Knowledge catalogue
arXiv:2603.05140v2 Announce Type: replace-cross Abstract: We characterise the computational power of recurrent graph neural networks (GNNs) in terms of arithmetic circuits over the real numbers. Our n
arXiv:2605.01450v1 Announce Type: new Abstract: Recent frameworks like ToFu and TEMPEH provide an automated alternative to classical registration pipelines by predicting 3D meshes in dense semantic co
arXiv:2605.02627v1 Announce Type: new Abstract: Explicit reconstruction constraints derived from the decoupled representation are further imposed to suppress abnormal channel amplification and chromat
arXiv:2506.19133v3 Announce Type: replace Abstract: Euclidean representations distort data with intrinsic non-Euclidean structure. While Riemannian representation learning offers a solution by embeddi
arXiv:2605.00869v1 Announce Type: cross Abstract: Device-free fall detection utilizing WiFi Channel State Information (CSI) has emerged as a promising, privacy-preserving solution for elderly health m
arXiv:2605.00888v1 Announce Type: new Abstract: Wearable sensor-based human gait analysis holds great promise in healthcare, rehabilitation, clinical diagnosis and monitoring, and sports activities. S
arXiv:2605.02611v1 Announce Type: new Abstract: We consider selective classification with abstention in the fixed-pool (or transductive) setting, where the unlabeled pool is given beforehand and only
arXiv:2602.13833v2 Announce Type: replace Abstract: Generalizing tool manipulation requires both semantic planning and precise physical control. Modern generalist robot policies, such as Vision-Langua
arXiv:2605.01144v1 Announce Type: new Abstract: Whole-slide images (WSIs) present a fundamental challenge for computational pathology due to their extreme resolution, multi-scale heterogeneity, and th
ServiceNow Inc. today unveiled a broad expansion of its artificial intelligence platform, stressing governance, security and autonomous execution as foundational requirements for enterprise AI adoptio
arXiv:2605.01924v1 Announce Type: new Abstract: Simultaneous perception of 2D objects in perspective view and 3D objects in Bird's Eye View (BEV) is challenging for multi-camera autonomous driving. Ex
arXiv:2510.24332v3 Announce Type: replace-cross Abstract: Purpose: Surgical scene understanding is key to advancing computer-aided and intelligent surgical systems. Current approaches predominantly re
arXiv:2605.00887v1 Announce Type: new Abstract: We propose SparseContrast, a new framework that merges dynamic sparse attention with contrastive learning for medical imaging, with a focus on chest X-r
arXiv:2605.00934v1 Announce Type: new Abstract: We introduce Analytic-CPD, a structured analytic variant of coherent point drift for non-rigid point set registration. The method retains the CPD poster
arXiv:2604.24920v2 Announce Type: replace-cross Abstract: Agentic systems increasingly act with user secrets for APIs, messaging platforms, and cloud services. Today's bearer-secret interfaces impleme
arXiv:2605.02201v1 Announce Type: new Abstract: Airborne Laser Scanning (ALS) can collect point clouds across large areas, enabling large-scale forest inventory. However, ALS point clouds are sparse a
arXiv:2603.20143v2 Announce Type: replace Abstract: Building facade defect inspection is fundamental to structural health monitoring and sustainable urban maintenance, yet it remains a formidable chal
arXiv:2605.02708v1 Announce Type: cross Abstract: Single-view RGB object pose estimators have reached a level of precision and efficiency that makes them good candidates for vision-based robot control
arXiv:2603.03235v2 Announce Type: replace-cross Abstract: Selecting the number of clusters remains a fundamental challenge in unsupervised learning. Existing approaches typically focus on identifying
arXiv:2603.05228v3 Announce Type: replace Abstract: Mechanistic interpretability typically relies on post-hoc analysis of trained networks. We instead adopt an interventional approach: testing hypothe
arXiv:2605.01537v1 Announce Type: new Abstract: Isolated word meanings are inherently uncertain. This uncertainty reduces when they are combined and anchored in context. We propose that grammar compre
arXiv:2605.01705v1 Announce Type: cross Abstract: Jamming attacks are proliferating and pose a significant threat to the security of 5G and beyond networks. These attacks target 5G radio frequency (RF
arXiv:2605.01928v1 Announce Type: new Abstract: Neural networks increasingly embed non-differentiable components (spiking neurons, quantized layers, discrete routing, blackbox simulators, etc.) where
arXiv:2605.01234v1 Announce Type: new Abstract: We present TT4D, a large-scale, high-fidelity table tennis dataset. It provides 140+ hours of reconstructed singles and doubles gameplay from monocular
arXiv:2605.02765v1 Announce Type: cross Abstract: LLMs are increasingly used for end-user task planning, yet their black-box nature limits users' ability to ensure reliability and control. While recen
arXiv:2602.02056v2 Announce Type: replace-cross Abstract: Ultrafast online learning is essential for high-frequency systems, such as controls for quantum computing and nuclear fusion, where adaptation
arXiv:2605.02762v1 Announce Type: new Abstract: Online mapping and end-to-end (E2E) planning in autonomous driving remain largely sensor-centric, leaving rich map priors, including HD/SD vector maps,
arXiv:2604.04934v2 Announce Type: replace Abstract: We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images,
arXiv:2605.02746v1 Announce Type: new Abstract: Accurate histological differentiation between adenocarcinoma (ADC) and squamous cell carcinoma (SCC) is critical for personalized treatment in non-small
