Knowledge catalogue
arXiv:2610.11784v1 Announce Type: new Abstract: Tabular in-context learning (ICL) has emerged as a training-free and accurate paradigm for tabular prediction, but current approaches to compressing its
arXiv:2610.12008v1 Announce Type: new Abstract: Abstract argumentation frameworks (AFs) introduced by Dung provide a formal foundation for non-monotonic reasoning in artificial intelligence. While dec
arXiv:2610.12328v1 Announce Type: new Abstract: We consider stochastic nonsmooth nonconvex composite optimization, which includes several important problems such as constrained optimization and the re
arXiv:2610.11548v1 Announce Type: new Abstract: Synthetic tasks are increasingly used both as probes of language-model capability and as pretraining data. Both uses are often justified by loss reducti
arXiv:2610.10829v1 Announce Type: cross Abstract: Conformal prediction provides prediction sets with finite-sample guarantees, but the label verification required for calibration can be expensive. We
arXiv:2602.03538v2 Announce Type: replace Abstract: While Dynamic Gaussian Splatting enables high-fidelity 4D reconstruction, its deployment is severely hindered by a fundamental dilemma: unconstraine
arXiv:2610.11621v1 Announce Type: new Abstract: Consensus can make pseudo-label learning more reliable, but only when its predictors contribute genuinely different evidence. Multiple models that repea
arXiv:2610.11908v1 Announce Type: cross Abstract: Existing model marketplaces typically trade and select individual models as indivisible units, limiting their ability to exploit complementarities amo
arXiv:2610.11108v1 Announce Type: new Abstract: Multi-domain physics-informed neural networks (PINNs) flexibly model medium-specific representations to solve fluid--solid conjugate heat transfer (CHT)
arXiv:2610.12115v1 Announce Type: new Abstract: In many machine learning applications, it is necessary to guard against worst-case scenarios and predictions that could result in substantial losses. In
arXiv:2610.11376v1 Announce Type: cross Abstract: Latent LiDAR pipelines suffer from flying pixels: convolutional VAEs blur sharp radial depth discontinuities, yielding edge depths that back-project t
arXiv:2610.11222v1 Announce Type: cross Abstract: Preclinical models poorly predict human drug efficacy, particularly in neurological disorders. Neural activity offers a uniquely rich source of transl
arXiv:2610.11853v1 Announce Type: new Abstract: Modern neural networks are heavily over-parameterized. This redundancy incurs substantial compute and memory overhead during training and inference. Exi
arXiv:2610.09892v2 Announce Type: replace-cross Abstract: Feedback from automated testing, human red teaming, and incident response can strengthen an AI system's defenses when discovered failures lead
arXiv:2610.11315v1 Announce Type: cross Abstract: In diffusion transformers, low-rank branches can mitigate 4-bit weight--activation (W4A4) post-training quantization (PTQ) loss by decomposing each we
arXiv:2610.12437v1 Announce Type: cross Abstract: Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view
arXiv:2610.11845v1 Announce Type: new Abstract: Spin in clinical trials includes reporting practices that distort the presentation of results. This is particularly critical in medicine, where spin is
arXiv:2610.12214v1 Announce Type: cross Abstract: Recent full-duplex spoken dialog models enable simultaneous listening and speaking, but fine-grained models still advance their backbone autoregressiv
arXiv:2610.11067v1 Announce Type: new Abstract: Prompt learning is a popular method for adapting foundation models, but learned prompts are typically task-specific and fail to generalize to new classe
arXiv:2610.12052v1 Announce Type: cross Abstract: Despite their empirical success, why diffusion models overcome the bottlenecks of classical score-based samplers remains unclear. In this work, we lev
arXiv:2610.11751v1 Announce Type: new Abstract: Co-denoising pretrained representations such as DINO can substantially improve the training speed and quality of flow matching models, but it introduces
arXiv:2502.20612v2 Announce Type: cross Abstract: In self-supervised contrastive learning, negative pairs are typically constructed using an anchor image and a sample drawn from the entire dataset, ex
arXiv:2610.10865v1 Announce Type: new Abstract: Self-supervised speech encoders contain linguistic and paralinguistic information in a shared, entangled representation space. We combine a TopK sparse
arXiv:2610.11141v1 Announce Type: new Abstract: Relative localization is crucial for a multi-robot system to collaboratively perform tasks, such as exploration and formation. However, this is highly c
arXiv:2610.11206v1 Announce Type: new Abstract: Flat loss landscapes have long been linked to better generalization in neural networks. However, its role as a causal mechanism for generalization is le
arXiv:2610.12048v1 Announce Type: new Abstract: Deep neural networks, including large language models, have achieved remarkable performance across various tasks. However, they are prone to overconfide
arXiv:2610.11706v1 Announce Type: new Abstract: Self-blended images are widely used to train face-swap detectors, but primarily capture blending artifacts. We investigate whether adding illumination i
arXiv:2610.11776v1 Announce Type: new Abstract: Long-term personalization requires language models to use interaction history to track users' preferences across sessions. Parametric memory encodes thi
arXiv:2610.11115v1 Announce Type: new Abstract: The escalating size of pretrained neural networks has rendered model compression a prerequisite for deployment under stringent memory and compute constr
arXiv:2610.11284v1 Announce Type: cross Abstract: Diffusion-based LLMs (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs by enabling bidirectional parallel refinemen
