fdsqefsgergd

T-representer's activity

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

upvoted 20 papers 3 days ago

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

Paper • 2511.22677 • Published 8 days ago • 18

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

Paper • 2511.18890 • Published 11 days ago • 28

GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation

Paper • 2512.01801 • Published 4 days ago • 22

Adversarial Flow Models

Paper • 2511.22475 • Published 8 days ago • 20

Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning

Paper • 2511.20549 • Published 10 days ago • 23

Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models

Paper • 2511.23319 • Published 7 days ago • 21

DiP: Taming Diffusion Models in Pixel Space

Paper • 2511.18822 • Published 11 days ago • 24

Rectifying LLM Thought from Lens of Optimization

Paper • 2512.01925 • Published 4 days ago • 22

CaptionQA: Is Your Caption as Useful as the Image Itself?

Paper • 2511.21025 • Published 9 days ago • 24

Architecture Decoupling Is Not All You Need For Unified Multimodal Model

Paper • 2511.22663 • Published 8 days ago • 28

LFM2 Technical Report

Paper • 2511.23404 • Published 7 days ago • 34

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published 4 days ago • 47

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

Paper • 2511.20649 • Published 10 days ago • 43

Geometrically-Constrained Agent for Spatial Reasoning

Paper • 2511.22659 • Published 8 days ago • 37

The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment

Paper • 2511.20614 • Published 10 days ago • 37

AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement

Paper • 2511.23475 • Published 7 days ago • 40

Vision Bridge Transformer at Scale

Paper • 2511.23199 • Published 7 days ago • 41

What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards

Paper • 2512.00425 • Published 6 days ago • 44

REASONEDIT: Towards Reasoning-Enhanced Image Editing Models

Paper • 2511.22625 • Published 8 days ago • 45

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

Paper • 2511.22570 • Published 8 days ago • 62