arXiv:2602.11320v1 Announce Type: new Abstract: Neural tangent kernel (NTK) methods are computationally limited by the need to evaluate large Jacobians across many data points. Existing approaches reduce this cost primarily through projecting and sketching the Jacobian. We show that NTK computation can also be reduced by compressing the data dimension itself using NTK-tuned dataset distillation. We demonstrate that the neural tangent space spanned by the input data can be induced by dataset distillation, yielding a 20-100$times$ reduction in […]

Ver mais

As Australia implemented a social media age restriction law requiring platforms like TikTok, Instagram, and YouTube to take “reasonable steps” to block Australians under 16 from creating or keeping accounts, the world waits and watches to see how it’ll play out. The ban aims to protect youth from harms like cyberbullying and mental health risks, though children can still view public content and use messaging apps, with platforms facing hefty fines for non-compliance. Is age-gating social media the […]

Ver mais

arXiv:2603.03383v1 Announce Type: new Abstract: To mitigate the Memory Wall bottleneck encountered by Large Language Models (LLMs) during inference on textbf{NPU} hardware, and addressing the scarcity of native support for mainstream speculative decoding algorithms on domestic infrastructure, this study presents an end-to-end speculative inference acceleration scheme for OpenPangu-7B.

Ver mais

arXiv:2601.17038v1 Announce Type: new Abstract: The construction industry produces significant volumes of debris, making effective sorting and classification critical for sustainable waste management and resource recovery. This study presents a hybrid vision-based pipeline that integrates deep feature extraction with classical machine learning (ML) classifiers for automated construction and demolition (C&D) debris classification. A novel dataset comprising 1,800 balanced, high-quality images representing four material categories, Ceramic/Tile, Concrete, Trash/Waste, and Wood was collected from real construction sites in the UAE, […]

Ver mais

arXiv:2603.24733v1 Announce Type: new Abstract: Quantifying human movement (kinematics) and musculoskeletal forces (kinetics) at scale, such as estimating quadriceps force during a sit-to-stand movement, could transform prediction, treatment, and monitoring of mobility-related conditions. However, quantifying kinematics and kinetics traditionally requires costly, time-intensive analysis in specialized laboratories, limiting clinical translation. Scalable, accurate tools for biomechanical assessment are needed. We introduce OpenCap Monocular, an algorithm that estimates 3D skeletal kinematics and kinetics from a single smartphone video. The method refines […]

Ver mais

arXiv:2601.08073v1 Announce Type: new Abstract: For a (possibly partial) Boolean function $fcolon{0,1}^nto{0,1}$ as well as a query complexity measure $M$ which maps Boolean functions to real numbers, define the composition limit of $M$ on $f$ by $M^*(f)=lim_{ktoinfty} M(f^k)^{1/k}$. We study the composition limits of general measures in query complexity. We show this limit converges under reasonable assumptions about the measure. We then give a surprising result regarding the composition limit of randomized query complexity: we show $R_0^*(f)=max{R^*(f),C^*(f)}$. Among […]

Ver mais

arXiv:2603.07122v1 Announce Type: cross Abstract: In the training of neural networks, adaptive moment estimation (Adam) typically converges fast but exhibits suboptimal generalization performance. A widely accepted explanation for its defect in generalization is that it often tends to converge to sharp minima. To enhance its ability to find flat minima, we propose its new variant named inverse Adam (InvAdam). The key improvement of InvAdam lies in its parameter update mechanism, which is opposite to that of Adam. Specifically, […]

Ver mais

arXiv:2603.15771v1 Announce Type: new Abstract: Autonomous driving requires safe planning, but most learning-based planners lack explicit self-correction ability: once an unsafe action is proposed, there is no mechanism to correct it. Thus, we propose CorrectionPlanner, an autoregressive planner with self-correction that models planning as motion-token generation within a propose, evaluate, and correct loop. At each planning step, the policy proposes an action, namely a motion token, and a learned collision critic predicts whether it will induce a collision […]

Ver mais

Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on everything else. This setting becomes especially difficult when deletion requests arrive sequentially, because the model must repeatedly adapt without erasing previously retained knowledge. Low-Rank Adaptation (LoRA) offers an efficient way to implement such updates, but naively combining many sequential LoRA modules leads to parameter collision, causing textit{strong interference} between tasks. We propose a static […]

Ver mais

arXiv:2604.08558v1 Announce Type: new Abstract: Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed Attention and Knowledge Distillation, a framework that adapts pretrained AR-TTS models to operate with constant computational and memory complexity. WAND separates the attention mechanism into two: persistent global attention over conditioning tokens and local sliding-window attention over generated tokens. To stabilize fine-tuning, […]

Ver mais