Knowledge catalogue
arXiv:2605.23362v1 Announce Type: new Abstract: Evaluating large language models increasingly relies on LLM-as-a-judge protocols, but such evaluations remain costly: different judges have different pr
arXiv:2605.23556v1 Announce Type: new Abstract: Why does the low dimensionality of representations, typically dapprox 1000, not prevent modern embedding-based retrieval models from scaling to billions
arXiv:2605.22892v1 Announce Type: cross Abstract: Modelling claim frequency and severity for non-life insurance pricing predominantly relies on generalised linear models, with gradient-boosted machine
arXiv:2605.23397v1 Announce Type: new Abstract: Accurate camera-LiDAR calibration is a prerequisite for robust multi-modal perception in robotics. Recent target-less approaches based on deep point cor
arXiv:2605.22857v1 Announce Type: cross Abstract: High-resolution range profile (HRRP)-based radar automatic target recognition suffers from severe performance degradation in composite jamming environ
arXiv:2605.23198v1 Announce Type: new Abstract: Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing
arXiv:2605.23878v1 Announce Type: new Abstract: Modern video generators produce visually compelling clips but still struggle with physical and motion consistency, limiting their use as reliable world
arXiv:2605.23287v1 Announce Type: new Abstract: We present LangFlash, a feed-forward framework for 3D Language Gaussian Splatting that reconstructs 3D scenes parameterized by Gaussian primitives enric
arXiv:2605.23255v1 Announce Type: new Abstract: Learning-augmented algorithms have emerged as a powerful paradigm to surpass traditional worst-case lower bounds by integrating potentially noisy predic
arXiv:2605.23708v1 Announce Type: new Abstract: The robustness of synchronization is typically characterized by scalar, per-node stability indices whose dependence on topology is studied via network s
arXiv:2605.23645v1 Announce Type: cross Abstract: In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher
arXiv:2605.23861v1 Announce Type: cross Abstract: Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approac
arXiv:2602.12534v2 Announce Type: replace-cross Abstract: In truncated linear regression, samples (x,y) are shown only when the outcome y falls inside a certain survival set S^star and the goal is to
arXiv:2601.18685v3 Announce Type: replace-cross Abstract: The capabilities of generative AI in mathematics education are rapidly evolving, posing significant challenges for research to keep pace. Rese
arXiv:2605.22976v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly integrated into software systems for diverse purposes, due to their versatility, flexibility, and abilit
arXiv:2605.23102v1 Announce Type: cross Abstract: Large language models (LLMs) offer a scalable mechanism to elicit domain-informed prior information for high-dimensional variable selection. However,
arXiv:2605.23901v1 Announce Type: cross Abstract: Existing scaling laws for Large Language Models (LLMs), predominantly monotonic power laws, fail to explain emerging non-monotonic phenomena such as c
arXiv:2601.14300v3 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models. Despite rece
arXiv:2605.23777v1 Announce Type: new Abstract: The grading of gemstones is currently a manual procedure performed by gemologists. A popular approach uses reference stones, where those are visually in
arXiv:2605.23563v1 Announce Type: new Abstract: Comprehensive evaluation of machine learning models is the key to make sure that they perform as robustly and consistently as desired. In order to summa
arXiv:2605.23507v1 Announce Type: new Abstract: The DEtection TRansformer (DETR) is a powerful end-to-end object detector, yet its one-to-one matching strategy suffers from slow convergence and low re
arXiv:2605.23384v1 Announce Type: cross Abstract: Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement
arXiv:2406.09250v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically de
arXiv:2507.12455v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated con
arXiv:2605.23840v1 Announce Type: new Abstract: Mueller matrix imaging provides rich, physically meaningful contrast for biomedical tissue analysis, but supervised learning is hindered by scarce dense
arXiv:2605.23259v1 Announce Type: cross Abstract: While Attention Residuals has shown some effectiveness in addressing the widespread issue of unbounded activation growth across deep residual layers,
arXiv:2605.23885v1 Announce Type: new Abstract: Cross-lingual knowledge transfer is critical for building high-performing multilingual language models for languages with insufficient training data. Wh
arXiv:2602.20210v2 Announce Type: replace-cross Abstract: Crystal modeling spans a family of conditional and unconditional generation tasks, including crystal structure prediction (CSP) and de novo ge
arXiv:2511.16014v2 Announce Type: replace Abstract: Digitisation in the cultural heritage sector has produced large but fragmented repositories of museum collection data, spanning structured catalogue
arXiv:2601.07545v2 Announce Type: replace Abstract: We study differentially private ordinary least squares (DP-OLS) with bounded data (X,Y) via sketching-based mechanisms. While Gaussian sketching app
arXiv:2604.05129v2 Announce Type: replace-cross Abstract: We investigate the strategic surplus obtainable against a Follow-the-Regularized-Leader (FTRL) learner with constant step size eta in nimes m
arXiv:2605.23192v1 Announce Type: new Abstract: Video editing has recently achieved remarkable progress with diffusion-based generative models, enabling diverse object-level manipulations from natural
