Wave Forcing: Towards Speed-of-Light Streaming Video Generation Paper • 2611.00859 • Published 19 days ago • 128
Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement Paper • 2610.33472 • Published 26 days ago • 24
MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion Paper • 2610.25404 • Published Oct 18 • 39
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published Oct 13 • 53
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation Paper • 2610.21601 • Published Oct 15 • 36
APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation Paper • 2610.18097 • Published Oct 13 • 21
ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning Paper • 2610.13316 • Published Oct 9 • 7
Learning Representations to Guide Pixel Diffusion Transformers Paper • 2610.12978 • Published Oct 9 • 21
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement Paper • 2610.11959 • Published Oct 8 • 83
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published Oct 7 • 65
SGF+: Decoupling Gradient Flows for Autoregressive Video Generation Paper • 2610.10429 • Published Oct 7 • 44
nanoMuse: An Open-Source Personal Agent for Every Device You Own Paper • 2610.08699 • Published Oct 6 • 105
DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation Paper • 2610.02188 • Published Oct 1 • 8
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence Paper • 2609.39222 • Published Sep 30 • 24
Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model Paper • 2609.18323 • Published Sep 16 • 58
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published Aug 26 • 76
ReWorld: An Interactive World Model with Long-Horizon Memory Paper • 2608.23565 • Published Aug 24 • 25
view article Article NEO-unify: Building Native Multimodal Unified Models End to End sensenova • Mar 5 • 181