Knowledge catalogue
arXiv:2606.11045v1 Announce Type: new Abstract: Reusing a held-out benchmark adaptively should, in principle, invite overfitting. Yet benchmark-driven machine learning (ML) has produced surprisingly l
arXiv:2606.10106v1 Announce Type: cross Abstract: The term agent harness now circulates widely in software engineering with generative artificial intelligence. It names the layer that wraps a language
arXiv:2606.10267v1 Announce Type: cross Abstract: Hierarchical vision-language-action (Hi-VLA) systems have emerged as a promising paradigm for complex robot manipulation, by using high-level VLM plan
Claude Fable efficiently processes tokens at high speed when initiating workflows, demonstrating rapid token consumption during execution. This observation from Ethan Mollick highlights the computatio
arXiv:2606.10249v1 Announce Type: new Abstract: We examine whether graph neural network (GNN) design rules generalize across benchmark families by studying aggregator selection (sum, mean, max) on 24
arXiv:2606.10868v1 Announce Type: new Abstract: Long-horizon autoregressive forecasting of oscillatory physical signals, such as seismograms, gravitational-wave strain, and similar wavefields is limit
arXiv:2606.09932v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training. SFT
arXiv:2606.11009v1 Announce Type: new Abstract: Large language models are increasingly used to adapt math word problems for personalized learning at scale, but it remains an open question whether thos
arXiv:2606.09882v1 Announce Type: new Abstract: The paradigm of digital twin cities is shifting from coarse visual mapping toward more precise and actionable digitization of urban assets. However, exi
With SoftBank apparently struggling to get a margin loan against it’s OpenAI shares, it’s maybe time to repost this, from two years ago. The vast majority of my earlier worries remain: 9 reasons that
wooh https://x.com/shadcn/status/2064671802509410806?s=46 You have Claude Fable for only a few days. Here's how to make the most of it. Introducing /improve: use your most capable model to audit your
arXiv:2606.11042v1 Announce Type: new Abstract: Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely
arXiv:2606.11129v1 Announce Type: new Abstract: We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fid
Wrote up my initial impressions of Claude Fable 5 - it has a big model smell: slow, expensive and capable of crunching through pretty much everything I threw at it https://simonwillison.net/2026/Jun/9
arXiv:2606.10877v1 Announce Type: cross Abstract: Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturbing input features and measuring the resulting c
👇@zerohedge confirms what I said here and in my May 29 Marcus on AI newsletter. Tokenmaxxing RIP. This morning @zerohedge out with a report on the death of Tokenmaxxing 'Microsoft’s AI Chief added to
arXiv:2603.04125v2 Announce Type: replace Abstract: Few-Shot Action Recognition (FS-AR) has shown promising results but is often limited by a closed-set assumption that fails in real-world open-set sc
arXiv:2601.11541v2 Announce Type: replace-cross Abstract: To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Mode
arXiv:2606.08669v1 Announce Type: cross Abstract: Voice biometric systems face growing threats from spoofing attacks, yet the evaluation of detection models remains inconsistent across datasets. To in
arXiv:2606.07653v1 Announce Type: cross Abstract: Given the increased adoption of Vision Language Models (VLMs) in human-interactive settings, it is important that we evaluate how well these models ca
arXiv:2606.07789v1 Announce Type: new Abstract: Data stream mining is fundamentally challenged by concept drift, where distributional changes can degrade model performance. Despite the proliferation o
arXiv:2606.08093v1 Announce Type: new Abstract: Pathology is the cornerstone of modern medicine, where accurate decision-making relies heavily on evidence-based practices. While artificial intelligenc
arXiv:2606.08644v1 Announce Type: cross Abstract: To interpret context correctly and retrieve relevant information, large language models must bind entities to their attributes and update these bindin
arXiv:2510.26307v3 Announce Type: replace-cross Abstract: Anomaly detection is a critical task in cybersecurity, where identifying insider threats, access violations, and coordinated attacks is essent
A TIL on using http://agentsview.io to calculate token spending with Claude Fable 5 despite that model not yet being included in the AgentsView pricing database https://til.simonwillison.net/llms/agen
arXiv:2606.09653v1 Announce Type: new Abstract: Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions
arXiv:2606.07524v1 Announce Type: cross Abstract: The explosive growth of large language models (LLMs) has created a heterogeneous and poorly documented ecosystem, making systematic model comparison i
arXiv:2606.08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). By constructing a s
arXiv:2505.21457v2 Announce Type: replace-cross Abstract: Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant informatio
arXiv:2606.09734v1 Announce Type: cross Abstract: Training parameterised quantum circuits (PQCs) on quantum hardware is bottlenecked by the measurement cost of gradient estimation, which under the par
arXiv:2606.07665v1 Announce Type: cross Abstract: Transformer inference increasingly depends on specialized compiler and runtime support, but real model graphs still require semantic decisions about w
