Knowledge catalogue
arXiv:2604.02653v2 Announce Type: replace Abstract: Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below
Auto-generated index of all people mentioned across the wiki.
arXiv:2604.07059v1 Announce Type: new Abstract: Electronic Control Units (ECUs) have played a pivotal role in transforming motorcars of yore into the modern vehicles we see on our roads today. They ac
At the enterprise level, agentic AI has become less of a prospective tool for businesses, evolving into a valuable asset for many organizations. As more companies shift from the experimentation phase
arXiv:2610.16776v1 Announce Type: new Abstract: Game-Creation-Agents (GCA) turns a natural-language request into a runnable Phaser 4 browser game. The pipeline first builds a multimodal game design do
arXiv:2610.18393v1 Announce Type: cross Abstract: Equivariant machine learning interatomic potentials (MLIPs) promise atomistic simulations with accuracy approaching that of quantum-mechanical calcula
Coding agents have changed how fast teams ship, and more of the software they ship now includes agents. A production agent spans model calls, routing decisions, tools, and the infrastructure underneat
arXiv:2610.06409v1 Announce Type: new Abstract: Machine-learned interatomic potentials extend atomistic simulations beyond the length- and timescales accessible to electronic-structure methods. Howeve
Amazon Bedrock AgentCore Runtime Instances gives multi-agent workflows AWS managed EC2 infrastructure with GPUs, persistent volumes, and multi-day sessions. In this post, we deploy a three-agent music
arXiv:2609.37784v1 Announce Type: new Abstract: Satellite observations, precomputed embeddings, and map products describe the same evolving Earth, yet are stored as independent, petabyte-scale data pr
arXiv:2609.33746v1 Announce Type: new Abstract: At each decoding step a language model attends over the key-value (KV) cache of every earlier token, so at long context the attention call is bounded by
After lunch, here’s what’s up next at Interrupt: 🎙️How @airbnb built Agentic AI on LangGraph 🎙️Deploying mission-critical agents to production w/ @VictorMoreira16 🎙️LangSmith for Mental Health AI w/ @
NVIDIA Confidential Computing (CC) secures large‑language‑model inference by providing encrypted virtual machines, GPUs, and NVLink, enabling processing of sensitive data in trusted hardware. Running
arXiv:2609.22643v1 Announce Type: new Abstract: Forecasting a long horizon from only the first observations of a sequence is ill-posed: many trajectories are consistent with the same short history. We
Every AI factory needs power and cooling that fit its computing architecture. As AI infrastructure expands, power, cooling, water, site and grid constraints are shaping what builders can deploy. Choos
arXiv:2609.15555v1 Announce Type: new Abstract: Bayesian optimisation (BO) typically relies on a single global Gaussian process (GP) model as its surrogate model. However, GP regression has cubic comp
First off, I know that GLM, Qwen, and DeepSeek absolutely dominate in terms of SOTA Open Source models, and that’s what I use in my personal projects and for school, however, I’m also responsible for
arXiv:2609.05641v1 Announce Type: cross Abstract: We consider the problem of minimizing error in quantized matrix multiplication C=AB. Scalar quantization of the factors introduces rounding errors who
1Password uses Codex across software delivery; its OpenAI case study reports 20.9% higher engineering productivity in a core cohort.
arXiv:2609.04678v1 Announce Type: new Abstract: Existing post-training pipelines for coding and terminal agents suffer severe token and control fidelity errors: simplified training environments mismat
Enterprise infrastructure is being rebuilt around agentic AI, and the center of gravity is shifting back toward private environments where data, cost and control sit under one roof. As inference workl
We ran Signal on Alyx, the AI engineering agent built into Arize AX. It surfaced a duplicate task-state loop and a 43-call dataset retry that appeared as valid tool activity or an OK root span. The po
The artificial intelligence infrastructure market is crossing an important threshold. The conversation is shifting from acquiring graphics processing units to building complete AI factories that can g
Mariko Wakabayashi is a Principal Applied Scientist at Microsoft who leads the development of agentic AI workflows for cybersecurity operations. She specializes in evaluating LLM‑powered systems and a
arXiv:2608.20371v1 Announce Type: cross Abstract: A common claim is that zero-shot large language models (LLMs) can replace fine-tuned NLU classifiers for intent detection. We test this claim head-to-
arXiv:2608.13426v1 Announce Type: cross Abstract: Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplicati
Suno is releasing Studio 2.0 with significant upgrades that push it closer to an actual digital audio workstation (DAW), rather than a bare-bones audio editor with generative AI features. The biggest
arXiv:2608.10288v1 Announce Type: cross Abstract: The Large Language Model from Power Law Decoder Representations (PLDR-LLM) and its attention, Power Law Graph Attention (PLGA), replace the fixed bili
arXiv:2608.08349v1 Announce Type: cross Abstract: Audio dramas weave dialogue, sound effects, and music into immersive stories. Creators often adapt books into audio dramas, but this process remains l
arXiv:2608.09343v1 Announce Type: new Abstract: Simulation-based optimization (SBO) evaluates executable policies under stochastic dynamics, but most methods treat the simulator as a black box: aggreg
