Knowledge catalogue
arXiv:2608.09174v1 Announce Type: new Abstract: To address the degradation of bearing fault diagnosis accuracy under strong noise, this paper proposes a time-frequency dual-domain multi-scale convolut
arXiv:2608.08126v1 Announce Type: cross Abstract: Credit scoring increasingly relies on models whose decision logic cannot be read off their parameters, in tension with supervisory expectations that a
arXiv:2608.08808v1 Announce Type: new Abstract: Timely crop-disease identification is critical to food security. Multi-crop recognition suits Mixture-of-Experts (MoE), but conventional soft-routing Mo
arXiv:2608.07859v1 Announce Type: new Abstract: Preferential Bayesian optimization (PBO) optimizes objectives accessible only through pairwise user comparisons. The standard approach fits a Gaussian p
arXiv:2608.09685v1 Announce Type: new Abstract: Autoregressive semantic ID recommenders are constrained by expensive beam-search decoding, which limits the practical length of item identifiers. Parall
arXiv:2608.08608v1 Announce Type: cross Abstract: Fourier neural operators (FNOs) provide efficient nonlocal spectral learning, but varying geometries and independently chosen discretizations remain d
arXiv:2510.13643v2 Announce Type: replace Abstract: Vision foundation models such as DINOv2 enable strong few-shot anomaly detection (FSAD) through simple non-parametric k-nearest-neighbor (k-NN) scor
arXiv:2608.09475v1 Announce Type: new Abstract: The MeViS-Audio track asks a system to segment the objects described by a spoken motion expression throughout a video and to return empty masks when the
arXiv:2608.09214v1 Announce Type: cross Abstract: Recent Retrieval-Augmented Generation (RAG) systems increasingly combine vector retrieval with structured knowledge, such as Graph RAG and Filtered ve
arXiv:2608.09355v1 Announce Type: new Abstract: RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in
arXiv:2312.12763v3 Announce Type: replace Abstract: Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both nat
arXiv:2607.15511v2 Announce Type: replace-cross Abstract: Serverless computing provides automatic resource management and pay-per-use execution, but effective autoscaling remains challenging because o
arXiv:2506.14194v2 Announce Type: replace Abstract: We present a theory for the construction of out-of-distribution (OOD) detection features for neural networks. We introduce random features for OOD t
arXiv:2509.03910v2 Announce Type: replace-cross Abstract: We formulate inverse problems in a Bayesian framework and aim to train an invertible generative model that is capable of simulation (i.e., sam
arXiv:2608.08732v1 Announce Type: cross Abstract: Multi-vector vision-language retrievers enable fine-grained Visual Document Retrieval (VDR) through late interaction, but storing and scoring hundreds
arXiv:2608.07471v1 Announce Type: cross Abstract: This study considers the task of applying artificial intelligence to recognize bank fraud. In recent years, due to the COVID19 pandemic, bank fraud ha
arXiv:2608.08872v1 Announce Type: new Abstract: In this paper we develop quantitative approximation results for shallow neural networks constructed using a dictionary based on metaplectic operators. F
arXiv:2608.08086v1 Announce Type: new Abstract: Diffusion language models (DLMs) iteratively refine a sequence, allowing earlier predictions to be revised as context evolves. This rollback capability
arXiv:2509.08421v2 Announce Type: replace-cross Abstract: For multimedia spatial intelligence through time, multi-view multi-object tracking (MVMOT) suffers from persistent challenges in maintaining c
arXiv:2603.00040v3 Announce Type: replace-cross Abstract: Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the ma
arXiv:2608.08027v1 Announce Type: cross Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding maliciou
arXiv:2608.09344v1 Announce Type: new Abstract: Recent advances in large vision-language models (LVLMs) have enabled powerful multimodal reasoning by integrating visual encoders with large language mo
arXiv:2601.17504v2 Announce Type: replace Abstract: Multi-modal MRI enables detailed brain tumor sub-region segmentation, but clinical deployment remains affected by missing sequences,boundary errors,
arXiv:2608.07572v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have demonstrated exceptional performance in high-fidelity image and video generation. To alleviate their massive comput
arXiv:2606.15812v2 Announce Type: replace Abstract: We introduce Brownian kernel ladders (BKLs), a recursive hierarchy of integral reproducing kernel Hilbert spaces built from linear functionals by re
arXiv:2608.09774v1 Announce Type: new Abstract: Thoracic pathologies rarely occur in isolation, yet standard multi-label classifiers rely on shared global descriptors, discarding where findings lie an
arXiv:2608.09392v1 Announce Type: new Abstract: CableDex is a computer vision system that addresses the time-consuming and inaccurate manual measurement of cable length on industrial reels from a sing
arXiv:2509.08813v2 Announce Type: replace Abstract: Robots often rely on RGB images for tasks like manipulation. However, reliable interaction typically requires a 3D scene representation that is metr
arXiv:2608.08451v1 Announce Type: cross Abstract: Harmful chat dialogues are ever-shifting through type-shifting and lexical evasion, yet we find they share invariant principles, i.e., an Ordered Reas
arXiv:2608.09485v1 Announce Type: new Abstract: Cooperative capabilities in language models are dual-use. The same social reasoning that supports civic deliberation can also enable strategic omission,
arXiv:2608.08288v1 Announce Type: new Abstract: Estimating counterfactual outcomes over time from longitudinal observational data is central to clinical decision support. Existing methods rely on doma
