arXiv:2607.00250v1 Announce Type: new Abstract: Maltese has decent text corpora and pretrained language models, but, like many languages outside the handful with large OCR benchmarks, only…
arXiv:2607.00124v1 Announce Type: new Abstract: Object-centric models inspired by DETR have become the dominant paradigm for open-vocabulary video instance segmentation (OV-VIS). While recent efforts have reduced…
arXiv:2607.00183v1 Announce Type: new Abstract: Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended…
arXiv:2607.01025v1 Announce Type: cross Abstract: Radio-frequency (RF) sensing is a central modality for counter-unmanned-aerial-system (counter-UAS) defence because it exploits the control, telemetry, and video links between…
arXiv:2606.20299v2 Announce Type: replace Abstract: Deep learning has managed to evade numerous intuitions from classical statistics to achieve unprecedented performance on a number of real-world tasks.…
arXiv:2605.30253v3 Announce Type: replace Abstract: We study the non-asymptotic contraction in Wasserstein distance of the sequential, parallel, and random-scan coordinate ascent variational inference algorithms. This is…
arXiv:2607.00035v1 Announce Type: new Abstract: LLMs and agents can generate web scrapers from natural-language requirements, but direct generation remains unreliable because of dependency errors, broken selectors,…
arXiv:2606.25518v2 Announce Type: replace Abstract: When people share experiences online, they often express thoughts in two ways: a star rating and a written review. In sentiment…
arXiv:2607.00374v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification. While supervised CIR relies on…
arXiv:2607.00125v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains…
arXiv:2607.00687v1 Announce Type: cross Abstract: Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences…
arXiv:2607.00190v1 Announce Type: new Abstract: Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games. As a byproduct, researchers have…
arXiv:2504.15388v3 Announce Type: replace-cross Abstract: In the context of multivariate nonparametric regression with missing covariates, we propose Pattern Embedded Neural Networks (PENNs), which can be applied…
arXiv:2607.00275v1 Announce Type: cross Abstract: Federated Learning (FL) is a distributed machine learning (ML) paradigm with collaboration among multiple clients without sharing data. FL is challenging…
arXiv:2607.00032v1 Announce Type: new Abstract: Many information systems are built around documents: self-contained units optimised for print production and linear reading. While effective for large-scale dissemination,…
arXiv:2607.01181v1 Announce Type: cross Abstract: RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such…
arXiv:2607.00274v1 Announce Type: new Abstract: Effective writing feedback is among the strongest drivers of student learning, yet producing it at scale is labor-intensive. LLMs offer a…
arXiv:2607.00115v1 Announce Type: new Abstract: This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories.…
arXiv:2509.03070v5 Announce Type: replace-cross Abstract: This letter presents a CWT-enhanced vibration sensing framework for bearing fault monitoring through localized time-frequency region detection on continuous wavelet transform…
arXiv:2508.04064v2 Announce Type: replace Abstract: Horizontal federated learning (HFL) backdoor audits often summarize model behavior through clean accuracy (CA), mean attack success rate (ASR), or a…
arXiv:2607.00669v1 Announce Type: cross Abstract: Autoencoders (AEs) have emerged as powerful tools for non-linear dimensionality reduction, often surpassing traditional linear methods such as Proper Orthogonal Decomposition…
arXiv:2504.09951v2 Announce Type: replace-cross Abstract: We revisit a classical assumption for analyzing stochastic gradient algorithms where the squared norm of the stochastic subgradient (or the variance…
arXiv:2603.21048v2 Announce Type: replace-cross Abstract: The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of…
arXiv:2510.24636v3 Announce Type: replace Abstract: Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both…