Traditional APM can collect every span and still leave developers guessing about intent, causality, and drift. As agents multiply, the observability stack must learn to interpret the systems it watche
Seen a ton of posts today about the DeepSeek API price hike. Half the feed is doom-posting, the other half is explaining basic GPU economics. Honestly, I get the cost side. Sub-cent tokens were never
arXiv:2608.00101v1 Announce Type: cross Abstract: AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different fr
arXiv:2607.28274v1 Announce Type: new Abstract: Modern Greek is a richly inflected language, yet the language models built for it are evaluated mainly on factual knowledge, and no benchmark is dedicat
At Google, AI is a soup-to-nuts endeavor. Obviously, we make leading AI models like Gemini and Nano Banana. We incorporate AI into the tools you use every day (think Gmail, BigQuery, AlloyDB, Google C
arXiv:2607.25626v1 Announce Type: new Abstract: Decoding speech information directly from scalp electroencephalography (EEG) into text provides a potential non-invasive neural communication pathway fo
arXiv:2607.23123v1 Announce Type: new Abstract: Existing evaluations of large language models cover knowledge, reasoning, coding, and tool use, but they rarely treat a verifiable deliverable produced
Together AI has released the Kimi K3 model on its platform as a Day‑0 launch partner for Moonshot AI’s open frontier agentic model, which supports long‑running workflows across code, tools, vision and
arXiv:2607.10467v2 Announce Type: replace-cross Abstract: Healthcare organizations often cannot freely centralize patient data because medical records are sensitive, regulated, and institutionally con
arXiv:2607.07052v1 Announce Type: cross Abstract: AI agents deployed for IT operations are typically permanent cost centers because every execution requires full LLM inference, even for previously sol
In this post, you build and connect that server end to end. You will implement MCP tools, set up two-layer JSON Web Token (JWT) authentication, deploy with AWS Cloud Development Kit (AWS CDK), and con
arXiv:2606.08048v1 Announce Type: cross Abstract: Diffusion language models (DLMs) offer substantial speed advantages through parallel decoding, but the lack of token dependencies limits generation qu
arXiv:2607.05113v1 Announce Type: new Abstract: Imagine two users interact with the same LLM. One has been told it is the cutting-edge flagship model; the other, an older, weaker model. They walk away
arXiv:2607.01610v1 Announce Type: new Abstract: Counterfactual explanation (CE) is widely used to enhance the interpretability of machine learning models and support data-driven decision-making based
arXiv:2606.28673v1 Announce Type: new Abstract: Sign Languages (SLs) are the primary means of communication for millions of deaf individuals, yet existing evaluation metrics for generated SL remain si
Replit organized a hackathon challenge in New York City on Saturday, June 27th, where participants had to build an app during a single train ride using the Replit platform. The event tested developers
arXiv:2606.21234v1 Announce Type: new Abstract: To generate natural and accurate sentence-level sign language, synthesizing the 'gloss', the fundamental semantic unit, is essential. However, most curr
arXiv:2606.11869v1 Announce Type: cross Abstract: Custom AI agents areagents that live inside their own application, talk to their own data and tools, enforce their own security boundaries, and carry
arXiv:2606.11686v1 Announce Type: cross Abstract: End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present
arXiv:2606.10315v1 Announce Type: cross Abstract: LLM-as-judge is the default instrument for evaluating conversational agents, yet its reliability is almost always reported as agreement with human rat
arXiv:2606.02762v1 Announce Type: new Abstract: Knowledge of real-time road slipperiness, or even better, a refined estimate of peak grip potential, is a critical input for vehicle warning and interve
arXiv:2601.21579v2 Announce Type: replace Abstract: The success of Hyper-Connections (HC) in neural networks (NN) has also highlighted issues related to training instability and restricted scalability
DeepAgents are AI systems designed to handle complex tasks through advanced reasoning and planning capabilities. The post outlines the key features that enable DeepAgents to excel at complicated probl
arXiv:2605.30736v1 Announce Type: cross Abstract: The rapid development of large language models, each with distinct capabilities and inference costs, raises a practical deployment question: given an
Since its inception over 20 years ago, Google has used Site Reliability Engineering (SRE) to keep services like Search, Gmail, Maps, YouTube and Google Cloud reliable and highly available, adhering to
arXiv:2605.27737v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly attractive for multimodal quality assessment, but their default reliance on autoregressive text generatio
arXiv:2605.28612v1 Announce Type: new Abstract: Parity functions are fundamental Boolean operations with critical applications across machine learning, cryptography, and error correction. Yet, learnin
Organizations are unlocking entirely new ways to use image generation and editing across their industries. To drive next-generation experiences, businesses are embedding AI directly into creative, age
arXiv:2605.27158v1 Announce Type: new Abstract: Discovering the governing equations of a dynamical system from observed trajectories provides deeper insight into its structure than mere prediction of
Learn how to design, calibrate, and run LLM-as-a-judge evaluators with fixed labels, human agreement checks, trace context, and Phoenix Evals. The post How to build LLM-as-a-Judge evaluators that hold