A Playground for Tabular Foundation Models

Nano vLLM

Code for finetuning TabPFN on one downstream tabular dataset.

Efficient autoregressive inference for TabPFN models

Lightweight and educational reimplementation of TabPFN https://arxiv.org/pdf/2511.03634

My Claude Code settings and custom commands

σ-GPT: A New Approach to Autoregressive Models

FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.

GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505

This repo mainly contains CS234 (Spring 2024) assignment's coding problems

Amortized Probabilistic Conditioning for Optimization, Simulation and Inference (Chang et al., AISTATS 2025)

[NeurIPS '25] Multi-Token Prediction Needs Registers

Neural Diffusion Processes

CausalPFN: Amortized Causal Effect Estimation via In-Context Learning

Annotated version of the Mamba paper

Helpful tools and examples for working with flex-attention

Repository for TabICL: A Tabular Foundation Model for In-Context Learning on Large Data

Analysis of modern slavery statements in response to the Modern Slavery Acts.

Probabilistic deep learning using JAX

Official implementation of ICML'24 paper "Offline Multi-Objective Optimization".

📊 Save matplotlib figures as TikZ/PGFplots for smooth integration into LaTeX.

Normalizing Flow Regression for Bayesian Inference with Offline Likelihood Evaluations