Knowledge catalogue
arXiv:2602.02611v2 Announce Type: replace Abstract: A prevailing paradigm in modern representation learning is the map-first approach, in which a representation map is learned from reconstruction, emb
arXiv:2609.25777v1 Announce Type: new Abstract: Accurate multi-step traffic forecasting remains challenging because observed traffic signals contain heterogeneous temporal dynamics with different char
arXiv:2609.23954v1 Announce Type: cross Abstract: Programmers write formal specifications, and LLMs implement them, proving that each implementation matches its spec. Taken to its extreme, this makes
arXiv:2601.06362v3 Announce Type: replace Abstract: Personalized large language models are often expected to follow explicit style instructions, yet we find that such instructions can undermine the us
arXiv:2609.26512v1 Announce Type: new Abstract: Convolutional neural networks (CNNs) and vision transformers are both used to model the human visual system, but whether the two architectures diverge a
arXiv:2607.10912v2 Announce Type: replace Abstract: 3D Gaussian Splatting represents scenes as finite mixtures of anisotropic Gaussians whose number of components K is set by heuristic density control
arXiv:2609.25746v1 Announce Type: new Abstract: ICP-based 3D Gaussian Splatting (3DGS) SLAM tracks in real time by registering incoming frames against map Gaussians, using each primitive's covariance
arXiv:2609.23945v1 Announce Type: new Abstract: In-band full-duplex (IBFD) multiple-input multiple-output (MIMO) systems enable simultaneous transmission and reception on the same frequency band, impr
arXiv:2609.25417v1 Announce Type: new Abstract: Biological torque control directly maps an estimated human joint moment to exoskeleton assistance, providing a task-agnostic strategy for supporting div
arXiv:2609.26039v1 Announce Type: cross Abstract: Point cloud generation has emerged as a crucial task for accurately capturing and reproducing the complexity of the physical world. However, existing
arXiv:2609.25155v1 Announce Type: cross Abstract: We empirically audit privacy leakage by testing whether outputs from edge-neighbouring inputs remain distinguishable, using statistically valid lower
arXiv:2609.25044v1 Announce Type: cross Abstract: This paper presents a quantum semantic communication (QSemCom) framework combining quantum machine learning (QML) and semantic communication (SemCom).
arXiv:2609.26733v1 Announce Type: new Abstract: The rapidly advancing capabilities of vision-language models (VLMs) present a systemic challenge to academic integrity. VLMs now allow students to bypas
arXiv:2609.23293v1 Announce Type: new Abstract: In the A* search algorithm, the tie-breaking strategies for nodes with the same f-value determines which states A* expands on the final f-layer. For nin
arXiv:2609.25962v1 Announce Type: new Abstract: Neural network verification has become a key tool for providing formal guarantees on the behaviour of neural networks. However, many verification proble
arXiv:2609.26077v1 Announce Type: new Abstract: A Strassen-type algorithm has many realizations with the same exact product and multiplication count yet different fp8 error because basis changes resha
arXiv:2502.16396v2 Announce Type: replace Abstract: Federated learning systems are increasingly threatened by data poisoning attacks, where malicious clients compromise global models by contributing t
arXiv:2609.25750v1 Announce Type: new Abstract: Manipulation requires both broad scene awareness and detailed local feedback, yet conventional camera rigs provide them through separate front and wrist
arXiv:2609.26605v1 Announce Type: cross Abstract: Foundation model embeddings of screening mammograms may encode pre-diagnostic tissue change without task-specific adaptation. We tested whether embedd
arXiv:2609.25085v1 Announce Type: cross Abstract: Data assimilation aims to infer the state of complex dynamical systems based on observational data. However, accurate inference of the multimodal post
arXiv:2609.24084v1 Announce Type: cross Abstract: Open-weight large language models (LLMs) can be copied, modified, and redeployed behind black-box APIs, making post-release ownership verification dif
arXiv:2609.25408v1 Announce Type: cross Abstract: Online A/B experiments are the decision standard for user engagement, but traffic and readout time limit how many conversational-AI changes can be tes
arXiv:2609.26484v1 Announce Type: new Abstract: Training-free visual-token pruning often uses token importance, redundancy, or related selection criteria as proxies for safe removal. We show that thes
arXiv:2609.22619v1 Announce Type: new Abstract: Tracking recovery of walking function requires detecting meaningful gait change across rehabilitation sessions, yet objective 3D measurement remains con
arXiv:2609.26508v1 Announce Type: new Abstract: Streaming principal component analysis (PCA) seeks to recover a leading spectral subspace in a single pass over a data stream. We give a new analysis of
arXiv:2609.25839v1 Announce Type: new Abstract: Flow-matching schedules affect both sampling dynamics and the variance of the regression target. For centered commuting Gaussians, we show that a direct
arXiv:2609.25605v1 Announce Type: cross Abstract: In this paper, we study the estimation of a marginal regression function from independent units with repeated binary, count, or continuous responses u
arXiv:2609.25247v1 Announce Type: new Abstract: Interaction understanding in 3D scenes requires a joint description of movable parts, their motion, and the regions through which they can be operated.
