Search: “local-ai”

Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents

arXiv:2608.03137v1 Announce Type: new Abstract: Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon i

Local Ai

When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding

DGX agent

arXiv:2608.03918v1 Announce Type: cross Abstract: Efficient long-video understanding requires vision--language models (VLMs) to reason over a small number of frames selected as sparse visual evidence.

local-aiarxiv-cs-ai

5 Aug 2026

When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning

arXiv:2608.02940v1 Announce Type: new Abstract: A reproducible compression statistic can still select the wrong candidate. A dense pruning score with 0.906 split-half reliability predicted a 16.1% gai

When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking

arXiv:2608.03902v1 Announce Type: new Abstract: Resource constraints on UAV platforms have driven a paradigm shift in aerial tracking, from pursuing performance toward balancing accuracy with efficien

Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering

arXiv:2608.01463v2 Announce Type: replace Abstract: Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims. We introduce Localized Mul

Action Chunk Scheduling for Batched Robot Policy Serving

arXiv:2608.00337v1 Announce Type: new Abstract: Deploying robot foundation models at scale is the next step towards realizing the potential of general-purpose robots. However, Vision-Language-Action (

AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting

arXiv:2603.25129v2 Announce Type: replace Abstract: While 3D Vision Foundation Models (3DVFMs) have demonstrated remarkable zero-shot capabilities in visual geometry estimation, their direct applicati

Assessing the Impacts of Imperfect Datasets on Client Selections in Federated Learning

arXiv:2608.02250v1 Announce Type: new Abstract: Federated learning (FL) is a popular distributed learning framework where multiple clients perform local training and a server aggregates the locally up

Belief-Contraction-Driven Active Inverse Source Localization and Characterization

arXiv:2501.13084v2 Announce Type: replace Abstract: Active inverse source localization and characterization (ISLC) in dynamic fields requires sequential decision making under partial observability, wh

Beyond Global Latents: Chunk-Based Sparse Grid VAE for Scalable 3D Modeling

arXiv:2608.02016v1 Announce Type: new Abstract: Sparse voxel grids preserve the spatial structure needed for detailed 3D reconstruction, but their memory still grows rapidly with resolution as active

Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection

arXiv:2608.00442v1 Announce Type: new Abstract: Medical anomaly detection identifies abnormal images and localizes lesions under scarce supervision while generalizing across organs and modalities. Exi

bFaaaP: An Inclusive, Head-Angle Piano-Pedal Interaction that Quantitatively Reproduces a Pianist's Intended Pedalling -- Foot-Free, for Acoustic and Electronic Pianos

arXiv:2608.00633v1 Announce Type: cross Abstract: Expressive piano performance depends on the sustain (damper) pedal, operated by foot, excluding players who cannot readily use their feet: wheelchair

CascadeLUT: Information-Ordered Streaming Inference for Bandwidth-Constrained FPGAs

arXiv:2608.00720v1 Announce Type: cross Abstract: Mapping neural networks to FPGAs enables low-latency, energy-efficient inference, particularly for lookup table (LUT)-based models that eliminate mult

CDG-MAE: Cross-view Masked Modeling using Diffusion Generated Views

arXiv:2506.18164v2 Announce Type: replace Abstract: Cross-view masked autoencoding has emerged as a powerful pretext task for learning dense correspondences, which are essential for applications such

Celty: SpMspV GPU Kernel and SIMT Co-Design for Efficient Dual-Sparse LLM Inference

arXiv:2608.01536v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly rely on sparsity to reduce inference cost, but most prior work targets a single sparsity source-either weigh

Device-First Feedback: Toward Mobile-Native LLM-Driven Neural Architecture Search

arXiv:2608.00078v1 Announce Type: new Abstract: Deploying convolutional neural networks generated by large language models (LLMs) on real mobile hardware requires more than GPU validation accuracy: IN

DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation

arXiv:2608.02495v1 Announce Type: new Abstract: Despite the remarkable progress over the past decades, accurately identifying small objects remains challenging because of their insufficient visual cue

