Quadruped locomotion provides a natural setting for understanding when model-free learning can outperform model-based control design, by exploiting data patterns to bypass the difficulty of optimizing over discrete contacts and the combinatorial explosion of mode changes. We give a principled analysis of why imitation learning with quadrupeds can be inherently effective in a small data regime, based on the structure of its limit cycles, Poincaré return maps, and local numerical properties of neural networks. The understanding motivates a […]

Ver mais

arXiv:2602.04986v1 Announce Type: new Abstract: We endorse and expand upon Susan Schneider’s critique of the linear model of AI progress and introduce two novel concepts: “familiar intelligence” and “strange intelligence”. AI intelligence is likely to be strange intelligence, defying familiar patterns of ability and inability, combining superhuman capacities in some domains with subhuman performance in other domains, and even within domains sometimes combining superhuman insight with surprising errors that few humans would make. We develop and defend a […]

Ver mais

Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set of pre-defined tasks or in a lifelong manner on several tasks arriving sequentially, assuming sufficient training on each task. Both settings overlook a common real-world property: problem patterns may drift continually over time, yielding massive tasks sequentially arising while offering only limited training resources per task. In this paper, we study a novel lifelong learning paradigm for neural […]

Ver mais

arXiv:2602.09273v1 Announce Type: new Abstract: We study approximation algorithms for Maximum Constraint Satisfaction Problems (Max-CSPs) under differential privacy (DP) where the constraints are considered sensitive data. Information-theoretically, we aim to classify the best approximation ratios possible for a given privacy budget $varepsilon$. In the high-privacy regime ($varepsilon ll 1$), we show that any $varepsilon$-DP algorithm cannot beat a random assignment by more than $O(varepsilon)$ in the approximation ratio. We devise a polynomial-time algorithm which matches this barrier under […]

Ver mais

arXiv:2511.16976v2 Announce Type: replace-cross Abstract: Deep equilibrium models (DEQs) have recently emerged as a powerful paradigm for training infinitely deep weight-tied neural networks that achieve state of the art performance across many modern machine learning tasks. Despite their practical success, theoretically understanding the gradient descent dynamics for training DEQs remains an area of active research. In this work, we rigorously study the gradient descent dynamics for DEQs in the simple setting of linear models and single-index models, filling […]

Ver mais

arXiv:2601.17082v1 Announce Type: new Abstract: Despite substantial efforts toward improving the moral alignment of Vision-Language Models (VLMs), it remains unclear whether their ethical judgments are stable in realistic settings. This work studies moral robustness in VLMs, defined as the ability to preserve moral judgments under textual and visual perturbations that do not alter the underlying moral context. We systematically probe VLMs with a diverse set of model-agnostic multimodal perturbations and find that their moral stances are highly fragile, […]

Ver mais

Below is my annual summary of some of the best books I read in the past year. There are a few themes that weave their way throughout: the brain, running, history, and biographies. Here I also try to rank them loosely – the first ones are my top choices. Enjoy!  The Strange Order of Things by Antonio Damasio I heard Damasio talk a few times and was unimpressed, feeling that his arrogance to substance ratio was too high […]

Ver mais

arXiv:2603.14387v1 Announce Type: cross Abstract: Label noise – incorrect labels assigned to observations – can substantially degrade the performance of supervised classifiers. This paper proposes a label noise cleaning method based on Bernoulli random sampling. We show that the mean label noise levels of subsets generated by Bernoulli random sampling containing a given observation are identically distributed for all clean observations, and identically distributed, with a different distribution, for all noisy observations. Although the mean label noise levels […]

Ver mais