Search: “local-ai”

Inpainting U-Net for seamless pedestrian-level wind prediction across urban morphologies

arXiv:2607.02560v1 Announce Type: new Abstract: Pedestrian-level wind prediction is essential for urban design and wind-comfort assessment, but high-fidelity simulations such as LES remain computation

Internal Pluralism and the Limits of Pairwise Comparisons

DGX agent

arXiv:2607.02672v1 Announce Type: new Abstract: Local pairwise comparisons are a standard tool for learning how people want decision rules to work, e.g., in participatory design or alignment. However,

local-aiarxiv-cs-ai

7 Jul 2026

Interpretable Nanoporous Materials Design with Symmetry-Aware Networks

arXiv:2509.15908v3 Announce Type: replace-cross Abstract: Nanoporous materials hold promise for diverse sustainable applications, yet their vast chemical space poses challenges for efficient design. M

Joint Velocity Slope Diffusion Prior for Structurally Constrained Velocity Model Building

arXiv:2607.04982v1 Announce Type: cross Abstract: High-resolution velocity models are crucial for reservoir characterization and subsurface delineation. However, the band limited nature of our surface

Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI

arXiv:2606.16533v3 Announce Type: replace Abstract: We introduce extbf{Kairos}, a regret-aware native world-action model stack for Physical AI. Kairos is motivated by the view that a physical world mo

KAM-WM: Kinematic Affordance Maps from Latent World Models for Robot Manipulation

arXiv:2607.04652v1 Announce Type: new Abstract: Learning manipulation from few demonstrations requires visual priors that capture not only where to interact, but also how the interaction should begin;

local-aiarxiv-cs-ro

LLM for the development of FCM

arXiv:2607.04983v1 Announce Type: cross Abstract: This article is about the development of a fuzzy cognitive map using a local large language model. In the light of recent advances it is evident that

LoMa: Local Feature Matching Revisited

arXiv:2604.04931v2 Announce Type: replace Abstract: Local feature matching has long been a fundamental component of 3D vision systems such as Structure-from-Motion (SfM), yet progress has lagged behin

LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

arXiv:2607.04733v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain

MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model

arXiv:2607.03013v1 Announce Type: cross Abstract: Images captured by consumer electronic devices, such as mobile phones and digital cameras, often suffer from low-light degradation due to sensor limit

Masked Generative-Contrastive Representation Learning for Cross-Dataset EEG-Based Emotion Recognition

arXiv:2607.04139v1 Announce Type: new Abstract: Self-supervised learning (SSL) shows strong potential for cross-dataset transfer by improving feature representation and generalization. However, its ap

MedMambaLite: Hardware-Aware Mamba for Medical Image Classification

arXiv:2508.05049v1 Announce Type: cross Abstract: AI-powered medical devices have driven the need for real-time, on-device inference such as biomedical image classification. Deployment of deep learnin

Memory-Orchestrated Semantic System (MOSS): An Auditable Agentic Memory Architecture

arXiv:2607.04391v1 Announce Type: new Abstract: Long-term memory remains a structural weakness of AI agents. The dominant approach, retrieval-augmented generation (RAG), relies on embedding-based simi

MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution

arXiv:2607.05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further

Missing Data Imputation under Manifold Hypothesis

arXiv:2607.03641v1 Announce Type: cross Abstract: The manifold hypothesis posits that high-dimensional data are concentrated near a low-dimensional embedded manifold. Recent advances in mixture variat

Multi-Large Language Model Orchestrated Severity Assessment of Clinical Records (MOSAIC)

arXiv:2607.05032v1 Announce Type: new Abstract: Background: Disease severity is a multidimensional construct difficult to capture with rule-based approaches in Electronic Healthcare Records (EHR). Age

Not Every Sync Is Safe: Calibrated DiLoCo Scheduling for Shared AI Infrastructure

arXiv:2607.02544v1 Announce Type: cross Abstract: DiLoCo-style training reduces communication by letting learner islands train locally before occasional outer synchronization, making it attractive for

Object-Centric Environment Modeling for Agentic Tasks

arXiv:2607.02846v1 Announce Type: new Abstract: Large language model (LLM) agents can improve through accumulated experience, but free-form textual memories become difficult to maintain, validate, and

OpenGlass: A Sensing-Computing Split Architecture for Local MLLM-Driven Real-Time Visual Assistance

arXiv:2607.03213v1 Announce Type: cross Abstract: We present OpenGlass, an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance, with a primary focus on blind

Phase-Preserving Trimodal Transformer for Tropical Forest Biomass Estimation Using Optical and PolInSAR Data

arXiv:2607.03663v1 Announce Type: cross Abstract: The accurate estimation of Above-Ground Biomass (AGB) in mature tropical forests remains a critical challenge in remote sensing, primarily due to the

Physics-Informed Domain-Invariant Feature Learning with Autoencoder-Driven Gaussian Clustering for Robust Non-line-of-Sight Scenarios

arXiv:2607.02537v1 Announce Type: cross Abstract: Jamming and spoofing pose significant threats to wireless and satellite navigation by disrupting radio-frequency (RF) signals and compromising availab

PulmoSight-XAI: An Explainable Multi-View Attention Ensemble with Gradient Boosting Meta-Learning for Multi-Label Chest X-Ray Classification

arXiv:2607.04478v1 Announce Type: cross Abstract: Automated chest X-ray classification remains challenging due to severe class imbalance, co-occurring pathologies, and the loss of localized features i

RePos: Relative-to-Absolute Output Factorization for Cross-Environment WiFi-Based 3D Human Pose Estimation

arXiv:2607.02986v1 Announce Type: new Abstract: Device-free 3D human pose estimation using commodity WiFi Channel State Information (CSI) enables privacy-preserving and illumination-robust human sensi

