All entries

Evals in CI: How to write your LLM evals as tests with Arize Phoenix

If you're struggling to get started with evals, you're not alone. This post explains how to write LLM evals as ordinary tests in CI with Phoenix, pytest, and Vitest/Jest. The post Evals in CI: How to

tutorialsarize-ai

Evaluating Agentic Harness Systems for Autonomous Computational Pathology

DGX agent

arXiv:2607.02598v1 Announce Type: new Abstract: Autonomous computational pathology (ACP) converts high-level pathology analysis goals into executable, traceable and clinically bounded workflows. Reali

model-releasesarxiv-cs-cv

7 Jul 2026

Evaluating and Understanding Model Editing for Medical Vision Language Models

arXiv:2607.05310v1 Announce Type: new Abstract: Model editing promises a fast, targeted way to correct post-deployment mistakes in medical vision-language models (VLMs) without costly retraining. Howe

Evaluating Generative Agents with Actions Grounded in Socially Distributed Task Environments using Incognita

arXiv:2607.02975v1 Announce Type: new Abstract: Effective agency in social environments depends on when an agent seeks knowledge, when it acts, and whether its actions are justified by acquired inform

agentsarxiv-cs-ai

Evaluating Intellectual Property Guardrails of Generative Image Models: A Technical Report

arXiv:2607.02582v1 Announce Type: new Abstract: Generative image models are capable of producing images that bear a strong resemblance to, or replicate, recognizable intellectual property (IP). In thi

Evaluating Large Language Models for Antisemitic Incident Classification

model-releasesarxiv-cs-cl

arXiv:2607.04890v1 Announce Type: new Abstract: Addressing hate and violence in society requires timely detection of hateful events from public reporting, but automated identification of hateful event

Evaluating LLM-Based Regression Test Generation

arXiv:2501.11086v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown tremendous promise in automated software engineering. In this paper, we investigate LLMs for just-in-t

Evaluating LLM Uncertainty in Long-Form Generation Using Deterministic Ground Truth

arXiv:2607.03870v1 Announce Type: new Abstract: As LLMs generate increasingly long outputs, effective uncertainty estimation must identify errors at fine-grained levels rather than discard entire resp

Evaluating the Effect of Linguistic Relatedness on Cross-Lingual Transfer in Large Multilingual Automatic Speech Recognition

arXiv:2607.04814v1 Announce Type: cross Abstract: Extending automatic speech recognition (ASR) to low-resource African languages is constrained by the prohibitive demands of data collection at scale.

Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence

arXiv:2607.02623v1 Announce Type: new Abstract: Time series foundation models (TSFMs) have shown strong zero-shot forecasting performance, but their generalization in covariate-driven, non-stationary

researcharxiv-cs-lg

EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration

arXiv:2607.04472v1 Announce Type: new Abstract: The rapid proliferation of artificial intelligence-generated content necessitates reliable multimodal forensics. Beyond video-level binary classificatio

Even before the agentic revolution, prompting tricks stopped being very valuable, as our research has shown. The best approach to AI right n…

Even before the agentic revolution, prompting tricks stopped being very valuable, as our research has shown. The best approach to AI right now is to clearly specify your goals, your output, what 'good

agentsethan-mollick--x

Event Detection in Videos: A Framework for the Development of New Methods

arXiv:2607.04372v1 Announce Type: new Abstract: Event detection tasks in videos, the most important aspect of video surveillance, aim to detect events either at the pixel-level, frame-level, or clip-l

researcharxiv-cs-cv

EventCoT: Event-centric Video Chain-of-thought for Reasoning Temporal Localization

arXiv:2607.04872v1 Announce Type: cross Abstract: Reasoning temporal localization (RTL) requires a model to generate an answer that itself contains the time interval supporting it, so high-level reaso

EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

arXiv:2607.05202v1 Announce Type: new Abstract: Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for

