Trending Research
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction".
Ranked #15 on
Image Generation
on ImageNet 256x256
MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
modelscope/ClearerVoice-Studio
•
•
To effectively solve the indirect elemental interactions across chunks in the dual-path architecture, MossFormer employs a joint local and global self-attention architecture that simultaneously performs a full-computation self-attention on local chunks and a linearised low-cost self-attention over the full sequence.
Ranked #1 on
Speech Separation
on WSJ0-2mix-16k
(using extra training data)
Papers-in-100-Lines-of-Code
MaximeVandegar/Papers-in-100-Lines-of-Code
•
•
Implementation of papers in 100 lines of code.
DeMo: Decoupled Momentum Optimization
bloc97/demo
•
•
Training large neural networks typically requires sharing gradients between accelerators through specialized high-speed interconnects.
Open-Sora Plan: Open-Source Large Video Generation Model
We introduce Open-Sora Plan, an open-source project that aims to contribute a large generation model for generating desired high-resolution videos with long durations based on various user inputs.
Scaling Transformers for Low-Bitrate High-Quality Speech Coding
The tokenization of speech with neural audio codec models is a vital part of modern AI pipelines for the generation or understanding of speech, alone or in a multimodal context.
Comprehensive Competition Mechanism in Palmprint Recognition
Faceplugin-ltd/Palm-Recognition
•
•
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2023
The traditional competition mechanism focuses solely on selecting the winner of different channels without considering the spatial information of the features.
emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation
Hands are the primary means through which humans interact with the world.
ShowUI: One Vision-Language-Action Model for GUI Visual Agent
showlab/showui
•
•
In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI connected graph, adaptively identifying their redundant relationship and serve as the criteria for token selection during self-attention blocks; (ii) Interleaved Vision-Language-Action Streaming that flexibly unifies diverse needs within GUI tasks, enabling effective management of visual-action history in navigation or pairing multi-turn query-action sequences per screenshot to enhance training efficiency; (iii) Small-scale High-quality GUI Instruction-following Datasets by careful data curation and employing a resampling strategy to address significant data type imbalances.
The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning
Machine learning based surrogate models offer researchers powerful tools for accelerating simulation-based workflows.
