Trending

Trajectory similarity learning is fundamental to efficient trajectory retrieval under complex distance measures. Existing learning-based methods typically rely on embeddings trained to approximate trajectory distances or rankings, but they…

Modern processors gain performance from interacting policies: prefetchers, predictors, replacement rules, and schedulers. These policies are often evaluated one at a time, yet a policy that wins in one stack may lose in another. To study…

Several inequivalent notions of tangent space exist for diffeological spaces, which has hindered the development of Riemannian geometry in this setting. On Blohmann's elastic diffeological spaces, the tangent functor carries a genuine…

Aihara developed an algorithm for Brauer tree algebras, which we call a mutation reduction, for getting from a Brauer tree algebra to the simpler Brauer star algebra using a sequence of mutations centered on edges. Schaps and Zvi, using the…

Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential…

We introduce Opt.Gear, a foundation model designed for efficient on-device deployment, real-tim inference, and strong task capability. It includes a dense model (1M, 270M, and 1B) with a context length of 64K. We designed a new hybrid…

Language models small enough to run on a handset, quantized to a few bits, are increasingly capable of acting for their user, making on-device task automation newly plausible. One such task is answering the phone. A phone secretary takes an…

Training error is what we can observe on a training set; test error is the quantity we actually care about. We study linear regression with squared-error in a deterministic $(d+1)$-dimensional single-spike model. Each stylized training…

In this paper, we introduce the double super Yangian $\mathrm{DY}_{h}(\mathfrak{gl}_{m|n}^{\mathfrak{s}})$ and $\mathrm{DY}_{h}(\mathfrak{sl}_{m|n}^{\mathfrak{s}})$ associated with any fixed $0^{m}1^{n}$--sequence $\mathfrak{s}$. First, we…

A 13.56 MHz, capacitively coupled plasma is investigated experimentally to determine the power absorption mechanism across a wide pressure range ({\approx} 5 - 600 mTorr) at {\approx} 10 W. Axial profiles of plasma parameters are measured…

Musculoskeletal robots require an internal body schema that remains consistent under a wide range of physical state changes, including abnormalities such as muscle rupture and actuator jamming. Conventional approaches based on autoencoders…

Deploying Vision-Language-Action (VLA) robots as mobile edge nodes within wireless sensor networks (WSNs) requires robust protection against physical adversarial threats. We present VLAGuard, a framework to assess and mitigate a critical…

Robot Task and Motion Planning (TAMP) algorithms enable autonomous operation by incorporating the specific functions and constraints of end-effector tools, such as grippers or soldering irons, directly into the planning process. In this…

In vehicular ad-hoc networks (VANETs), maintaining the freshness of status information among vehicles is critical for enabling timely and reliable safety-related decisions. In this paper, we consider the problem of scheduling cooperative…

This study investigates a new approach for scheduling freight rail engineers based on call windows under the Hours of Service (HOS) regulations. Unlike planned trip assignments, call windows specify a time interval during which an engineer…

We study the problem of optimizing physical layouts for automated warehouses, where hundreds to thousands of robots are coordinated to transport packages. Previous works have shown that optimizing the warehouse layout (e.g., the physical…

We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and the provable per-input…

The search for candidate Kitaev materials has largely focused on 4$d$ and 5$d$ transition-metal compounds with various lattice geometries. In contrast, investigations of rare-earth 4$f$ systems have thus far been restricted mainly to…

In an age of rapid model turnover, how do we make hallucination evaluation more perennial? We explore whether human-written hallucination samples could take the place of model-generated hallucinations, in order to make benchmarking…

Collaborative inference deploys Large Vision-Language Models (LVLMs) by partitioning computation between edge devices and the cloud. While withholding raw inputs supposedly ensures privacy, transmitting intermediate hidden states exposes a…