Anja Šurina
I am a PhD candidate at advised by Prof Caglar Gulcehre and Prof Emmanuel Abbe, and a Research Fellow at
Inherent Laboratories.
My research focuses on post-training and test-time scaling of LLMs, particularly for scientific and mathematical discovery, and on understanding their cognition and intelligence.
Previously, I did research at:
-
Google DeepMind on the AlphaEvolve and AlphaProof Nexus teams -
Mila in Prof Yoshua Bengio’s lab
-
Stanford in Prof Jure Leskovec’s lab -
IBM Research, in the Emerging Computing and Circuits group
I received an MSc in Neural Systems and Computation from and a BSc in Electrical Engineering from the
University of Ljubljana.
Publications
-
Replicating a paper demands the same hypothesis-driven exploration as open-ended research, making it a training ground for research taste. Trained on this task with long-horizon RL, our 27B-parameter AI scientist, Faraday, outperforms frontier agents Claude Opus 4.8 and GPT-5.5 at replicating research, a step toward models capable of autonomous innovation.
-
Language models are fast becoming our default interface to facts, yet what they recognize as true often differs from what they can recall. We trace how this generation-verification gap emerges and evolves over a fact’s lifecycle. Our findings call for rethinking how we measure factuality in language models. As more training data from the web is written by models themselves, the gap also risks a quiet drift in what counts as usable knowledge.
-
We developed AlphaProof Nexus, Google DeepMind’s Gemini-powered agent for formal proof search. It autonomously solved 9 open Erdős problems (two of them open for 56 years) and advanced research-level mathematics across various fields, with every proof verified in Lean.
-
Using AlphaProof Nexus, we resolved an open question in min-max optimization by proving that Anchored Gradient Descent Ascent achieves the faster O(1/t) rate. The agent autonomously discovered both the proof and the new step-size schedule that makes it work, verified in Lean.
-
We developed EvoTune, which uses reinforcement learning to let an LLM learn from its own discoveries during evolutionary search. By training the model to become a better search operator, EvoTune finds better algorithms faster than AlphaEvolve-style search with a fixed LLM, a step toward self-improving LLMs for algorithm design.
-
Actor networks are a known bottleneck in offline RL. We show that regularizers already standard in deep learning, such as dropout and layer normalization, applied to the actor improve performance across algorithms and benchmarks.
-
We developed CaML, a causal meta-learning framework that predicts the personalized effects of a novel intervention, such as a newly invented drug, without ever seeing that intervention during training. On large-scale patient records and cell-line perturbation data, its zero-shot predictions outperform even baselines trained directly on data from the new intervention.
-
Backpropagation through time is ill-suited to online learning, since it must store every past neural state. We show that e-prop, a local, biologically inspired approximation of it, can train recurrent spiking neural networks online on neuromorphic hardware, with performance competitive with full-precision training.
* equal contribution