smellslikeml Claim this profile

Real-Time Spatio-Temporally Localized Activity Detection by Tracking Body Keypoints

InstructSAM in native C++/ggml — natural-language image segmentation, CPU-only

Motion transfer booth for a 1 hour everybody dance now video generation using EdgeTPU and Tensorflow 2.0

Conserve water with image classification for plant droop detection deployed on the Arduino platform.

Convolutional Autoencoders for Anomaly Detection to Reduce Bandwidth in Streaming Video

EEG wearable device using CNN for seizure prediction

Kindbot: an app, sensors, voice-control, and state-of-the-art computer vision to maximize yields

End-to-End ML on Databricks Workshop materials

Deep Pose Estimation using Tensorflow for Yoga virtual trainer

deep learning applied to Network Intrusion Detection with NSL-KDD data

Never forget the resource that helps to close that sales call! Power a real-time speech-to-text agent with retrieval augmented generation based on webscraped customer use-cases.

No description.

donkeycar fork for LitterBug

train a custom classifier to score dart throws, relate to throwing form through pose estimation

resources for programmatically redacting personally identifiable information

Put your drone on a longer leash executing programmed flight on a powered Pi zero. Perform YOLO object recognition connect over Hologram CLI

image search engine using elasticsearch and mobilenet image embeddings

ROS 1 wrapper for NeuralRecon - https://github.com/zju3dv/NeuralRecon

Knowledge gathering and useful resources for the Coral EdgeTPU dev board

Sniffing BLE, trilateralize beacon with Machine Learning to guess location, Alexa for VUI

Spark notebooks outlining video rate-distortion optimization using content info

conceptual overview and code for various intro hacking references

Implementation of Motion Transfer using Person Segmentation

Training CNN model to generate image embeddings

Repository to detect deepfakes

Compose multimodal datasets 🎹 - experimental

Example of training a GLM model with Keras and MLflow in R

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

collection of jupyter notebooks exploring Kaggle competition datasets to implement simple baseline models

This repository contains the code for the paper: A Comprehensive Framework for Uncertainty Quantification of Voxel-wise Supervised Deep Learning Models in IVIM MRI

A neurosymbolic perspective on LLMs

LLM-Crowdsourced: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models

Implementation of Multi-Agent Guided Policy Optimization (MAGPO).

Project codebase

This repository contains code for leveraging Human-AI synergy in adaptive active learning to optimize continuous lithium carbonate crystallization. As demand rises, our framework accelerates lithium extraction from challenging sources, improving impurity tolerance and promoting sustainable utilization of North American reserves.

No description.

FastDepth PyTorch implementation using image and disparity map

Basic E2E ML Demo on Databricks

A no-nonsense demo of MLflow on Databricks

Parquet-based ML data format optimized for working with unstructured data

TensorFlow Recommenders is a library for building recommender system models using TensorFlow.

The code for "InstructSAM: Segment Any Instance with Any Instructions"

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Ultralytics YOLO 🚀

A framework for few-shot evaluation of language models.

PyTorch building blocks for the OLMo ecosystem

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

A framework for building realtime voice AI agents 🤖🎙️📹

AllenAI's post-training codebase

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Train transformer language models with reinforcement learning.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Scalable data pre processing and curation toolkit for LLMs

Go ahead and axolotl questions

A high-throughput and memory-efficient inference and serving engine for LLMs

LLM inference in C/C++

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Official inference repo for FLUX.1 models

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Generative Models by Stability AI

Large Language Model Text Generation Inference

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

No description.

🤗 smolagents: a barebones library for agents that think in code.

PyTorch native post-training library

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

The simplest, fastest repository for training/finetuning small-sized VLMs.

No description.

Implementation of Contrastive Neuron Attribution for behavioral detection and steering.

We write your reusable computer vision tools. 💜

MTEB: Massive Text Embedding Benchmark

🙌 OpenHands: AI-Driven Development

End-to-End Speech Processing Toolkit

The agent that grows with you

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

DSPy: The framework for programming—not prompting—language models

MLX: An array framework for Apple silicon

A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

Build resilient agents.

Evaluation and Tracking for LLM Experiments and AI Agents

slime is an LLM post-training framework for RL Scaling.

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

Repo housing the open sourced code for the ai2 scholar qa app and also the corresponding library

No description.

