Seungyoun, Shin

SDPO. Reinforcement Learning via Self-Distillation (SDPO)

self-distillation-analysis. Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”

oh-my-openclaw. oh-my-opencode patterns ported to OpenClaw

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Qwen3-TTS. Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

nanoRLHF. nanoRLHF: from-scratch journey into how LLMs and RLHF really work.

AI-Scientist-v2. The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

ToolOrchestra. ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

aideml. AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.

audio-ai-hub. The hub for audio AI research: papers, open models, benchmarks & datasets across audio LLMs, speech recognition, TTS, music & audio generation.

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

miles. Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

deepagents. The batteries-included agent harness.

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

large-scale-lm-tutorials. Large-scale language modeling tutorials with PyTorch

Qwen3-Omni. Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

DICE-Bench. [ACL 2025] DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues

DeepResearch. Tongyi Deep Research, the Leading Open-source Deep Research Agent

matcha_tts_e. Jupyter Notebook

Agent-R1. Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

minimal-r1. Python

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

nano-vllm. Nano vLLM

openai-cs-agents-demo. Demo of a customer service use case implemented with the OpenAI Agents SDK

delayed-streams-modeling. Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

lerobot-mujoco-tutorial. Jupyter Notebook

ch-tts-llasa-rl-grpo. Python

Absolute-Zero-Reasoner. Official Repository of Absolute Zero Reasoner

csm-hf. Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers

ToRL. Python

LUCY. LUCY: Linguistic Understanding and Control Yielding Early Stage of Her

OpenManus-RL. A live stream development of RL tunning for LLM agents

audio_refiner. Python

MOSHI_forTPU. Python

Decision-Transformers-For-Trading. Jupyter Notebook

simpleRL-reason. Simple RL training for reasoning

open-r1. Fully open reproduction of DeepSeek-R1

search-and-learn. Recipes to scale inference-time compute of open models

NeurIPS-2024-LLM-Papers. Accepted LLM Papers in NeurIPS 2024

stable-codec. A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

moshi. Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

BayLing-Speech. LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

quiet-star. Code for Quiet-STaR

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

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

LLM101n. LLM101n: Let's build a Storyteller

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

llama3-tokenizer-js. JS tokenizer for LLaMA 3 and LLaMA 3.1

tau-bench. Code and Data for Tau-Bench

VLM_manipulation. Manipulation in the simulation and realworld environment. GPT4 and G-DINO based reasoning is utilized for commonsense image reasoning.

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

SolarLLMChatDemo. Full Stack SolarLLM Zero to All

gym-aloha. A gym environment for ALOHA

FishNet. Implementation code of the paper: FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction, NeurIPS 2018

ri-motion. This repo contains useful implementations for handling motions maintained by rilab.ku

evalverse. The Universe of Evaluation. All about the evaluation for LLMs.

llama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

InstructDet. Python

SPIN. The official implementation of Self-Play Fine-Tuning (SPIN)

reflect. [CoRL 2023] REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction

spots. Implementation about 'SPOTS: Stable Placement of Objects with Reasoning in Semi-Autonomous Teleoperation Systems'

yet-another-gpt-tutorial-v2. Jupyter Notebook

open_x_embodiment. Jupyter Notebook

CLARA-SaGC-Code. Jupyter Notebook

Retrieval-QA-Benchmark. Benchmark baseline for retrieval qa applications

yet-another-pytorch-tutorial-v2. Jupyter Notebook

llm-search. Querying local documents, powered by LLM

chat-ui. JavaScript

inst-inpaint. A novel inpainting framework that can remove objects from images based on the instructions given as text prompts.

Llama2-Code-Interpreter. Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internet

yet-another-gpt-tutorial. Jupyter Notebook

KoVicuna.

MultiThor. MultiAgent Cooperative instruction following Env.

skypilot. The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

RILAB-SEG. Python

KoAlpaca. KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델 (KoAlpaca: An open-source language model to understand Korean instructions)

the-algorithm. Source code for the X Recommendation Algorithm

flame. Official implementation of the paper "FLAME: Free-form Language-based Motion Synthesis & Editing"

FILM. Official repository of ICLR 2022 paper FILM: Following Instructions in Language with Modular Methods

TEACh_FILM. Official Repo of EMNLP 2022 "Don’t Copy the Teacher: Data and Model Challenges in Embodied Dialogue"

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

diffuser. Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

Awesome-LLM-Robotics. A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

simple-mujoco-usage-v2. Jupyter Notebook

mdetr. Python

yolov5. Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

FAI-Model. FriendliAI Model Hub

2022-1-deep-learning-applications.

