…AI-generated summary Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors . In this paper, we demonstrate that these priors can be utilized…
…On ImageNet-256, DRoRAE reduces rFID from 0.57 to 0.29 and improves generation FID from 1.74 to 1.65 (with AutoGuidance ), with gains also transferring to text-to-image…
…Extensive experiments on different architectures, including SD3-Medium and Longcat-Image, demonstrate that CDM provides highly competitive visual fidelity for few-step image generation without relying on complex auxiliary objectives. Code is…
…Fine-Grained Image Edit with Bounding Box Guidance (2026) LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing (2026) ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent…
…Shaokai Ye , , , , , Abstract A balanced reinforcement learning framework for image captioning that jointly optimizes correctness, coverage, and linguistic quality while improving performance over existing methods. AI-generated summary Image captioning is one…
…in comparative image selection tasks, as demonstrated by the Visual Aesthetic Benchmark which reveals significant performance gaps and shows that fine-tuning on expert examples can improve accuracy. AI-generated summary Multimodal…
…A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing (2026) Latent-Compressed Variational Autoencoder for Video Diffusion Models (2026) Coevolving Representations in Joint Image-Feature Diffusion (2026) TC-AE: Unlocking Token…
…AI-generated summary While multimodal large language models have advanced across text, image, and audio, personalization research has remained primarily vision-language, with unified omnimodal benchmarking that jointly covers text, image, and…
…AI-generated summary Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference…
…Models (2026) Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context (2026) OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model (2026) MemMachine: A Ground-Truth…
