Stay updated with the latest research and technology news
arXiv:2602.11040v1 Announce Type: new Abstract: We investigate document page ordering on 5,461 shuffled WOO documents (Dutch freedom of information releases) using page embeddings. These documents...
arXiv:2602.11041v1 Announce Type: new Abstract: We present a new algorithm for fast matrix multiplication using tensor decompositions which have special features. Thanks to these features...
arXiv:2602.11044v1 Announce Type: new Abstract: Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and...
arXiv:2602.11047v1 Announce Type: new Abstract: We frame embedding inversion as conditional masked diffusion, recovering all tokens in parallel through iterative denoising rather than sequential autoregressive...
arXiv:2602.11049v1 Announce Type: new Abstract: Ensuring safe robot operation in cluttered and dynamic environments remains a fundamental challenge. While control barrier functions provide an effective...
arXiv:2602.11052v1 Announce Type: new Abstract: Graphs are foundational across domains but remain hard to use without deep expertise. LLMs promise accessible natural language (NL) graph...
arXiv:2602.11055v1 Announce Type: new Abstract: This work investigates generative facial expression interfaces for intelligent agents from a meta-design perspective. We propose the Generative Personalized Facial...
arXiv:2602.11057v1 Announce Type: new Abstract: The multi-commodity flow (MCF) problem is a fundamental topic in network flow and combinatorial optimization, with broad applications in transportation,...
arXiv:2602.11058v1 Announce Type: new Abstract: We focus on robust, survivable communication networks, where network links and nodes are affected by an uncertainty set. In this...
arXiv:2602.11062v1 Announce Type: new Abstract: Graph neural networks (GNNs) have revolutionized recommender systems by effectively modeling complex user-item interactions, yet data sparsity and the item...
arXiv:2602.11063v1 Announce Type: new Abstract: To ensure frequency security in power systems, both the rate of change of frequency (RoCoF) and the frequency nadir (FN)...
arXiv:2602.11064v1 Announce Type: new Abstract: Synthetic data offers a compelling path to scalable pretraining when real-world data is scarce, but models pretrained on synthetic data...
arXiv:2602.11065v1 Announce Type: new Abstract: Human conversation is organized by an implicit chain of thoughts that manifests as timed speech acts. Capturing this perceptual pathway...
arXiv:2602.11066v1 Announce Type: new Abstract: We propose PuriLight, a lightweight and efficient framework for self-supervised monocular depth estimation, to address the dual challenges of computational...
arXiv:2602.11072v1 Announce Type: new Abstract: Simultaneous speech translation requires translating source speech into a target language in real-time while handling non-monotonic word dependencies. Traditional approaches...
arXiv:2602.11073v1 Announce Type: new Abstract: Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to...
arXiv:2602.11074v1 Announce Type: new Abstract: AI technologies that sense student attention and emotions to enable more personalised teaching interventions are increasingly promoted, but raise pressing...
arXiv:2602.11075v1 Announce Type: new Abstract: Despite the sustained scaling on model capacity and data acquisition, Vision-Language-Action (VLA) models remain brittle in contact-rich and dynamic manipulation...
arXiv:2602.11076v1 Announce Type: new Abstract: Sixth-generation (6G) radio access networks (RANs) must enforce strict service-level agreements (SLAs) for heterogeneous slices, yet sudden latency spikes remain...
arXiv:2602.11077v1 Announce Type: new Abstract: Credit-based congestion pricing (CBCP) and discount-based congestion pricing (DBCP), which respectively allot travel credits and toll discounts to subsidize low-income...
arXiv:2602.11079v1 Announce Type: new Abstract: We propose activation-based data attribution, a method that traces behavioral changes in post-trained language models to responsible training datapoints. By...
arXiv:2602.11081v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong general reasoning and language understanding, yet their performance degrades in domains governed by strict...
arXiv:2602.11082v1 Announce Type: new Abstract: Characterization of fragmented rock piles is a fundamental task in the mining and quarrying industries, where rock is fragmented by...
arXiv:2602.11083v1 Announce Type: new Abstract: Remote change detection in LLMs is a difficult problem. Existing methods are either too expensive for deployment at scale, or...