arXiv:2610.11790v1 Announce Type: new Abstract: Byte-level language models such as the Byte Latent Transformer (BLT) group bytes into patches and run their large global model once per patch. BLT start
arXiv:2610.11303v1 Announce Type: new Abstract: Radiology report generation can automatically generate clinical descriptions from X-ray images, thereby significantly improving the efficiency of radiol
arXiv:2609.34181v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they still suffer from overthinking, generating redundant reasoning
arXiv:2610.11347v1 Announce Type: new Abstract: Physically grounded manipulation of articulated objects requires understanding both the maximum forces encountered during contact and the work performed
arXiv:2312.01221v2 Announce Type: replace Abstract: Quantum Natural Language Processing (QNLP) is taking huge leaps in solving the shortcomings of classical Natural Language Processing (NLP) technique
arXiv:2610.11690v1 Announce Type: cross Abstract: In the graph model for conflict resolution (GMCR), a decision maker (DM) either moves the conflict to another state or does nothing. The basic definit
arXiv:2610.11380v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in generative modeling, with their sampling procedures routinely modified to control generation and im
arXiv:2610.10666v1 Announce Type: new Abstract: Understanding why deep neural networks make a given prediction is of great importance for their safe deployment. In computer vision, saliency maps, whic
arXiv:2601.12654v3 Announce Type: replace-cross Abstract: SHAP explanations are widely used in high-stakes settings to justify decisions, yet they can differ substantially across repeated runs, even w
arXiv:2610.11379v1 Announce Type: new Abstract: JEV models make multimodal decisions by directly scoring candidates. Although the common context is encoded once, candidate evaluation can still repeat
arXiv:2610.11459v1 Announce Type: cross Abstract: Outside the linear-Gaussian regime, conditional sampling from Gaussian processes (GPs) is challenging. Recent methods such as FlowGP (Moss et al., (20
arXiv:2610.12102v1 Announce Type: cross Abstract: Flow matching has emerged as a scalable paradigm for training high-quality generative models, but sampling from the learned probability flow requires
arXiv:2610.12245v1 Announce Type: new Abstract: Social and service robots in public spaces need to anticipate which nearby person is about to approach and touch them, so that a response can be prepare
arXiv:2510.04440v2 Announce Type: replace Abstract: We develop a source-driven fractional heat-kernel framework for semi-super-vised graph learning that combines nonlocal propagation with sustained la
arXiv:2610.11412v1 Announce Type: new Abstract: We propose Fresco++, a unified optimization framework for fine-grained and view-consistent head avatar reconstruction. Head avatar optimization is typic
arXiv:2602.01683v2 Announce Type: replace-cross Abstract: Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous percep
arXiv:2610.11472v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning often improves language-model performance by giving models additional computation before answering. However, explicit C
arXiv:2610.12241v1 Announce Type: new Abstract: Microscopic robots require accurate task geometry despite changes in language, parts, and focus. We present a semantic-to-physical framework that maps i
arXiv:2610.10642v1 Announce Type: cross Abstract: This paper studies the construction of an explanatory space for a weighted naive Bayes classifier from the supervised representation induced by the mo
arXiv:2610.11818v1 Announce Type: cross Abstract: While massive, closed-source Vision-Language Models (VLMs) set strong benchmarks for document understanding, their dependence on commercial APIs limit
arXiv:2610.11787v1 Announce Type: new Abstract: Multimodal depression assessment offers a promising approach to analyzing behavioral patterns associated with depression. However, existing methods ofte
arXiv:2610.11770v1 Announce Type: new Abstract: AI-Native video creation is shifting from isolated video clips toward iterative video creation workflows. However, existing datasets remain largely vide
arXiv:2610.12305v1 Announce Type: new Abstract: As Multimodal Large Language Models (MLLMs) can describe increasingly complex visual scenes, token-level grounding becomes crucial. Yet, when an MLLM ge
arXiv:2610.11458v1 Announce Type: cross Abstract: AI research progress can be viewed as the interaction between two processes: benchmark creation and method discovery. Historically, both were driven b
arXiv:2610.12009v1 Announce Type: cross Abstract: Physics-informed machine learning has gained significant attention in recent years. In regimes of limited data, parametrized Gaussian processes have b
arXiv:2512.21476v2 Announce Type: replace-cross Abstract: Colonoscopic Polyp Re-Identification (ReID) aims to match the same polyp across a large gallery of images captured from different viewpoints a
arXiv:2409.01656v4 Announce Type: replace-cross Abstract: We consider the problem of estimating graph limits, known as graphons, from observations of sequences of sparse finite graphs. In this paper w
arXiv:2607.08987v2 Announce Type: replace Abstract: Spectral embedding methods are widely used for dimensionality reduction and clustering of high-dimensional datasets with intrinsic low-dimensional s
arXiv:2610.11231v1 Announce Type: new Abstract: Small vision-language models may be able to read external evidence yet struggle to obtain it. We introduce Harness Compilation (HC), an offline procedur
arXiv:2610.12147v1 Announce Type: new Abstract: False negatives remain a critical limitation of computer-aided diagnosis (CAD) systems for breast cancer screening due to delayed detection and treatmen