Knowledge catalogue
arXiv:2604.13951v1 Announce Type: new Abstract: This study evaluates colorectal risk factors and compares classical models against Quantum Neural Networks (QNNs) for anastomotic leak prediction. Analy
arXiv:2604.13292v1 Announce Type: new Abstract: Autonomous drone delivery systems are rapidly advancing, but ensuring safe and reliable package drop-offs remains highly challenging in cluttered urban
arXiv:2604.13861v1 Announce Type: new Abstract: This paper develops a unified Markov Decision Process (MDP) framework for optimising two recurring in-match decisions in T20 cricket namely batting orde
arXiv:2604.14089v1 Announce Type: new Abstract: We present UMI-3D, a multimodal extension of the Universal Manipulation Interface (UMI) for robust and scalable data collection in embodied manipulation
arXiv:2604.13687v1 Announce Type: cross Abstract: Glitches frequently contaminate data in gravitational-wave detectors, complicating the observation and analysis of astrophysical signals. This work in
arXiv:2604.13318v1 Announce Type: cross Abstract: Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with lon
We’ve also added support for 90+ plugins in Codex, giving it more ways to gather context and take action across the tools you already use for docs, project management, code review, creative work, depl
arXiv:2604.13055v1 Announce Type: new Abstract: Today's evolving labor markets rely increasingly on recommender systems for hiring, talent management, and workforce analytics, with natural language pr
arXiv:2512.09953v2 Announce Type: replace-cross Abstract: Machine unlearning aims to remove the influence of specific data points from a trained model to satisfy privacy, copyright, and safety require
arXiv:2604.12765v1 Announce Type: new Abstract: Marker-based motion capture (MoCap) systems have long been the gold standard for accurate 4D human modeling, yet their reliance on specialized hardware
arXiv:2604.12497v1 Announce Type: new Abstract: Large language models (LLMs) can generate survey responses at low cost, but their reliability varies substantially across questions and is unknown befor
arXiv:2603.18104v3 Announce Type: replace Abstract: Prevailing AI training infrastructure assumes reverse-mode automatic differentiation over IEEE-754 arithmetic. The memory overhead of training relat
An experimental voice pipeline for the Agents SDK enables real-time voice interactions over WebSockets. Developers can now build agents with continuous STT and TTS in just ~30 lines of server-side cod
arXiv:2604.11957v1 Announce Type: cross Abstract: Self-driving laboratories promise to accelerate materials discovery. Yet current automated solid-state synthesis platforms are limited to ambient cond
arXiv:2603.21011v2 Announce Type: replace-cross Abstract: Finite element (FE) analysis guides the design and verification of nearly all manufactured objects. It is at the core of computational enginee
arXiv:2604.11839v1 Announce Type: cross Abstract: Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A
arXiv:2511.22364v2 Announce Type: replace-cross Abstract: Open-vocabulary mobile manipulation (OVMM) requires robots to follow language instructions, navigate, and manipulate while updating their worl
arXiv:2604.12307v1 Announce Type: new Abstract: The proliferation of highly realistic AI-Generated Image (AIGI) has necessitated the development of practical detection methods. While current AIGI dete
arXiv:2604.12305v1 Announce Type: cross Abstract: Pneumonia remains a leading cause of childhood mortality worldwide, with a heavy burden in low-resource settings such as Bangladesh where radiologist
arXiv:2604.12525v1 Announce Type: new Abstract: Recent advanced diffusion methods typically derive strong generative priors by scaling diffusion transformers. However, scaling fails to generalize when
arXiv:2604.12411v1 Announce Type: new Abstract: Segmentation models based on deep neural networks demonstrate strong generalization for medical image segmentation. However, they often exhibit overconf
arXiv:2604.12031v1 Announce Type: new Abstract: Worm-inspired robots provide an effective locomotion strategy for constrained environments by combining cyclic body deformation with alternating anchori
arXiv:2604.12781v1 Announce Type: new Abstract: Recently, detecting AI-generated images produced by diffusion-based models has attracted increasing attention due to their potential threat to safety. A
arXiv:2603.27306v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been proposed as supervisory agents for spacecraft operations, but existing approaches rely on static prompt
arXiv:2604.12447v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models inherit rich world knowledge from vision-language backbones and acquire executable skills via action demonstrations.
A community-built framework that layers on top of Ollama to transform any spare PC into a fully private, locally-run AI assistant inspired by Iron Man's JARVIS, featuring voice interaction, 29 built-i
arXiv:2604.12440v1 Announce Type: cross Abstract: Real-world industrial inspection requires not only localizing defects, but also explaining them in natural language and generating controlled defect e
arXiv:2604.12311v1 Announce Type: cross Abstract: The emergence of vibe coding, a paradigm where non-technical users instruct Large Language Models (LLMs) to generate executable codes via natural lang
arXiv:2601.10398v3 Announce Type: replace Abstract: In LLM-based text-to-SQL systems, unanswerable and underspecified user queries may generate not only incorrect text but also executable programs tha
Danish agentic artificial intelligence startup Leapwork ApS has announced the launch of its fully automated Continuous Validation Platform, aiming to help enterprises keep up with the velocity of gene
arXiv:2604.12108v1 Announce Type: cross Abstract: Integration testing is critical for the quality and reliability of complex software systems. However, diagnosing their failures presents significant c
arXiv:2604.12218v1 Announce Type: new Abstract: System log anomaly detection is critical for maintaining the reliability of large-scale software systems, yet traditional methods struggle with the hete
arXiv:2604.12096v1 Announce Type: new Abstract: On online advertising platforms, newly introduced promotional ads face the cold-start problem, as they lack sufficient user feedback for model training.
