Search: “models”

Introducing Agent Executor, Google’s distributed Agent Runtime

model-releasesgoogle-cloud-ai

As models and harnesses improve, agents are taking on increasingly complex tasks that can run for hours or even days. But as we push agents to do more, this has surfaced a new operational problem: lon

Local Ai

Landscape-Awareness for Geometric View Diffusion Model

DGX agent

arXiv:2605.19865v1 Announce Type: new Abstract: Accurate camera viewpoint estimation under sparse-view conditions remains challenging, particularly in two-view scenarios. Recent approaches leverage di

local-aiarxiv-cs-cv

20 May 2026

LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening

model-releasesarxiv-cs-cl

arXiv:2605.19597v1 Announce Type: new Abstract: Evaluating large language models (LLMs) on natural-language logical reasoning is essential because rule-governed tasks require conclusions to follow str

Performance Monitoring of Proton Exchange Membrane Water Electrolyzer by Transformers-Based Machine Learning Model

arXiv:2605.19107v1 Announce Type: new Abstract: Green hydrogen plays an essential role in decarbonization, with capacity projected to scale to 560 GW by 2030 (vs. 1.39 GW in 2023) in net-zero settings

applicationsarxiv-cs-lg

SpecX: A Large-Scale Benchmark for Multi-Modal Spectroscopy and Cross-Paradigm Evaluation

model-releasesarxiv-cs-cv

arXiv:2605.18791v1 Announce Type: cross Abstract: Existing spectral benchmarks are limited in scale, modality alignment, and evaluation scope, and typically focus on either specialized models or multi

Stability and Discretization Error of State Space Model Neural Operators

arXiv:2605.18905v1 Announce Type: cross Abstract: Neural operators have emerged as a powerful, discretization-invariant framework for solving partial differential equations (PDEs). Although establishe

applicationsarxiv-cs-ai

TabQL: In-Context Q-Learning with Tabular Foundation Models

arXiv:2605.18979v1 Announce Type: new Abstract: We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) w

researcharxiv-cs-lg

Towards Family-Grouped Hierarchical Federated Learning on Sub-5KB Models: A Feasibility Study of Privacy-Preserving ECG Monitoring for Ultra-Resource-Constrained Wearables

arXiv:2605.18862v1 Announce Type: cross Abstract: Cardiovascular disease remains the leading cause of death worldwide, and early detection of arrhythmias through continuous ECG monitoring on wearable

researcharxiv-cs-ai

An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration

arXiv:2605.18648v1 Announce Type: cross Abstract: Central to human-aligned AI is understanding the benefits of human-elicited labels over synthetic alternatives. While human soft-labels improve calibr

Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation

arXiv:2601.01593v2 Announce Type: replace Abstract: Manual font design is an intricate process that transforms a stylistic visual concept into a coherent glyph set. This challenge persists in automate

researcharxiv-cs-cv

Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Model

arXiv:2605.17327v1 Announce Type: cross Abstract: Fast and reliable initialization is critical for monocular visual-inertial navigation systems (VINS), as it establishes the starting conditions for su

researcharxiv-cs-ai

Face inpainting with Identity Preserving Latent Diffusion Models

arXiv:2605.16696v1 Announce Type: new Abstract: Face inpainting techniques recover missing or occluded facial regions in a visually realistic manner, but preserving the identity in the final output re

safetyarxiv-cs-cv

Gemini 3.5 Flash on AI Gateway

model-releasesvercel-blog

Vercel announced the integration of Google's Gemini 3.5 Flash model into its AI Gateway, enabling developers to access this fast and efficient language model through Vercel's unified API infrastructur

Good flavor search in SU(5): a machine learning approach

model-releasesarxiv-cs-lg

arXiv:2511.08154v2 Announce Type: replace-cross Abstract: We revisit the fermion mass problem of the SU(5) grand unified theory using machine learning techniques. The original SU(5) model proposed by

Google just redesigned the search box for the first time in 25 years — here’s why it matters more than you think.

model-releasesventurebeat-ai

For a quarter century, the Google search box has been one of the most recognizable interfaces in computing: a thin white rectangle, a blinking cursor, a few typed words, and a list of blue links. On T

