Papers13

#Flow Matching

Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers

The paper shows that using information from many layers of a language model (not just one) helps text-to-image diffusion transformers follow prompts much better.

#Diffusion Transformer#Text Conditioning#Multi-layer LLM Features

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

Intermediate

I. Apanasevich, M. Artemyev et al.Jan 31arXiv

Green-VLA is a step-by-step training recipe that teaches one model to see, understand language, and move many kinds of robots safely and efficiently.

#Vision-Language-Action#Unified Action Space#Multi-embodiment Pretraining

A Pragmatic VLA Foundation Model

Intermediate

Wei Wu, Fan Lu et al.Jan 26arXiv

LingBot-VLA is a robot brain that listens to language, looks at the world, and decides smooth actions to get tasks done.

#Vision‑Language‑Action#foundation model#Flow Matching

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

Intermediate

Shengbang Tong, Boyang Zheng et al.Jan 22arXiv

Before this work, most text-to-image models used VAEs (small, squished image codes) and struggled with slow training and overfitting on high-quality fine-tuning sets.

#Representation Autoencoder#RAE#Variational Autoencoder

Qwen3-TTS Technical Report

Intermediate

Hangrui Hu, Xinfa Zhu et al.Jan 22arXiv

Qwen3-TTS is a family of text-to-speech models that can talk in 10+ languages, clone a new voice from just 3 seconds, and follow detailed style instructions in real time.

#Qwen3-TTS#text-to-speech#voice cloning

ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models

Intermediate

Linqing Zhong, Yi Liu et al.Jan 16arXiv

Robots usually think in words and pictures, but their hands need exact motions, so there is a gap between understanding and doing.

#Vision-Language-Action#Action Chain-of-Thought#Explicit Action Reasoner

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

Intermediate

Dongting Hu, Aarush Gupta et al.Jan 13arXiv

This paper shows how to make powerful image‑generating Transformers run fast on phones without needing the cloud.

#Diffusion Transformer#Sparse Attention#Adaptive Sparse Self-Attention

TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts

Intermediate

Yu Xu, Hongbin Yan et al.Jan 12arXiv

TAG-MoE is a new way to steer Mixture-of-Experts (MoE) models using clear task hints, so the right “mini-experts” handle the right parts of an image job.

#Task-Aware Gating#Mixture-of-Experts#Unified Image Generation

FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing

Intermediate

Xijie Huang, Chengming Xu et al.Jan 5arXiv

This paper makes video editing easier by teaching an AI to spread changes from the first frame across the whole video smoothly and accurately.

#First-Frame Propagation#Video Editing#FFP-300K

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

Intermediate

Shengjun Zhang, Zhang Zhang et al.Jan 1arXiv

This paper shows that when teaching image generators with reinforcement learning, only a few early, very noisy steps actually help the model learn what people like.

#E-GRPO#Group Relative Policy Optimization#Flow Matching

Animate Any Character in Any World

Intermediate

Yitong Wang, Fangyun Wei et al.Dec 18arXiv

AniX is a system that lets you place any character into any 3D world and control them with plain language, like “run forward” or “play a guitar.”

#AniX#3D Gaussian Splatting#world models

RecTok: Reconstruction Distillation along Rectified Flow

Intermediate

Qingyu Shi, Size Wu et al.Dec 15arXiv

RecTok is a new visual tokenizer that teaches the whole training path of a diffusion model (the forward flow) to be smart about image meaning, not just the starting latent features.

#Rectified Flow#Flow Matching#Visual Tokenizer

1 2