PAPER·18 hours agoTILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic RewardHugging Face Papers
PAPER·23 hours agoOmniPhys: Knowledge-Graph-Driven Benchmarking and Collective Optimization for Physical Commonsense in Text-to-Image GenerationarXiv
PAPER·2 days agoPRISM: Prompt Refinement via Image-grounded Self-rewarding Mechanism for Text-to-Image GenerationarXiv
TECH·5 days agoMicrosoft releases image generation AI "MAI-Image-2.5-Pro," integrating in-house AI into Office products and others to reduce dependence on other companiesGIGAZINE
PAPER·June 2, 2026Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference OptimizationHugging Face Papers
TECH·May 27, 2026Microsoft releases image generation AI 'MAI-Image-2.5', ranking third in the world for text-to-image generationGIGAZINE
PAPER·May 23, 2026AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image AlignmentHugging Face Papers
PAPER·May 23, 2026RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-EvolutionHugging Face Papers
PAPER·May 22, 2026SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion TransformersHugging Face Papers