arXiv:2602.07697v2 Announce Type: replace-cross Abstract: Predictive coding (PC) is a biologically plausible alternative to standard backpropagation (BP) that minimises an energy function with respect
arXiv:2512.19199v2 Announce Type: replace-cross Abstract: The paper establishes generalization bounds for multitask deep neural networks using operator-theoretic techniques. The authors propose a tigh
arXiv:2605.23879v1 Announce Type: cross Abstract: Gradient-flow sampling interprets a Gibbs distribution as the minimizer of an energy functional over probability measures and generates dynamics conve
arXiv:2605.23458v1 Announce Type: cross Abstract: Recent advances have substantially improved real-time interactive video generation in the autoregressive regime. However, most existing few-step autor
arXiv:2605.23668v1 Announce Type: cross Abstract: Although large language model (LLM) conversational systems process millions of multi-turn dialogues daily, they remain fundamentally reactive: they re
arXiv:2605.23409v1 Announce Type: cross Abstract: In human computer interaction, real-time detection and classification of dynamic hand gestures is challenging as: 1) the system must run in a real-tim
arXiv:2602.08927v3 Announce Type: replace-cross Abstract: We study the problem of online monotone density estimation, where density estimators must be constructed in a predictable manner from sequenti
arXiv:2512.19184v2 Announce Type: replace-cross Abstract: This paper presents novel generalization bounds for vector-valued neural networks and deep kernel methods, focusing on multi-task learning thr
arXiv:2605.23726v1 Announce Type: new Abstract: We prove optimal sampling bounds achieving (1pmarepsilon)-relative error for a broad class of Lipschitz continuous classification loss functions under v
arXiv:2605.23066v1 Announce Type: cross Abstract: In a landscape of high-performance distributed ML systems, JAX has emerged as a framework of choice. However, JAX's modular design philosophy leaves i
arXiv:2605.23402v1 Announce Type: cross Abstract: Effectively modeling non-stationary dynamics in probabilistic multivariate time series(MTS) forecasting requires balancing expressiveness with robustn
arXiv:2605.23074v1 Announce Type: new Abstract: The emergence of Large Reasoning Language Models (LRMs) has paved the way for tackling complex reasoning tasks through test-time scaling by generating l
arXiv:2605.23531v1 Announce Type: new Abstract: Low-light images exhibit severe noise, contrast loss, and semantic ambiguity, making enhancement a joint problem of denoising and detail recovery. We pr
arXiv:2603.21437v2 Announce Type: replace Abstract: Transformer-based embedding models frequently exhibit geometric pathologies, such as anisotropy and length-induced representation collapse, which ca
arXiv:2603.02897v2 Announce Type: replace Abstract: Recent advances in generative image compression (GIC) have delivered remarkable improvements in perceptual quality. However, many GICs rely on large
arXiv:2605.23550v1 Announce Type: cross Abstract: We study nonsmooth difference-of-convex programs whose subtracted convex term is a finite maximum of smooth convex functions. In this setting, standar
arXiv:2605.23028v1 Announce Type: cross Abstract: Machine learning methods rely on data. However, gathering suitable data can be challenging due to availability constraints, cost, or the need for doma
arXiv:2605.22937v1 Announce Type: new Abstract: Inference-time scaling can reduce errors in structured query generation, but methods to allocate the compute for query code generation remains underexpl
arXiv:2605.22864v1 Announce Type: new Abstract: The maximum softmax probability (MSP) represents a default approach when evaluating uncertainty quantification for language model generation with struct
arXiv:2605.22836v1 Announce Type: cross Abstract: Rapid earthquake magnitude estimation is crucial for effective early warning systems that can save lives and reduce economic damage. In this paper, we
arXiv:2605.23472v1 Announce Type: new Abstract: Vision foundation models pretrained on web-scale data have recently shown strong transfer capabilities on many downstream tasks, but their effectiveness
arXiv:2605.22986v1 Announce Type: cross Abstract: Learning reward functions from demonstrations assumes that demonstrations provide adequate supervision over all features -- or task-relevant aspects o
arXiv:2502.13731v5 Announce Type: replace Abstract: This paper addresses a key limitation in existing counterfactual inference methods for Markov Decision Processes (MDPs). Current approaches assume a
arXiv:2605.23175v1 Announce Type: cross Abstract: Proprietary large language models (LLMs) face risks of intellectual property (IP) violation, as adversaries can replicate an LLM by collecting input-o
arXiv:2605.23115v1 Announce Type: new Abstract: Bike-sharing models trained on historical station-hour data may degrade when deployed in later years because travel patterns change over time. This pape
arXiv:2403.12401v2 Announce Type: replace Abstract: Neural Representations for Videos(NeRV) have emerged as a promising paradigm for video compression by representing videos as compact neural networks
arXiv:2605.23467v1 Announce Type: new Abstract: Message-passing neural networks (MPNNs) often suffer from an information bottleneck when capturing long-range dependencies, leading to the oversquashing
arXiv:2605.23194v1 Announce Type: cross Abstract: Fast and reliable optimal power flow (OPF) approximation is essential for reliable smart-grid operation, yet many learning-based surrogates either fla