138 citations · 402 across the 159 of their papers we have counts for
39 papers · 1 filter
Optimal Search for Finding Satellites Post-Launch
Carlo Schreiber, Duncan Eddy, Mahdi Al-Husseini +3
This paper introduces Bayesian Continuation Model Predictive Control (BC-MPC), an adaptive method that replans near-term antenna pointings while continuing a feasible baseline swee…
Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard
Michael Hardy, Ruhana Azam, Anka Reuel +2
Agent evaluations are increasingly used to compare LLMs and inform deployment decisions, yet ranks can reflect not only the model but also the effects of the evaluation conditions…
Stochastic World Models for Verifying Vision-Based Neural Feedback Systems
I. Samuel Akinwande, Mykel J. Kochenderfer, Clark Barrett
Verifying a vision-based neural feedback system requires a model of the observations its controller acts upon. Such a model must capture the variation the sensor produces, while re…
Probe-Space Preconditioning for Fast and Stable Zero-Order Training
Francois Chaubard, Mykel J. Kochenderfer, Chris Ré
Backpropagation (BP) dominates deep learning but imposes a massive memory tax. For example, training OPT-30B with Adam requires 600GB of GPU memory (assuming batch size 8…
Scaling Zero-Order Pretraining through Model Sharding
Francois Chaubard, Mykel J. Kochenderfer, Chris Ré
Zero-order optimization (ZO) trains without backpropagation, making it relevant to forward-only hardware and non-differentiable loss, but its gradient variance grows with perturbed…
Risk-Averse Lander Site Selection under Altitude-Limited Information
Vikas A. Patel, Mahdi Al-Husseini, Duncan Eddy +1
In aerospace systems, powered descent requires efficiently selecting a landing site while fine-scale hazards remain unresolvable until low altitude. This process presents a decisio…
Self-Organizing Agent Teams Learn to Reason Together
Aneesh Pappu, Mirac Suzgun, Yongchan Kwon +5
Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unknown, useful roles and division…
Chance-Constrained Belief-Space Maneuver Planning for Autonomous Collision Avoidance Under Uncertainty
Grace Ra Kim, Duncan Eddy, Mykel J. Kochenderfer
Increasing conjunction frequency in low Earth orbit places growing pressure on spacecraft operators to determine not only whether an encounter requires mitigation, but whether suff…
GPU-Accelerated Astrodynamics World Models for Spacecraft Rendezvous and Proximity Operations
Duncan Eddy, Isaac R. Ward, Grace Ra Kim +1
World models are an emerging paradigm in representation learning in which an agent jointly learns state-action dynamics and observation models from offline trajectory data, enablin…
Protection Levels for Vision-Based Pose Estimation
Olivia Beyer Bruvik, Romeo Valentin, Marc R. Schlichting +2
Vision-based navigation complements Global Navigation Satellite Systems, but certification demands integrity guarantees that account for faulty measurements. Previous work presente…
Semi-Decentralized Multi-Spacecraft Collision Avoidance under Communication Constraints
Grace Ra Kim, Mahdi Al-Husseini, Duncan Eddy +1
Current spacecraft collision-avoidance operations rely on intermittent ground-station contacts, requiring operators to plan with delayed and asynchronously updated information. Con…
Importance Sampling and PCA for Finding Failures in Commercial Autonomous Vehicles
Hailey Warner, Duncan Eddy, Shreya Parjan +6
Methods for discovering rare failures in autonomous systems have so far been demonstrated almost exclusively in simulations with simple, academic driving stacks, leaving open wheth…
Real-Time Flight Test Maneuver Selection with Monte Carlo Tree Search
Nicholas E. Bostock, Helen Pruitt-Kennett, Marc R. Schlichting +1
Flight test is shifting toward a data-centric approach in which data contribute to model refinement, reducing reliance on pre-scripted test points. An open problem is how to sequen…
Retriever: Composing the Perception-Reasoning-Action Loop for Long-Horizon Manipulation
Linfeng Zhao, Haojie Huang, Jiayuan Mao +3
Building long-horizon robot agents requires composing closed-loop pipelines -- perception, belief update, planning, and control -- whose components run at different clocks and with…
RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences
Logan Mondal Bhamidipaty, Mykel Kochenderfer, Subramanian Ramamoorthy
World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset. However, they are vulnerable to mod…
Simplifying Flow Matching Transformations with Low-Rank Mixture Models
Liam A. Kruse, Houjun Liu, Alexandros E. Tzikas +2
Normalizing flows are powerful generative models that learn an invertible mapping between complex data distributions and simple latent distributions, typically a standard normal de…
Optimizing Lithium Production Decisions under Geological, Demand, and Pricing Uncertainties: A POMDP Framework for Multi-Objective Decision Making
Anna C. Edmonds, Mansur M. Arief, Robert J. Moss +2
Decision making in lithium production is challenging, whether from an investor's perspective or a strategic production standpoint. Determining which mines to open and when to open…
Free-Placement Optimization of Ground Station Locations for Low-Earth Orbit Satellites
Grace Ra Kim, Duncan Eddy, Vedant Srinivas +1
Rapidly expanding low Earth orbit satellite constellations are placing increasing demands on terrestrial ground networks, motivating the development of more efficient ground statio…
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting
Avijit Ghosh, Anka Reuel, Jenny Chim +45
AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs. The cost is interpretive: readers can…
How Language Models Fail: Token-Level Signatures of Committed and Persistent Reasoning Failures
Tanvi Thoria, Kiana Jafari, Marc R. Schlichting +1
Failures in language model reasoning emerge through distinct processes that leave identifiable signatures in the reasoning trace. We characterize these failures using token-level u…
Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
Andreas Haupt, Justin Hartenstein, Anka Reuel +2
AI benchmarks have well-documented limitations, with prior work examining contamination, saturation, and construct underspecification. Aggregation has received far less attention:…
Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
Max Lamparth, Daniel Fein, Andreas Haupt +2
Single-axis mitigations of reward-model biases (e.g., reducing proxy reliance on length, sycophancy, or style) can rotate optimization pressure onto correlated proxies rather than…
Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
Romeo Valentin, Olivia Beyer Bruvik, Marc R. Schlichting +1
EASA's learning-assurance guidance requires data-driven aviation systems to build and monitor their own situation representation, yet for neural networks the technical means to pro…
Imperfect World Models are Exploitable
Logan Mondal Bhamidipaty, Esmeralda S. Whitammer, David Abel +2
We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy should be strictly preferred o…