Knowledge catalogue
arXiv:2610.16734v1 Announce Type: new Abstract: The diagnostic capability of WSI agents relies on effective slide navigation to identify diagnostically relevant regions and efficiently integrate evide
arXiv:2610.14012v1 Announce Type: new Abstract: Many systems read the latent space of a variational autoencoder (VAE) as discrete codes, and rely on each latent being read back as the code it was writ
arXiv:2610.17848v1 Announce Type: new Abstract: Persistence diagrams (PDs) represent multiscale topological information as multisets of birth-death pairs (b,d). How best to use them with Transformers,
arXiv:2507.05291v2 Announce Type: replace Abstract: We propose a physics-informed machine learning framework called P-DivGNN to reconstruct local stress fields at the micro-scale, in the context of mu
arXiv:2610.14028v1 Announce Type: new Abstract: Data selection for LLM fine-tuning faces two facts about real training: data pools draw from many distinct domains, and evaluation spans diverse tasks.
arXiv:2509.19774v3 Announce Type: replace Abstract: Electrocardiography (ECG) is the clinical gold standard for cardiovascular disease (CVD) assessment, yet continuous monitoring is constrained by the
arXiv:2610.16809v1 Announce Type: cross Abstract: This study addresses the prediction of audio popularity on an online sharing platform by leveraging both metadata and acoustic feature representations
arXiv:2610.16983v1 Announce Type: cross Abstract: Most prior work on predicting mental health help-seeking treats it as post-hoc classification of users already active in clinical communities, which c
arXiv:2610.14001v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning
arXiv:2610.14770v1 Announce Type: new Abstract: Multimodal contrastive learning typically relies on manually specified scoring functions, such as cosine similarity, to quantify the similarity between
arXiv:2610.14942v1 Announce Type: new Abstract: Bilevel data selection is a fundamental task with numerous applications in machine learning and statistics. A common strategy for tackling this problem
arXiv:2610.16287v1 Announce Type: new Abstract: Automated visual inspection is essential for efficient repair and recycling of metallic components. AI-based defect detection is a strong fit. However,
arXiv:2512.03923v3 Announce Type: replace Abstract: Solving reservoir seepage partial differential equations (PDEs) is critical for hydrocarbon development optimization and production forecasting. Con
arXiv:2610.16082v1 Announce Type: new Abstract: Heterogeneous medical image data motivate domain-specialized diffusion experts, but expert specialization alone does not determine how their predictions
arXiv:2610.18804v1 Announce Type: new Abstract: Raw image intensities are a poor surrogate for similarity across images in correspondence problems. Further, while auxiliary segmentation labels can pro
arXiv:2610.17722v1 Announce Type: cross Abstract: Quantum Machine Learning (QML) has a theoretical advantage over classical algorithms for specific synthetic data that is computationally hard. However
arXiv:2610.18417v1 Announce Type: new Abstract: End-to-end deep learning pipelines for camera-radar 3D object detection are well established in driver assistance systems and autonomous vehicles; howev
arXiv:2610.14269v1 Announce Type: new Abstract: Humanoid face robots can now move their lips in sync with speech and show detailed facial expressions. Give such a robot the face of a real person and d
arXiv:2604.01581v4 Announce Type: replace Abstract: Drone-view geo-localization (DVGL) typically assumes access to satellite imagery during task-specific development. We study a late-arriving-gallery
arXiv:2610.15965v1 Announce Type: new Abstract: We study pretraining when compute is abundant but unique training data are finite, requiring repeated training on the same data. We first revisit infini
arXiv:2610.14187v1 Announce Type: cross Abstract: Urban traffic systems are becoming increasingly complex, demanding real-time traffic perception, proactive collision prediction, and intelligent manag
arXiv:2610.14004v1 Announce Type: new Abstract: People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines. In contrast
arXiv:2512.10581v2 Announce Type: replace Abstract: Current methods for all-in-one image restoration increasingly rely on complex mechanisms, such as Mixture-of-Experts or prompt learning, to handle d
arXiv:2601.11266v2 Announce Type: replace Abstract: Robust generalization in robotic manipulation is crucial for robots to adapt flexibly to diverse environments. Existing methods usually improve gene
arXiv:2610.15764v1 Announce Type: new Abstract: Audio-Visual Segmentation (AVS) requires predicting pixel-wise masks of sounding objects by grounding acoustic signals in visual space. In multi-source
arXiv:2610.16264v1 Announce Type: new Abstract: Electroencephalography (EEG) is a non-invasive, scalable source of quantitative biomarkers for the early diagnosis of brain disorders, and deep represen
arXiv:2302.00985v3 Announce Type: replace-cross Abstract: We consider online scheduling on unrelated (heterogeneous) machines in a speed-oblivious setting, where an algorithm is unaware of the exact j
arXiv:2610.18005v1 Announce Type: new Abstract: Surface reconstruction from range scans is challenging in the presence of noise and outliers, as fidelity to observations must be balanced against sensi
arXiv:2610.15095v1 Announce Type: new Abstract: LLM multi-agent systems split work across agents that communicate through text. An agent summarizes its findings, another agent receives the text. This
arXiv:2610.17448v1 Announce Type: new Abstract: Gaps, skips, and mistakes are the normal state of a historical register: rows go missing, tables cross page breaks, columns slip under wrong names, and
