Search: “local-ai”

Integrating Local and Global Entropy for Uncertainty Quantification in LLMs

arXiv:2606.09875v1 Announce Type: cross Abstract: Large language models hallucinate confidently, making uncertainty quantification (UQ) essential for reliable deployment. Existing methods rely predomi

Local Ai

Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents

DGX agent

arXiv:2606.10616v1 Announce Type: new Abstract: Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts that exceed their finite context windows, making memory rete

local-aiarxiv-cs-ai

10 Jun 2026

Link to workflow: https://comfy.org/workflows/be0889296f65-be0889296f65/

This entry references a ComfyUI workflow shared via a direct link, likely demonstrating a specific image generation or processing pipeline using the ComfyUI node-based interface. The workflow ID (be08

local-aicomfyui--x

LTX 2.3 : Union Control & SDXL

local-air-stablediffusion

LTX-2.3-22b Union Control is a unified control IC-LoRA (In-Context LoRA) trained on top of LTX-2.3-22b that enables multiple control signals to be used for video generation from text and reference fra

MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting

arXiv:2606.09855v1 Announce Type: cross Abstract: Korean folk painting (minhwa) is built from a small vocabulary of auspicious symbols, a tiger for protection, a pair of birds for marital harmony, a p

MTP doubled my generation, but at 64k context it cuts total latency by only ~3%. Measured the prefill wall on a 3090.

MTP (Multi-Token Prediction) doubled generation speed but provided only ~3% total latency reduction at 64k context length on an RTX 3090 GPU. The limited overall benefit at large context sizes suggest

local-air-ollama

Multi-Level Analyzation of Imbalance to Resolve Non-IID-Ness in Federated Learning

arXiv:2606.10250v1 Announce Type: cross Abstract: Class imbalance is a common problem in deep learning that severely degrades performance. In federated learning (FL), it is a critical factor contribut

Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads

arXiv:2606.09956v1 Announce Type: cross Abstract: The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severel

Nanocoder hit 2,000 GitHub stars 🌟

Nanocoder is an open coding agent for the terminal built by a community collective rather than a company. It allows users to bring their own model, keep code on their machine, and owe nothing to anyon

local-air-ollama

Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks

arXiv:2606.10909v1 Announce Type: cross Abstract: Reconstructing local stress fields in heterogeneous microstructures under non-linear, history-dependent loading remains a major computational bottlene

Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning

arXiv:2606.10989v1 Announce Type: new Abstract: Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities. Many unlearning objectives focus

Operator Fusion for LLM Inference on the Tensix Architecture

arXiv:2606.09879v1 Announce Type: new Abstract: This study addresses on-device inference bottlenecks of Transformer models on Tenstorrent's Tensix architecture and proposes an operator fusion strategy

PatchSTG: Scalable Spatiotemporal Graph Transformers for Traffic Forecasting on Irregular Sensor Networks

arXiv:2606.09872v1 Announce Type: cross Abstract: Traffic forecasting is a fundamental component of intelligent transportation systems, yet remains challenging in real-world settings due to irregular

Post-Quantum Secure Federated DeFi for Inclusive Banking

arXiv:2606.10658v1 Announce Type: cross Abstract: Recent advances in error-corrected qubits have accelerated the timeline for practical quantum computing. It poses a threat to cryptographic primitives

RunPod AI Hub - Public Beta 1.34 live

local-air-stablediffusion

RunPod Hub is a centralized catalog of preconfigured AI repositories that you can browse, deploy, and share, optimized for RunPod's Serverless infrastructure to deploy in minutes. The platform include

SPARX: Secure and Privacy-Aware Approximate CNN Acceleration with Edge RISC-V SoC

arXiv:2606.09946v1 Announce Type: cross Abstract: Edge-AI systems increasingly require real-time CNN inference under strict energy, performance, security, and privacy constraints. Approximate computin

Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding

arXiv:2606.10738v1 Announce Type: cross Abstract: Recent multimodal large language models mainly process audio as monaural signals, thereby discarding the spatial cues contained in spatial audio for s

Spatiotemporal Seismic Hazard Assessment Using VQ-VAE and Seismic Statistical Features

arXiv:2606.10069v1 Announce Type: new Abstract: In this paper we build upon a previous study in which we demonstrated, using XGBoost and earthquake catalogue data from Japan and Chile, that a set of 6

TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation

arXiv:2606.11184v1 Announce Type: new Abstract: Contact-rich manipulation requires robots to continuously perceive and regulate evolving physical interactions under dynamic contact transitions or comp

local-aiarxiv-cs-ro

Taking 3D Characters From Comfy To Blender https://x.com/i/broadcasts/1vKpPPVrwMmKE

This Twitter broadcast demonstrates a workflow for exporting and importing 3D character models from ComfyUI, a node-based generative AI tool, into Blender for further refinement and animation. The ses

local-aicomfyui--x

Time-frequency localization of bird calls in dense soundscapes

arXiv:2606.10407v1 Announce Type: cross Abstract: Passive acoustic monitoring enables large-scale observation of wildlife, but most bioacoustic classifiers only predict species presence in a time wind

Tractogram foundation model

arXiv:2606.09893v1 Announce Type: cross Abstract: Diffusion MRI (dMRI) tractography is the only noninvasive approach for mapping white-matter pathways in the living human brain. It represents each bra

Transformer Based Model for Spatiotemporal Feature Learning in EEG Emotion Recognition

arXiv:2606.10718v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a widely adopted technique for monitoring brain activity, offering valuable insights into neurological states due to i

Ugh, I’m completely lost. I can’t get VS Code on Windows to connect to Ollama, it’s installed on a local Ubuntu server and I’m struggling to configure it.

