Matthew Kenney
@baykenney.bsky.social
Founder - Algorithmic Research Group. Previously: Senior ML Engineer at Apple, Asst. Research Prof at Duke University, Duke Data Science | PSU '15 | Cornell '11
If you're working on ML and this resonates, I’d love to hear what you'd want it to do. We're opening up a limited beta. Link below: prospectml.com
ProspectML | A research assistant that helps researchers generate insights and code to accelerate their work.
A research assistant that helps researchers generate insights and code to accelerate their work.
prospectml.com
May 19, 2025 at 1:42 PM
If you're working on ML and this resonates, I’d love to hear what you'd want it to do. We're opening up a limited beta. Link below: prospectml.com
It’s built on top of a foundation of parsed metadata from papers, code, and repos—models, metrics, datasets, SOTA claims, GPU counts (and types), ablation studies, citations, etc. It’s already become crucial to our internal research, and we hope it can be helpful to others, too.
May 19, 2025 at 1:42 PM
It’s built on top of a foundation of parsed metadata from papers, code, and repos—models, metrics, datasets, SOTA claims, GPU counts (and types), ablation studies, citations, etc. It’s already become crucial to our internal research, and we hope it can be helpful to others, too.
It’s designed to support that murky, nonlinear part of the research process, where you're still figuring out what's interesting.
May 19, 2025 at 1:42 PM
It’s designed to support that murky, nonlinear part of the research process, where you're still figuring out what's interesting.
You give it a question like “How can we improve generalization in low-resource RL?” and it returns distilled insights, speculative ideas, and experimental code. Not final answers, just something to push the thinking forward.
May 19, 2025 at 1:42 PM
You give it a question like “How can we improve generalization in low-resource RL?” and it returns distilled insights, speculative ideas, and experimental code. Not final answers, just something to push the thinking forward.
Most of the time, I end up manually digging through papers, chasing links, and piecing together ideas. It works, but it’s slow, and it doesn’t scale with curiosity. I’ve been trying to fix that with a platform we're building called ProspectML.
May 19, 2025 at 1:42 PM
Most of the time, I end up manually digging through papers, chasing links, and piecing together ideas. It works, but it’s slow, and it doesn’t scale with curiosity. I’ve been trying to fix that with a platform we're building called ProspectML.
That’s because it was from 2022
November 30, 2024 at 3:40 AM
That’s because it was from 2022
What! If it works for umap-learn vs umap i’m in.
November 25, 2024 at 10:00 AM
What! If it works for umap-learn vs umap i’m in.
I have a community project in Eleuther and open source all of my research:
bsky.app/profile/bayk...
bsky.app/profile/bayk...
(re-posting from X)
Can we get AI to accelerate AI research and development?
I’m excited to release ML Research Benchmark, an agentic benchmark of 7 ML conference competition tasks.
Paper: arxiv.org/abs/2410.22553
Tasks: github.com/AlgorithmicR...
Agent: github.com/AlgorithmicR...
Can we get AI to accelerate AI research and development?
I’m excited to release ML Research Benchmark, an agentic benchmark of 7 ML conference competition tasks.
Paper: arxiv.org/abs/2410.22553
Tasks: github.com/AlgorithmicR...
Agent: github.com/AlgorithmicR...
ML Research Benchmark
Artificial intelligence agents are increasingly capable of performing complex tasks across various domains. As these agents advance, there is a growing need to accurately measure and benchmark their c...
arxiv.org
November 25, 2024 at 9:36 AM
I have a community project in Eleuther and open source all of my research:
bsky.app/profile/bayk...
bsky.app/profile/bayk...
Jk the rest are great. Just a big uncle nearest fan
November 25, 2024 at 3:13 AM
Jk the rest are great. Just a big uncle nearest fan
We welcome PRs, contributions, additional tasks, and task revisions. Excited to see how agents perform on this benchmark.
November 24, 2024 at 8:02 PM
We welcome PRs, contributions, additional tasks, and task revisions. Excited to see how agents perform on this benchmark.
We develop a baseline agent, with tools for coding, research (via Semantic Scholar), and model training, built on top of Sonnet 3.5 and GPT-4o. Our baseline agent performs well across tasks, but generally fails to move beyond baseline implementations.
November 24, 2024 at 8:02 PM
We develop a baseline agent, with tools for coding, research (via Semantic Scholar), and model training, built on top of Sonnet 3.5 and GPT-4o. Our baseline agent performs well across tasks, but generally fails to move beyond baseline implementations.
ML Research Bench adapts tasks from ML conference competitions like ‘NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day’ and ‘LLM Merging Competition’. We prompt agents to complete these challenging tasks. These tasks move beyond simple ML tasks.
November 24, 2024 at 8:02 PM
ML Research Bench adapts tasks from ML conference competitions like ‘NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day’ and ‘LLM Merging Competition’. We prompt agents to complete these challenging tasks. These tasks move beyond simple ML tasks.