Search: “automated”

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via @Fi…

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via @FireworksAI_HQ fast inference APIs. Kimi K2.6 has impressive a

agentsdair-ai--x

21 Apr 2026

Agents

What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations

DGX agent

arXiv:2510.17795v3 Announce Type: replace Abstract: Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate exec

agentsarxiv-cs-cl

21 Apr 2026

A PennyLane-Centric Dataset to Enhance LLM-based Quantum Code Generation using RAG

arXiv:2503.02497v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) offer powerful capabilities in code generation, natural language understanding, and domain-specific reasoning. Th

Applications

AI-assisted Protocol Information Extraction For Improved Accuracy and Efficiency in Clinical Trial Workflows

arXiv:2602.00052v2 Announce Type: replace-cross Abstract: Increasing clinical trial protocol complexity, amendments, and challenges around knowledge management create significant burden for trial team

applicationsarxiv-cs-ai

AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units

arXiv:2601.07160v2 Announce Type: replace Abstract: To meet the ever-increasing demand for computational efficiency, Neural Processing Units (NPUs) have become critical in modern AI infrastructure. Ho

AST: Adaptive, Seamless, and Training-Free Precise Speech Editing

arXiv:2604.16056v1 Announce Type: cross Abstract: Text-based speech editing aims to modify specific segments while preserving speaker identity and acoustic context. Existing methods rely on task-speci

AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt

arXiv:2512.24625v2 Announce Type: replace-cross Abstract: Accurate traffic prediction is essential for Intelligent Transportation Systems, including ride-hailing, urban road planning, and vehicle flee

Breakout-picker: Reducing false positives in deep learning-based borehole breakout characterization from acoustic image logs

arXiv:2604.16011v1 Announce Type: new Abstract: Borehole breakouts are stress-induced spalling on the borehole wall, which are identifiable in acoustic image logs as paired zones with near-symmetry az

researcharxiv-cs-cv

Bureaucratic Silences: What the Canadian AI Register Reveals, Omits, and Obscures

arXiv:2604.15514v1 Announce Type: new Abstract: In November 2025, the Government of Canada operationalized its commitment to transparency by releasing its first Federal AI Register. In this paper, we

Can LLMs Understand the Impact of Trauma? Costs and Benefits of LLMs Coding the Interviews of Firearm Violence Survivors

arXiv:2604.16132v1 Announce Type: cross Abstract: Firearm violence is a pressing public health issue, yet research into survivors' lived experiences remains underfunded and difficult to scale. Qualita

Characterising LLM-Generated Competency Questions: a Cross-Domain Empirical Study using Open and Closed Models

arXiv:2604.16258v1 Announce Type: new Abstract: Competency Questions (CQs) are a cornerstone of requirement elicitation in ontology engineering. CQs represent requirements as a set of natural language

ChemGraph-XANES: An Agentic Framework for XANES Simulation and Analysis

arXiv:2604.16205v1 Announce Type: cross Abstract: Computational X-ray absorption near-edge structure (XANES) is widely used to probe local coordination environments, oxidation states, and electronic s

Safety

Cognitive Agency Surrender: Defending Epistemic Sovereignty via Scaffolded AI Friction

arXiv:2603.21735v2 Announce Type: replace-cross Abstract: The proliferation of Generative Artificial Intelligence has transformed benign cognitive offloading into a systemic risk of cognitive agency s

safetyarxiv-cs-ai

Tutorials

Cross-modal learning for plankton recognition

arXiv:2603.16427v2 Announce Type: replace Abstract: This paper considers self-supervised cross-modal coordination as a strategy enabling utilization of multiple modalities and large volumes of unlabel

tutorialsarxiv-cs-cv

Tutorials

Discovering quantum phenomena with Interpretable Machine Learning

arXiv:2604.16015v1 Announce Type: cross Abstract: Interpretable machine learning techniques are becoming essential tools for extracting physical insights from complex quantum data. We build on recent

tutorialsarxiv-cs-lg

Enabling Predictive Maintenance in District Heating Substations: A Labelled Dataset and Fault Detection Evaluation Framework based on Service Data

arXiv:2511.14791v2 Announce Type: replace-cross Abstract: Early detection of faults in district heating substations is imperative to reduce return temperatures and enhance efficiency. However, progres