arXiv:2608.07759v1 Announce Type: cross Abstract: Cardiovascular AI models can classify clean elec- trocardiogram (ECG) signals, but real wearable signals change because of motion, breathing, posture,
arXiv:2608.08922v1 Announce Type: cross Abstract: Transformer layers generate state-dependent interaction networks: token representations determine the attention matrix, which in turn updates the repr
arXiv:2608.07751v1 Announce Type: cross Abstract: Safe and efficient robot navigation in crowds requires anticipating pedestrian motion despite uncertain and potentially shifting prediction errors. Ex
arXiv:2608.07719v1 Announce Type: new Abstract: Offline reinforcement learning repeatedly trains policies from a fixed transition pool, making redundant data costly across seeds and hyperparameters, w
arXiv:2604.01653v2 Announce Type: replace Abstract: Electroencephalography (EEG) provides a non-invasive insight into the brain's cognitive and emotional dynamics. However, modeling how these states e
arXiv:2608.09391v1 Announce Type: new Abstract: Accurate medical image interpolation and anatomical structure segmentation are fundamental for computer-aided diagnosis and treatment planning. Anisotro
arXiv:2608.08082v1 Announce Type: new Abstract: Classifier-free guidance (CFG) is usually kept on throughout masked diffusion language model decoding, although its benefit varies across prompts and ov
arXiv:2601.14609v2 Announce Type: replace-cross Abstract: Multi-site collaboration can power survival models that no single hospital could fit alone, but privacy rules and protected computing environm
arXiv:2603.29512v3 Announce Type: replace Abstract: The reliable operation of Unmanned Underwater Vehicle (UUV) clusters is highly dependent on continuous acoustic communication. However, this communi
arXiv:2608.09792v1 Announce Type: new Abstract: Narrating the visual component of movies is known as audio description. It is a narrative technique designed to enable blind and visually impaired indiv
arXiv:2608.08204v1 Announce Type: cross Abstract: This work proposes deep nonparametric Instrumental variable quantile regression (IVQR), a two-stage estimator that combines conditional diffusion mode
arXiv:2608.07867v1 Announce Type: new Abstract: Multimodal emotion recognition often treats self-reported labels as reliable supervision while overlooking self-report unreliability and cross-modal con
arXiv:2608.07795v1 Announce Type: cross Abstract: Prediction intervals for multi-modal regression with tabular variables, text, images, or other input sources are difficult to calibrate when those sou
arXiv:2608.08414v1 Announce Type: new Abstract: We study constrained statistical learning over infinite-dimensional hypothesis classes in the fully nonconvex setting, and establish universal PACC lear
arXiv:2608.08122v1 Announce Type: new Abstract: In this paper we discuss the foundations behind a novel methodology for the validation of semantic mappings between different data sources based upon di
Back after ~6 months — rebuilding my spiking language model around CPU-first inference Hey everyone. It’s been around six months since I last posted anything about this project here. Some of you might
arXiv:2608.07551v1 Announce Type: cross Abstract: This paper studies incremental stability of holomorphic dynamical systems through the infinitesimal Kobayashi metric, an intrinsic pseudometric on com
arXiv:2608.09101v1 Announce Type: new Abstract: Semantic segmentation models are trained and evaluated against human-drawn masks, yet remote-sensing annotations are often coarse, incomplete, or misali
arXiv:2608.09382v1 Announce Type: cross Abstract: Electromagnetic inverse scattering is a nonlinear and ill-posed problem, where accurate reconstruction is challenging due to measurement limitations,
arXiv:2608.08965v1 Announce Type: new Abstract: Underwater images often suffer from diverse and coexisting degradations, including color distortion, scattering haze, texture attenuation, and uneven il
arXiv:2607.18323v2 Announce Type: replace-cross Abstract: Exhaustive site-by-site interventions on a neural network's computational graph -- activation-patching sweeps, circuit-discovery searches, sys
arXiv:2608.08638v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools. All TTS systems require faithful ling
arXiv:2608.08955v1 Announce Type: new Abstract: Fine-grained damage classification of 3D point cloud data (PCD) remains a persistent challenge, constrained by high computational demands and limited la
arXiv:2601.02096v2 Announce Type: replace-cross Abstract: Ballroom dancing is a structured yet expressive motion category. Its highly diverse movement and complex interactions between leader and follo
arXiv:2608.07643v1 Announce Type: new Abstract: Traffic data collection is dominated today by deep object detectors followed by tracking-by-detection, a pipeline that presupposes what is often missing
arXiv:2608.07472v1 Announce Type: new Abstract: Wildfire prediction models typically discretize study areas into uniform grids, ignoring the heterogeneous spatial distribution of ignitions. We challen
arXiv:2602.11149v2 Announce Type: replace Abstract: Supervised fine-tuning (SFT) on chain-of-thought data is an essential post-training step for reasoning language models. Standard machine learning in
arXiv:2608.07904v1 Announce Type: new Abstract: Industrial anomaly inspection is severely hindered by the scarcity of real anomalous data.Zero-shot industrial anomaly generation addresses this by gene
arXiv:2608.08926v1 Announce Type: new Abstract: Neuroimaging and genetic testing are two important clinical references for nervous system diseases, offering complementary diagnostic information. Howev