Papers46

#flow matching

SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder

Minglei Shi, Haolin Wang et al.Dec 12arXiv

This paper shows you can train a big text-to-image diffusion model directly on the features of a vision foundation model (like DINOv3) without using a VAE.

#text-to-image#diffusion transformer#flow matching

Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization

Intermediate

Tsai-Shien Chen, Aliaksandr Siarohin et al.Dec 11arXiv

Omni-Attribute is a new image encoder that learns just the parts of a picture you ask for (like hairstyle or lighting) and ignores the rest.

#open-vocabulary attribute encoder#attribute disentanglement#visual concept personalization

UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving

Intermediate

Hao Lu, Ziyang Liu et al.Dec 10arXiv

UniUGP is a single system that learns to understand road scenes, explain its thinking, plan safe paths, and even imagine future video frames.

#UniUGP#vision-language-action#world model

OmniPSD: Layered PSD Generation with Diffusion Transformer

Intermediate

Cheng Liu, Yiren Song et al.Dec 10arXiv

OmniPSD is a new AI that can both make layered Photoshop (PSD) files from words and take apart a flat image into clean, editable layers.

#OmniPSD#layered PSD generation#RGBA-VAE

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Intermediate

Zheng Ding, Weirui YeDec 9arXiv

TreeGRPO teaches image generators using a smart branching tree so each training run produces many useful learning signals instead of just one.

#TreeGRPO#reinforcement learning#diffusion models

Scaling Zero-Shot Reference-to-Video Generation

Intermediate

Zijian Zhou, Shikun Liu et al.Dec 7arXiv

Saber is a new way to make videos that match a text description while keeping the look of people or objects from reference photos, without needing special triplet datasets.

#reference-to-video generation#zero-shot video synthesis#masked training

Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image

Intermediate

Yanran Zhang, Ziyi Wang et al.Dec 4arXiv

This paper teaches a computer to turn one single picture into a moving 3D scene that stays consistent from every camera angle.

#4D scene generation#single-image to 4D#joint geometry and motion

EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture

Intermediate

Xin He, Longhui Wei et al.Dec 4arXiv

EMMA is a single AI model that can understand images, write about them, create new images from text, and edit images—all in one unified system.

#EMMA#unified multimodal architecture#32x autoencoder

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Intermediate

Zhenglin Cheng, Peng Sun et al.Dec 3arXiv

TwinFlow is a new way to make big image models draw great pictures in just one step instead of 40–100 steps.

#TwinFlow#one-step generation#twin trajectories

PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling

Intermediate

Bowen Ping, Chengyou Jia et al.Dec 2arXiv

This paper teaches image models to keep things consistent across multiple pictures—like the same character, art style, and story logic—using reinforcement learning (RL).

#consistent image generation#pairwise reward modeling#reinforcement learning

1 2 3 4