Load balancing and scaling LLM serving involves distributing inference requests across multiple model instances or GPUs to prevent bottlenecks and ensure consistent response times under varying traffi
arXiv:2604.12301v1 Announce Type: cross Abstract: We present a systematic measurement study of seven tactics for reducing cloud LLM token usage when a small local model can act as a triage layer in fr
Vercel has introduced logs filtering functionality for Vercel Workflows, allowing users to more efficiently search and narrow down log output within their workflow executions. This feature enables dev
arXiv:2603.00137v2 Announce Type: replace-cross Abstract: Knowledge tracing (KT) models are commonly evaluated by training on early interactions from all students and testing on later responses. While
arXiv:2508.12260v5 Announce Type: replace Abstract: Infectious disease forecasting in novel outbreaks or low-resource settings is hampered by the need for large disease and covariate data sets, bespok
arXiv:2604.11868v1 Announce Type: new Abstract: While medical Vision-Language models (VLMs) achieve strong performance on tasks such as tumor or organ segmentation and diagnosis prediction, their opaq
Meta Platforms Inc. has announced a new deal with Broadcom Inc., extending a partnership that already sees the two companies work together on the design of the social media giant’s in-house artificial
Meta Platforms Inc. today announced a new deal with Broadcom Inc., extending a partnership that already sees the two companies work together on the design of the social media giant’s in-house artifici
Today, we’re announcing U.S. and EU multi-region endpoints for Claude on Vertex AI are available in public preview. By pooling capacity across multiple regions, these endpoints dynamically route reque
arXiv:2604.11854v1 Announce Type: cross Abstract: End-to-End (E2E) autonomous driving models are usually trained and evaluated with a fixed ego-vehicle, even though their driving policy is implicitly
arXiv:2604.12076v1 Announce Type: cross Abstract: The Identifiable Victim Effect (IVE) - the tendency to allocate greater resources to a specific, narratively described victim than to a statistically
arXiv:2505.23209v3 Announce Type: replace Abstract: Model merging has emerged as an efficient method to combine multiple single-task fine-tuned models. The merged model can enjoy multi-task capabiliti
Simon Last and Sarah Sachs from Notion discuss their extensive experimentation with AI-native product development, including rebuilding core Notion features five times as capabilities evolved and inte
OllamaGPT is a self-hosted, ChatGPT-style web interface that runs locally using Ollama as its backend LLM engine, requiring no API keys or external services. It is designed for developers and power us
arXiv:2410.04960v5 Announce Type: replace Abstract: The Segment Anything Model (SAM) is a foundational model for image segmentation tasks, known for its strong generalization across diverse applicatio
arXiv:2504.02169v3 Announce Type: replace-cross Abstract: We study the geometry of Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves in binary classification problems. The key f
arXiv:2604.13006v1 Announce Type: cross Abstract: Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness when trivially constrained? We show
Orders of Magnitude No orbital launch provider but SpaceX has ever put even 1,000 satellites in orbit; SpaceX has launched >11,000. What has @elonmusk said about this unprecedented accomplishment? “It
arXiv:2604.12526v1 Announce Type: cross Abstract: Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on e
arXiv:2604.12852v1 Announce Type: new Abstract: Collaborative transport requires robots to infer partner intent through physical interaction while maintaining stable loco-manipulation. This becomes pa
arXiv:2604.00136v2 Announce Type: replace-cross Abstract: Multi-model LLM serving operates in a non-stationary, noisy environment: providers revise pricing, model quality can shift or regress without
arXiv:2604.12239v1 Announce Type: new Abstract: Accurate inter-vehicle distance estimation is a cornerstone of Advanced Driver Assistance Systems (ADAS) and autonomous driving. While LiDAR and radar p
arXiv:2604.12348v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training without sharing raw data, offering a promising path toward privacy preserving artificial in
arXiv:2604.11943v1 Announce Type: cross Abstract: An OS kernel that runs LLM inference internally can read logit distributions before any text is generated -- and act on them as a governance primitive
Project Think is Cloudflare's initiative to develop next-generation AI agents built on its global network infrastructure, leveraging tools like Workers AI, Durable Objects, and the Workers platform to
proud to see @excalidraw evangelism catching on at cog the insight here is more general than bugchecking: - All Engineering is about making tradeoffs - AI Engineering is about pushing AI Pareto Fronti
arXiv:2603.29977v2 Announce Type: replace-cross Abstract: Multimodal deep learning for cancer prognosis is commonly assumed to benefit from synergistic cross-modal interactions, yet this assumption ha