- Amsterdam
Stars
This is an official repository for "RTD-Lite: Scalable Topological Analysis for Comparing Weighted Graphs in Learning Tasks" accepted for AISTATS 2025 conference.
Open-source implementation of AlphaEvolve
Code for the paper "VAE with a VampPrior", J.M. Tomczak & M. Welling
This is the official code release for Bayesian Flow Networks.
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
Kernel Herding for probability density estimation
Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".
Test-time scaling by sampling perturbations in the latent space.
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
A centralized place for deep thinking code and experiments
A generative world for general-purpose robotics & embodied AI learning.
Environments for LLM Reinforcement Learning
The repo for code, that hasn't been published yet
[COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
verl: Volcano Engine Reinforcement Learning for LLMs
An extensible benchmark for evaluating large language models on planning
The official implementation of Self-Play Preference Optimization (SPPO)
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.
Implementation for our paper "How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad"
A Database of Real Faults and an Experimental Infrastructure to Enable Controlled Experiments in Software Engineering Research
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024