arXiv:2510.06470v2 Announce Type: replace-cross Abstract: We investigate the use of a point cloud measurement in terrain-aided navigation. Our goal is to aid an inertial navigation system, by explorin
arXiv:2610.17908v1 Announce Type: cross Abstract: In manga translation, visual context outside speech-bubble text, including speaker identities, referents, and scene tone, is depicted in page images,
arXiv:2610.14279v1 Announce Type: new Abstract: Learning long-range dependencies with recurrent neural networks (RNNs) is difficult because of the vanishing gradient problem. Gated recurrent neural ne
arXiv:2610.15807v1 Announce Type: new Abstract: Generating coherent videos grounded in a unified underlying world remains a major challenge, particularly under large viewpoint changes, where existing
arXiv:2610.14846v1 Announce Type: new Abstract: Indoor human perception is the foundation for smart homes and healthcare. However, RGB cameras raise privacy concerns in private indoor environments, wh
arXiv:2610.15038v1 Announce Type: new Abstract: Real-world Vision-Language Navigation (VLN) requires agents to act under partial observability, where map structure, semantic cues, and target locations
arXiv:2610.14153v1 Announce Type: new Abstract: Classifier-free guidance (CFG) typically applies a shared scale to all latent tokens, although their velocity predictions evolve differently during samp
arXiv:2610.14394v1 Announce Type: cross Abstract: Training large-scale recommender systems on dynamic industrial platforms, such as Short-Form Video (SFV) services with billions of daily interactions,
arXiv:2610.16146v1 Announce Type: new Abstract: We present Unravel, a training-free framework that turns a single image into an interactive 3D scene, where every object is an independent and movable a
arXiv:2610.15963v1 Announce Type: cross Abstract: High-pileup conditions in CMS during the HL-LHC era make charged-particle tracking increasingly challenging as detector occupancy and combinatorics gr
arXiv:2610.18363v1 Announce Type: cross Abstract: In this work, we present a fundamentally new approach to visual servoing using lines. It is based on a theoretical and geometrical study of the main l
arXiv:2610.18147v1 Announce Type: new Abstract: We present a real-time framework for expressive legged locomotion that enables independent control over velocity and style. Unlike existing data-driven
arXiv:2610.17376v1 Announce Type: cross Abstract: A shared latent space is often assumed to make representations from different schemas directly interchangeable, yet sharing parameters, dimensionality
arXiv:2610.16020v1 Announce Type: new Abstract: Layer-wise post-training quantization methods let each layer compensate for the quantization error inherited from earlier layers. We ask under what assu
arXiv:2610.16337v1 Announce Type: new Abstract: Rotary Positional Embedding (RoPE) is widely used to encode relative positions in Transformers. In multi-view settings, however, patch coordinates are d
cuda : warnings cleanup Signed-off-by: Adrien Gallouët angt@huggingface.co Update ggml/src/ggml-cuda/common.cuh Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co Signed-off-by: Adrien
This post is to let people know about a workshop/tutorial on Machine Learning that will run on the (blue) math discord server: discord.gg/maths. The place is nice, people are cool and helpful, and as
On October 13, 2026 NVIDIA released the complete Run:ai platform—an AI workload and GPU orchestration system—as open‑source software under its DSX AI Factory Platform. The modular release includes fou
IBM Research has presented a new approach that scales AI‑driven chip design by employing open “agent factories,” lowering inference cost by 11.5 × compared to fully proprietary setups. The method enab
arXiv:2603.03753v2 Announce Type: replace-cross Abstract: The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge
arXiv:2510.00734v2 Announce Type: replace-cross Abstract: Bayesian optimal experimental design provides a principled framework for selecting experimental configurations that maximize obtained informat
arXiv:2610.12977v1 Announce Type: new Abstract: Generative recommendation (GR) of social media platforms commonly retrieves items by autoregressively decoding discrete Semantic IDs (SIDs) with finite-
arXiv:2610.13891v1 Announce Type: cross Abstract: Light Detection and Ranging (LiDAR) is critical for autonomous perception, yet its performance is known to degrade in adverse weather. While existing
arXiv:2505.22184v3 Announce Type: replace-cross Abstract: Social media platforms have experienced a significant rise in toxic content, including abusive language and discriminatory remarks, presenting
arXiv:2610.13059v1 Announce Type: new Abstract: Radiology reports are essential for diagnostic reasoning and patient care, yet their manual preparation is time-consuming and cognitively demanding. Aut
arXiv:2610.12915v1 Announce Type: new Abstract: Minimax optimization is fundamental to adversarial learning yet suffers from severe stability challenges, often manifesting as persistent limit cycles o
arXiv:2610.13299v1 Announce Type: cross Abstract: Pretrained vision transformers learn structured image representations spanning spatial patch tokens and non-spatial tokens. Recent analyses suggest th
arXiv:2610.12916v1 Announce Type: new Abstract: Existing governance approaches in decentralized financial networks rely on manual review processes conducted by human committees, which introduces subje
arXiv:2603.12769v2 Announce Type: replace Abstract: Interactive Imitation Learning (IIL) typically relies on extensive human involvement for both offline demonstration and online interaction. Prior wo
arXiv:2610.12542v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) is often proposed for scheduling directed-acyclic-graph (DAG) workflows, yet most studies never run the comparison that c