Knowledge catalogue
arXiv:2606.06550v1 Announce Type: cross Abstract: Self-supervised learning (SSL) yields powerful, context-rich representations for speech emotion recognition (SER), yet aggregating these representatio
arXiv:2606.07102v1 Announce Type: cross Abstract: We propose GP-Adapter, a training-free framework that augments CLIP (Contrastive Language-Image Pre-training) with Gaussian Process (GP) uncertainty m
arXiv:2606.06833v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transc
arXiv:2209.00188v4 Announce Type: replace-cross Abstract: Long-latency load requests continue to limit the performance of high-performance processors. To increase the latency tolerance of a processor,
arXiv:2606.07044v1 Announce Type: new Abstract: Accurate and coherent passenger demand forecasting is essential for Urban Rail Transit (URT) operations. Passenger demand has a hierarchical structure i
arXiv:2606.07218v1 Announce Type: cross Abstract: Multi-hop RAG poses a data-engineering problem beyond passage matching: under fixed retrieval budgets, a system must organize retrieved text into evid
arXiv:2606.06635v1 Announce Type: cross Abstract: Failures in language model reasoning emerge through distinct processes that leave identifiable signatures in the reasoning trace. We characterize thes
arXiv:2606.06743v1 Announce Type: cross Abstract: The popularity of neural audio codecs as speech tokenizers has surged with the advent of Multimodal Large Language Models. New codec architectures wit
I wrote my first neural networks in pure C, then in Matlab, then in NumPy, before eventually upgrading to Theano. Since then I have seen and tried pretty much every NN framework ever developed. Some a
arXiv:2408.08973v3 Announce Type: replace Abstract: Purpose: A major barrier to the implementation of artificial intelligence for medical applications is automated CNNs' lack of explainability and hig
arXiv:2606.07381v1 Announce Type: cross Abstract: Background and Purpose: Automated detection of focal cortical dysplasia (FCD) requires large volumes of voxelwise lesion-delineated MRI data, which ar
arXiv:2606.07498v1 Announce Type: new Abstract: Scientific observations generate large quantities of unlabeled data which is laborious to hand-label, making unsupervised learning techniques valuable f
arXiv:2606.06664v1 Announce Type: cross Abstract: Despite high accuracy, Vision Transformer (ViT) predictions can be driven by spurious cues, raising the need to understand their inner workings before
arXiv:2606.06671v1 Announce Type: new Abstract: Existing implicit neural representation (INR) approaches suffer from stochastic initialization that does not guarantee consistent or high-quality perfor
arXiv:2606.07240v1 Announce Type: new Abstract: Cross-lingual voice cloning aims to generate speech in a target language while preserving speaker identity from a source-language reference. This task i
arXiv:2603.02970v2 Announce Type: replace Abstract: We introduce LAGO, a LocAl-Global Optimization framework coupling Bayesian Optimization (BO) and gradient-based trust region local refinement throug
arXiv:2606.06805v1 Announce Type: cross Abstract: Lane changing entails simultaneous longitudinal and lateral motions that affect driving comfort and mobility efficiency. Because these motions are tig
arXiv:2508.17821v3 Announce Type: replace-cross Abstract: This paper investigates the limitations of the normalization in attention mechanisms. We begin with a theoretical framework that enables the i
arXiv:2606.06953v1 Announce Type: new Abstract: We argue that high-quality motion data can steer tracking policies toward better optimization trajectories early in training. In this work, we introduce
arXiv:2504.00613v2 Announce Type: replace Abstract: Finding deletion-correcting codes of maximum size has been an open problem for over 70 years, even for a single deletion. We adapt FunSearch, a larg
arXiv:2602.14209v2 Announce Type: replace-cross Abstract: Block diffusion LLMs are an emerging paradigm for parallel language generation, but their KV caching makes memory access the dominant bottlene
arXiv:2606.07057v1 Announce Type: cross Abstract: Evaluating the quality of automatically generated keyphrases remains a complex challenge. Traditional metrics either rely on exact lexical matching or
arXiv:2606.06760v1 Announce Type: new Abstract: Medical large vision-language models (Med-LVLMs) have recently achieved remarkable progress in vision-language comprehension and medical image segmentat
arXiv:2510.05363v2 Announce Type: replace Abstract: Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated
arXiv:2606.07394v1 Announce Type: new Abstract: In Video Instance Segmentation (VIS), classification, segmentation, and tracking objectives are jointly evaluated, but their individual contributions to
arXiv:2506.01850v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in instruction-following tasks by integrating pretrained visual enco
arXiv:2411.09734v3 Announce Type: replace Abstract: In this paper, we propose a continuous-time formulation for the AdaGrad, RMSProp, and Adam optimization algorithms by modeling them as first-order i
arXiv:2606.06738v1 Announce Type: new Abstract: Building monolingual language models (LMs) for low-resource languages typically relies on adapting pretrained language models (PLMs) by finetuning the w
arXiv:2602.16908v2 Announce Type: replace-cross Abstract: Allegro is a machine learning interatomic potential model designed to predict atomic properties in molecules using E(3) equivariant neural net
arXiv:2606.06762v1 Announce Type: new Abstract: Off-board control of mobile robots from cameras embedded in the environment offers a practical path to scalable autonomy, moving sensing and compute off
