PAPER·17 hours agoTILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic RewardHugging Face Papers
TECH·yesterdayWorld’s First Agentic Diffusion Model Arrives: Correcting Errors While Acting, 128K Context Matches Autoregressive Models量子位
PAPER·July 21, 2026Accelerating Text-to-Video Generation with Calibrated Sparse AttentionApple Machine Learning Research
PAPER·June 2, 2026StressDream: Steering Video World Models for Robust Policy Evaluation and ImprovementHugging Face Papers
PAPER·June 1, 2026When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language ModelsHugging Face Papers
PAPER·May 29, 2026Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State ReformulationHugging Face Papers
PAPER·May 29, 2026CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy DistillationHugging Face Papers