One framework to evaluate any VLA model on any robot simulation benchmark.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Containers for machine learning

Build, Manage and Deploy AI/ML Systems

Label Studio is a multi-type data labeling and annotation tool with standardized output format

🦉 Data Versioning and ML Experiments

A system for quickly generating training data with weak supervision

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Open-source, secure environment with real-world tools for enterprise-grade agents.

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

Scrapy, a fast high-level web crawling & scraping framework for Python.

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

The LLM Evaluation Framework

Synthetic data curation for post-training and structured data extraction

Tools for handling multimodal data in machine learning projects.

A lightweight, powerful framework for multi-agent workflows

A lightweight, powerful framework for multi-agent workflows

Research artifacts from Recursive's automated AI research system

Graph Neural Network Library for PyTorch

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

slime is an LLM post-training framework for RL Scaling.

PyTorch native post-training library

No description.

No description.

DRIVE: Dynamic Rule Inference and Verified Evaluation for Constraint-Aware Autonomous Driving

No description.

The official implementation of "P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis"

No description.

No description.

This is an official implementation for "Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models".

No description.

No description.

This repository contains the official implementation for the paper: "Inferring Transition and Reward Machines for Policy Learning in Partially Observable Markov Decision Processes".

Code and Data for paper "Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time"

VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework

Partially Observable Benchmarks in JAX

No description.

This repository contains code and data to replicate the study On LLM Assisted Generation of Smart Contracts from Business Processes (in submission).

This is the accompanying code repository for the paper Efficient Machine Unlearning via Influence Approximation by Jiawei Liu, Chenwang Wu, Defu Lian, and Enhong Chen.

A comprehensive study on optimizing hyperparameters for lightweight deep learning models aimed at real-time image classification on edge devices. Includes training configs, scripts, and performance benchmarks.

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

This repository contains all code, prompts, and evaluation scripts as a part of paper titled "Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery" submitted to NeurIPS 2025.

Causal Responsibility EXplanations for Image Classifiers and Tabular Data

No description.

Source code for the paper "Advancing Fetal Ultrasound Image Quality Assessment in Low-Resource Settings." (MIRASOL Workshop @ MICCAI 2025)

Data-driven quantum Koopman method for simulating nonlinear dynamics

SmartCLIP: A training method to improve CLIP with both short and long texts

Analysing cultural stereotypes in the stories GPT tells.

No description.

Official repo for the paper "COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP"

GRPO for Automated Program Repair

A Library for Advanced Deep Time Series Models.

No description.

KDD Cup 2025 Meta CRAG-MM Challenge 🥉 Solution for Task 1

No description.

Attention-Guided Training for Materials Mechnics

Repository for the paper "Multivariate Conformal Prediction via Conformalized Gaussian Scoring"

Assistax: A Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotic

Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

No description.

No description.

Challenging Memory-based Deep Reinforcement Learning Agents

No description.

No description.

Repository for MedARC group tackling Algonauts 2025 challenge

No description.

GFNet-Dynn is a hybrid deep learning model that combines the benefits of GFNet and Dynn architectures.

No description.

Fully open reproduction of DeepSeek-R1

No description.

MPaGE: Pareto-Grid-Guided Large Language Models for Fast and High-Quality Heuristics Design in Multi-Objective Combinatorial Optimization

🚀 Efficient implementations of state-of-the-art linear attention models

Optspa: Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression

No description.

No description.

A simple maze navigation game which is additional material for a paper

Code for "Outage Performance and Novel Loss Function for an ML-Assisted Resource Allocation: An Exact Analytical Framework", Nidhi Simmons, David Simmons and Michel Yacoub.

No description.

No description.

A sklearn-style GA interface.

Does visualization help AI understand data? Supplementary & replication material.

No description.

C2G-KD

No description.

[ICML 2025] Official Repo for Stability-guided Adaptive Diffusion Acceleration. 🚀🌙Accelerating off-the-shelf diffusion model with a unified stability criterion.

No description.

No description.

No description.

The Ever-Evolving Science Exam

Repo for the Configurable Optimizer project, which aims at searching in the space of one-shot optimizers

A Foundation Model for Industrial Signal Comprehensive Representation

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

No description.

No description.

No description.

llama.cpp for ROS 2

No description.

Arduino documentation (docs.arduino.cc)

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

No description.