A rigor-matched, three-seed audit of two periodic-step, search-based methods that make this decision online at inference time and re-evaluate it every few generation steps: a confidence-gated early-exit baseline (ConfLayers) and genuine self-speculative decoding (SWIFT, Xia et al. 2024).
Comparing machine learning and deep learning models for classifying postural states in VR under visual perturbations suggests that multimodal sensing, temporal deep learning, and explainable AI can support reliable classification of balance-related instability in VR.
N. Anjum, M. Pavel, Robert Gonzalez et al.· 0 citations
This work establishes quantum signal processing (QSP) as a solvable quantum model of the representation-learning regime, and proves a sparse-data guarantee for the full nonlinear gradient flow without freezing or ensemble-averaging the kernel.
We establish quantitative convergence to the target and uniform-in-time propagation of chaos for Langevin-regularized Stein variational gradient descent. The Stein interaction need not be small relative to the confining Langevin drift and does not generally yield a contractive particle coupling. At the mean-field level, the Stein and Langevin components dissipate the same relative entropy in the kernel-induced Stein and $2$-Wasserstein geometries, producing the squared kernel Stein discrepancy and relative Fisher information. Under a log-Sobolev inequality for the target, this yields exponential last-iterate convergence. We also derive a finite-particle entropy identity relative to the product target, giving exponential-in-time convergence of the empirical measure up to polynomial sampling errors. For propagation of chaos, we develop two complementary finite-time approaches. A synchronous coupling, combined with exponential moment estimates for the nonlinear mean-field diffusion, yields explicit single-exponential bounds in Wasserstein distance and kernel Stein discrepancy (KSD). Moving-product entropy gives joint-law relative entropy control relative to the evolving mean-field product law and, through entropy superadditivity and concentration, fixed-marginal relative entropy and total variation bounds and empirical KSD estimates. Under an additional $T_2$ inequality for the initial law, it also yields Wasserstein bounds. Combining these finite-time estimates with target convergence at a logarithmic cutoff time gives polynomial uniform-in-time propagation of chaos rates in expectation for empirical KSD and $W_2^2$, and for fixed-marginal total variation and $W_2^2$. All bounds control the last iterate in physical time. We also compare the two finite-time mechanisms and identify regimes in which each gives the sharper polynomial exponent.
Sayan Banerjee, Dohyeon Kim· 1 citation· ⚡1
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work develops efficient algorithms based on the difference-of-convex function algorithm (DCA) and the alternating direction method of multipliers (ADMM) to enhance sparsity and identifiability of the learned factors in separable nonnegative matrix factorization.
ASTRA, an agentic system for ticket resolution in which a central orchestrator coordinates three specialist information-gathering agents and drives a judge-orchestrator refinement loop to produce evidence-backed troubleshooting reports, is proposed.
Shashidhar Reddy Javaji, Mohamed Trabelsi, Jin Cao et al.· 0 citations
Adversarial Calibration Attack (ACA), the first physical attack against camera-LiDAR online calibration, is presented and demonstrated that online calibration is a practical and safety-critical attack surface for AVs.
Liang-Kai Liu, Qingzhao Zhang, Kang G. Shin· 0 citations
This work proposes a unified autoregressive diffusion-based graph generative model that jointly learns structure and features, constructing complete 3DSGs bottom-up from observed vertical planes across arbitrary hierarchy depths, and proposes an adaptation of the Fused Gromov--Wasserstein distance for principled graph-level evaluation of generated 3DSGs against ground truth.
J. A. Millan-Romera, Samuel Cognolato, Holger Voos et al.· 0 citations
ORDDAR (Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery) is presented, a reasoning framework that models reasoning as cognitive state transitions, detects localized distortions, retrieves related reasoning from prior experiences, and repairs only the affected states.
Deblina Kar, Anant Nawalgaria, S. D. Das Mandal· 0 citations
Match controls on training recipe as well as capacity, and buy compression robustness with codec diversity before architecture, and buy compression robustness with codec diversity with codec diversity before architecture.
The effectiveness of the proposed source codecs are demonstrated by achieving state-of-the-art performance in distributed semantic segmentation at below 0.2 bits per pixel, measured using the mean intersection-over-union metric on ADE20K (Cityscapes).
Danish Nazir, Timo Bartels, Thorsten Bagdonat et al.· 0 citations
This work uses the abundant compute resources of the cloud to run a highly-accurate oracle model that will guide the retraining process of the on-vehicle model, leading to improved inference accuracy over time.
Yu-Heng Zhu, Dhruva Ungrupulithaya, Boluo Ge et al.· 2024 IEEE 100th Vehicular Te...· 1 citation
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
Adaptive AI agents can help make BIM data more machine-readable by navigating IFC models, interpreting inconsistent information, and mapping it to defined standards. In this blog, Alok Rawat shares findings from a real-world pilot in construction workflows. The post Adaptive AI Agents in Construction Workflows appeared first on GPT-Lab.
