tkukurin
Follow
Lists (5)
Stars
official repository for “Reinforcement Learning for Reasoning in Large Language Models with One Training Example”
fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
Open source interpretability artefacts for R1.
Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"
Medical Hallucination in Foundation Models and Their Impact on Healthcare (2025)
The one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE, WMDP, and many unlearning methods. All features: benchmarks, methods, evaluations, models etc. are easily ext…
A small and lightweight Python package for working with and generating data from www.PrefLib.org.
High-velocity, monorepo-scale workflow for Git
Lbster: Language models for Biological Sequence Transformation and Evolutionary Representation
Digital planner for Supernote and ReMarkable // Support Ukraine 🇺🇦 https://savelife.in.ua/en
Smart glasses OS, with dozens of built-in apps. Users get AI assistant, notifications, translation, screen mirror, captions, and more. Devs get to write 1 app that runs on any pair of smart glases.
NiceWebRL is a Python library for quickly making human subject experiments that leverage machine reinforcement learning environments.
DataGene - Identify How Similar TS Datasets Are to One Another (by @firmai)
Jupyter Notebooks for learning the PyRosetta platform for biomolecular structure prediction and design
(Crafter + NetHack) in JAX. ICML 2024 Spotlight.
BlackJAX is a Bayesian Inference library designed for ease of use, speed and modularity.
MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user develop their prompts into full models.
This repo contains the results data for Round 1 of Adaptyv Bio’s EGFR Protein Design Competition.
Massively parallel rigidbody physics simulation on accelerator hardware.
An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"
Goal-conditioned reinforcement learning like 🔥
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…