Knowledge catalogue
arXiv:2605.22334v1 Announce Type: new Abstract: Correlation matrices are fundamental summaries of functional brain networks, yet standard analyses often treat entries independently, ignoring the curve
arXiv:2603.21610v2 Announce Type: replace Abstract: Compliance monitoring in rule-governed domains (tax administration, clinical protocol adherence, environmental regulation) faces three structural ob
arXiv:2605.22112v1 Announce Type: cross Abstract: We present a framework for detecting transient gamma-ray phenomena in a controlled environment by combining end-to-end simulations of the Fermi-LAT sk
arXiv:2605.22205v1 Announce Type: cross Abstract: Large language models increasingly require specialization across diverse domains, yet existing approaches struggle to balance multi-domain capacities
SpaceX successfully launched an updated version of its Starship V3 on May 22, 2026, the first test flight of the upgraded booster and upper stage designed as part of NASA's Artemis lunar program. The
🦔This one happened yesterday but is still worth flagging. Starbucks killed its AI-powered inventory counting tool after nine months in North American stores. The system used LiDAR sensors and cameras
arXiv:2605.22621v1 Announce Type: cross Abstract: The detection of previously unseen network attacks remains a major challenge for intrusion detection systems. Although supervised learning methods oft
Cybercriminal group TeamPCP is executing an unprecedented wave of software supply chain attacks, compromising hundreds of open source tools and breaching organizations through poisoned code. The incid
arXiv:2605.22132v1 Announce Type: new Abstract: Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones
This article discusses three AI infrastructure startups—Exa, Modal, and TurboPuffer—that have recently achieved unicorn status (valued at $1 billion or more). The piece likely covers their funding rou
arXiv:2605.21653v1 Announce Type: cross Abstract: AI text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary. On raw encoders before any task supervision, pr
Ollama has added MLX support for Qwen3.5 and Gemma 4 , with both MLX and NVFP4 quantization variants available for these models. There have been issues with broken Qwen3.6 NVFP4 generation on Ollama ,
arXiv:2605.21224v1 Announce Type: cross Abstract: As a rapidly emerging interdisciplinary field that intrinsically integrates microwave and photonics, microwave photonics (MWP) provides disruptive sol
arXiv:2605.21688v1 Announce Type: new Abstract: Autonomous contact-based micromanipulation is challenging because surface and interfacial interactions at the microscale are difficult to model accurate
arXiv:2602.08023v3 Announce Type: replace-cross Abstract: Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objec
arXiv:2605.21964v1 Announce Type: new Abstract: Computational imaging enables compact infrared systems, but deep-learning pipelines that combine image reconstruction and object detection often introdu
arXiv:2605.21984v1 Announce Type: cross Abstract: Static 'human data' faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from 'exper
arXiv:2503.17599v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated considerable potential in general practice. However, existing benchmarks and evaluation frameworks pr
arXiv:2605.21862v1 Announce Type: new Abstract: Chunked vision-language-action (VLA) policies predict multi-step robot controls, conditioning each update on the current visual observation alone. Yet r
arXiv:2605.20210v1 Announce Type: cross Abstract: Agentic AI systems - systems that can pursue goals through multi-step planning and tool-mediated action with limited direct supervision - are moving f
arXiv:2605.22258v1 Announce Type: new Abstract: Large language models (LLMs) require robust toxicity evaluation beyond explicit wording. This setting remains underexplored in Chinese, where toxicity m
arXiv:2605.22064v1 Announce Type: new Abstract: Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B,
Disaggregated infrastructure is displacing the all-in-one data center stack — and the economics of AI are making that reality impossible to ignore. The vast majority of enterprise data still resides o
arXiv:2605.22272v1 Announce Type: cross Abstract: Whole-body Humanoid-Object Interaction (HOI) is bottlenecked by the scarcity of high-fidelity 3D data. While video generative priors offer a promising
arXiv:2605.21935v1 Announce Type: new Abstract: Safe manipulation-oriented navigation for humanoid robots requires scene memory that remains reliable under locomotion-induced perceptual distortion, en
arXiv:2605.21914v1 Announce Type: new Abstract: This paper presents a non-contact approach for vibration-based structural damage detection using an autonomous and customized cost-effective unmanned ae
NuExtract3 is a unified 4B vision-language reasoning model for document understanding that combines structured information extraction with image-to-Markdown conversion, suitable for OCR and RAG prepro
Open-source AI agents are changing software development, empowering both developers and citizen builders alike in a domain once reserved for professional engineers. But the influx of agents now spread
arXiv:2603.20405v2 Announce Type: replace-cross Abstract: We report on an experiment in which Claude Opus~4.6, equipped with a suite of Model Context Protocol (MCP) tools for the Rocq proof assistant,
arXiv:2605.22591v1 Announce Type: new Abstract: Frozen Vision Foundation Models (VFMs) with lightweight classification heads are increasingly used in medical imaging because they offer efficient and r
arXiv:2509.23582v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for image generation, demonstrating superior scalability and performance
arXiv:2605.21788v1 Announce Type: new Abstract: Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VL
arXiv:2605.21168v1 Announce Type: new Abstract: Safety-critical scenarios are central to evaluating autonomous driving systems, yet their rarity in naturalistic logs makes simulation-based stress test
arXiv:2605.22693v1 Announce Type: new Abstract: Autonomous robot teams navigating partially known environments face costly backtracking when ground robots encounter blocked roads that are only reveale
arXiv:2605.22633v1 Announce Type: new Abstract: The Python robotics ecosystem faces a challenge: while many libraries exist for rigid body transformations, few are both lightweight and mathematically
New York Times: Sources: WH approved a $9B request to acquire advanced AI chips for spy agencies; Anthropic is finalizing a classified contract for NSA to keep using its tools — The C.I.A. and N.S.A.
