Search: “tools”

Valley3: Scaling Omni Foundation Models for E-commerce

model-releasesarxiv-cs-ai

arXiv:2605.01278v1 Announce Type: new Abstract: In this work, we present Valley3, an omni multimodal large language model (MLLM) developed for diverse global e-commerce tasks, with unified understandi

6 May 2026

very fun to collab with @harvey on their Long Horizon Legal Agent Benchmark. We need more industry specific benchmarks, and Harvey is paving…

DGX agent

Harrison Chase expresses enthusiasm about collaborating with Harvey on their Long Horizon Legal Agent Benchmark, highlighting the value of developing industry-specific benchmarks for AI evaluation. Th

model-releasesharrison-chase--x

6 May 2026

Will the Carbon Border Adjustment Mechanism Impact European Electricity Prices? A GNN-Based Network Analysis

arXiv:2605.03304v1 Announce Type: new Abstract: The European Union's Carbon Border Adjustment Mechanism (CBAM) creates a complex challenge for the interconnected European electricity market. Tradition

safetyarxiv-cs-lg

6 May 2026

Industry

10 trillion samples a day: Scaling beyond traditional monitoring infra at Databricks

Databricks describes their approach to handling massive-scale observability and monitoring infrastructure that processes 10 trillion samples daily, moving beyond conventional monitoring solutions. The

industrydatabricks

2D-ThermAl: Physics-Informed Framework for Thermal Analysis of Circuits using Generative AI

arXiv:2512.01163v2 Announce Type: replace Abstract: Thermal analysis is increasingly critical in modern integrated circuits, where non-uniform power dissipation and high transistor densities can cause

A Category-Theoretic Analysis of Conformal Prediction

arXiv:2507.04441v4 Announce Type: replace-cross Abstract: Conformal prediction (CP) produces prediction regions with finite-sample, distribution free coverage guarantees, but its interpretation as a q

A Language for Describing Agentic LLM Contexts

arXiv:2605.01920v1 Announce Type: cross Abstract: Large language models are increasingly used within larger systems ('LLM agents'). These make a sequence of LLM calls, each call providing the LLM with

agentsarxiv-cs-cl

Active Reasoning Vision-Language Models via Sequential Experimental Design

arXiv:2605.01345v1 Announce Type: new Abstract: Visual perception in modern Vision-Language Models (VLMs) is constrained by a fundamental perceptual bandwidth bottleneck: a broad field of view inevita

researcharxiv-cs-cv

Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation

arXiv:2605.02742v1 Announce Type: cross Abstract: Motion in-betweening is one of the most artistically demanding and time consuming stages of 3D animation, where the expressivity and rhythm of motion

safetyarxiv-cs-lg

AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction

arXiv:2602.05353v3 Announce Type: replace-cross Abstract: Large Language Models have shown strong capabilities in complex problem solving, yet many agentic systems remain difficult to interpret and co

agentsarxiv-cs-cl

Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure

arXiv:2605.00055v1 Announce Type: cross Abstract: We report a safety incident in a deployed multi-agent research system in which a primary AI agent installed 107 unauthorized software components, over

safetyarxiv-cs-ai

Analyzing Adversarial Inputs in Deep Reinforcement Learning

arXiv:2402.05284v2 Announce Type: replace Abstract: In recent years, Deep Reinforcement Learning (DRL) has become a popular paradigm in machine learning due to its successful applications to real-worl

safetyarxiv-cs-lg

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction

arXiv:2605.02234v1 Announce Type: cross Abstract: We present a method for diagnosing interpretation in neural networks by identifying an input subspace where a proposed interpretation is highly faithf

Industry

Codex is gaining steam

Codex, likely referring to OpenAI's code generation model, is experiencing increased adoption and usage. The article from Ben's Bites discusses the growing momentum and applications of this AI coding

industryben-s-bites

Constructing Interpretable Features from Compositional Neuron Groups

arXiv:2506.10920v2 Announce Type: replace Abstract: A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally expla