arXiv:2606.06740v1 Announce Type: cross Abstract: Discrete speech units obtained via k-means clustering of self supervised embeddings entangle phonetic, speaker, and language information, causing spea
arXiv:2606.06573v1 Announce Type: cross Abstract: We introduce scale-selective Proper Orthogonal Decomposition (POD) for transformer attention fields, inspired by the use of POD for extracting energet
arXiv:2606.07116v1 Announce Type: cross Abstract: Low-bit quantization has been widely adopted to accelerate the inference of large language models (LLMs) by significantly reducing computational cost
arXiv:2606.07449v1 Announce Type: cross Abstract: This paper addresses orbital stabilization of a circular motion primitive for a dynamic extension of the Dubins car model within a transverse-lineariz
arXiv:2606.07257v1 Announce Type: cross Abstract: Phase retrieval - recovering a complex-valued field from intensity measurements - is typically solved using variants of the Gerchberg-Saxton (GS) algo
arXiv:2602.00541v2 Announce Type: replace Abstract: Clinical events captured in Electronic Health Records (EHR) are irregularly sampled and may consist of a mixture of discrete events and numerical me
arXiv:2603.13042v2 Announce Type: replace Abstract: Digital Compute-in-Memory (DCiM) accelerates neural networks by reducing data movement. Approximate DCiM can further improve power-performance-area
arXiv:2606.06764v1 Announce Type: cross Abstract: Recent progress has been made in understanding the statistical generalization performance of gradient descent methods for overparameterized neural net
arXiv:2606.06521v1 Announce Type: cross Abstract: FP8 (E4M3) acceleration for attention computation offers significant throughput gains, but the 3-bit mantissa introduces precision challenges when the
arXiv:2603.07704v2 Announce Type: replace Abstract: Inter-object relations underpin spatial intelligence, yet existing representations -- linguistic prepositions or object-level scene graphs -- are to
arXiv:2606.07030v1 Announce Type: cross Abstract: We analyse error patterns of raw waveform acoustic models on TIMIT phone recognition beyond the overall phone error rate (PER). PER is decomposed acro
arXiv:2606.07300v1 Announce Type: new Abstract: Language is a vehicle for thought, intricately tied to sounds, symbols, and meaning. However, most large language model (LLM) research focuses on meanin
arXiv:2606.07476v1 Announce Type: cross Abstract: This paper investigates multi-degrees of freedom (DoF) joint kinematics estimation under partially observed surface electromyography (sEMG), where onl
arXiv:2502.00527v2 Announce Type: replace-cross Abstract: The KV cache in large language models is a dominant factor in memory usage, limiting their broader applicability. Quantizing the cache to lowe
arXiv:2606.06908v1 Announce Type: new Abstract: Modern image-analysis pipelines often convert images into structured semantic variables, such as facial attributes, object concepts, and scene descripto
arXiv:2602.16864v2 Announce Type: replace-cross Abstract: Time series (TS) modeling has come a long way from early statistical, mainly linear, approaches to the current trend in TS foundation models.
arXiv:2509.11208v3 Announce Type: replace-cross Abstract: Transformers used for evidence-grounded binary adjudication (e.g., support/refute, yes/no, or verifier-backed pass/fail decisions) can be sens
arXiv:2606.07083v1 Announce Type: new Abstract: Reinforcement learning has become the prevailing approach to humanoid locomotion control: policies transfer reliably from simulation to hardware and rec
arXiv:2606.06624v1 Announce Type: new Abstract: In the current era of deep learning and especially generative models, there is significant investment in training very large generative models. Thus far
arXiv:2602.01177v3 Announce Type: replace-cross Abstract: We develop an information-theoretic framework connecting stability, privacy, and generalization for quantum learning algorithms. Learning proc
arXiv:2603.13546v2 Announce Type: replace Abstract: We introduce Probabilistic Gaussian Homotopy (PGH), a probability-space continuation framework for nonconvex optimization. Unlike classical Gaussian
arXiv:2606.06516v1 Announce Type: cross Abstract: We advance a new probabilistic supervised learning approach that permits reliable, automated, and early individualised prediction of the severity with
arXiv:2403.10318v3 Announce Type: replace Abstract: Recent advances have shifted the paradigm of tabular learning toward tabular foundation models, yet their accuracy relies on a heavy inference cost
arXiv:2606.06812v1 Announce Type: new Abstract: We perform the largest known computational analysis of Canadian news narratives about police-involved deaths, spanning 4,000 articles from the last quar
arXiv:2606.06614v1 Announce Type: cross Abstract: Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data. It remains uncle
arXiv:2606.06497v1 Announce Type: cross Abstract: Generative video models have achieved remarkable visual fidelity, yet their prompt-only interface offers thin creative agency and obscures the model's
arXiv:2606.07249v1 Announce Type: new Abstract: Accurate monitoring of forest disturbances is essential for understanding carbon dynamics and land management, yet traditional approaches typically rely
arXiv:2505.11470v3 Announce Type: replace Abstract: We introduce two reference-free metrics for quality evaluation of taxonomies in the absence of labels. The first metric evaluates robustness by calc
arXiv:2512.14391v3 Announce Type: replace-cross Abstract: In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextu
arXiv:2602.02014v2 Announce Type: replace-cross Abstract: Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However,