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

arXiv:2601.05808v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are expected to be trained to act as agents in various real-world environments, but this process relies on rich a

agentsarxiv-cs-ai

Local Ai

ExoNet: Multimodal Deep Learning for TESS Exoplanet Candidate Identification via Phase-Folded Light Curves, Stellar Parameters, and Multi-Head Attention Fusion

arXiv:2604.15560v1 Announce Type: cross Abstract: NASA's Transiting Exoplanet Survey Satellite (TESS) has identified thousands of exoplanet candidates, yet many remain unconfirmed due to the limitatio

local-aiarxiv-cs-lg

Explainable Iterative Data Visualisation Refinement via an LLM Agent

arXiv:2604.15319v1 Announce Type: cross Abstract: Exploratory analysis of high-dimensional data relies on embedding the data into a low-dimensional space (typically 2D or 3D), based on which visualiza

agentsarxiv-cs-ai

Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation

arXiv:2505.21072v4 Announce Type: replace Abstract: Large Language Models (LLMs) enhanced with retrieval, an approach known as Retrieval-Augmented Generation (RAG), have achieved strong performance in

researcharxiv-cs-cl

IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering

arXiv:2510.23536v2 Announce Type: replace Abstract: Intent identification serves as the foundation for generating appropriate responses in personalized question answering (PQA). However, existing benc

Safety

Long-Term Memory for VLA-based Agents in Open-World Task Execution

arXiv:2604.15671v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated significant potential for embodied decision-making; however, their application in complex chemical

safetyarxiv-cs-ro

Industry

Mercedes-Benz Builds a Cross-Cloud Data Mesh with Delta Sharing and Intelligent Replication, Cutting Costs by 66%

Mercedes-Benz implemented a cross-cloud data mesh architecture using Databricks Delta Sharing and intelligent replication to optimize their data infrastructure across multiple cloud providers. The sol

industrydatabricks

Hardware

Mitigating Indirect AGENTS.md Injection Attacks in Agentic Environments

NVIDIA researchers discovered a vulnerability in AI coding assistants where malicious software dependencies can inject harmful instructions into AGENTS.md configuration files, allowing attackers to re

hardwarenvidia-developer

Neurosymbolic Repo-level Code Localization

arXiv:2604.16021v1 Announce Type: cross Abstract: Code localization is a cornerstone of autonomous software engineering. Recent advancements have achieved impressive performance on real-world issue be

Tools

New TIL on fetching data from a Datasette instance into Google Sheets using importdata(), named custom functions or Google Apps Script https…

Simon Willison shared a tutorial on integrating Datasette instances with Google Sheets, demonstrating multiple methods including the importdata() function, custom named functions, and Google Apps Scri

toolssimon-willison--x

Qwen3.5-Omni Technical Report

arXiv:2604.15804v1 Announce Type: new Abstract: In this work, we present Qwen3.5-Omni, the latest advancement in the Qwen-Omni model family. Representing a significant evolution over its predecessor,

Training Time Prediction for Mixed Precision-based Distributed Training

arXiv:2604.16145v1 Announce Type: cross Abstract: Accurate prediction of training time in distributed deep learning is crucial for resource allocation, cost estimation, and job scheduling. We observe

TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis

arXiv:2505.24672v2 Announce Type: replace Abstract: Large Language Models (LLMs) excel in various natural language processing tasks but remain vulnerable to generating harmful content or being exploit

🔴 BREAKING Speculative decoding just got real for local LLMs. llama.cpp merged speculative checkpointing (PR #19493). Expect 0-50% speedups…

model-releasesclem-delangue--x

🔴 BREAKING Speculative decoding just got real for local LLMs. llama.cpp merged speculative checkpointing (PR #19493). Expect 0-50% speedups on coding tasks with `--spec-type ngram-mod`. This means: •

19 Apr 2026

Adding a new content type to my blog-to-newsletter tool

model-releasessimon-willison

Agentic Engineering Patterns > Here's an example of a deceptively short prompt that got a lot of work done in a single shot. First, some background. I send out a free Substack newsletter around once a

18 Apr 2026

Industry

I sat down with Emad Mostaque (@EMostaque)—and he told me something I can’t shake: the biggest AI labs already have models they’ll never rel…

I sat down with Emad Mostaque (@EMostaque)—and he told me something I can’t shake: the biggest AI labs already have models they’ll never release. We dug into why, how reinforcement learning may be kil

industryemad-mostaque--x

18 Apr 2026

Nice paper from Google. And a great application of AI agents. Wearables capture a staggering amount of physiological signals every day. CoDa…

