Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Synthetic data curation for post-training and structured data extraction

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

Strong and Open Vision Language Assistant for Mobile Devices

Awesome Mobile LLMs

Universal LLM Deployment Engine with ML Compilation

A powerful tool for creating fine-tuning datasets for LLM

A quick guide (especially) for trending instruction finetuning datasets

The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".

S1-Bench: Exposing System 1 Thinking Barriers of Large Reasoning Models

Time-R1 is a two-stage reinforcement fine-tuning framework that trains large language models to perform slow-thinking, step-by-step reasoning for accurate and explainable time series forecasting.

Official code for "Kairos: Towards Adaptive and Generalizable Time Series Foundation Models"

PyTorch implementation of "ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data" (AAAI 2025 [oral])

Listing some diffusion papers in NLP domain I have read, text generation is main, table will continue to be updated.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models

Awesome-LLM: a curated list of Large Language Model

LLM Adversarial Robustness Toolkit, a toolkit for evaluating LLM robustness through adversarial testing.

[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models

Planet as a Brain: Towards Decentralized Agent Networks based on AIOS Server

Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.

Demonstration Agents for AIOS

My coding projects for university application