Dynamic Resolution Routing for Efficient Egocentric Grounding

arXiv:2608.01638v1 Announce Type: new Abstract: Egocentric visual grounding requires high-resolution inputs to localize small objects. However, scaling Multimodal Large Language Models to this domain

Efficient nonlinear flame response modeling for propulsion thermoacoustic analysis using limited numerical data

arXiv:2409.05885v2 Announce Type: replace Abstract: Characterizing nonlinear flame response is critical for predicting thermoacoustic instabilities in propulsion combustors, yet obtaining a comprehens

Empowering Credit Risk Detection in Weixin Pay with Billion-Scale Deep Graph Learning

arXiv:2608.02168v1 Announce Type: new Abstract: Credit risk detection, particularly mitigating individual fraud, is crucial for maintaining the stability of digital financial ecosystems. Accurately id

EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents

arXiv:2608.01359v1 Announce Type: new Abstract: Outcome-based reinforcement learning enables search-augmented language agents to learn from verifiable final answers, but its trajectory-level credit ca

local-aiarxiv-cs-cl

FAST-GS: Frequency Aware Space-time Gaussian Splatting for Photorealistic Dynamic Novel View Synthesis

arXiv:2608.01958v1 Announce Type: new Abstract: 4D Gaussian Splatting (4DGS) excels in dynamic 3D reconstruction and real-time novel view synthesis via efficient 4D Gaussian representations and parall

FlowPilot: Real-Time World-Action Modeling for Agile UAV Navigation

arXiv:2608.00635v1 Announce Type: new Abstract: We present FlowPilot, a compact world-action model for real-time onboard UAV navigation from depth. Unlike map-then-optimize pipelines that require loca

FreqAnchorAD: Language-Free Zero-Shot Anomaly Detection via Frequency-Deviation Anchoring

arXiv:2608.00695v1 Announce Type: new Abstract: Zero-shot anomaly detection (ZSAD) aims to detect anomalies and localize defective regions in unseen target domains without target training data. Recent

FreqNav: Stage-Wise Frequency Routing for Object-Oriented Aerial Vision-Language Navigation

arXiv:2608.00970v1 Announce Type: new Abstract: Object-oriented aerial vision-and-language navigation (VLN) requires searching for a described target and landing on it precisely, under long-horizon an

Generalized Quadratic Gradient: A New Direction in Optimization via the Fusion of Positive-Definite Curvature Matrices and Gradients into A Unified Framework

arXiv:2608.01552v1 Announce Type: cross Abstract: Quadratic Gradient (QG) is a Newton-type optimization framework that bridges first-order gradient descent and second-order optimization by incorporati

Geometric-Topological Perception and Motion Prior for Real-Time Satellite Video Object Tracking

arXiv:2603.07564v2 Announce Type: replace Abstract: Satellite video object tracking (SVOT) remains fundamentally challenging due to texture scarcity, arbitrary rotation, aspect ratio changes, and seve

GitHub - john-paul-ruf/spirit-guides: A reflective companion for self-guided inner work — AI-powered guides lead introspective sessions drawn from therapy, spirituality, and philosophy. Desktop app (Electron + React) with local markdown storage

I would love some feedback on this work in progress. Create, dialog with, mash up, and evolve spirit guides based on real concepts spanning psychological, philosophical, and religious origins. Honestl

local-air-ollama

GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models

arXiv:2603.13418v2 Announce Type: replace Abstract: Structured pruning is widely applied to compress large language models (LLMs), but its performance depends heavily on how neuron importance is estim

Help with a prompt on Synthid

First I want to say how evil Synthid sounds. Did the creator want it to be like the Sith Lord or something?! For text generation the claim is it chooses word outputs that can be watermarked easily? Ma

local-air-ollama

Hugging Face CEO says China is winning the AI race and dominating on open models

This is something that was spoken here and there, and now it is like writing on the wall. The main additional point is that China has created an independent supply chain. Starting from raw materials a

local-air-localllama

I added a verify-before-load safety check for Ollama models

I maintain llm-checker, and I’ve added structural model-file validation for Ollama. Ollama stores downloaded models as local blobs. If one is truncated, malformed, or has invalid internal offsets, you

local-air-ollama

K-space Gaussian Representation for Parallel MRI

arXiv:2608.00075v1 Announce Type: new Abstract: Accelerated magnetic resonance imaging (MRI) aims to recover the k-space signal from acquired measurements, where accurate estimation of missing samples

