Stars
A curated list of papers related to constrained decoding of LLM, along with their relevant code and resources.
Text2SQL-Eval is a Text-to-SQL evaluating component for LLM trained on an open-source training dataset.
SoTA LLM for converting natural language questions to SQL queries
Recipes to scale inference-time compute of open models
Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"
[ICLR2025] DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RL, published in ICLR 2023
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
Stable Video Diffusion Training Code and Extensions.
Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
Multi-Objective Molecule Generation using Interpretable Substructures (ICML 2020)
Our own implementation of Neural Message Passing for Computer Vision paper
A curated collection of papers on probabilistic circuits, computational graphs encoding tractable probability distributions.
Compiled parser combinators and regular expressions in pure julia
A structured list of resources about Sum-Product Networks (SPNs)
Probabilistic Circuits from the Juice library
Tutorials given as one of the TAs for the class "Algorithm Design and Analysis" at Nanjing University
TinyXML2 is a simple, small, efficient, C++ XML parser that can be easily integrated into other programs.