M. Kochenderfer

Adaptive Science Operations in Deep Space Missions using Robust Precomputed Autonomy

Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard

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 such as the scaffolds or tasks. This makes reliability claim-dependent: an evaluation that reliably ranks deployed systems may not reliably...

Probe-Space Preconditioning for Fast and Stable Zero-Order Training

Backpropagation (BP) dominates deep learning but imposes a massive memory tax. For example, training OPT-30B with Adam requires $\approx$ 600GB of GPU memory (assuming batch size 8 and sequence length 2048). Alternatively, zero-order optimization (ZOO) trains in inference-mode (requiring only $\approx$ 60GB for the sam...

Scaling Zero-Order Pretraining through Model Sharding

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 dimension, inhibiting large-model training. Sharded Optimization Mixture of Assemblies (SOMA) trains LSTM experts independently on $N$ data...

Stochastic World Models for Verifying Vision-Based Neural Feedback Systems

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 remaining tractable for closed-loop analysis. Generative adversarial networks (GANs) have served as perception surrogates, but they are large,...

Self-Organizing Agent Teams Learn to Reason Together

Self-Organizing Agent Teams (SAT) are introduced, fixed teams of AI agents that learn reusable strategies from prior collaborations to organize roles, conversational phases, participation, and information flow, suggesting that organization itself can become an agent capability.

GPU-Accelerated Astrodynamics World Models for Spacecraft Rendezvous and Proximity Operations

An open-source, JAX-based International Space Station docking environment supporting parallel GPU simulation of spacecraft orbit and attitude dynamics is introduced and a transformer-based world model is introduced, a transformer-based world model that encodes relative kinematic states and body-fixed camera imagery int...

Chance-Constrained Belief-Space Maneuver Planning for Autonomous Collision Avoidance Under Uncertainty

Increasing conjunction frequency in low Earth orbit places growing pressure on spacecraft operators to determine not only whether an encounter requires mitigation, but whether sufficient information is available to commit to a maneuver. This work formulates this information-action tradeoff as a belief-space planning pr...

RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences

This work proposes to repair exploitation directly using human preferences over imagined rollouts, leveraging the strong intuitive physics that allows humans to easily spot egregious dynamics hallucinations in pretrained world models.