AIConfPaper
← Search

Samuel Holt

14 accepted papers

2026

Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback

Evgeny S. Saveliev, Samuel Holt, Nabeel Seedat, David Bentley, Jim Weatherall, Mihaela van der Schaar
ICML 2026poster

Large Language Models (LLMs) offer a promising avenue for scientific discovery, yet their application to symbolic regression is often constrained by inefficient search strategies and coarse feedback signals. Current methods typically guide LLMs using scalar metrics (e.g., global Mean Squared Error),…

Cited by 0Source ↗Scholar ↗
2026

Position: The AI Imperative: Scaling High-Quality Peer Review in Machine Learning

Qiyao Wei, Samuel Holt, Jing Yang, Markus Wulfmeier, Mihaela van der Schaar
ICML 2026oral

Peer review, the bedrock of scientific advancement in machine learning (ML), is strained by a crisis of scale. Exponential growth in manuscript submissions to premier ML venues such as NeurIPS, ICML, and ICLR is outpacing the finite capacity of qualified reviewers, leading to concerns about review q…

Cited by 0Source ↗Scholar ↗
2025

Demonstrating MuJoCo Playground

Kevin Zakka, Baruch Tabanpour, Qiayuan Liao, Mustafa Haiderbhai, Samuel Holt, Jing Yuan Luo +7
RSS 2025poster

We introduce MuJoCo Playground, a fully open-source framework for robot learning built with MJX, with the express goal of streamlining simulation, training, and sim-to-real transfer onto robots. With a simple installation process, researchers can train policies in minutes on a single GPU. Playground…

Cited by 0PDF ↗Scholar ↗
2025

EvoControl: Multi-Frequency Bi-Level Control for High-Frequency Continuous Control

Samuel Holt, Todor Davchev, Dhruva Tirumala, Ben Moran, Atil Iscen, Antoine Laurens +5
ICML 2025poster

High-frequency control in continuous action and state spaces is essential for practical applications in the physical world. Directly applying end-to-end reinforcement learning to high-frequency control tasks struggles with assigning credit to actions across long temporal horizons, compounded by the…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration

Samuel Holt, Max Ruiz Luyten, Antonin Berthon, Mihaela van der Schaar
ICML 2025poster

Constructing robust simulators is essential for asking "what if?" questions and guiding policy in critical domains like healthcare and logistics. However, existing methods often struggle, either failing to generalize beyond historical data or, when using Large Language Models (LLMs), suffering from…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Automatically Learning Hybrid Digital Twins of Dynamical Systems

Samuel Holt, Tennison Liu, Mihaela van der Schaar
NeurIPS 2024spotlight

Digital Twins (DTs) are computational models that simulate the states and temporal dynamics of real-world systems, playing a crucial role in prediction, understanding, and decision-making across diverse domains. However, existing approaches to DTs often struggle to generalize to unseen conditions in…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2024

Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models

Samuel Holt, Zhaozhi Qian, Tennison Liu, Jim Weatherall, Mihaela van der Schaar
NeurIPS 2024poster

The discovery of dynamical systems is crucial across a range of fields, including pharmacology, epidemiology, and physical sciences. *Accurate* and *interpretable* modeling of these systems is essential for understanding complex temporal processes, optimizing interventions, and minimizing adverse ef…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Dense Reward for Free in Reinforcement Learning from Human Feedback

Alex James Chan, Hao Sun, Samuel Holt, Mihaela van der Schaar
ICML 2024poster

Reinforcement Learning from Human Feedback (RLHF) has been credited as the key advance that has allowed Large Language Models (LLMs) to effectively follow instructions and produce useful assistance. Classically, this involves generating completions from the LLM in response to a query before using a…

Cited by 36Source ↗PDF ↗code ↗Scholar ↗
2024

Discovering Preference Optimization Algorithms with and for Large Language Models

Chris Lu, Samuel Holt, Claudio Fanconi, Alex James Chan, Jakob Nicolaus Foerster, Mihaela van der Schaar +1
NeurIPS 2024poster

Offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. Typically, preference optimization is approached as an offline supervised learning task using manually crafted convex loss functions. While these methods are based on theo…

Cited by 16Source ↗PDF ↗Scholar ↗
2024

L2MAC: Large Language Model Automatic Computer for Extensive Code Generation

Samuel Holt, Max Ruiz Luyten, Mihaela van der Schaar
ICLR 2024poster

Transformer-based large language models (LLMs) are constrained by the fixed context window of the underlying transformer architecture, hindering their ability to produce long and coherent outputs. Memory-augmented LLMs are a promising solution, but current approaches cannot handle long output genera…

Cited by 14Source ↗PDF ↗Scholar ↗
2024

ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference

Krzysztof Kacprzyk, Samuel Holt, Jeroen Berrevoets, Zhaozhi Qian, Mihaela van der Schaar
ICLR 2024spotlight

Inferring unbiased treatment effects has received widespread attention in the machine learning community. In recent years, our community has proposed numerous solutions in standard settings, high-dimensional treatment settings, and even longitudinal settings. While very diverse, the solution has mos…

Cited by 7Source ↗PDF ↗Scholar ↗
2023

Neural Laplace Control for Continuous-time Delayed Systems

Samuel Holt, Alihan Hüyük, Zhaozhi Qian, Hao Sun, Mihaela van der Schaar
AISTATS 2023poster

Many real-world offline reinforcement learning (RL) problems involve continuous-time environments with delays. Such environments are characterized by two distinctive features: firstly, the state x(t) is observed at irregular time intervals, and secondly, the current action a(t) only affects the futu…

Cited by 15Source ↗PDF ↗code ↗Scholar ↗