Hybrid Quantum-MambaVision: A Quantum-enhanced State Space Model for Calibrated Mixed-type Wafer Defect Detection

arXiv:2605.16404v1 Announce Type: new Abstract: Extracting actionable knowledge from industrial visual data is fundamentally bottlenecked by extreme class imbalance and the prohibitive computational c

applicationsarxiv-cs-cv

Isolating Nonlinear Independent Sources in fMRI with eta-TCVAE Models

arXiv:2605.16708v1 Announce Type: new Abstract: Learning meaningful latent representations from nonlinear fMRI data remains a fundamental challenge in neuroimaging analysis. Traditional independent co

applicationsarxiv-cs-lg

Isotonic Survival Regression: Calibrated Survival Distributions from Deep Cox Models

arXiv:2605.16571v1 Announce Type: cross Abstract: Time-to-event data is widespread across the life sciences and engineering, but it is typically encountered together with censoring, which complicates

applicationsarxiv-cs-ai

Tutorials

Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits

arXiv:2602.15405v2 Announce Type: replace Abstract: Robust classification in noisy environments remains a fundamental challenge in machine learning. Standard approaches typically treat signal enhancem

tutorialsarxiv-cs-lg

LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning

arXiv:2605.16675v1 Announce Type: new Abstract: We introduce LinAlg-Bench, a diagnostic benchmark evaluating 10 frontier large language models on structured linear algebra computation across a strict

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization

arXiv:2605.17877v1 Announce Type: new Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks. Group Relative Policy Optimization (GRPO) has been emerging as a l

Position: Age Estimation Models Do Not Process Biometric Data

arXiv:2605.17347v1 Announce Type: cross Abstract: When a neural network estimates someone's age from a photograph, does it process biometric data? The answer depends on whether identity-discriminative

safetyarxiv-cs-cv

Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts

model-releasesarxiv-cs-cl

arXiv:2510.07239v2 Announce Type: replace Abstract: Automated red-teaming has emerged as a scalable approach for auditing Large Language Models (LLMs) prior to deployment, yet existing approaches lack

Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models

arXiv:2508.06974v2 Announce Type: replace Abstract: 1-bit LLM quantization offers significant advantages in reducing storage and computational costs. However, existing methods typically train 1-bit LL

researcharxiv-cs-cl

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards

arXiv:2509.21319v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in

SADP: Subgoal-Aware Diffusion Policy for Explainable Robots Learned from Foundation Model Generated Demonstrations

arXiv:2605.16871v1 Announce Type: new Abstract: Explainable robots require not only successful task execution but also the ability to expose internal decision-making process in a user-friendly manner.

safetyarxiv-cs-ro

Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings

arXiv:2510.26384v2 Announce Type: replace Abstract: The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks necessitates the creation of small yet representative da

Hardware

Spherical Harmonic Optimal Transport: Application to Climate Models Comparisons

arXiv:2605.18389v1 Announce Type: new Abstract: Optimal transport provides a powerful framework for comparing measures while respecting the geometry of their support, but comes with an expensive compu

hardwarearxiv-cs-lg

StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model

arXiv:2511.14223v3 Announce Type: replace Abstract: This paper focuses on the task of speech-driven 3D facial animation, which aims to generate realistic and synchronized facial motions driven by spee

researcharxiv-cs-cv

StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video

arXiv:2605.16381v1 Announce Type: cross Abstract: Proactive streaming video understanding requires models to continuously process video streams and decide when to respond, rather than merely what to r

STRIDE-AI: A Threat Modeling Framework for Generative AI Security Assessment

arXiv:2605.17163v1 Announce Type: cross Abstract: Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to

applicationsarxiv-cs-ai

Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling

arXiv:2605.18281v1 Announce Type: new Abstract: Modern deep learning science often assumes that neural networks learn from a fixed data distribution. However, many practically important learning probl

safetyarxiv-cs-lg

The future of agentic development: Redefining the data practitioner lifecycle with Data Agent Kit

model-releasesgoogle-cloud-ai

The modern software development landscape isn’t happening just on one surface — it’s happening across an entire ecosystem of agentic tools. Agents are being developed at an unprecedented scale, and th

