Knowledge catalogue
arXiv:2609.25500v1 Announce Type: new Abstract: Training data quantity and quality greatly affect object detection model performance, regardless of model architecture. When using object detection mode
arXiv:2609.25444v1 Announce Type: new Abstract: This work studies prediction parameterization for stochastic generative dynamics in diffusion models. Existing velocity-based generative models provide
arXiv:2609.24061v1 Announce Type: cross Abstract: In this paper, we propose MECT, a speaker verification model that integrates the Mixture-of-Experts (MoE) mechanism into a CNN-Transformer backbone wi
arXiv:2609.25853v1 Announce Type: new Abstract: Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be
arXiv:2609.26103v1 Announce Type: new Abstract: Medical Image Super-Resolution (MISR) aims to enhance spatial resolution without requiring hardware modifications. Although deep learning has yielded pr
arXiv:2609.26025v1 Announce Type: cross Abstract: Human feedback can vary in cost and informativeness. Strong feedback can reveal severe errors but is costly, so cheaper quality ratings can help decid
arXiv:2609.25454v1 Announce Type: cross Abstract: Geographic measurements are often sparse, leaving large areas without labels for the quantities we want to map. Geographic implicit neural representat
arXiv:2609.25166v1 Announce Type: new Abstract: Diffusion data-point unlearning is typically evaluated immediately after each deletion, even though subsequent requests may repeatedly update the same m
arXiv:2609.26272v1 Announce Type: new Abstract: Neural samplers are trained against an unnormalised target ildepi=e^{-E} with no samples from pi, which leaves the practitioner with no way to tell whet
arXiv:2609.25334v1 Announce Type: new Abstract: Intrinsically disordered proteins (IDPs) differ from folded proteins in that they are dynamic, lack a stable three-dimensional conformation, and have lo
arXiv:2609.26267v1 Announce Type: new Abstract: Free-floating space manipulator systems face operational challenges due to dynamic coupling. While traditional reactionless manipulation eliminates base
arXiv:2609.25179v1 Announce Type: new Abstract: Predicting the remaining useful life (RUL) is essential for effective predictive maintenance. Spatio-Temporal Graph Neural Networks (ST-GNNs), which can
arXiv:2609.25972v1 Announce Type: new Abstract: NAWE (Neural-Assisted Watermark Extraction) combines an explicit signal-processing watermarking construction with a pretrained neural host predictor. A
arXiv:2512.22760v2 Announce Type: replace Abstract: Vision Transformers (ViTs) have achieved remarkable success in visual recognition tasks, but redundant token representations limit their computation
arXiv:2609.26105v1 Announce Type: cross Abstract: Prediction of pathological complete response before neoadjuvant chemotherapy may facilitate more tailored therapeutic planning for breast cancer patie
arXiv:2609.25874v1 Announce Type: new Abstract: Deep neural networks approximate functions by composing affine maps with nonlinear activations, but how composition itself creates approximation power i
arXiv:2609.26537v1 Announce Type: new Abstract: These notes develop the mathematical foundations and construction of a Fourier-Bessel wavelet family inspired by the disk harmonics of Shaqfa et al.[9].
arXiv:2609.24757v1 Announce Type: cross Abstract: This paper presents the design, optimization, implementation, and on-board validation of a neural processing unit (NPU) accelerator for real-time vehi
arXiv:2508.13339v2 Announce Type: replace-cross Abstract: This work highlights the duality between state estimation and model predictive control. A model predictive controller, observed control, is pr
arXiv:2609.25597v1 Announce Type: new Abstract: The annotation used to select a segmentation threshold is part of the evaluation protocol, yet its effect is easily conflated with model quality. We exa
arXiv:2609.26624v1 Announce Type: cross Abstract: Sparse Gaussian processes achieve O(N) inference by replacing the kernel with an appropriate expansion in a fixed basis {phi_j} on the input space. Gi
arXiv:2609.23774v1 Announce Type: new Abstract: Probabilistic inference is generally only tractable in low-treewidth graphical models, limiting its effective applicability in high-treewidth settings.
