News
-
Two of my papers have been accepted to the Workshop on the Philosophy of Machine Learning (PhilML) at ICML 2026.
Reality and Practice: A Relational Reading of the Platonic Representation Hypothesis
I revisit the Platonic Representation Hypothesis — the claim that large models trained for different objectives converge on a shared statistical model of reality. I accept the empirical convergence but argue the Platonic framing is not forced by the mathematics, and offer a Wittgensteinian alternative: categories are useful compressions linked by family resemblance, and the convergent geometry reflects convergence toward a relational system of use, shaped by human practice under physical constraints. Read on OpenReview.
Measuring the Ruler: Reading Benchmark Saturation as Evidence
I argue that the inference from a benchmark score to a capability claim is conditional on the system being evaluated: a benchmark supports a claim only once the benchmark–system pair has been validated. On this view, benchmark saturation is not merely a sign that harder tests are needed — it is evidence about the validity relation itself. Illustrated on MMLU, GSM8K, and HumanEval, the paper proposes a short Validity Transfer Report that benchmark papers can use to make these assumptions explicit. Read on OpenReview.
-
I'm serving as an Area Chair for NeurIPS 2026.
-
We've launched Latent-Y at Latent Labs, the first lab-validated AI agent for drug design, which I lead. Powered by Latent-X2, it autonomously designs antibodies and therapeutic peptides from natural-language prompts — compressing weeks of expert work into hours.
-
The paper PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis from my time at Altos Labs has been accepted to Neurips 2025 Datasets and Benchmarks Track.
-
Our team at Latent Labs as published a preprint for our new all-atom protein design model Latent-X, where we demonstrate lab-validated state-of-the-art performance for the de-novo design of cyclic peptides and minibinders! Also check out the platform.
-
I am excited to join Latent Labs to work on the next generation of biologics frontier models!
-
Our team at Altos Labs will be presenting our paper PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis as a spotlight presentation at the Neurips workshop on AI for New Drug Modalities. If you're planning to attend, feel free to reach out — we'd love to connect!
-
Together with Bastian Grossenbacker Rieck and Juius von Rohrscheidt we investigate what happens when Bayesian Computation Meets Topology. Now accepted at TMLR!
-
I am serving as an Area Chair at AISTATS 2025.
-
Our paper on Approximate Bayesian Computation with Path Signatures has been recognized with the outstanding paper award at UAI 2024!
{% include figure.liquid loading="eager" path="assets/img/uai_best_paper.png" title="UAI award" class="img-fluid rounded z-depth-1" %} -
Our paper on Approximate Bayesian Computation with Path Signatures got accepted as a Spotlight paper at UAI 2024!
-
I am serving as an Area Chair at Neurips 2024.
-
Our paper on simulation-based inference for agent-based models has been published in the Journal of Economics Dynamics and Control.
-
I have moved to Cambridge to join Altos Labs as a Senior Staff Machine Learning Engineer.