arXiv:2603.14342v2 Announce Type: replace-cross Abstract: Modern agricultural data is sourced from diverse platforms and spans multiple spatial scales, ranging from ground-level close-up photography t
arXiv:2606.09556v1 Announce Type: new Abstract: AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds. We test a different
arXiv:2606.09100v1 Announce Type: cross Abstract: Community detection is a fundamental problem in the analysis of complex networks. It has applications across social, biological, and financial domains
arXiv:2606.09447v1 Announce Type: new Abstract: We present AliyunConsoleAgent, a web agent framework for automated documentation verification in real-world cloud consoles. Major cloud platforms encomp
arXiv:2510.18428v4 Announce Type: replace Abstract: Optimization modeling underlies critical decision-making across industries, yet remains difficult to automate: natural-language problem descriptions
Also, I found that Hermes Agent + Nemotron 3 Ultra is a mighty combo! Excited to launch a new way to upskill with AI agents. This is how we are making it possible for anyone to learn to build with cod
arXiv:2606.07633v1 Announce Type: cross Abstract: Accurate classification of nuclei subtypes in histopathology images is critical for downstream tasks including tumor grading, immune infiltrate quanti
Anthropic just announced Claude Fable 5, a new AI model it said is the most powerful model it has ever made widely available. According to the company, Fable 5 'shows exceptional performance in softwa
Anthropic: Anthropic says Claude Fable 5 uses conservative safety classifiers that trigger a fallback to Claude Opus 4.8 in <5% of sessions, in areas like cybersecurity — Today we're launching Claude
Matthias Bastian / The Decoder: Anthropic says Fable 5 has invisible safeguards that use prompt modification, steering vectors, or PEFT to limit its effectiveness for building frontier LLMs — Key Poin
Rebecca Bellan / TechCrunch: Anthropic says Fable 5 is available on Pro, Max, Team, and seat-based Enterprise plans through June 22, after which using Fable 5 will require usage credits — Anthropic is
Derek B. Johnson / CyberScoop: Anthropic says red team tests of Fable 5 found no universal jailbreaks, and it will keep first- and third-party user traffic on Mythos-class models for 30 days — Claude
Anthropic PBC today introduced Claude Mythos 5 and Claude Fable 5, two large language models that it says outperform the competition across a wide range of benchmarks. The LLMs are derived from the Cl
arXiv:2606.08761v1 Announce Type: cross Abstract: W4A4 quantization promises full utilization of INT4 Tensor Cores, yet group dequantization overhead on CUDA Cores has driven existing systems to mixed
Joe Rossignol / MacRumors: Apple says 79% of all iPhones and 86% of iPhones released in the past four years were running iOS 26 as of June 7, vs. 82% and 88% for iOS 18 before WWDC 2025 — Apple has sh
arXiv:2606.08894v1 Announce Type: new Abstract: Reasoning Vision-Language Models (VLMs) achieve strong performance on complex multimodal tasks, but reliable real-world application requires handling vi
arXiv:2606.09648v1 Announce Type: cross Abstract: Multi-modal data management has emerged as a central research topic in the database community, spanning data integration, semantic query processing, a
arXiv:2606.08728v1 Announce Type: new Abstract: Mathematical reasoning has long served as a stringent test of machine intelligence; over the past decade, it has moved from a niche problem within NLP t
arXiv:2606.09634v1 Announce Type: cross Abstract: 3D object detection is the backbone of perception for automated vehicles (AV) and broader intelligent transportation systems applications. Long-range
arXiv:2606.08590v1 Announce Type: cross Abstract: Kubernetes incidents are diagnosed reliably only when a root-cause system's reported gains come from incident evidence rather than scenario-specific s
arXiv:2606.08381v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly released and deployed through opaque development and deployment pipelines, enabling model providers to i
Aujourd'hui, Cohere a annoncé un nouveau partenariat avec le gouvernement du Québec. Le Québec est depuis longtemps l'un des écosystèmes d'IA les plus importants au monde. Nous sommes fiers de collabo
arXiv:2606.07721v1 Announce Type: new Abstract: Objectives: Automatic data extraction from free-text radiology reports enables large-scale research, but few studies assessed the performance of large l
arXiv:2606.09682v1 Announce Type: new Abstract: AutoMegaKernel (AMK) compiles a HuggingFace Llama-family model into a single persistent cooperative CUDA kernel that runs the whole forward pass in one
arXiv:2606.07643v1 Announce Type: cross Abstract: Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their a
Amazon Web Services Inc. today introduced an artificial intelligence tool designed to help organizations lower their cloud bills. AWS FinOps Agent is initially available in public preview. It’s the la
arXiv:2606.08611v1 Announce Type: cross Abstract: We study data-driven real-time economic optimization of a multi-product chemical reactor when no reliable first-principles model is available beyond a
arXiv:2606.09433v1 Announce Type: new Abstract: Wastewater influenza surveillance can reveal community circulation before clinical reporting, but wastewater alone is not a fully identifiable proxy for
arXiv:2511.03877v2 Announce Type: replace Abstract: Social and collaborative platforms emit multivariate time-series traces in which early interactions -- such as views, likes, or downloads -- are fol