SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

First translation hack for the Japanese videogame GARAGE: Bad Dream Adventure ｢ガラージュ｣

🌐 The Internet Computer! Free, Open-Source, and Self-Hostable.

Extremely fast NDS Emulator for ARM32/PSVita

dLLM: Simple Diffusion Language Modeling

Explanation and full RCE PoC for CVE-2025-55182

Reproduce DeFi hacked incidents using Foundry.

Decompilation of 3D Pinball for Windows – Space Cadet

NumPy implementation of infinite latent feature model (aka Indian Buffet Process or IBP)

A fast DOM based XSS vulnerability scanner with simplicity.

A small PoC for bpfdoor malware technique

This is the official implement of Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement

Command and Conquer: Red Alert

ArtSpeech: Adaptive Text-to-Speech Synthesis with Articulatory Representations

UTokyo-SaruLab MOS Prediction System

An extension to parrot.live, with support for more animations! http://ascii.live

This github repo is for Neurips 2021 and Interspeech 2022 papers on Non-Matching Reference based estimation of speech quality assessment.

ezXSS is an easy way for penetration testers and bug bounty hunters to test (blind) Cross Site Scripting.

UniSpeech - Large Scale Self-Supervised Learning for Speech

Voice Conversion With Just Nearest Neighbors

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

Implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion"

🦦 Insanely fast image printing in your terminal

Monte Carlo N-Particle Transport Code: Uranium Scout and Editor

XSS spider - 66/66 wavsep XSS detected