Semantic Integration and Lexical Expectation Shape N400 and P600 Dynamics During Naturalistic Reading

arXiv:2607.04107v1 Announce Type: new Abstract: Word surprisal is a well-established computational predictor of human neural responses during language comprehension, but it remains less clear whether

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

arXiv:2601.08303v3 Announce Type: replace Abstract: Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to

Sparse4D-Radar: An Efficient and Robust Framework for Surround-View 3D Object Detection via 4D Radar-Camera Fusion

arXiv:2607.04098v1 Announce Type: new Abstract: In recent years, 4D imaging radar has gained wide attention in autonomous driving for its robustness against harsh weather and ability to output target

Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models

arXiv:2602.04356v2 Announce Type: replace Abstract: Targeted adversarial attacks on Large Vision-Language Models (LVLMs) test whether small image perturbations can steer model responses toward attacke

Survey: Chinese companies plan to allocate 46% of their AI accelerator budget to domestic products in the next 12 months, up from 30% today, a shift from Nvidia (Gao Yuan/Bloomberg)

Gao Yuan / Bloomberg: Survey: Chinese companies plan to allocate 46% of their AI accelerator budget to domestic products in the next 12 months, up from 30% today, a shift from Nvidia — Chinese compani

local-aitechmeme

SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery

arXiv:2607.02807v1 Announce Type: new Abstract: Long-running coding agents such as autoresearch can persistently discover optimizations for open-ended problems. However, they tend to converge onto a s

Syntiant, which makes low-power chips for on-device AI, files for initial public offering

A chipmaker called Syntiant Corp. that specializes in making low-powered processors that run artificial intelligence locally on devices has filed to go public. The company filed its initial public off

local-aisiliconangle

TACO: TActile World Model as a Self-COrrector forScalable VLA Post-Training

arXiv:2607.02840v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown promising generalization in robotic manipulation, but they still struggle with contact-rich tasks, where

local-aiarxiv-cs-ro

The Multiscale Single-Index Model: A Stylized Model for Hierarchical Feature Learning

arXiv:2607.03347v1 Announce Type: new Abstract: We consider the Multiscale Single-Index Model (MSIM), first introduced in ite{oymak2021learning}, as a stylized model for hierarchical learning with sca

Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generation

arXiv:2607.02798v1 Announce Type: new Abstract: Modern image-and-text-to-video diffusion models can synthesize highly realistic videos by iteratively denoising an initial Gaussian noise tensor conditi

Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning

arXiv:2509.22082v3 Announce Type: replace Abstract: Federated learning enables distributed information sharing and collaborative model training without exposing raw client data. However, shared gradie

Transformer-based Multisensor Data Fusion of Ultrasonic Guided Wave and FBG-based Strain Measurements for Multitask Aerospace Structural Health Monitoring

arXiv:2607.02545v1 Announce Type: cross Abstract: Structural health monitoring (SHM) has emerged as an essential tool for ensuring the integrity and reliability of critical engineering structures, par

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models

arXiv:2603.14504v2 Announce Type: replace-cross Abstract: Optimizing the noise samples of diffusion and flow models is an increasingly popular approach to align these models to target rewards at infer

UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization

arXiv:2607.04498v1 Announce Type: new Abstract: With the proliferation of AI-generated content, sophisticated multimedia manipulation has raised critical concerns about malicious applications such as

v0.31.2

Ollama v0.31.2-rc1 is a pre-release version released on July 6, 2026. This release includes CI improvements to avoid unbounded parallelism, fixes for CUDA toolkit lookup, updates to cloud documentatio

local-aiollama-releases

v0.31.2-rc2: llm: allow iGPU mmproj offload with fit padding (#16996)

This release candidate introduces support for offloading the image GPU projection (mmproj) to an integrated GPU when using fit padding in Ollama's LLM processing, addressing technical improvements for

local-aiollama-releases

When Words Predict Workload

arXiv:2607.04951v1 Announce Type: cross Abstract: Standard distributed ac{llm} schedulers rely on static token counts or rolling latency averages, making them susceptible to failures on statutorily co

WPG-MoE: Weak-Prior-Guided Dense Mixture-of-Experts for User-Level Social Media Depression Detection

arXiv:2607.04350v1 Announce Type: new Abstract: Online social media posts provide scalable signals for early depression screening, and recent studies mainly improve pre-classification evidence through

b9879

b9879 is a release build identifier in the llama.cpp project, a C/C++ implementation of Meta's LLaMA language models. This release likely contains bug fixes, performance improvements, and feature upda

b9881

b9881 is a release of llama.cpp, an LLM inference tool written in C/C++. This release likely includes bug fixes, performance improvements, and platform support enhancements for running large language

b9884

B9884 is a llama.cpp release that addresses a Vulkan 32-bit integer overflow fix in CEIL_DIV . Released on July 6, 2026 , the build also includes platform-specific binaries for macOS, Linux, Android,

b9885

B9885 is a build-tagged release of llama.cpp, an open-source C/C++ inference engine for running large language models locally. The project does not use traditional semantic versions; instead it ships

b9886

Release b9886 of llama.cpp addresses a bug fix for K/V rotation input handling in attention mechanisms, specifically when buffers are unallocated during DFlash speculative decoding's KV-injection pass

b9891

b9891 is a build release of llama.cpp, the open-source C/C++ inference engine for running large language models locally. This release enables LLM inference with minimal setup and state-of-the-art perf

b9892

Release b9892 is a version identifier for llama.cpp, an open-source C/C++ framework for running large language model inference on consumer hardware. This specific build (b9892) represents a snapshot o