Knowledge catalogue
arXiv:2510.21891v2 Announce Type: replace-cross Abstract: To deploy large language models (LLMs) in high-stakes application domains that require substantively accurate responses to open-ended prompts,
arXiv:2608.08066v1 Announce Type: new Abstract: Motion deblurring has achieved remarkable progress with deep learning, yet pre-trained deblurring models often suffer from performance degradation in re
arXiv:2608.08585v1 Announce Type: new Abstract: Event cameras, with high temporal resolution, high dynamic range, and asynchronous sensing characteristics, have shown great potential for dense 3D reco
arXiv:2403.09752v4 Announce Type: replace-cross Abstract: The Internet of Medical Things transcends traditional medical boundaries, enabling a transition from reactive treatment to proactive preventio
arXiv:2608.08281v1 Announce Type: new Abstract: Recently, Large Language Models (LLMs) have shown considerable capability for situational understanding, reasoning, and decision making in different dom
arXiv:2608.09048v1 Announce Type: new Abstract: Deep learning-based building footprint extraction from high-resolution imagery often produces topologically inconsistent vectors unfit for direct GIS da
arXiv:2608.08010v1 Announce Type: cross Abstract: Time series forecasting (TSF) plays an important role in a wide range of real-world applications. Recently, time series foundation models (TSFMs), pre
arXiv:2608.08056v1 Announce Type: new Abstract: Medical data, by its nature, exhibit a high degree of heterogeneity on multiple levels ranging from (a) different modalities like images, text and time
arXiv:2608.09483v1 Announce Type: new Abstract: Recently, tensor-based physics-informed neural networks (T-PINNs) have received increasing attention. However, existing T-PINNs still face a fundamental
ONESTRUCTION, with technical advisory from the AWS Generative AI Innovation Center, built Ishigaki-IDS, a foundation model specialized for construction and BIM workflows. This architectural case study
arXiv:2608.09433v1 Announce Type: cross Abstract: In regulated domains such as finance, a model that cannot be explained cannot be deployed, yet many interpretable classifiers defeat their own purpose
arXiv:2608.08430v1 Announce Type: cross Abstract: Virtual cells employ machine learning models to simulate and predict cellular behaviors, serving as a critical computational framework for investigati
arXiv:2608.08825v1 Announce Type: cross Abstract: Foundation models for time series forecasting demonstrate impressive zero-shot generalization but often underperform on specialized domains such as hi
arXiv:2608.09073v1 Announce Type: new Abstract: Image-goal navigation with latent world models requires not only accurate future prediction, but also a planning cost that reliably ranks candidate acti
arXiv:2511.20849v2 Announce Type: replace-cross Abstract: We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed
Leveraging the frontier ecosystem We work with neolabs like @trajectorylabs and @EngramLab and inference + post-training infra providers like @baseten, @FireworksAI_HQ, and @appliedcompute to post-tra
arXiv:2602.23290v2 Announce Type: replace Abstract: Extracting routable road networks from satellite imagery requires accurate topology recovery beyond pixel-level segmentation. Recent methods decompo
arXiv:2603.04568v2 Announce Type: replace Abstract: Many real-world computer vision tasks, such as depth completion, must handle inputs with arbitrarily shaped regions of missing or invalid data. For
arXiv:2608.09405v1 Announce Type: new Abstract: Diffusion-based super-resolution (SR) achieves strong perceptual quality but requires costly iterative denoising. Existing one-step distillation methods
arXiv:2608.07946v1 Announce Type: cross Abstract: Text-to-SQL benchmarks ship schemas whose column names already say what the columns mean. Production warehouses are the inverse: cryptic identifiers,
arXiv:2411.16758v4 Announce Type: replace Abstract: The creation of 3D human avatars from multi-view videos is a significant yet challenging task in computer vision. However, existing techniques rely
arXiv:2608.09782v1 Announce Type: new Abstract: This paper presents a review of the NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge. The objective of the competition was to merge a set of
arXiv:2608.09016v1 Announce Type: cross Abstract: Node ranking is a fundamental problem in graph information retrieval, measuring the relative importance of nodes and supporting a wide range of applic
arXiv:2608.09373v1 Announce Type: new Abstract: Real-world image super-resolution (Real-ISR) aims to reconstruct high-quality (HQ) images from low-quality (LQ) inputs subject to diverse real-world deg
arXiv:2512.20070v2 Announce Type: replace Abstract: Recent advances in learned image codecs have extended from human perception toward machine perception However, progressive image compression with fi
arXiv:2608.07705v1 Announce Type: new Abstract: Clinical foundation models trained on large-scale patient data are increasingly used for decision support, screening, and public health. As deployment e
arXiv:2603.10937v2 Announce Type: replace Abstract: The use of synthetic data has become increasingly popular as a privacy-preserving alternative to sharing real datasets, especially in sensitive doma
arXiv:2601.10168v3 Announce Type: replace-cross Abstract: Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet
arXiv:2608.09222v1 Announce Type: new Abstract: Inverse decision modeling infers latent properties of decision processes from observed behavior, but existing formulations rely primarily on action traj
arXiv:2608.09846v1 Announce Type: new Abstract: This paper presents a methodological framework for real-time climate risk assessment using data-driven nowcasting techniques to enhance supply chain res
arXiv:2608.09492v1 Announce Type: new Abstract: World Action Models (WAMs) jointly predict future actions and the evolution of the environment. At each inference, a WAM generates a chunk of actions an
arXiv:2608.08075v1 Announce Type: cross Abstract: Most video-retrieval systems assume a bounded corpus and return ranked files or timestamps. Agents operating over cameras, screens, streams, and archi
arXiv:2608.08839v1 Announce Type: cross Abstract: World-Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation. However, most existing WAMs generate future videos and actio
arXiv:2608.08884v1 Announce Type: new Abstract: As collaborative robots have entered domains such as manufacturing, agriculture, and healthcare, programming or adapting robot behavior typically requir
Bloomberg: Singapore raises its 2026 GDP growth forecast to 4.5%-5.5% from 2%-4%, citing stronger-than-expected global AI investment and improved external demand — Singapore upgraded its 2026 economic
Data interoperability is quickly becoming a practical requirement for companies trying to move artificial intelligence into production. Picking the right model or adding computing capacity is only par
arXiv:2608.08873v1 Announce Type: new Abstract: Facial Emotion Recognition (FER) is an important task that has significant implications across various fields such as biometrics, health, and human-comp
arXiv:2608.09556v1 Announce Type: new Abstract: Multi robot teams performing cooperative transportation face a fundamental challenge: maintaining stable control while keeping communications efficient.
