Papers arxiv:2605.12305 Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation Published on May 12 Submitted by taesiri on May 13 Authors: , , , , Abstract INSET is a unified multimodal model…
…AI-generated summary Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generate interleaved text-image sequences. Most existing approaches combine…
…We show that the pixel AsymFlow model finetuned from FLUX.2 klein 9B establishes a new state of the art for pixel-space text-to-image generation , beating its latent base on…
…AI-generated summary We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability . To address the reconstruction…
…On text-to-image generation and image editing benchmarks, ARR-RPO outperforms pairwise reward models and VLM judges, demonstrating that explicitly externalizing implicit preference knowledge into structured rubrics achieves more reliable, data…
…On text-to-image benchmarks , NTM matches or outperforms strong image generation baselines in just four sampling steps while uniquely retaining exact likelihood over the generative trajectory. View arXiv page View PDF…
…Reasoning Text-to-Image Generation , where the model actively infers implicit user intents, and Self-Reflective Refinement , where it autonomously diagnoses and corrects misalignments in generated outputs. To address the challenge of…
…It combines an image-bank reference protocol, which allows tool-generated images to be reused across later tool calls, with a closed-loop data evolution pipeline driven by policy rollouts. The results…
…AI-generated summary Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation and additional model training. This creates…
…AI-generated summary Recent single-image relighting methods, powered by advanced generative models , have achieved impressive photorealism on synthetic benchmarks. However, their effectiveness in the complex visual landscape of the real world…