arXiv:2509.13813v3 Announce Type: replace Abstract: Large language models are known to hallucinate, generating linguistically plausible but incorrect answers to questions. Uncertainty quantification h
arXiv:2609.26342v1 Announce Type: new Abstract: Residual Vector Quantization turns continuous representations into discrete, multi-level token sequences. Yet most methods operate in Euclidean space, d
arXiv:2609.25963v1 Announce Type: new Abstract: Transformer architectures exhibit cross-layer redundancies, yet post-training compression pipelines typically optimize layers in isolation or rely on he
arXiv:2609.22475v1 Announce Type: new Abstract: Process discovery rarely yields a single coherent process structure. For analysis, a common step is to cluster process variants based on structural simi
arXiv:2609.25776v1 Announce Type: cross Abstract: Nonlinear activations can create equivariant interactions between irreducible representations that linear maps cannot. We use the Gaussian degree deco
arXiv:2609.25966v1 Announce Type: new Abstract: This paper introduces GRIP, a pose-conditioned refinement framework for pixel-to-point matching and 2D to 3D registration. Given an initial coarse pose
arXiv:2609.25584v1 Announce Type: new Abstract: Hi-OPD addresses a failure mode left uncontrolled by flat open-prompt training: descendant retrieval need not persist under ancestor queries when multi-
arXiv:2609.26256v1 Announce Type: new Abstract: High-fidelity tactile feedback is essential for robotic teleoperation, enabling precise manipulation and critical decision-making. While biomimetic fing
arXiv:2603.14023v3 Announce Type: replace Abstract: This work introduces and demonstrates the first system capable of imaging fast-moving extended non-rigid objects through strong atmospheric turbulen
arXiv:2609.25658v1 Announce Type: new Abstract: Deterministic dynamics modeling of tendon-driven continuum robots remains challenging owing to uncertainties in material behavior, tendon transmission,
arXiv:2609.26032v1 Announce Type: cross Abstract: We construct the first type of non-Euclidean non-autoregressive neural quantum state (NQS) in the form of the hyperbolic Restricted Boltzmann Machine
arXiv:2609.25837v1 Announce Type: new Abstract: This work presents a video summarization algorithm based on multi-object tracking and person reidentification. We integrate facial embeddings, 3D body-s
arXiv:2609.25130v1 Announce Type: new Abstract: Memory systems for coding agents must decide, when a repository changes, which of their stored claims have become false. Content anchoring invalidates a
arXiv:2609.25685v1 Announce Type: new Abstract: Contour initialization and numerical stopping can jointly affect the evaluation of active-contour segmentation. We examine their interaction using the o
arXiv:2609.25697v1 Announce Type: new Abstract: Purpose: To develop and evaluate an interpretable artificial intelligence (AI) framework for glaucoma screening from low-cost portable, handheld retinal
arXiv:2609.25980v1 Announce Type: new Abstract: Probabilistic time series foundation models (TSFMs) provide coordinate-wise predictive distributions, but these marginals do not determine a joint distr
arXiv:2609.25862v1 Announce Type: new Abstract: We present the first experiments on isolated sign language recognition (ISLR) for Icelandic Sign Language (ITM). We use ITM SignWiki, a dataset derived
arXiv:2609.26634v1 Announce Type: new Abstract: We introduce Knowledge Pull Requests (KPRs), a framework for continual document authoring that makes each change interpretable. Documents require ongoin
arXiv:2609.25643v1 Announce Type: cross Abstract: Large language models (LLMs) excel at reasoning when scaled to hundreds of billions of parameters, but small- and mid-scale models remain brittle reas
arXiv:2609.26430v1 Announce Type: new Abstract: Dataset distillation (DD) compresses a large training set into a compact synthetic set while preserving downstream training utility. Although DD has bee
arXiv:2609.23378v1 Announce Type: new Abstract: We introduce leaky-integrator reconstruction, a training-free method that cures the error accumulation of recursive differenced forecasting. Our first c
arXiv:2609.25411v1 Announce Type: cross Abstract: Classifier-free Guidance (CFG) is widely adopted in text-to-speech (TTS) systems to enhance generation quality and conditioning fidelity by interpolat
arXiv:2609.25163v1 Announce Type: new Abstract: The paper proposes a novel data-driven framework for designing and training a feedback linearizing controller by explicitly incorporating relative degre
arXiv:2609.25803v2 Announce Type: new Abstract: High-rate dense perception in dynamic environments is limited by the low update rate of RGB cameras, as rapid scene changes can occur between frames. Ev
arXiv:2601.08358v2 Announce Type: replace Abstract: Even though the ocean covers the majority of the planet's surface, it remains the least explored ecosystem. As light and radio waves do not propagat
arXiv:2609.23589v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio repre
arXiv:2609.26205v1 Announce Type: new Abstract: Aligning with the human visual system~(HVS) in perceiving and evaluating the quality of visual signals is a central objective of machine-vision-based vi
LLM next-token prediction is already a probabilistic classifier, so an open LLM can serve a Jev-like interface: discrete options in, fast probabilities out. Our own @ekzhang1 made it better at the job
arXiv:2609.26662v1 Announce Type: new Abstract: Purposes: To characterize longitudinal retinal vascular changes in myopic children treated with orthokeratology (OK) or multifocal defocus lenses (Defoc
arXiv:2609.26443v1 Announce Type: new Abstract: Recent advances in Artificial Intelligence (AI)-powered Computer-Aided Diagnosis (CAD) systems have substantially improved breast cancer screening, diag
arXiv:2609.26238v1 Announce Type: new Abstract: The manipulation of Deformable Linear Objects (DLOs) such as cables poses a significant challenge for automation due to their infinite degrees of freedo
arXiv:2609.26081v1 Announce Type: new Abstract: Fixed-budget robustness evaluation can select the wrong frozen vision encoder. An encoder that survives a shallow attack may lose most of that robustnes