DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance Paper • 2505.14708 • Published May 17, 2025 • 1
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Paper • 2608.05102 • Published 2 days ago • 55
LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation Paper • 2608.00079 • Published 9 days ago • 14
Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations Paper • 2608.01628 • Published 4 days ago • 22
LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation Paper • 2608.00079 • Published 9 days ago • 14
LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation Paper • 2608.00079 • Published 9 days ago • 14
Self-Adversarial One Step Generation via Condition Shifting Paper • 2604.12322 • Published Apr 14 • 13
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook Paper • 2604.02029 • Published Apr 2 • 152
FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition Paper • 2604.02088 • Published Apr 2 • 6
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published Jan 21 • 75
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders Paper • 2601.16208 • Published Jan 22 • 55
OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer Paper • 2601.14250 • Published Jan 20 • 48
UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation Paper • 2601.11522 • Published Jan 16 • 18
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards Paper • 2512.00473 • Published Nov 29, 2025 • 27