arXiv:2605.22536v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pr
This article argues that specialized AI models often outperform larger, general-purpose models for specific use cases, challenging the common procurement assumption that bigger is always better. It li
arXiv:2605.22564v1 Announce Type: new Abstract: Today, tool-calling agents are commonly evaluated or tested on static datasets of execution traces, including input commands, agent responses, and assoc
Bitwarden acknowledges Nous Research for collaboration on security initiatives that extend to AI agents, emphasizing inclusive security practices. The post suggests a partnership or joint effort betwe
arXiv:2601.05106v4 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strengths across diverse domains. However, achieving strong performance across these domains with a singl
arXiv:2511.02014v2 Announce Type: replace Abstract: The detection of Protected Health Information (PHI) in medical imaging is critical for safeguarding patient privacy and ensuring compliance with reg
arXiv:2605.22493v1 Announce Type: cross Abstract: Behavioral cloning becomes difficult when the same observation admits several valid actions. We study this problem for action-chunking policies and sh
arXiv:2605.21313v1 Announce Type: new Abstract: Deep neural networks have achieved impressive performance on a variety of tasks, but their brittleness to distributional shifts remains a significant ba
arXiv:2605.20530v1 Announce Type: cross Abstract: Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but the benchmarks used to evalu
arXiv:2605.21481v1 Announce Type: cross Abstract: Recent advances in artificial intelligence (AI) have accelerated the growth of both human-authored and AI-generated research outputs, placing increasi
arXiv:2605.20237v1 Announce Type: new Abstract: We present a lightweight appearance adapter for Stable Diffusion that enables controllable and consistent anime character generation under diverse editi
Another win for open-source robotics! 🔥 @huggingface just released a fully open-source humanoid robot, and you can build one for $2,500. I'm a huge advocate of open-source in robotics space. Why? Robo
arXiv:2605.21214v1 Announce Type: new Abstract: Reinforcement learning (RL) often exhibits high variance across training runs, leading to unreliable performance and posing a major challenge to deploym
arXiv:2605.20337v1 Announce Type: new Abstract: How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into hi
arXiv:2602.03209v2 Announce Type: replace Abstract: Autonomous field robots operating in unstructured environments require robust perception to ensure safe and reliable operations. Recent advances in
arXiv:2605.20551v1 Announce Type: new Abstract: Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art meth
arXiv:2602.13485v2 Announce Type: replace Abstract: Networks of modern industrial systems are increasingly monitored by distributed sensors, where each system comprises multiple subsystems generating
arXiv:2605.20892v1 Announce Type: new Abstract: Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-qu
arXiv:2605.20727v1 Announce Type: new Abstract: Deep neural networks (DNNs) experience significant performance degradation when processing noisy labels, primarily due to overfitting on mislabeled data
arXiv:2605.20896v1 Announce Type: cross Abstract: Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft in
arXiv:2605.20469v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used for medical image interpretation, yet they frequently hallucinate, generating clinically plausible b
arXiv:2603.26539v2 Announce Type: replace Abstract: How does the extent to which a model is open or closed impact the scientific inferences that can be drawn from research that involves it? In this pa
if you work across multiple machines, highly recommend using Grok Build with its subagents to manage SSH tunnels and interact with tmux. We are working on making this experience more native, think of
arXiv:2605.20595v1 Announce Type: new Abstract: Dense low-altitude aerial operations require more than pre-flight route coordination and last-resort collision avoidance. Once aircraft are airborne, di