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features

arXiv:2602.10437v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features a

Creating and Evaluating Figurative Language Dataset for Sindhi

arXiv:2605.01323v1 Announce Type: new Abstract: In this article, we introduce SiNFluD, a novel benchmark dataset for Sindhi figurative language classification. We first collect raw text from various b

Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages

arXiv:2605.02608v1 Announce Type: new Abstract: Transformer-based models achieve state-of-the-art dependency parsing for high-resource languages, yet their advantage over simpler architectures in low-

DIAGRAMS: A Review Framework for Reasoning-Level Attribution in Diagram QA

arXiv:2605.00905v1 Announce Type: new Abstract: Diagram question answering (Diagram QA) requires reasoning-level attribution that links each question-answer pair to all visual regions needed to derive

FeedbackLLM: Metadata driven Multi-Agentic Language Agnostic Test Case Generator with Evolving prompt and Coverage Feedback

arXiv:2605.01264v1 Announce Type: cross Abstract: Traditional approaches to test case generation often involve manual effort and incur significant computational overhead. Additionally, these approache

From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs

model-releasesarxiv-cs-cv

arXiv:2605.02130v1 Announce Type: new Abstract: Human-level agentic intelligence extends beyond low-level geometric perception, evolving from recognizing where things are to understanding what they ar

GA-VisAgent: A Multi-Agent application for code generation and visualization in interactive learning

arXiv:2605.01299v1 Announce Type: new Abstract: Geometric Algebra (GA) presents challenges to learners due to its highly abstract mathematical structure and complex operational rules, as translating a

agentsarxiv-cs-lg

Hallucinations Undermine Trust; Metacognition is a Way Forward

arXiv:2605.01428v1 Announce Type: new Abstract: Despite significant strides in factual reliability, errors -- often termed hallucinations -- remain a major concern for generative AI, especially as LLM

agentsarxiv-cs-cl

Hardware

How to Build In-Vehicle AI Agents with NVIDIA: From Cloud to Car

The automotive cockpit is undergoing a fundamental shift from rule-based interfaces to agentic, multimodal AI systems capable of reasoning, planning, and acting. This is enabled by an agentic AI pipel

hardwarenvidia-developer

IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning

arXiv:2605.01668v1 Announce Type: new Abstract: Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to r

researcharxiv-cs-cv

KANs need curvature: penalties for compositional smoothness

arXiv:2605.02190v1 Announce Type: new Abstract: Kolmogorov-Arnold networks (KANs) offer a potent combination of accuracy and interpretability, thanks to their compositions of learnable univariate acti

Last Week in AI #340 - OpenAI vs Musk + Microsoft, DeepSeek v4, Vision Banana

model-releaseslast-week-in-ai

This newsletter episode covers recent AI industry developments including a legal dispute between OpenAI and Elon Musk, Microsoft's involvement in AI developments, the release of DeepSeek's v4 model, a

Tutorials

Learning Koopman operators for coupled systems via information on governing equations of subsystems

arXiv:2605.01835v1 Announce Type: new Abstract: Nonlinear coupled systems are ubiquitous in science and engineering. The analysis and modeling of such systems is challenging due to their high dimensio

tutorialsarxiv-cs-lg

Linear-Readout Floors and Threshold Recovery in Computation in Superposition

arXiv:2605.01192v1 Announce Type: new Abstract: Two recent approaches to computation in superposition reach different recursive capacity regimes: Hanni et al. certify ilde{O}(d^{3/2}) computable featu

LITcoder: A General-Purpose Library for Building and Comparing Encoding Models

arXiv:2509.09152v2 Announce Type: replace Abstract: We introduce LITcoder, an open-source library for building and benchmarking neural encoding models. Designed as a flexible backend, LITcoder provide

MedScribe: Clinically Grounded CT Reporting through Agentic Workflows

arXiv:2605.01779v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown potential for automated radiology report generation, yet existing approaches rely on global embedding compressi

agentsarxiv-cs-cv

MolViBench: Evaluating LLMs on Molecular Vibe Coding

arXiv:2605.02351v1 Announce Type: new Abstract: Molecular Vibe Coding, a paradigm where chemists interact with LLMs to generate executable programs for molecular tasks, has emerged as a flexible alter

