Published 11 days ago • 30

upvoted 2 papers 11 days ago

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

Paper • 2603.25716 • Published 14 days ago • 152

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

Paper • 2603.25730 • Published 14 days ago • 51

upvoted 2 papers 14 days ago

Voxtral TTS

Paper • 2603.25551 • Published 14 days ago • 57

PixelSmile: Toward Fine-Grained Facial Expression Editing

Paper • 2603.25728 • Published 14 days ago • 117

upvoted 2 papers 15 days ago

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

Paper • 2603.18742 • Published 22 days ago • 10

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation

Paper • 2603.23500 • Published 16 days ago • 35

upvoted a paper 16 days ago

TrajLoom: Dense Future Trajectory Generation from Video

Paper • 2603.22606 • Published 17 days ago • 5

upvoted 3 papers 17 days ago

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

Paper • 2603.22276 • Published 17 days ago • 13

Manifold-Aware Exploration for Reinforcement Learning in Video Generation

Paper • 2603.21872 • Published 18 days ago • 33

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

Paper • 2603.21986 • Published 18 days ago • 121

upvoted 2 papers 18 days ago

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

Paper • 2603.17989 • Published 22 days ago • 17

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

Paper • 2603.19209 • Published 21 days ago • 5