Papers14

#diffusion models

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

Yasaman Haghighi, Alexandre AlahiFeb 27arXiv

SenCache speeds up video diffusion models by reusing past answers only when the model is predicted to change very little.

#diffusion models#video generation#caching

From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors

Intermediate

Liangbing Zhao, Le Zhuo et al.Feb 25arXiv

The paper turns image editing from a one-step “before → after” trick into a mini physics simulation that follows real-world rules.

#physics-aware image editing#physical state transition#latent transition priors

Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models

Intermediate

Sen Ye, Mengde Xu et al.Feb 17arXiv

Big idea: Make image-making AIs stop, think, check, and fix their own work so they get better at both creating pictures and understanding them.

#multimodal models#image generation#reasoning

iFSQ: Improving FSQ for Image Generation with 1 Line of Code

Intermediate

Bin Lin, Zongjian Li et al.Jan 23arXiv

This paper fixes a hidden flaw in a popular image tokenizer (FSQ) with a simple one-line change to its activation function.

#image generation#finite scalar quantization#iFSQ

SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer

Intermediate

Tongcheng Fang, Hanling Zhang et al.Jan 23arXiv

Videos are made of very long lists of tokens, and regular attention looks at every pair of tokens, which is slow and expensive.

#SALAD#sparse attention#linear attention

HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models

Intermediate

Xin Xie, Jiaxian Guo et al.Jan 22arXiv

Diffusion models make pictures from noise but often miss what people actually want in the prompt or what looks good to humans.

#diffusion models#rectified flow#hypernetwork

Alterbute: Editing Intrinsic Attributes of Objects in Images

Intermediate

Tal Reiss, Daniel Winter et al.Jan 15arXiv

Alterbute is a diffusion-based method that changes an object's intrinsic attributes (color, texture, material, shape) in a photo while keeping the object's identity and the scene intact.

#intrinsic attribute editing#visual named entities#identity preservation

DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies

Intermediate

Renke Wang, Zhenyu Zhang et al.Jan 5arXiv

DiffProxy turns tricky multi-camera photos of a person into a clean 3D body and hands by first painting a precise 'map' on each pixel and then fitting a standard body model to that map.

#human mesh recovery#SMPL-X#dense correspondence

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

Intermediate

Shengming Yin, Zekai Zhang et al.Dec 17arXiv

The paper turns one flat picture into a neat stack of see‑through layers, so you can edit one thing without messing up the rest.

#image decomposition#RGBA layers#alpha blending

GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models

Intermediate

Bozhou Li, Sihan Yang et al.Dec 17arXiv

This paper is about making the words you type into a generator turn into the right pictures and videos more reliably.

#diffusion models#text encoder#multimodal large language model

Few-Step Distillation for Text-to-Image Generation: A Practical Guide

Intermediate

Yifan Pu, Yizeng Han et al.Dec 15arXiv

Big text-to-image models make amazing pictures but are slow because they take hundreds of tiny steps to turn noise into an image.

#text-to-image#diffusion models#few-step generation

StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space

Intermediate

Tjark Behrens, Anton Obukhov et al.Dec 11arXiv

StereoSpace turns a single photo into a full 3D-style stereo pair without ever estimating a depth map.

#stereo generation#monocular-to-stereo#diffusion models

1 2