Search: “local-ai”

An Interpretable, Controllable Time-Varying IIR Denoiser for On-Device Assistive Hearing

arXiv:2603.02794v2 Announce Type: replace-cross Abstract: We present TVF (Time-Varying Filtering), an interpretable, low-latency speech enhancement model for real-time, on-device assistive hearing. A

b9839

Build b9839 of llama.cpp adds offline mode support to the llama download command for checking cached models without network access, and fixes a use-after-free bug in the URL-task callback. llama.cpp i

local-aillama-cpp-releases

29 Jun 2026

b9840

b9840 is a release of llama.cpp, a tool for LLM inference in C/C++. The release enables running AI models locally on Windows, Linux, and macOS. This specific build tag likely contains bug fixes, perfo

Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding

arXiv:2603.10863v2 Announce Type: replace Abstract: Despite the remarkable capabilities of Multimodal Large Language Models (MLLMs), they still suffer from visual fading in long-context scenarios. Spe

CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection

arXiv:2504.01882v2 Announce Type: replace Abstract: The use of DNS over HTTPS (DoH) tunneling by an attacker to hide malicious activity within encrypted DNS traffic poses a serious threat to network s

Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis

arXiv:2606.27634v1 Announce Type: new Abstract: Small Language Models (SLMs) are increasingly being considered for deployment on edge devices such as laptops, enabling private, low-latency, and locall

Decentralized Orchestration Architecture for Fluid Computing: A Secure Distributed AI Use Case

arXiv:2603.12001v2 Announce Type: replace-cross Abstract: Distributed AI and IoT applications increasingly execute across heterogeneous resources spanning end devices, edge/fog infrastructure, and clo

DIM-WAM: World-Action Modeling with Diverse Historical Event Memory

arXiv:2606.27677v1 Announce Type: cross Abstract: World-action models have shown promising robot-manipulation performance by jointly predicting future visual states and actions. However, existing meth

Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization

arXiv:2606.27663v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models leverage large-scale vision-language pretraining for flexible robot manipulation, yet at test time they remain britt

local-aiarxiv-cs-ro

Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment

arXiv:2606.27731v1 Announce Type: cross Abstract: Despite their strong general capabilities, large language models (LLMs) often remain unreliable when outputs must be numerically precise. A key reason

Hybrid coupling with operator inference and the overlapping Schwarz alternating method

arXiv:2511.20687v3 Announce Type: replace-cross Abstract: This paper presents a novel hybrid approach for coupling subdomain-local non-intrusive Operator Inference (OpInf) reduced order models (ROMs)

Image-based Geo-localization for Robotics: Are Black-box Vision-Language Models there yet?

arXiv:2501.16947v2 Announce Type: replace Abstract: The advances in Vision-Language models (VLMs) offer exciting opportunities for robotic applications involving image geo-localization - the problem o

Long-Term Prediction of Local and Global Human Motion with Occlusion Recovery

arXiv:2606.27900v1 Announce Type: new Abstract: Human motion describes the three-dimensional full-body movement of a person. Anticipating such motion holds significant relevance across a wide range of

NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning

arXiv:2606.27771v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that a

Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models

arXiv:2606.27593v1 Announce Type: new Abstract: We introduce a categorical framework called ODYSSEY for constructing verifiable, local truth-preserving foundation models as compositions of foundries:

OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal

arXiv:2606.28094v1 Announce Type: cross Abstract: Real-world object removal is challenging due to two key difficulties: the target object's non-local effects, such as shadows and reflections, which ar

Perceptual 3D Simulation With Physical World Modeling

arXiv:2606.27575v1 Announce Type: new Abstract: Predicting how a scene will evolve after a desired 3D transformation from images is a central goal in vision, graphics, and robotics. Yet unlike ideal s

Physics-Guided Robotic Radiation Source Localization along Arbitrary Measurement Paths in Unstructured Environments

arXiv:2606.27624v1 Announce Type: cross Abstract: Using robots to estimate the location of the radiation source is an effective way to improve efficiency and safety. Existing methods focus on planning

Psychometric Comparability of LLM-Based Digital Twins

arXiv:2601.14264v2 Announce Type: replace-cross Abstract: Large language models (LLMs) act as digital twins for human respondents, yet their psychometric comparability remains uncertain. We propose a

Radar Guided Camera Verification for Automatic Emergency Braking Rethinking Object Detection in Radar Camera Fusion

arXiv:2606.27556v1 Announce Type: new Abstract: Radar camera fusion is widely used in Automatic Emergency Braking AEB systems because radar provides reliable range and velocity measurements while came

Scene and Human in One World: Reconstruction in a Feedforward Pass

arXiv:2606.27720v1 Announce Type: new Abstract: Reconstructing humans in dynamic scenes from moving monocular cameras remains challenging due to scale ambiguity, human-scene misalignment, and occlusio

SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Clouds

arXiv:2606.27491v1 Announce Type: new Abstract: Automated instance segmentation of forest LiDAR point clouds is increasingly critical as forest monitoring moves toward scalable, detailed, 3D measureme

Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection

arXiv:2606.27655v1 Announce Type: new Abstract: Accurately localizing and segmenting small targets in low signal-to-noise ratio (SNR) infrared sequences remains a challenging task. Since targets are o

Tessellating The Earth

arXiv:2606.27514v1 Announce Type: new Abstract: Geolocation encoders, which map geographic coordinates to learned representations, are emerging as an effective means of capturing visual and non-visual