Language Equality has a Price: A Systematic Investigation of Multi-turn LLM Performance for EU-24+

arXiv:2608.01395v1 Announce Type: new Abstract: We evaluate large language models (LLMs) as language agents playing goal-directed dialogue games in self-play across 30 languages: the 24 official EU la

local-aiarxiv-cs-cl

Local Margin Restoration for Test-Time Adaptation of Vision-Language Models

arXiv:2608.02216v1 Announce Type: new Abstract: Vision-language models (VLMs) such as CLIP exhibit remarkable zero-shot capabilities, yet their performance frequently degrades sharply under unexpected

Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation

arXiv:2603.03672v2 Announce Type: replace Abstract: The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space. Exis

Location-Aware Fine-Grained Representation Learning for Medical Vision Foundation Models

arXiv:2608.00976v1 Announce Type: new Abstract: Fine-grained visual representations are essential for medical image analysis, particularly when diagnostically relevant evidence is subtle and spatially

LOCUS-DT: Localization via Observation-Conditioned Uncertainty Scoring with Digital Twins

arXiv:2608.00406v1 Announce Type: cross Abstract: Accurate indoor localization is essential for emerging applications in robotic navigation and search and rescue. While classical methods typically foc

MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping

arXiv:2608.02014v1 Announce Type: new Abstract: Cross-embodiment dexterous grasping aims to synthesize stable grasps across heterogeneous multi-fingered hands with little or no embodiment-specific tun

MBO Scheme for Local Chan--Vese Segmentation

arXiv:2608.00893v1 Announce Type: new Abstract: Robust to intensity inhomogeneity, the local Chan--Vese (LCV) model extends the classical Chan--Vese (CV) image segmentation method by incorporating loc

Open-DiffLoco: Open-Source Differentiable Learning for Deployable Blind Quadruped Locomotion

arXiv:2608.02069v1 Announce Type: cross Abstract: Developing deployable locomotion policies through conventional reinforcement learning often requires complex reward engineering and expensive training

Open-Set Visual Text Forensics via Sparse-Constraint Rectified Flow

arXiv:2608.02258v1 Announce Type: new Abstract: Rapidly evolving Generative AI enables sophisticated visual text manipulations that increasingly evade current forensic detectors. Existing discriminati

Paris as a 15-Minute City: An Explainable AI Perspective

arXiv:2608.00815v1 Announce Type: new Abstract: The 15-minute city promotes access to everyday services within a short walk or bicycle ride, but its relationship with observed mobility remains difficu

PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding

arXiv:2601.02457v2 Announce Type: replace Abstract: Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent

PixelSR: Efficient Screen Content Super-Resolution via Pixel Classification

arXiv:2608.00646v1 Announce Type: new Abstract: Screen content images are generally composed of texts and graphics. Compared to natural images, these man-made images contain a large quantity of sharp

Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality

arXiv:2608.02575v1 Announce Type: new Abstract: Diffusion models rely on stochastic inputs, yet on finite-precision hardware, the 'randomness' they consume is realized as deterministic numerical orbit

RadYOLO: Computationally Efficient 3D Object Detection and Segmentation in CT and MRI

arXiv:2608.00508v1 Announce Type: new Abstract: Object detection and segmentation in three-dimensional medical images is a very active area of research. However, most proposed deep learning models car

Reconstruction-Shift Discrimination via Mask-Guided Latent Diffusion for Medical Anomaly Detection

arXiv:2608.00444v1 Announce Type: new Abstract: Unsupervised medical anomaly detection learns normal anatomical patterns from healthy training images and identifies deviations at test time. Reconstruc