Local Ai

Open-access model for detecting openly dumped dispersed municipal solid waste from crowdsourced UAV imagery in Sub-Saharan Africa

arXiv:2605.02316v1 Announce Type: new Abstract: Managing municipal solid waste in rapidly urbanizing Sub-Saharan Africa remains challenging due to dispersed informal dumping and limited high-resolutio

local-aiarxiv-cs-cv

OpenAI GPT-5 System Card

arXiv:2601.03267v2 Announce Type: replace Abstract: This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers

Local Ai

Parllama -- a terminal UI for Ollama model management and multi-provider LLM chat

Parllama is a TUI (Text UI) application designed for easy management and use of Ollama-based LLMs that also works with major cloud-provided LLMs. It provides core model management features including f

local-air-ollama

Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning

arXiv:2605.02168v1 Announce Type: cross Abstract: Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they con

Principles and Guidelines for Randomized Controlled Trials in AI Evaluation

arXiv:2605.02050v1 Announce Type: cross Abstract: This work establishes a foundational framework for standardizing AI evaluation RCTs (sometimes called human uplift studies). Drawing on established ex

Random-Effects Algorithm for Random Objects in Metric Spaces

arXiv:2605.02693v1 Announce Type: cross Abstract: Across many scientific disciplines, multiple observations are collected from the same experimental units, and in modern datasets these observations of

Reconstructing conformal field theoretical compositions with Transformers

arXiv:2605.01072v1 Announce Type: cross Abstract: We study the use of transformers to reconstruct the compositions of tensor products of two-dimensional rational conformal field theories (RCFTs) based

Reinforcement Learning from Compiler and Language Server Feedback

arXiv:2510.22907v2 Announce Type: replace Abstract: Coding agents fail when text-level guesses outrun program facts: they hallucinate APIs, drift to the wrong symbol, and apply edits without evidence

safetyarxiv-cs-cl

SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning

arXiv:2605.01489v1 Announce Type: cross Abstract: Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents

Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis

arXiv:2605.00314v1 Announce Type: cross Abstract: An agent skill is a configuration package that equips an LLM-driven agent with a concrete capability, such as reading email, executing shell commands,

agentsarxiv-cs-ai

so well explained ! this is like applying Richard Sutton’s Bitter Lesson to agent systems. leverage comes from feedback loops, not handcraft…

so well explained ! this is like applying Richard Sutton’s Bitter Lesson to agent systems. leverage comes from feedback loops, not handcrafted prompts. attaching feedback to traces is the missing piec

agentsharrison-chase--x

Sound Source Localization for Spatial Mapping of Surgical Actions in Dynamic Scenes

arXiv:2510.24332v3 Announce Type: replace-cross Abstract: Purpose: Surgical scene understanding is key to advancing computer-aided and intelligent surgical systems. Current approaches predominantly re

agentsarxiv-cs-cv

Spectral Model eXplainer: a chemically-grounded explainability framework for spectral-based machine learning models

arXiv:2605.02684v1 Announce Type: new Abstract: Spectral-based machine learning models have been increasingly deployed in chemometrics and spectroscopy, where predictive accuracy is as important as ex

StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer

arXiv:2605.00924v1 Announce Type: new Abstract: AI-generated content (AIGC) detectors are increasingly deployed in high-stakes settings such as academic integrity screening, yet their reliability rest

SUDP: Secret-Use Delegation Protocol for Agentic Systems

arXiv:2604.24920v2 Announce Type: replace-cross Abstract: Agentic systems increasingly act with user secrets for APIs, messaging platforms, and cloud services. Today's bearer-secret interfaces impleme

agentsarxiv-cs-ai

SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion

arXiv:2605.01510v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in high-quality image synthesis, sparking interest in image-guided generation tasks such as subject-dr

safetyarxiv-cs-cv