arXiv:2608.08806v1 Announce Type: new Abstract: Objective. Healthcare IT is usually organized by the technologies it adopts. We instead organize it by the unit of information a system makes computable
arXiv:2608.08508v1 Announce Type: new Abstract: This paper presents doctoral research on adaptive video super-resolution and perceptual quality modeling under real-world conditions. Existing video sup
arXiv:2608.07630v1 Announce Type: new Abstract: We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty
arXiv:2608.07534v1 Announce Type: cross Abstract: Ultraconstructive Model Theory (UCMT) replaces idealized satisfaction, at finite compu- tational scale, by bounded adversarial survival. A finite part
arXiv:2608.09356v1 Announce Type: new Abstract: Closely related languages written in different scripts expose little surface overlap to multilingual models, limiting cross-lingual transfer. We compare
arXiv:2608.07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collect
arXiv:2608.09110v1 Announce Type: new Abstract: Reconstructing 3D shapes from a single image remains a fundamental yet challenging problem in computer vision. Traditional monocular 3D generation pipel
arXiv:2608.09122v1 Announce Type: cross Abstract: The localized depiction of perceptual quality has long been a crucial, yet underexplored, challenge in image quality assessment (IQA). Existing approa
arXiv:2608.06801v1 Announce Type: new Abstract: Physical adversarial attacks against person detectors have evolved from localized patches to full-body textures. However, achieving both visual naturaln
arXiv:2608.07359v1 Announce Type: cross Abstract: The proliferation of AI-generated music in broadcast media raises concerns about transparency and fair compensation, but reliable detection under real
arXiv:2608.06729v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially ob
arXiv:2608.06849v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by quadratic attention computation and growing KV-cache costs. Existing sparse attention and KV-compression
arXiv:2608.06501v1 Announce Type: new Abstract: Creative capabilities of MLLMs matter in design, communication, education, and human--AI collaboration, yet remain difficult to evaluate because explici
arXiv:2608.07256v1 Announce Type: new Abstract: Canonicalizing 3D object orientation is fundamental to 3D understanding and analysis. Existing approaches often rely on geometric cues, although 3D cano
arXiv:2608.06952v1 Announce Type: cross Abstract: Impersonation is a fundamental security threat in face recognition systems (FRSs). While the security of FRSs has been challenged by various attack ve
arXiv:2608.06516v1 Announce Type: cross Abstract: Lightweight connectors make frozen multimodal encoders composable at the representation level. Deployment exposes a second problem at the level of tas
arXiv:2608.06640v1 Announce Type: cross Abstract: The widespread integration of AI coding assistants offers undeniable boosts to engineering velocity. Yet, recent studies point to a growing trade-off,
arXiv:2608.07364v1 Announce Type: new Abstract: Contribution: This paper presents a six-phase AI-assisted instructional design architecture based on the Curriculum as Code paradigm, integrating Genera
Cybersecurity is the ultimate venue for real-world RL: 2p0s game, sim-able, clean reward signals Cybersecurity in a year will be fought between swarms of good and bad playing an exceptionally fast, co
arXiv:2511.12738v2 Announce Type: replace Abstract: Vision Language Models (VLMs) mix visual tokens and text tokens. A puzzling issue is the fact that visual tokens most related to the query receive l
arXiv:2511.09432v2 Announce Type: replace Abstract: Machine learning (ML) models achieve remarkable performance but remain hard to interpret due to their scale and complexity. In particular, their act
arXiv:2608.07285v1 Announce Type: cross Abstract: AI-generated music is increasingly used at the stem level, with producers integrating synthetic drums, basslines, or vocals alongside human-performed