MLINFO COLLECTION
Recent advances in visuospatial understanding and agentic reasoning enable direct robotic manipulation with general-purpose multimodal models, but their embodied capabilities remain poorly…
Robot swarms coordinate through directed, time-varying local communication links, some of which may be compromised to allow the transmission of arbitrary malicious data. We provide an algorithm that…
Cascade world-action models (WAMs) use predicted visual futures to condition robot actions, but inherit costly iterative inference from diffusion-pretrained experts. We ask what a single-step…
Safe autonomous navigation of UASs requires tactical deconfliction to address conflicts that strategic coordination cannot prevent. This task is challenging under partial observability, when sensor…
Learning loco-manipulation policies requires demonstrations that capture coordinated base and arm motion on the target embodiment. Robot-free interfaces allow demonstrations to be collected…
In earlier work by Jonasson, Steif and Zetterqvist (2023), fully connected deep neural networks with layers of width $n$, i.i.d.\ standard Gaussian weights, sign activations and no bias terms were…
History-dependent robotic manipulation requires task context and interaction history, as the current observation alone is insufficient to determine the next action. Hierarchical frameworks use task…
Vision-language-action (VLA) robustness is commonly summarized by aggregate task success, which obscures how individual executions change under distribution shifts and where failures emerge in…
Action-free videos are an appealing substitute for costly teleoperated data. Latent action models (LAMs) turn videos into a supervision signal by inferring abstract actions between frames.
Human-collected real-world robotic manipulation demonstrations often contain mixed-quality trajectories, including hesitant, indirect, or inefficient action segments. While diffusion- and flow-based…
Diffusion models have emerged as the foundation of modern generative systems, yet their high memorization capacity raises privacy concerns. While differentially private (DP) training provides formal…
Smart-city applications often combine scarce labeled data with abundant unlabeled observations. Semi-supervised learning (SSL) exploits both labeled and unlabeled data to improve classification under…
Spatial and spatiotemporal point process models are widely used to analyze event data across many scientific disciplines, but likelihood-based Bayesian inference is often computationally prohibitive…
Offline reinforcement learning is fundamentally limited by the coverage of the available data, while collecting additional trajectories through online exploration may be costly, unsafe, or…
Model-based reinforcement learning in partially observable environments requires inferring hidden states, learning latent dynamics, and planning under the resulting belief. Practical algorithms often…
Bayesian neural networks (BNNs) offer a principled framework for quantifying epistemic uncertainty. However, standard weight-space priors yield complex, high-dimensional neural network posteriors…
Approximate leave-one-out (ALO) refers to methods that provide computationally efficient and statistically accurate approximations to leave-one-out risk estimation. These methods have recently…
Real-world audio typically contains concurrent sound events, yet standard self-supervised methods treat each clip as an isolated training unit without explicitly modeling mixture--constituent…
The evaluation of large language models (LLMs) is inherently multi-objective, as different models may offer different tradeoffs across performance dimensions such as math, code, and writing. Because…
We develop a Bayesian machine learning approach for estimating direct and spillover effects in cluster-randomized trials with treatment noncompliance. To flexibly model outcomes and treatment receipt…
As language-model agents grow more capable, they can carry more of a task without asking anyone for help. Falling reliance on a human partner is easy to read as a failure of collaboration when it may…
Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading agents. If a simulator misprices this mechanism, agents learn policies that are…
World models enable embodied agents to anticipate action consequences, yet jointly modeling locomotion and manipulation across diverse embodiments remains challenging due to heterogeneous action…
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify physical RSI through a…