AIDDA Institute

Panel: What are the current limitations and drawbacks of automated research?

Autoscience: Automated Algorithmic Discovery in Machine Learning

DiscoGen: Learning to Discover Learning Algorithms

DiscoGen addresses the limitations of current machine learning algorithm discovery benchmarks by providing a procedural generation framework capable of creating over 100 billion unique tasks. By strictly decoupling meta-training and meta-testing data, this system prevents contamination and enables the development of mo...

Hiverge: Algorithm Discovery In Practice

SkyDiscover: A Flexible Framework for AI-Driven Scientific and Algorithmic Discovery

TTT-Discover: Learning to Discover at Test Time

TTT-Discover introduces a test-time reinforcement learning framework designed to solve verifiable scientific discovery problems, such as optimizing GPU kernels or mathematical bounds. Unlike standard reinforcement learning that targets average reward, this approach optimizes for maximum reward on a single, specific pro...

LEVI: Stronger Search Architectures Can Substitute for Larger LLMs in Evolutionary Search

ShinkaEvolve, Evolved: Faster, Cheaper, in Your Coding Agent

CodeEvolve: Evolutionary Agents for Scientific Discovery

AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?

Automated Algorithm Design - LLM4AD