Nice paper from Google. And a great application of AI agents. Wearables capture a staggering amount of physiological signals every day. CoDaS is an AI co-data-scientist that turns raw wearable sensor

agentsdair-ai--x

18 Apr 2026

A multi-platform LiDAR dataset for standardized forest inventory measurement at long term ecological monitoring sites

model-releasesarxiv-cs-ro

arXiv:2604.14635v1 Announce Type: new Abstract: We present a curated multi-platform LiDAR reference dataset from an instrumented ICOS forest plot, explicitly designed to support calibration, benchmark

An Intelligent Robotic and Bio-Digestor Framework for Smart Waste Management

arXiv:2604.14882v1 Announce Type: cross Abstract: Rapid urbanization and continuous population growth have made municipal solid waste management increasingly challenging. These challenges highlight th

agentsarxiv-cs-lg

Local Ai

Beyond Augmentation: Cross-Modal Transformer Fusion with Bi-directional Attention for Low-Data Aneurysm Screening

arXiv:2512.22185v2 Announce Type: replace Abstract: Intracranial aneurysm rupture causes subarachnoid hemorrhage with mortality near 50%, making early detection critical. Although CTA enables rapid sc

local-aiarxiv-cs-cv

Safety

Building Trust in the Skies: A Knowledge-Grounded LLM-based Framework for Aviation Safety

arXiv:2604.13101v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into aviation safety decision-making represents a significant technological advancement, yet their sta

safetyarxiv-cs-ai

ChatSVA: Bridging SVA Generation for Hardware Verification via Task-Specific LLMs

arXiv:2604.02811v2 Announce Type: replace-cross Abstract: Functional verification consumes over 50% of the IC development lifecycle, where SystemVerilog Assertions (SVAs) are indispensable for formal

DigiForest: Digital Analytics and Robotics for Sustainable Forestry

arXiv:2604.14652v1 Announce Type: new Abstract: Covering one third of Earth's land surface, forests are vital to global biodiversity, climate regulation, and human well-being. In Europe, forests and w

agentsarxiv-cs-ro

Tools

Download Cursor to use the agents window: http://cursor.com/download

Cursor is an AI-powered code editor that offers a download option for users to access the agents window feature. The agents window allows developers to leverage AI capabilities within the Cursor envir

toolscursor--x

EchoAgent: Towards Reliable Echocardiography Interpretation with 'Eyes','Hands' and 'Minds'

arXiv:2604.05541v2 Announce Type: replace Abstract: Reliable interpretation of echocardiography (Echo) is crucial for assessing cardiac function, which demands clinicians to synchronously orchestrate

agentsarxiv-cs-cv

Estimating the Diameter at Breast Height of Trees in a Forest from RGB

arXiv:2505.03093v3 Announce Type: replace Abstract: Forest inventories rely on accurate measurements of the diameter at breast height (DBH) for ecological monitoring, resource management, and carbon a

researcharxiv-cs-cv

EuropeMedQA Study Protocol: A Multilingual, Multimodal Medical Examination Dataset for Language Model Evaluation

arXiv:2604.14306v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated high proficiency on English-centric medical examinations, their performance often declines when fac

Geometrically Consistent Multi-View Scene Generation from Freehand Sketches

arXiv:2604.14302v1 Announce Type: new Abstract: We tackle a new problem: generating geometrically consistent multi-view scenes from a single freehand sketch. Freehand sketches are the most geometrical

researcharxiv-cs-cv

Local Ai

HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization

arXiv:2604.14159v1 Announce Type: new Abstract: Mobile input method editors (IMEs) are the primary interface for text input, yet they remain constrained to manual typing and struggle to produce person

local-aiarxiv-cs-cl

IMPACTX: improving model performance by appropriately constraining the training with teacher explanations

arXiv:2502.12222v2 Announce Type: replace Abstract: The eXplainable Artificial Intelligence (XAI) research predominantly concentrates to provide explainations about AI model decisions, especially Deep

researcharxiv-cs-lg

Introducing Genie Agent Mode

Databricks introduced Genie Agent Mode, a feature that enables autonomous AI agents to perform tasks within the Databricks platform by interpreting natural language instructions and executing data ope

agentsdatabricks

Learning to Concatenate Quantum Codes

arXiv:2604.14931v1 Announce Type: cross Abstract: Concatenating quantum error correction codes scales error correction capability by driving logical error rates down double-exponentially across levels

researcharxiv-cs-lg