Conditional-Motion-In-Betweening. 🕹️ Official Implementation of Conditional Motion In-betweening (CMIB) 🏃

onnxjs. ONNX.js: run ONNX models using JavaScript

MotionCLIP. Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

Uncertainty-Aware-Robust-Learning. Jupyter Notebook

InteractivePickup. Interactive Text2Pickup Network for Natural Language based Human-Robot Collaboration

BABEL. Code accompanying the BABEL dataset (CVPR 2021).

mindall-e. PyTorch implementation of a 1.3B text-to-image generation model trained on 14 million image-text pairs

Mixquality_AL. Final term project for Bayesian Machine Learning Lecture (XAI-623)

CenterNet. Object detection, 3D detection, and pose estimation using center point detection:

neat. [ICCV'21] NEAT: Neural Attention Fields for End-to-End Autonomous Driving

deep-text-recognition-benchmark. Text recognition (optical character recognition) with deep learning methods.

Transformer-in-Vision. Recent Transformer-based CV and related works.

transformers. 🤗 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.

Data_Structures_and_Algorithms_in_Python. :book: Worked Solutions of "Data Structures & Algorithms in Python", written by Michael T. Goodrich, Roberto Tamassia and Michael H. Goldwasser. ✏️

Human-In-The-Loop-MLN-Project. Python

peg-in-hole. Python

pytorch-mnist-VAE. Jupyter Notebook

Transformer-Explainability. [CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

Transformer-MM-Explainability. [ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

Cartoon-StyleGAN. Fine-tuning StyleGAN2 for Cartoon Face Generation

choicenet. Implementation of ChoiceNet

AlgorithmArchive. Algorithm / Data Structure archive

JoCoR. CVPR'20: Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization

KLUE. 📖 Korean NLU Benchmark

bbopt. Black Box Optimization Methods

upstage-basic-deeplearning. PyTorch Tutorial for Boostcamp AI Tech

applied-ml. 📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

Deepjsccf_Autotune. https://arxiv.org/abs/1911.11174

irl_rocks. Cool Inverse Reinforcement Learning Papers

bayes-nn. Lecture notes on Bayesian deep learning

LossLandscape. Explores the ideas presented in Deep Ensembles: A Loss Landscape Perspective (https://arxiv.org/abs/1912.02757) by Stanislav Fort, Huiyi Hu, and Balaji Lakshminarayanan.

yet-another-pytorch-tutorial. Yet Another PyTorch Tutorial

mnist-c. Jupyter Notebook

Deep-learning-Uncertainty-papers. Uncertainty in Deep Learning Papers

confidence-aware-learning. Confidence-Aware Learning for Deep Neural Networks (ICML2020)

injae-kim.github.io. 지식과 경험을 공유하는 개발 블로그

enjoy-design-pattern. 🏡Java 언어로 배우는 디자인 패턴 입문

SellyDev. Autonomous-driving delivery robot project : Selly

gpt-3. GPT-3: Language Models are Few-Shot Learners

arcface-pytorch. Python

kaggle-humpback. Code for 3rd place solution in Kaggle Humpback Whale Identification Challenge.

Adaptive-Wing-Loss-for-Robust-Face-Alignment-via-Heatmap-Regression. Adaptive-Wing-Loss-for-Robust-Face-Alignment-via-Heatmap-Regression

object_detection_for_retail. an autonomous solution for unmanned shops based on computer vision

EXTD_Pytorch. Official EXTD Pytorch code

PoseFix_RELEASE. Official TensorFlow implementation of "PoseFix: Model-agnostic General Human Pose Refinement Network", CVPR 2019

2019-2-OSSP1-3355-3. 2019-2-OSSP1-3355-3

Realtime_Multi-Person_Pose_Estimation. Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

EXTD_Pytorch. Official EXTD Pytorch code

people-counting-pose. Odin: Pose estimation-based tracking and counting of people in videos

Classify_Cars. simple CNN model classifying 4 classes of car (Keras)

iamleejihye.github.io. My portfolio site based on blog

BERT-pytorch. Google AI 2018 BERT pytorch implementation