MLINFO COLLECTION
Motion retargeting maps a demonstrated human movement onto a robot to compute its joint motion. This study examines how the construction of the desired wrist position affects whether computed arm…
The short-time Fourier transform (STFT) characterizes the local frequency content of time-varying signals by evaluating the discrete Fourier transform over a sliding analysis window. The STFT is…
Model discrepancy may prevent a single calibration parameter from reproducing a physical response across the context domain. In addition, uncertainties in observations and contexts affect calibration…
Agile robots require spatiotemporal intelligence to interpret scenes, reason about interactions, and anticipate future events. Yet it remains unclear how well foundation vision models support these…
Manipulation policies are evaluated predominantly by binary task success, which cannot tell whether the commanded gesture is the one the object's kinematics admit. We introduce Constraint-Referenced…
Failure diagnosers for robot manipulation are increasingly vision--language models (VLMs), trained and evaluated on single-arm failures produced by perturbing a successful demonstration. Bimanual…
As egocentric video becomes increasingly available for embodied learning, an important research question is how to turn this low-cost, scalable source of data into robot manipulation capabilities.…
An input skip can reduce reconstruction error while leaving a model's distribution of new samples unchanged. For a Gaussian variational autoencoder (VAE) with constant input skip $0\leqα<1$, a model…
Communication between agents has mostly been studied on tasks with a shared objective and fast, clear feedback. Trading has neither: each agent manages its own account, with decisions being scored by…
Density estimation with generative models is a common task in the physical sciences, for example in background estimation in particle physics. Existing machine learning techniques, however, lack…
We describe the agent we submitted to the GLEE Competition, which plays bargaining, negotiation, and persuasion games against a shared pool of human and AI opponents. The agent is built around three…
We study the computational limits of clustering $n$ observations drawn from a mixture of $K$ isotropic distributions in $\mathbb R^d$, in the regime where the number $K$ of groups is much larger than…
The vision-language-action (VLA) and world-action model (WAM) communities debate whether control policies should inherit pretrained knowledge from vision-language models or from visual generators.…
World action models (WAMs) predict the visual consequences of the actions they generate, which makes test-time selection a natural way to improve a fixed policy: imagine the futures of candidate…
Coronary guidewire navigation during percutaneous coronary intervention requires continuous interpretation of vessel anatomy, guidewire position, and target stenosis under two-dimensional X-ray…
Multimodal perception forms the foundation of multimodal intelligence. In particular, spatial perception and multimodal long-context understanding are two pivotal tasks that underpin embodied AI and…
Audio systems aim to maximise the listener's perceived quality, traditionally evaluated through mean opinion scoring (MOS), a subjective process that is slow, costly, and collected only after…
Mutual information (MI) is fundamental to representation-learning analysis in deep networks, but in high dimensions MI estimators depend on hyperparameters whose bias often dominates the signal. We…
Self-driving laboratories (SDLs) are laboratory systems that couple experimental planning, automated execution, and measurement feedback in a closed loop. Integrating flexible robot control with the…
Token systems support repeated service exchange without monetary transfers, but their viability depends on the stability of token balances. We study token systems with compatibility constraints among…
This paper presents an approach to achieve side-by-side autonomous motion with a pair of personal mobility vehicles (PMVs). Given a global path, two PMVs plan cooperatively so as to hold a social…
Flow-based policies for language-conditioned multi-task manipulation commonly share a single $\textit{Gaussian}$ source prior and a common linear transport path across tasks. However, reliably…
Sparse event responses produce uneven keypoint errors whose effects on spacecraft pose depend on correspondence geometry and the reliability of successive observations. We present a reliability-aware…
Recent work has shown that, in zero-sum games, an optimizer can extract $Ω(\sqrt{T})$ strategic surplus---cumulative payoff above the minimax benchmark---against noiseless no-regret learners with a…