PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

智能检索张维为表情包

Acoustic-to-Articulatory Speech Inversion (AAI) Model

🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"

This is a repository for fine-tuning Qwen2-Audio, currently supporting Distributed Data Parallel (DDP) and DeepSpeed.

Qwen2.5 0.5B GRPO

Official Implementation for Diffusion Models Without Classifier-free Guidance

research impl of Native Sparse Attention (2502.11089)

Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper

TokenSkip: Controllable Chain-of-Thought Compression in LLMs

Repository for "TESS-2: A Large-Scale, Generalist Diffusion Language Model"

A Python library for high-quality, fast, and customizable dynamic audio compression and peak limiting.

Inference-time scaling of Flux beyond denoising steps.

SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs

SkyReels V1: The first and most advanced open-source human-centric video foundation model

[CVPR 2020] "Learning to Structure an Image with Few Colors". Critical structure for network recognition. #explainable-ai

16khz, 24khz, 32khz to 32khz decoding from mel spectrogram

Source code and complementary material for "Keep what you need : extracting efficient subnetworks from large audio representation models".

Updated list of public BitTorrent trackers