Siyuan Guo — accepted AI-conference papers

2026

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning

Patrik Reizinger, Bálint Mucsányi, Siyuan Guo, Benjamin Eysenbach, Bernhard Schölkopf, Wieland Brendel

ICLR 2026poster

Self-supervised feature learning and pretraining methods in reinforcement learning (RL) often rely on information-theoretic principles, termed mutual information skill learning (MISL). These methods aim to learn a representation of the environment while also incentivizing exploration thereof. Howeve…

Cited by 0 Source ↗Scholar ↗

2025

Counterfactual reasoning: an analysis of in-context emergence

Moritz Miller, Bernhard Schölkopf, Siyuan Guo

NeurIPS 2025poster

Large-scale neural language models exhibit remarkable performance in in-context learning: the ability to learn and reason about the input context on the fly. This work studies in-context counterfactual reasoning in language models, that is, the ability to predict consequences of a hypothetical scena…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Do-PFN: In-Context Learning for Causal Effect Estimation

Jake Robertson, Arik Reuter, Siyuan Guo, Noah Hollmann, Frank Hutter, Bernhard Schölkopf

NeurIPS 2025spotlight

Causal effect estimation is critical to a range of scientific disciplines. Existing methods for this task either require interventional data, knowledge about the ground-truth causal graph, or rely on assumptions such as unconfoundedness, restricting their applicability in real-world settings. In the…

Cited by 0 Source ↗Scholar ↗

2025

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

Patrik Reizinger, Siyuan Guo, Ferenc Huszár, Bernhard Schölkopf, Wieland Brendel

ICLR 2025spotlight

Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields developed rather independently. We observe that several structure and representation identifiability methods, particularly those that require multiple en…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

CausalCite: A Causal Formulation of Paper Citations

Ishan Agrawal, Zhijing Jin, Ehsan Mokhtarian, Siyuan Guo, Yuen Chen, Mrinmaya Sachan +1

ACL 2024findings

Citation count of a paper is a commonly used proxy for evaluating the significance of a paper in the scientific community. Yet citation measures are widely criticized for failing to accurately reflect the true impact of a paper. Thus, we propose CausalCite, a new way to measure the significance of a…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning

Siyuan Guo, Cheng Deng, Ying Wen, Hechang Chen, Yi Chang, Jun Wang

ICML 2024poster

In this work, we investigate the potential of large language models (LLMs) based agents to automate data science tasks, with the goal of comprehending task requirements, then building and training the best-fit machine learning models. Despite their widespread success, existing LLM agents are hindere…

Cited by 45 Source ↗PDF ↗code ↗Scholar ↗

2024

Do Finetti: On Causal Effects for Exchangeable Data

Siyuan Guo, Chi Zhang, Karthika Mohan, Ferenc Huszár, Bernhard Schölkopf

NeurIPS 2024oral

We study causal effect estimation in a setting where the data are not i.i.d.$\ $(independent and identically distributed). We focus on exchangeable data satisfying an assumption of independent causal mechanisms. Traditional causal effect estimation frameworks, e.g., relying on structural causal mode…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

Out-of-Variable Generalisation for Discriminative Models

Siyuan Guo, Jonas Bernhard Wildberger, Bernhard Schölkopf

ICLR 2024poster

The ability of an agent to do well in new environments is a critical aspect of intelligence. In machine learning, this ability is known as $\textit{strong}$ or $\textit{out-of-distribution}$ generalization. However, merely considering differences in distributions is inadequate for fully capturing di…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2023

Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data

Siyuan Guo, Viktor Tóth, Bernhard Schölkopf, Ferenc Huszár

NeurIPS 2023poster

Constraint-based causal discovery methods leverage conditional independence tests to infer causal relationships in a wide variety of applications. Just as the majority of machine learning methods, existing work focuses on studying $\textit{independent and identically distributed}$ data. However, it…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗

2023

Learning Generalizable Agents via Saliency-guided Features Decorrelation

Sili Huang, Yanchao Sun, Jifeng Hu, Siyuan Guo, Hechang Chen, Yi Chang +2

NeurIPS 2023spotlight

In visual-based Reinforcement Learning (RL), agents often struggle to generalize well to environmental variations in the state space that were not observed during training. The variations can arise in both task-irrelevant features, such as background noise, and task-relevant features, such as robot…

Cited by 9 Source ↗PDF ↗Scholar ↗