PAPER·yesterdayTILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic RewardHugging Face Papers
TECH·2 days agoWorld’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 1, 2026When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language ModelsHugging Face Papers
PAPER·May 29, 2026YoCausal: How Far is Video Generation from World Model? A Causality PerspectiveHugging Face Papers
PAPER·May 29, 2026minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World ModelsHugging Face Papers
PAPER·May 29, 2026minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World ModelsarXiv
PAPER·May 28, 2026Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion ModelsarXiv
PAPER·May 27, 2026Squeezing Capacity from Multimodal Large Language Models for Subject-driven GenerationHugging Face Papers