arXiv:2609.25705v1 Announce Type: cross Abstract: Federated learning (FL) is intrinsically heterogeneous: honest clients may have different data-generating models. On top of that, adversarial clients
arXiv:2609.26388v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have made them widely used for code-related tasks. Identifier names are statistically informative in n
arXiv:2609.26334v1 Announce Type: new Abstract: The dimensional collapse of representations in self-supervised contrastive learning is an ever-present issue. One notable technique to prevent such a co
arXiv:2609.26097v1 Announce Type: new Abstract: Remote-sensing (RS) multimodal large language models (MLLMs) are trained and evaluated only in English, while text-only instruction data covers over 100
arXiv:2609.26435v1 Announce Type: new Abstract: Drifting provides a direct route to one-step generative models, but applying it directly to stochastic transition modeling requires multiple samples of
arXiv:2609.26249v1 Announce Type: new Abstract: Diffusion language models (dLLMs), such as LLaDA and Dream, have become competitive with autoregressive (AR) LLMs in generation quality while supporting
arXiv:2609.25375v1 Announce Type: new Abstract: Global point-cloud registration remains challenging when limited overlap, repetitive geometry, and sensor noise produce correspondence sets dominated by
arXiv:2609.26199v1 Announce Type: new Abstract: A large graph is often available only in part: a crawl stopped by its budget, a panel, a partial dump. When the sampled fraction s is known by design th
arXiv:2609.25832v1 Announce Type: new Abstract: Part segmentation is a fundamental problem in computer graphics and 3D vision. Recent works have expanded 3D part segmentation beyond fixed taxonomies,
arXiv:2609.26629v1 Announce Type: new Abstract: Procedural character generation aims to populate games, simulations, and other virtual worlds with diverse characters. Large language models (LLMs) offe
arXiv:2609.25057v1 Announce Type: cross Abstract: Radar pulse de-interleaving is a foundational Electronic Support Measures (ESM) task that aims to separate chronologically interleaved pulse streams f
arXiv:2609.23023v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) require coordinated choices over network representation, sampling, loss construction, and optimization, while e
arXiv:2609.24881v2 Announce Type: new Abstract: In high-stakes decision-making applications of large language models (LLMs), practitioners require not only accurate LLMs but also uncertainty estimates
arXiv:2609.25538v1 Announce Type: new Abstract: While single-view 3D reconstruction has seen significant progress, extrapolating complex 3D structures from inherently ambiguous 2D observations remains
arXiv:2609.26474v1 Announce Type: cross Abstract: Scattered light is common in biomedical images, yet its removal remains challenging. The difficulty arises from three aspects: first, aligned scattere
arXiv:2609.25430v1 Announce Type: new Abstract: Neural surrogates can substantially accelerate computer-aided engineering (CAE) workflows, but their use in design requires uncertainty estimates that r
arXiv:2606.18473v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to remove specified knowledge while preserving the rest of the model's capabilities. Howeve
arXiv:2609.26683v1 Announce Type: cross Abstract: Accurately predicting fast solar wind conditions is challenging, as uncertainties are large and unquantified by traditional single-value prediction mo
arXiv:2609.26288v1 Announce Type: new Abstract: Comparative studies of predictive models often end by ranking candidate models, yet these rankings depend on evaluation protocols whose influence is rar
arXiv:2609.26425v2 Announce Type: new Abstract: KV cache memory has become a major deployment bottleneck for video generation and world models, which motivates low-bit quantization study for efficienc
arXiv:2609.26578v1 Announce Type: new Abstract: Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced CT remains clinically challenging because clear cell R
arXiv:2609.26492v1 Announce Type: new Abstract: Radiomics provides quantitative descriptions of tumour appearance that may complement disease-specific foundation models in small labelled cohorts. We i
arXiv:2607.14109v2 Announce Type: replace Abstract: Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central
arXiv:2609.26093v1 Announce Type: new Abstract: Vision-language models can answer spatial relation questions confidently even when the image supports an incompatible relation. We formulate relation-gr
arXiv:2609.26579v1 Announce Type: new Abstract: A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In par
arXiv:2509.20634v3 Announce Type: replace-cross Abstract: We provide a new framework for estimating peer effects when outcomes are multivariate behavioral measures derived from written text using an L
arXiv:2601.22355v2 Announce Type: replace Abstract: Understanding the distributional structure of high-dimensional datasets has become an important topic, yet direct visual characterization is difficu
arXiv:2609.25797v1 Announce Type: new Abstract: We reply to the comments by M. Sienicki and K. Sienicki (arXiv:2512.07881) and by K. Sienicki (arXiv:2601.06104) on our work on quantum-mechanical stati
arXiv:2604.00531v2 Announce Type: replace Abstract: Multi-task representation learning exploits the shared structure among related tasks by learning a common latent representation, thereby improving s
arXiv:2609.25492v1 Announce Type: new Abstract: Large vision-language models (VLMs) can be efficiently deployed under stringent memory and latency constraints through post training quantization (PTQ).
arXiv:2609.26648v1 Announce Type: cross Abstract: Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under chall
arXiv:2608.24268v2 Announce Type: replace Abstract: This paper proposes methods to extract over 50 types of events from a Dutch historical corpus spanning the 17th and 18th centuries. The methods we p
arXiv:2609.26270v1 Announce Type: cross Abstract: We introduce the category mathbf{SSS} of sample-smooth spaces over a mixed site. The test objects are the products Omega_n := R^n imes Omega of a Cart
arXiv:2609.25728v1 Announce Type: new Abstract: Self-supervised learning for combinatorial optimization has emerged as a promising paradigm for solving discrete optimization problems with neural netwo
arXiv:2609.26610v1 Announce Type: new Abstract: Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction. In this study, we are interested
arXiv:2606.19966v2 Announce Type: replace-cross Abstract: Whole-slide images (WSIs) are widely used for computational cancer prognosis. However, most existing methods primarily focus on in-domain perf
arXiv:2602.04577v3 Announce Type: replace Abstract: Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outpu
arXiv:2603.03806v2 Announce Type: replace Abstract: The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting considerable attention for its efficient han