arXiv:2605.01101v1 Announce Type: cross Abstract: This paper develops Virtual Speech Therapist (VST), an intelligent agent-based platform that streamlines stuttering assessment and delivers customized
arXiv:2605.00875v1 Announce Type: new Abstract: Technical traders have long relied on visual analysis of candlestick charts to identify market patterns and predict price movements. While deep learning
Want to run the same harness across multiple interfaces? Try ACP. Deep Agents ships with it out of the box. open-weight LLMs have come a long way on agent tasks! but the harness you wrap them in matte
Z-Image Turbo upscaling involves using latent upscaling followed by a second sampling step to refine images after the initial upscale. Common artifacts in Z-Image Turbo generation can result from usin
arXiv:2605.01787v1 Announce Type: cross Abstract: Autonomous navigation and obstacle avoidance remain a core challenge of modern Unmanned Aerial Vehicles (UAVs). While traditional control methods stru
arXiv:2605.00650v1 Announce Type: new Abstract: Fine-tuning LLMs is necessary for various dedicated downstream tasks, but classic backpropagation-based fine-tuning methods require substantial GPU memo
arXiv:2605.00171v1 Announce Type: cross Abstract: In this paper, we study norm-based regularization methods for neural networks. We compare existing penalization approaches and introduce two regulariz
This article from Latent Space likely explores the distinction between AI systems designed for general-purpose utility versus those optimized for specific alternative applications or use cases. The pi
arXiv:2605.00270v1 Announce Type: new Abstract: Standard methods for aggregating natural language judgments, such as majority voting, often fail to produce logically consistent results when applied to
arXiv:2605.00058v1 Announce Type: cross Abstract: The primary goal of Design Verification (DV) is to ensure that a proposed chip design implementation (either in code, or physical form) exactly matche
llama.cpp enables LLM inference in C/C++ , and release b9014 represents a build revision or commit snapshot from the llama.cpp repository on GitHub. This release would include bug fixes, feature impro
Release b9016 is a build of llama.cpp, an LLM inference implementation in C/C++ . This build designation represents a specific intermediate version in the project's development cycle, similar to other
b9019 is a release of llama.cpp, a C/C++ implementation for LLM inference. As a release tag from the ggml-org/llama.cpp repository, it represents a specific commit or version of the project that inclu
B9022 is a release of llama.cpp created on May 4, 2026, with commit d8794ee signed with GitHub's verified signature. The llama.cpp project is the main playground for developing new features for the gg
b9025 is a release from llama.cpp, a C/C++ project for LLM inference . The release uses a build numbering system for intermediate versions of the library. As a llama.cpp release, it likely includes up
Banger paper from Meta FAIR. They introduce Autodata, an agentic data scientist that builds high-quality training and evaluation data autonomously. The headline result: on a CS research QA task, an Ag
arXiv:2605.00545v1 Announce Type: new Abstract: Inferring cellular trajectories from destructive snapshots is complicated by the challenges of stochasticity and non-conservative mass dynamics such as
arXiv:2604.00070v2 Announce Type: replace-cross Abstract: Complete and high-quality multi-modal Magnetic Resonance Imaging (MRI) is essential for accurate neuro-oncological assessment, as each contras
arXiv:2605.00029v1 Announce Type: cross Abstract: Traditional glass-based optics are typically optimized for narrow spectral bands, such as the visible (400-700nm) or shortwave infrared (1000-1800nm).
arXiv:2605.00649v1 Announce Type: new Abstract: Assigning one of K options to each of N groups under a total cost budget is a recurring problem in machine learning, appearing in mixed-precision quanti
Today, Amazon SageMaker AI introduces capacity aware instance pool for new and existing inference endpoints. You define a prioritized list of instance types, and SageMaker AI automatically works throu
arXiv:2602.02443v2 Announce Type: replace Abstract: Test-time scaling improves LLM performance by generating multiple candidate solutions, yet token-level sampling requires temperature tuning that tra
arXiv:2603.01267v2 Announce Type: replace-cross Abstract: We show that the factor graph and certifiable estimation paradigms, which have thus far been treated as essentially independent in the literat
arXiv:2507.01946v2 Announce Type: replace-cross Abstract: Biological function arises through the dynamical interactions of multiple subsystems, including those between brain areas, within gene regulat
arXiv:2605.00460v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully
arXiv:2510.01948v2 Announce Type: replace Abstract: Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world rob
arXiv:2503.19034v2 Announce Type: replace Abstract: We propose SW-Guidance, a training-free approach for image generation conditioned on the color distribution of a reference image. While it is possib
arXiv:2605.00119v1 Announce Type: new Abstract: There is a significant gap in evaluating cultural reasoning in LLMs using conversational datasets that capture culturally rich and dialectal contexts. M
DeepSeek V3 and R1 API free tier includes 500M tokens per month , indicating free access remains available for API users. The search results focus on a major service outage in March 2026 and the recen
arXiv:2405.13901v4 Announce Type: replace Abstract: Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initializ
arXiv:2605.00675v1 Announce Type: new Abstract: Medical imaging datasets are often characterized by extreme class imbalances, where rare pathologies are significantly underrepresented compared to comm