Tomorrow, we're releasing an ML model for on-device PII redaction, which is far smaller than existing models, but is surprisingly effective.…

Tomorrow, we're releasing an ML model for on-device PII redaction, which is far smaller than existing models, but is surprisingly effective. It is a first iteration. Will be live at 12:30! A big relea

local-aiclem-delangue--x

TruEye: Fine-Grained Detection of AI-Generated Human Subjects in Images

arXiv:2606.27505v1 Announce Type: new Abstract: AI generated images are proliferating across the Internet. While some are used for entertainment, others are weaponized for fraud and social engineering

Trustworthy Predictive Distributions for Tail Events with Semiparametric Diagnostic Transport Maps

arXiv:2603.11229v2 Announce Type: replace-cross Abstract: Machine learning forecast systems are moving beyond point predictions to full predictive distributions for future outcomes y conditional on co

Understanding Rollout Error in Graph World Models

arXiv:2606.27780v1 Announce Type: new Abstract: World models are often used for planning by rolling learned dynamics forward. Many planning environments, however, are not vectors or images; they are g

v0.30.12

v0.30.12 is a release candidate (rc0) that fixes a gemma4:12b floating point exception crash on x86, CUDA, Linux, and Windows systems. It includes improvements to ollama launch for Hermes Desktop, all

local-aiollama-releases

Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing

arXiv:2606.27926v1 Announce Type: new Abstract: Geometry Problem Solving have increasingly adopt the neuro-symbolic paradigm, combining neural intuition with symbolic rigor. However, current framework

We actually kickstart things early tomorrow with 2 workshops on Local AI See you guys tomorrow

Swyx announced two workshops on Local AI scheduled for the following day. The announcement was made via X (formerly Twitter) to invite the community to attend these early-morning sessions.

local-aiswyx--x

b9829

Build b9829 is an intermediate release of llama.cpp, the open-source C/C++ project that enables users to run large language models on consumer hardware without expensive GPUs or cloud infrastructure.

b9830

llama.cpp b9830 is a release of the open-source LLM inference project enabling local language model execution with minimal setup . The release likely includes backend improvements and optimizations fo

b9831

Release b9831 of llama.cpp includes backend detection improvements and synchronization enhancements, particularly for async CUDA copies and Vulkan backend operations. Llama.cpp is designed to enable L

b9832

B9832 is a build release of llama.cpp from the ggml-org project , which is a free and open-source tool that allows you to run AI models locally on Windows, Linux and macOS . The release likely contain

b9833

Release b9833 is a build of llama.cpp, an open-source project for LLM inference in C/C++. This release represents an incremental update within the llama.cpp development cycle, following the standard r

Ends Tuesday. Top winners each get $ + DGX Spark + Stripe credits.

Ends Tuesday. Top winners each get $ + DGX Spark + Stripe credits. The Hermes Agent Accelerated Business Hackathon presented by @NVIDIAAI × @stripe × @NousResearch starts now, for builders making agen

local-ainous-research--x

MASSIVE NEWS Teamed up with NVIDIA to make Local AI The Default

MASSIVE NEWS has partnered with NVIDIA to advance local AI deployment as a default option, addressing the shift toward on-device and edge AI processing rather than cloud-dependent models. This collabo

local-aiswyx--x

b9822

b9822 is a release of llama.cpp, a project for LLM inference in C/C++ . As a build version in the ongoing development sequence of the llama.cpp project, this release likely includes bug fixes, perform

b9824

The search results show information about other llama.cpp releases and the project generally, but do not contain specific details about release b9824. Based on the available information about llama.cp

b9825

b9825 is a release of llama.cpp, the C/C++ implementation for large language model inference . This build represents an intermediate version in the ongoing development of llama.cpp, part of the ggml-o

b9826

B9826 is a release of llama.cpp, an LLM inference project written in C/C++ . llama.cpp enables users to run large language models on consumer hardware without expensive GPUs or cloud infrastructure .

b9827

Release b9827 of llama.cpp, released on June 27, 2026, added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy for improved CUDA tensor copying performance. When tensors are not fully contiguous but each

b9828

B9828 is a llama.cpp release featuring OpenCL flash attention improvements, including reworked FA kernels for f16 and f32, prefill prepass kernels, and FA kernels for q4_0 and q8_0 quantization format

Model page: https://ollama.com/library/ornith

Ornith is a model available through the Ollama library, a platform for running large language models locally. The specific capabilities and parameters of this model can be found on its dedicated model

local-aiollama--x

A Multi-Fidelity Convolutional Autoencoder-Transfer Learning Framework for Guided-Wave-Based Damage Diagnosis Using Large Simulated and Limited Experimental Datasets

arXiv:2606.27304v1 Announce Type: new Abstract: Guided wave-based structural health monitoring (GWSHM) with onboard transducers offers significant potential for the early diagnosis of damage in engine

26 Jun 2026

A Multi-Level Validation and Traceability Framework for AI-Generated Telescope Scheduling Decisions

arXiv:2606.26585v1 Announce Type: new Abstract: With the gradual introduction of AI into telescope scheduling, AI-based decision-making has shown advantages in handling complex multi-constraint proble

26 Jun 2026

Accelerated sampling using SamAdams variable timesteps and position-adaptive Langevin dynamics

arXiv:2606.26881v1 Announce Type: cross Abstract: We introduce an accelerated Langevin-based sampling method that is based on two complementary devices: SamAdams adaptive timestepping, which automatic