About Me
I am a Postdoctoral Researcher at LIONS, EPFL. Before I was an ELLIS Ph.D. student at the University of Freiburg advised by Frank Hutter and co-advised by Yee Whye Teh at the University of Oxford. Since 2025 I am also an ELLIS member.
Research Interests
-
Adaptive Computation
Reasoning, looping, test-time training
-
Global Optimization
Hyperparameter optimization, multi-objective optimization, architecture search
-
Artificial Life
Cellular automata, evolutionary computation
News
- Sep 2026 "TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting" is accepted at NeurIPS 2026.
- Jun 2026 "Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training" was accepted for Oral presentation at ALife 2026.
- May 2026 I joined Volkan Cevher's LIONS lab at EPFL as a postdoc.
- Jan 2026 "Improving LLM-based Global Optimization with Search Space Partitioning" is accepted at ICLR 2026.
- Nov 2025 "TempoPFN: Towards Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting" is accepted at AITD@EurIPS 2025.
- Oct 2025 I successfully defended my PhD Thesis with summa cum laude.
- Sep 2025 "DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products" is accepted at NeurIPS 2025.
- May 2025 "Regularized Neural Ensemblers" is accepted at AutoML Conference 2025.
- Mar 2025 "DeltaProduct: Increasing the Expressivity of DeltaNet Through Products of Householders" is accepted at FM-WILD Workshop at ICLR 2025 as an Oral.
- Feb 2025 2 papers accepted at ICLR 2025. "Multi-objective Differentiable Neural Architecture Search" as a Poster and "Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues" as an Oral.
- Oct 2024 3 papers accepted at NeurIPS 2024 workshops: "Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues" (Oral), "GAMformer" (Poster), and "Ensembling Finetuned Language Models for Text Classification" (Poster).
- Sep 2024 "HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models" was accepted to NeurIPS 2024 Datasets and Benchmarks Track.
- Jun 2024 "Multi-objective Differentiable Neural Architecture Search" was accepted to the WANT workshop at ICML 2024.
Recent Talks / Seminars
- Nov 2024
- Mar 2024
Publications
2026
-
NeurIPS TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting
Advances in Neural Information Processing Systems 2026
-
arXiv -
arXiv -
ALIFE (Oral) Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training
The 2026 Artificial Life Conference (Oral)
-
ICLR Improving LLM-based Global Optimization with Search Space Partitioning
International Conference on Learning Representation 2026
-
arXiv -
arXiv
2025
-
NeurIPS DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
Advances in Neural Information Processing Systems 2025
-
AutoML-Conf -
ICLR (Oral) Unlocking State-Tracking in Linear RNNs through Negative Eigenvalues
International Conference on Learning Representation 2025 (Oral)
-
ICLR Multi-objective Differentiable Neural Architecture Search
International Conference on Learning Representation 2025 (Poster)
-
JCM Toward Artificial Intelligence in Oncology and Cardiology: A Narrative Review of Systems, Challenges, and Opportunities
Journal of Clinical Medicine 14(21), 2025
2024
-
TLR@NeurIPS GAMformer: In-Context Learning for Generalized Additive Models
NeurIPS 2024 Workshop on Table Representation Learning
-
FITML@NeurIPS Ensembling Finetuned Language Models for Text Classification
NeurIPS 2024 Workshop on Fine-Tuning in Machine Learning
-
NeurIPS DBT HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
Advances in Neural Information Processing Systems 2024, Datasets and Benchmarks Track
2023
-
IJCV Neural architecture search for dense prediction tasks in computer vision
International Journal of Computer Vision 2023
2022
-
ICLR NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy
International Conference on Learning Representation 2022
-
NeurIPS DBT NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies
Advances in Neural Information Processing Systems 2022, Datasets and Benchmarks Track
-
NeurIPS DBT JAHS-Bench-201: A Foundation For Research On Joint Architecture And Hyperparameter Search
Advances in Neural Information Processing Systems 2022, Datasets and Benchmarks Track
-
ICLR Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks
International Conference on Learning Representation 2022
2021
-
NeurIPS Neural Ensemble Search for Uncertainty Estimation and Dataset Shift
Advances in Neural Information Processing Systems 2021
-
NeurIPS How Powerful are Performance Predictors in Neural Architecture Search?
Advances in Neural Information Processing Systems 2021
-
UDL@ICML 2021 Multi-headed Neural Ensemble Search
ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning
-
IJCNN Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
International Joint Conference on Neural Networks 2021
2020
-
ICLR NAS-Bench-1Shot1: Benchmarking and dissecting one-shot neural architecture search
International Conference on Learning Representation 2020
-
ICLR (Oral) Understanding and Robustifying Differentiable Architecture Search
International Conference on Learning Representation 2020 (Oral)
2019
-
ICCV AutoDispNet: Improving Disparity Estimation With AutoML
International Conference on Computer Vision 2019
No publications match your search.