Papers14

All Beginner Intermediate Advanced

All Sources arXiv

#rectified flow

LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model

Intermediate

Zebin You, Xiaolu Zhang et al.Mar 1arXiv

LLaDA-o is a new AI that understands pictures and text and can also make images, all in one model.

#LLaDA-o#Mixture of Diffusion#masked diffusion models

Mode Seeking meets Mean Seeking for Fast Long Video Generation

Intermediate

Shengqu Cai, Weili Nie et al.Feb 27arXiv

Short videos are easy for AI to make sharp and lively, but long videos need stories and memory, and there isn’t much training data for that.

#long video generation#flow matching#distribution matching

World Guidance: World Modeling in Condition Space for Action Generation

Intermediate

Yue Su, Sijin Chen et al.Feb 25arXiv

WoG (World Guidance) teaches a robot to imagine just the right bits of the near future and use those bits to pick better actions.

#Vision-Language-Action#world modeling#condition space

TactAlign: Human-to-Robot Policy Transfer via Tactile Alignment

Beginner

Youngsun Wi, Jessica Yin et al.Feb 14arXiv

Robots learn faster and more flexibly when they can use human touch data, but humans and robots feel touch with very different sensors.

#tactile alignment#human-to-robot transfer#rectified flow

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Intermediate

Dianyi Wang, Chaofan Ma et al.Feb 2arXiv

UniReason is a single, unified model that plans with world knowledge before making an image and then edits its own result to fix mistakes, like a student drafting and revising an essay.

#unified multimodal model#world knowledge reasoning#text-to-image generation

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

ShapeR: Robust Conditional 3D Shape Generation from Casual Captures

Intermediate

Yawar Siddiqui, Duncan Frost et al.Jan 16arXiv

ShapeR builds clean, correctly sized 3D objects from messy, casual phone or glasses videos by using images, camera poses, sparse SLAM points, and short text captions together.

#ShapeR#3D reconstruction#object-centric

CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation

Intermediate

Chengzhuo Tong, Mingkun Chang et al.Jan 15arXiv

This paper turns a video model into a step-by-step visual thinker that makes one final, high-quality picture from a text prompt.

#Chain-of-Frame#visual reasoning#text-to-image

MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing

Intermediate

Xiaokun Sun, Zeyu Cai et al.Jan 1arXiv

MorphAny3D is a training-free way to smoothly change one 3D object into another, even if they are totally different (like a bee into a biplane).

#3D morphing#Structured Latent#SLAT

ProEdit: Inversion-based Editing From Prompts Done Right

Intermediate

Zhi Ouyang, Dian Zheng et al.Dec 26arXiv

ProEdit is a training-free, plug-and-play method that fixes a common problem in image and video editing: the model clings too hard to the original picture and refuses to change what you asked for.

#ProEdit#inversion-based editing#KV-mix

PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence

Intermediate

Xiaopeng Lin, Shijie Lian et al.Dec 18arXiv

Robots learn best from what they would actually see, which is a first-person (egocentric) view, but most AI models are trained on third-person videos and get confused.

#egocentric vision#first-person video#vision-language model

DeContext as Defense: Safe Image Editing in Diffusion Transformers

Intermediate

Linghui Shen, Mingyue Cui et al.Dec 18arXiv

This paper protects your photos from being misused by new AI image editors that can copy your face or style from just one picture.

#Diffusion Transformer#cross-attention#in-context image editing

1 2