3 citations · 5 across the 17 of their papers we have counts for
20 papers
GeoPrior-Mamba: Structured Process Priors with Mamba for Fine-Resolution XCO2 Reconstruction
Zhao Meng, Yinan Cai, Siru Zhong +2
Reconstructing fine-resolution column-averaged dry-air CO2 (XCO2) fields from sparse satellite observations requires models to infer spatial structure that is only weakly constrain…
CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental Regimes
Yuche Gao, Arik Reuter, Siyuan Guo +3
Causal foundation models (CFMs) amortise causal inference over priors of synthetic structural causal models (SCMs), predicting the effect of an experiment on a specific variable. H…
Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning
Hsiao-Ru Pan, Bernhard Schölkopf
Direct Advantage Estimation (DAE) has been shown to improve the sample efficiency of deep reinforcement learning algorithms. However, its reliance on full environment observability…
On the Variance of Temporal Difference Learning and its Reduction Using Control Variates
Hsiao-Ru Pan, Bernhard Schölkopf
We analyze the variance of temporal difference (TD) learning using the phased setting with tabular representation, and show that one of the mechanisms behind its ability to reduce…
Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles
Zhanghan Ni, Yanjing Li, Zeju Qiu +4
Generative models have recently advanced protein design by learning the statistical regularities of natural structures. However, current approaches face three ke…
The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
Alejandro H. Artiles, Martin Weiss, Levin Brinkmann +6
Scientific discovery is constrained not only by what is true, but by what is cognitively available to researchers. Many directions are coherent in light of the literature yet unlik…
Use What You Know: Causal Foundation Models with Partial Graphs
Arik Reuter, Anish Dhir, Cristiana Diaconu +6
Estimating causal quantities traditionally relies on bespoke estimators tailored to specific assumptions. Recently proposed Causal Foundation Models (CFMs) promise a more unified a…
On the Emergence and Test-Time Use of Structural Information in Large Language Models
Michelle Chao Chen, Moritz Miller, Bernhard Schölkopf +1
Learning structural information from observational data is central to producing new knowledge outside the training corpus. This holds for mechanistic understanding in scientific di…
Is Generation Required for Data-Efficient Perception?
Jack Brady, Bernhard Schölkopf, Thomas Kipf +2
It has been hypothesized that achieving the data efficiency of human visual perception requires a generative approach in which internal representations result from inverting a deco…
TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models
Léo Grinsztajn, Klemens Flöge, Oscar Key +23
The first tabular foundation model, TabPFN, and its successor TabPFNv2 have impacted tabular AI substantially, with dozens of methods building on it and hundreds of applications ac…
Cultural Alien Sampler: Open-ended art generation balancing originality and coherence
Alejandro H. Artiles, Hiromu Yakura, Levin Brinkmann +6
In open-ended domains like art, autonomous agents must generate ideas that are both original and internally coherent, yet current Large Language Models (LLMs) either default to fam…
PENEX: AdaBoost-Inspired Neural Network Regularization
Klaus-Rudolf Kladny, Bernhard Schölkopf, Michael Muehlebach
AdaBoost sequentially fits so-called weak learners to minimize an exponential loss, which penalizes misclassified data points more severely than other loss functions like cross-ent…
Physics of Learning: A Lagrangian perspective to different learning paradigms
Siyuan Guo, Bernhard Schölkopf
We study the problem of building an efficient learning system. Efficient learning processes information in the least time, i.e., building a system that reaches a desired error thre…
Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning
Patrik Reizinger, Bálint Mucsányi, Siyuan Guo +3
Self-supervised feature learning and pretraining methods in reinforcement learning (RL) often rely on information-theoretic principles, termed mutual information skill learning (MI…
In-silico biological discovery with large perturbation models
Djordje Miladinovic, Tobias Höppe, Mathieu Chevalley +6
Data generated in perturbation experiments link perturbations to the changes they elicit and therefore contain information relevant to numerous biological discovery tasks -- from u…
Multi-megabase scale genome interpretation with genetic language models
Frederik Träuble, Lachlan Stuart, Andreas Georgiou +9
Understanding how molecular changes caused by genetic variation drive disease risk is crucial for deciphering disease mechanisms. However, interpreting genome sequences is challeng…
Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering
Klaus-Rudolf Kladny, Bernhard Schölkopf, Michael Muehlebach
Generative models lack rigorous statistical guarantees for their outputs and are therefore unreliable in safety-critical applications. In this work, we propose Sequential Conformal…
Detecting and Identifying Selection Structure in Sequential Data
Yujia Zheng, Zeyu Tang, Yiwen Qiu +2
We argue that the selective inclusion of data points based on latent objectives is common in practical situations, such as music sequences. Since this selection process often disto…
Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
Patrik Reizinger, Siyuan Guo, Ferenc Huszár +2
Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather indepe…
Learning Beyond Pattern Matching? Assaying Mathematical Understanding in LLMs
Siyuan Guo, Aniket Didolkar, Nan Rosemary Ke +3
We are beginning to see progress in language model assisted scientific discovery. Motivated by the use of LLMs as a general scientific assistant, this paper assesses the domain kno…