This post discusses troubleshooting steps for connecting Visual Studio Code running on Windows to an Ollama instance installed on a local Ubuntu server, addressing configuration and connectivity issue

local-air-ollama

Unifying Local Communications and Local Updates for LLM Pretraining

arXiv:2606.11081v1 Announce Type: cross Abstract: Communication-efficient pre-training of LLMs is increasingly important as training draws on compute distributed across clusters, data centers, and low

Unleashing Correlation and Continuity for Hyperspectral Reconstruction from RGB Images

arXiv:2501.01481v2 Announce Type: replace-cross Abstract: Reconstructing Hyperspectral Images (HSI) from RGB images can yield high spatial resolution HSI at a lower cost, demonstrating significant app

Vector Map as Language: Toward Unified Remote Sensing Vector Mapping

arXiv:2606.10701v1 Announce Type: new Abstract: Remote sensing vector mapping aims to generate structured maps of geospatial entities, such as buildings, roads, and water bodies, from remote sensing i

What is the best open sourced image model?

local-air-stablediffusion

The best open-source image generation models in 2026 include FLUX.1 [schnell], Stable Diffusion 3.5 Large, HiDream-I1-Full, SANA-Sprint 1.6B, and HunyuanImage-3.0 . FLUX.1 [dev] holds the crown for ph

When Attribution Patching Lies: Diagnosis and a Second-Order Correction

arXiv:2606.09899v1 Announce Type: cross Abstract: A central goal of mechanistic interpretability is to identify which internal components causally drive a language model's behavior. Because these impo

A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic Prediction

arXiv:2606.07724v1 Announce Type: new Abstract: High-fidelity computational fluid dynamics (CFD) is crucial to vehicle aerodynamic analysis, but its cost still constrains early-stage design exploratio

A systematic investigation of molecular encoding methods for drug property predictions across neural network and Transformer encoder-based model

arXiv:2606.08973v1 Announce Type: cross Abstract: Fundamental investigations into how different molecular encoding methods affect molecular property prediction remain relatively limited. In this study

Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules

arXiv:2606.08802v1 Announce Type: new Abstract: Standard flow and diffusion pre-training matches the distribution of available data (e.g., molecules), which often covers only a small fraction of the v

AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving

arXiv:2606.09613v1 Announce Type: cross Abstract: Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program ex

AI-Native Closed-Loop Security for 6G-Enabled Cyber-Physical Systems: From Edge Detection to Network-Wide Mitigation

arXiv:2606.08173v1 Announce Type: cross Abstract: In sixth-generation (6G) networks, billions of cyber-physical systems (CPSs) - autonomous vehicles, smart grids, industrial robots, and remote-surgica

An Alternative Trajectory for Generative AI

arXiv:2603.14147v2 Announce Type: replace Abstract: The generative artificial intelligence (AI) ecosystem is undergoing rapid transformations that threaten its sustainability. As models transition fro

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

arXiv:2510.13554v2 Announce Type: replace-cross Abstract: The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across

b9572

Release b9572 of llama.cpp fixes a bug in the ggml-cpu rms_norm_back function that produced incorrect output under in-place aliasing conditions. The release includes multiple pre-built binaries for va

b9573

b9573 is a build release of llama.cpp, an open-source C/C++ project for LLM inference that aims to enable language model inference with minimal setup and state-of-the-art performance on various hardwa

b9577

Release b9577 of llama.cpp adds a --log-prompts-dir feature to the server that writes each prompt to a separate text file in a specified directory. The release was co-authored by Xuan-Son Nguyen and i

b9578

Release b9578 of llama.cpp includes a refactor of video subprocess handling in the mtmd (multi-threaded multi-device) component via pull request #24316 . The release provides prebuilt binaries across

b9580

b9580 is a llama.cpp release that adds v_dot2_f32_f16 support in matrix-matrix multiplication and Flash Attention via Vulkan, implementing support for Valve's fp16 dot2 extension. The release also inc

b9581

llama.cpp b9581 is a release that includes optimization for Vulkan backend memory usage, specifically reducing iq1 shared memory usage for mul_mm operations. Released on June 9, 2026 , this build prov

b9584

The search results don't contain specific information about release b9584. Based on the context from other llama.cpp releases in the results, b9584 is likely an intermediate build version of llama.cpp

b9585

Release b9585 of llama.cpp fixes granite speech model inference by applying embedding scale when deepstack is not used . The release was published on June 9, 2026, and represents a bug fix within the

Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets

arXiv:2606.09051v1 Announce Type: new Abstract: Convolutions have successfully transitioned from image processing to the complex realm of non-Euclidean higher-order domains, particularly in hypergraph

Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model

arXiv:2606.07771v1 Announce Type: cross Abstract: Foundation models for astronomical surveys offer powerful learned representations that can be transferred to downstream regression tasks such as galax

CANS: Accelerating Multiuser Collaborative Edge Inference via Cooperative Autodidactic NeuroSurgeon

arXiv:2606.09175v1 Announce Type: cross Abstract: Recently, mobile edge computing (MEC)-enabled collaborative deep neural network (DNN) inference has emerged as a promising approach for delivering int

Collaborative Edge-to-Server Inference for Vision-Language Models

arXiv:2512.16349v2 Announce Type: replace-cross Abstract: We propose a collaborative edge-to-server inference framework for vision-language models (VLMs) that reduces communication cost while maintain