Time-Efficient Hybrid Hyperparameter Tuning Approach for Cardiovascular Disease Classification

arXiv:2411.18234v2 Announce Type: replace-cross Abstract: Cardiovascular diseases (CVDs) are any serious illness of the heart, which require accurate diagnosis to prevent fatal consequences. Hyperpara

Why Modeling Human Haptic Material Perception with AI Is Difficult

arXiv:2605.16602v1 Announce Type: cross Abstract: Touch plays a central role in how humans perceive and recognize materials through physical contact. Despite decades of research, the mechanisms by whi

researcharxiv-cs-ai

Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making

arXiv:2605.16054v1 Announce Type: cross Abstract: Recent work has framed decision-making as a sequence modeling problem using generative models such as diffusion models. Although promising, these appr

Artificial Aphasias in Lesioned Language Models

arXiv:2605.16222v1 Announce Type: new Abstract: Aphasias, selective language impairments which can arise from brain damage, reveal the functional organization of human language by providing causal lin

researcharxiv-cs-cl

CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models

arXiv:2605.15549v1 Announce Type: cross Abstract: The demand for clean energy is ever increasing, with new nuclear technologies presenting a complementary solution to renewable energies. However, desi

Detecting Heel Strike and toe off Events Using Kinematic Methods and LSTM Models

arXiv:2503.00794v2 Announce Type: replace Abstract: Accurate gait event detection is crucial for gait analysis, rehabilitation, and assistive technology, particularly in exoskeleton control, where pre

safetyarxiv-cs-ro

Agents

Enterprises are facing an integration problem no model alone can fix

Enterprise AI integration has become the defining challenge for organizations moving from pilot programs to production — and the companies solving it are reshaping how work gets done across every indu

agentssiliconangle

Entropy-Based Characterisation of the Polarised Regime in Latent Variable Models

arXiv:2605.15965v1 Announce Type: new Abstract: Variational Autoencoders (VAEs) often exhibit a polarised regime in which latent variables separate into active, passive, and mixed subsets. Existing cr

researcharxiv-cs-lg

Judge Circuits

model-releasesarxiv-cs-cl

arXiv:2605.16023v1 Announce Type: new Abstract: LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when its

Linked Multi-Model Data on Russian Domestic and Foreign Policy Speeches

arXiv:2605.15886v1 Announce Type: new Abstract: This paper introduces a dataset of interlinked multimodal political communications from the Russian government, addressing persistent deficiencies in th

safetyarxiv-cs-cl

Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding

model-releasesarxiv-cs-cv

arXiv:2605.15342v1 Announce Type: new Abstract: Video reasoning models are a core component of egocentric and embodied agents. However, standard benchmarks for assessing models provide only evaluation

NEW paper worth reading. GPT-5.4 nano plus a critic-comparator orchestration loop hits 76.4% on SWE-bench Verified, matching standalone Gemi…

NEW paper worth reading. GPT-5.4 nano plus a critic-comparator orchestration loop hits 76.4% on SWE-bench Verified, matching standalone Gemini 3 Pro and Claude Opus 4.5 Thinking. The trick is to selec

model-releasesdair-ai--x

Perforated Neural Networks for Keyword Spotting

model-releasesarxiv-cs-lg

arXiv:2605.15647v1 Announce Type: new Abstract: Edge machine learning presents a unique set of constraints not encountered in cloud-scale model deployment: strict memory budgets, limited compute, and

Towards a more realistic evaluation of machine learning models for bearing fault diagnosis

arXiv:2509.22267v4 Announce Type: replace Abstract: Reliable detection of bearing faults is essential for maintaining the safety and operational efficiency of rotating machinery. While recent advances

safetyarxiv-cs-lg

Agents

Training on Documents About Monitoring Leads to CoT Obfuscation

arXiv:2605.15257v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is one of the most promising tools we have for detecting model misbehavior, but its effectiveness depends on models fa

agentsarxiv-cs-lg