Yusuf Demir

ydemir-itu's activity

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

upvoted 2 papers 1 day ago

FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

Paper • 2610.36545 • Published 9 days ago • 36

WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search

Paper • 2610.16927 • Published 6 days ago • 24

upvoted 2 papers 2 days ago

EditAgent: Rethinking Agentic Image Editing

Paper • 2610.39664 • Published 7 days ago • 13

WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video

Paper • 2610.38352 • Published 8 days ago • 25

upvoted 2 papers 3 days ago

T-DIG: Text-Conditioned Diversity for Image Generation

Paper • 2610.29003 • Published 15 days ago • 4

OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images

Paper • 2610.35684 • Published 10 days ago • 59

upvoted 5 papers 4 days ago

Diffusion Language Models Change Speed Across Tasks and Languages

Paper • 2610.25835 • Published 16 days ago • 20

F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation

Paper • 2610.31623 • Published 14 days ago • 9

Self-Distilling Future Video Representations for World Action Models

Paper • 2610.30320 • Published 15 days ago • 37

Editing Images into Reusable Layers via Compositional Edit-Prior Distillation

Paper • 2610.24738 • Published 19 days ago • 178

HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience

Paper • 2610.34186 • Published 11 days ago • 7

upvoted a paper 5 days ago

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

Paper • 2610.32749 • Published 13 days ago • 32

upvoted 2 papers 6 days ago

Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation

Paper • 2610.36466 • Published 9 days ago • 13

ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence

Paper • 2610.34283 • Published 11 days ago • 36

upvoted a paper 7 days ago

EmbodiedLab: Benchmarking Embodied Agents That Act to Know

Paper • 2610.35385 • Published 10 days ago • 12

upvoted 2 papers 8 days ago

SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing

Paper • 2610.14253 • Published 22 days ago • 5

Speculative Diffusion is a Tale of Two Tradeoffs

Paper • 2610.31819 • Published 14 days ago • 11

upvoted a paper 12 days ago

Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation

Paper • 2610.29989 • Published 15 days ago • 48

upvoted 2 papers 14 days ago

Consistent Distribution Matching for Data-Free Diffusion Distillation

Paper • 2610.09221 • Published 30 days ago • 21

MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing

Paper • 2610.23751 • Published 20 days ago • 24