Evolutionary Guided Decoding: Iterative Value Refinement for LLMs

arXiv:2503.02368v4 Announce Type: replace-cross Abstract: While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs wit

safetyarxiv-cs-ai

EvoOtter: Evolutionary Reproduction Test Generator

arXiv:2607.02854v1 Announce Type: cross Abstract: Before fixing an issue, it is useful to first reproduce it by generating a bug reproduction test (BRT). However, generating a BRT is itself a challeng

tutorialsarxiv-cs-lg

EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs

arXiv:2512.22240v5 Announce Type: replace-cross Abstract: Machine learning models are primarily judged by predictive performance, especially in applied genomics, where explanations are read as biologi

Excellent investigation of the mechanics of language models. 🫢A notable blindspot, however: several teams have actually been directly c…

model-releasesyann-lecun--x

Excellent investigation of the mechanics of language models. 🫢A notable blindspot, however: several teams have actually been **directly** comparing the working of LLMs to those of the human brain 🧠 fo

Exp2VLA: Enabling Vision-Language-Action for Drone Navigation from Expert Demonstrations

arXiv:2607.03146v1 Announce Type: new Abstract: Vision-language-action (VLA) models open a new path toward intuitive robot control by directly linking perception, language, and action in a single end-

safetyarxiv-cs-ro

Expanding Managed Agents in Gemini API: background tasks, remote MCP and more

Google expands Managed Agents in Gemini API with support for background execution , and adds the ability to register remote Model Context Protocol (MCP) servers to extend agent capabilities . Develope

model-releasesgoogle-ai

Explainable AI for Screening Abuse-Related Trauma in Bangladeshi Children: A Training-Free Multimodal Framework Evaluated on Noise-Aware Synthetic Data

arXiv:2607.04010v1 Announce Type: new Abstract: Bangladesh has an estimated 1.17 mental-health professionals per 100,000 population and only six child psychiatrists nationwide. No Bengali-language, cu

Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks

arXiv:2503.10496v2 Announce Type: replace-cross Abstract: Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions. However, ANNs often suffer from

tutorialsarxiv-cs-ai

Explainable Flood Segmentation on Sentinel-1 SAR1 Imagery Using CNN and Transformer Architectures

arXiv:2606.16302v2 Announce Type: replace Abstract: Rapid and accurate flood prediction is essential for disaster response and mitigation planning. Synthetic Aperture Radar (SAR) sensors in satellites

Explainable Novel Category Discovery in Semantic Concept Space

arXiv:2607.04548v1 Announce Type: cross Abstract: Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing meth

Explainable Reinforcement Learning for Adaptive Traffic Signal Control

arXiv:2607.03703v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for adaptive traffic signal control. However, in safety-critical infrastructure like traf

safetyarxiv-cs-ai

Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning

arXiv:2601.21523v2 Announce Type: replace Abstract: To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards th

agentsarxiv-cs-lg

Exploring Context-aware and LLM-driven Locomotion for Immersive Virtual Reality

arXiv:2504.17331v3 Announce Type: replace-cross Abstract: Locomotion plays a crucial role in shaping the user experience within virtual reality environments. In particular, hands-free locomotion offer

Local Ai

Exploring Convolutional Neural Processes for Weather Downscaling

arXiv:2607.04190v1 Announce Type: new Abstract: Global reanalysis products such as ERA5-Land provide spatially complete weather fields but at resolutions too coarse for local applications, particularl

local-aiarxiv-cs-lg

Applications

Exploring SAM Supervision for Fine-Grained UAV Target Segmentation under Data Scarcity

arXiv:2607.03754v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) target segmentation remains challenging due to the small size of objects, appearance variations, cluttered backgrounds, an

applicationsarxiv-cs-cv

Exploring the Rashomon Set for Concept-Based Models

arXiv:2511.19636v2 Announce Type: replace-cross Abstract: In many machine learning problems, there may exist multiple models that achieve nearly identical predictive performance while relying on funda

ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion

arXiv:2607.03110v1 Announce Type: new Abstract: Multi-Exposure Fusion (MEF) effectively extends dynamic range, but practical deployment is hindered by motion-induced ghosting and the scarcity of high-

Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens

arXiv:2508.04928v5 Announce Type: replace-cross Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images. Despite being

safetyarxiv-cs-ai

EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention

arXiv:2508.16771v3 Announce Type: replace-cross Abstract: Code Language Models (CodeLLMs) learn token importance from data correlations, whereas human developers attend selectively to semantically sal

tutorialsarxiv-cs-ai

F-ACVAE: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks

model-releasesarxiv-cs-lg

arXiv:2607.04698v1 Announce Type: new Abstract: The rapid proliferation of Internet of things (IoT) devices has significantly expanded the cyber-attack surface, necessitating robust and privacy-preser

🚨 Fable 5 is extended through July 12th! The number of people that upgraded to Claude Max in the last few days must have been very high.

model-releasesallie-k--miller--x

Fable 5's event period was extended to July 12th, likely due to unexpectedly high upgrade rates to Claude Max in the preceding days. This announcement suggests strong user interest in Anthropic's prem

Facing US export controls, China's DeepSeek plans to make its own chips

model-releasesars-technica

Chinese AI startup DeepSeek is developing its own inference chips to reduce Nvidia dependence and break U.S. export controls, as China moves to protect its AI ecosystem. DeepSeek has been quietly deve

Failures and Successes to Learn a Core Conceptual Distinction from the Statistics of Language

arXiv:2607.04523v1 Announce Type: cross Abstract: Generic statements like 'tigers are striped' and 'cars have radios' communicate information that is, in general, true. However, while the first statem

Fair-GPTQ: Bias-Aware Quantization for Large Language Models

arXiv:2509.15206v3 Announce Type: replace Abstract: The high memory demands of generative language models have drawn attention to quantization, which reduces memory usage by mapping model weights to l

safetyarxiv-cs-cl

FairFlow: Demystifying and Mitigating Stereotype Bias in Text-to-Image Diffusion Transformers

arXiv:2607.03180v1 Announce Type: new Abstract: Multimodal diffusion transformers (MM-DiTs) have emerged as the prevalent backbone for modern text-to-image generation systems. However, they exhibit cr

Faithfulness to Refusal: A Causal Audit of Neuron Selectors

arXiv:2607.05355v1 Announce Type: new Abstract: Attribution scores increasingly identify which neuron rows of a language model matter for applications such as pruning, interpretability, and editing fo

safetyarxiv-cs-cl

Industry

Falcon 9 landing confirmed

SpaceX's Falcon 9 rocket successfully completed a landing, likely referring to either a first-stage booster landing on a drone ship or ground pad, or a full rocket recovery. Elon Musk announced the co

industryelon-musk--x

Falcon delivers 81 satellites to orbit

model-releaseselon-musk--x

SpaceX's Falcon rocket successfully deployed 81 satellites into orbit in a single launch, demonstrating the vehicle's significant payload capacity. This mission likely involved Starlink satellites or

Fast 3D Foundation Model Initialized Gaussian Splatting

arXiv:2607.03209v1 Announce Type: new Abstract: This paper introduces a fast method for high-quality 3D Gaussian Splatting (3DGS) reconstruction without traditional Structure-from-Motion (SfM). The pr

agentsarxiv-cs-cv

Local Ai

FAST: A Holistic Framework for Optimizing Memory-I/O, Computation, and Sampling in Temporal GNN Training

arXiv:2607.05095v1 Announce Type: new Abstract: Temporal Graph Neural Networks (TGNNs) are widely used for learning from dynamic graphs in applications such as recommendation, social network analysis,

local-aiarxiv-cs-lg

Hardware

Fast Asymptotically Optimal Kinodynamic Planning via Vectorization

arXiv:2607.03987v1 Announce Type: new Abstract: Sampling-based motion planners have been shown to be effective for systems with complex kinodynamic constraints and high dimensionality. However, these

hardwarearxiv-cs-ro

Fast, Parallel, Query-Efficient Binary Classification

arXiv:2607.04062v1 Announce Type: cross Abstract: We study the fundamental classification problem of computing a separating hyperplane for a binary-labeled dataset of size n with normalized d-dimensio

researcharxiv-cs-lg

FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms

arXiv:2508.02641v2 Announce Type: replace-cross Abstract: Molecular crystal structure prediction (CSP) is essential for applications in pharmaceuticals and organic electronics. However, CSP remains ch

researcharxiv-cs-lg