MARS5 speech model (TTS) from CAMB.AI

LLM training in simple, raw C/CUDA

Fast strong hash functions: SipHash/HighwayHash

Torchhd is a Python library for Hyperdimensional Computing and Vector Symbolic Architectures

This is a collection of our NAS and Vision Transformer work.

[ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"

Code for "SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation"

Official Repository for ICML 2023 paper "Can Neural Network Memorization Be Localized?"

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization"

Official implementation for the paper "Understanding Hyperdimensional Computing for Parallel Single-Pass Learning"

PyTorch Implementation of the paper "A Neuro-vector-symbolic architecture for Solving Raven's Progressive Matrices" published in Nature Machine Intelligence 2023.

QLoRA: Efficient Finetuning of Quantized LLMs

A retargetable MLIR-based machine learning compiler and runtime toolkit.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 2…

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

Using ControlNet right in Blender.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

[NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows to finetune the explainability maps of Vision Transformers t…

[Preprint] OneFormer: One Transformer to Rule Universal Image Segmentation.

SimVLM ---SIMPLE VISUAL LANGUAGE MODEL PRETRAINING WITH WEAK SUPERVISION

[NeurIPS 2022] Open source code for reusing prior computational work in RL.

📄 Semi-Supervised Semantic Segmentation with Cross-Consistency Training (CVPR 2020).

Neural Network proposal for WASI

[NeurIPS 2022] Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Official PyTorch implementation of SegFormer