local ai

Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents

arXiv:2607.22688v1 Announce Type: new Abstract: Post-training agents for automated AI research requires optimizing not only model parameters, but also the runtime harness that shapes how research traj

CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models

DGX agent

arXiv:2607.24312v1 Announce Type: new Abstract: Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency acro

local-aiarxiv-cs-cl

28 Jul 2026

Context-Aware Concept Distillation for Trustworthy Flood Prediction

arXiv:2607.23237v1 Announce Type: cross Abstract: Effective flood risk management relies on accurate forecasting, yet the 'black box' nature of stateof-the-art Deep Learning models creates a barrier t

Development of Vision-Language Model-based GNSS Spoofing Detection for Autonomous Vehicle Navigation

arXiv:2607.23962v1 Announce Type: new Abstract: Autonomous vehicles (AVs) depend on Global Navigation Satellite Systems (GNSS) for localization and navigation, making them vulnerable to spoofing attac

Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety

arXiv:2607.22929v1 Announce Type: new Abstract: A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produc

DRC-Aid: Design-Rule Correction via Agentic Framework utilizing Inference-Time Large Language Models

arXiv:2607.22761v1 Announce Type: cross Abstract: Resolving Design Rule Violations (DRVs) in layouts entails an iterative loop of geometric edits and verification. We present DRC-Aid, a closed-loop ag

Embeddings based Anomaly Detection for Cleaning Global Crop Type Reference Datasets

arXiv:2607.23908v1 Announce Type: new Abstract: High quality reference data remain a critical bottleneck for crop-type mapping at any spatial and temporal scale. Operational systems such as WorldCerea

Escaping the Euclidean Void: Manifold-Informed Flow Matching for Sequential Recommendation

arXiv:2607.23762v1 Announce Type: cross Abstract: Conventional recommenders capture users' preferences by optimizing observed user-item relations, whereas continuous generative recommendation addition

Falsifiable Commitment Planning for Self-Correcting Web Agents

arXiv:2607.24167v1 Announce Type: new Abstract: Long-horizon web agents often go off track before final failure: a trajectory can remain locally plausible even after the current state, reused skill, o

Fisher Information based Stochastic Gradient Ascent for Online Learning of Dirichlet Process Mixture and Theory

arXiv:2412.08951v3 Announce Type: replace Abstract: Scalable algorithms of posterior approximation allow Bayesian nonparametrics such as Dirichlet process mixture to scale up to larger dataset at frac

Generative Video Compression with Adaptive Score Distillation

arXiv:2607.22772v1 Announce Type: cross Abstract: Diffusion models provide strong generative capabilities for video compression at ultra-low bitrates. Existing diffusion-based video codecs adapt base

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs

arXiv:2607.23115v1 Announce Type: cross Abstract: This paper aims to enable computation- and communication-efficient GPU sharing across devices within local area networks (LANs), facilitating ubiquito

Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries

arXiv:2607.23967v1 Announce Type: new Abstract: Delayed generalization, or grokking, remains poorly understood despite extensive empirical study. We identify an exactly solvable late-time relaxation m

Harnessing X-ray Absorption Spectroscopy Data through Multimodal Mining of Battery Literature

arXiv:2607.23886v1 Announce Type: cross Abstract: X-ray absorption spectroscopy (XAS) is central to understanding the local electronic and atomic structure of materials, yet most published spectra rem

I Just Built an Open-Source Alternative to Flora AI

Hey, I just made a node editor for generating assets using AI. It’s something similar to ComfyUI, but it’s more simple and abstract. You can say it’s the open-source alternative to Flora AI. It’s curr

Infrared Organization and Critical Cognitive Field Formation in Transformer Dynamics

arXiv:2607.10923v2 Announce Type: replace Abstract: Large language models exhibit remarkable emergent behaviors, yet the physical mechanism governing their collective dynamics remains poorly understoo

Intuitionistic j-Do-Calculus in Topos Causal Models

arXiv:2510.17944v2 Announce Type: replace-cross Abstract: In this paper, we generalize Pearl's do-calculus to an Intuitionistic setting called j-stable causal inference inside a topos of sheaves. Our

I've been tracking RTX 5090 prices across EU stores since March, it's up €1,061 and still climbing

Been running a GPU price tracker (https://www.pricesquirrel.com) since March, covering 20+ EU stores, recently added RAM, SSDs and CPUs too. Every GPU tier has gotten cheaper since launch. The RTX 509

local-air-localllama

K2Lab: Standalone(ish) Krea2 bbox style prompting and lora containment

I've been digging into Krea2 to see if there's any way to condition inference in specific regions of pixel -> latent space to implement bbox type prompting in order to apply multiple simultaneous char

KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability

arXiv:2607.24730v1 Announce Type: cross Abstract: Computer vision models have become highly effective for medical applications, yet their black-box nature continues to undermine clinician trust. In cl

Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting

arXiv:2607.22568v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed on mobile and embedded devices to improve privacy and reduce network latency. Yet on-device infer

LCMamNet: A Lightweight Cross-scale Mamba Network for Infrared Small Target Detection

arXiv:2607.24184v1 Announce Type: new Abstract: Infrared small target detection (IRSTD) is important for low-altitude perception, unmanned-system warning, and security monitoring. However, weak target

Learning-based Hierarchical Tracheal Anatomy Understanding from Sparse Surgical Demonstration Annotations for Ultrasound Robots

arXiv:2607.22789v1 Announce Type: cross Abstract: Tracheostomy requires precise localization of the tracheal incision site; however, conventional manual palpation is subjective and often unreliable, w

Let AI Agents Translate Networks, Not Reason About Them

arXiv:2607.22947v1 Announce Type: new Abstract: A formal model enables verifying reachability, localizing an outage, or anticipating the blast radius of a change. Yet, virtually no production network

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding

arXiv:2607.24555v1 Announce Type: cross Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys

LOCUS: Local Visual Cue Search for Enhancing Fine-Grained Perception in Multimodal Large Language Models

arXiv:2606.16586v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) remain unreliable on fine-grained visual perception, even when high-resolution inputs preserve the necessar

Manga Coloring Tool 2

Hey everyone! 👋 I'm excited to announce the official release of Manga Coloring Tool 2.0, a completely free, local, open-source web application designed to colorize manga pages and chapters effortlessl

MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning

arXiv:2607.24064v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) have achieved remarkable success in visual understanding, driven by the growing availability of high-quality imag

McBess style lora (lokr) for Krea2: <5 Mb size.

https://civitai.com/models/2813960/mcbess-style Happy to share my holy grail of a style lora. I have been chasing the edgy alt-rubber hose style of McBess since SDXL training was a thing. Krea finally

Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers

local-aiapple-ml-research

Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple’s most powerful on-device foundation model. This work presents th

microsoft/VibeVoice-ASR-BitNet

VibeVoice-ASR-BitNet is a compressed variant of VibeVoice-ASR optimized for real-time inference on edge CPUs — no GPU required. Through heterogeneous quantization, the model is compressed from 4.62 GB

local-air-localllama

Multimodal Surface EMG Hand Gesture Recognition Using Query-Based Transformers for Prosthetic Control

arXiv:2607.22779v1 Announce Type: cross Abstract: Hand gesture recognition via surface electromyography (sEMG) is fundamental to prosthetic control. In this field, deep learning approaches have become

Multivariate Time Series Forecasting with Adaptive Non-Local Observables

arXiv:2607.24399v1 Announce Type: cross Abstract: Multivariate time series forecasting (MTSF) predicts future values of multiple variables from historical data. While quantum neural networks have been

My first longer Wan2.2 continuation generation. I am so excited

Hey guys, I am so excited to share this with you guys. I know for a lot of Pros here, this maybe a baby's work so please be gentle. Until a month ago, I didnt know anything but to use those google AI

Neonatal Hypoxic-ischaemic Encephalopathy Classification from the EEG and HRV Signals Using a Conformer based Masked Autoencoder

arXiv:2607.23554v1 Announce Type: cross Abstract: In this paper, we propose the MAEConformer, a novel self-supervised learning framework that combines the Conformer architecture with the Masked Autoen

Now, this: 1,100 current/former frontier-AI employees sign a petition calling for US gov't to step in for 'pacing' frontier development

So, it appears that this is the week of open letters in AI🥲... an open letter signed by current and former employees of OpenAI, Anthropic and Google primarily - calling for a slow-down in frontier AI

local-air-localllama

Observer-Assisted Relative-Velocity Compensation with LPV-H_infty Robust Correction for 3D Trajectory Tracking of Underactuated Non-Minimum-Phase AUVs under Ocean Currents

arXiv:2607.23653v1 Announce Type: cross Abstract: This paper develops an observer-assisted control architecture for 3D trajectory tracking of torpedo-type underactuated AUVs with non-minimum-phase swa

local-aiarxiv-cs-ro

Perplexity’s Personal Computer turns Windows PCs into AI agents

Perplexity has expanded its agentic Personal Computer tool to Windows, allowing computers running the world's most popular OS to be used as a locally run AI system. Like the Mac version that Perplexit

local-aithe-verge-ai

Perturbative-NeuSA: A Structured Spectral Framework for Time-Dependent PDEs

arXiv:2607.24345v1 Announce Type: new Abstract: Neural spectral PDE solvers often learn an entire unresolved vector field even when an inexpensive approximate model can already capture most of the tra

Physically Verifiable Evidence and LLM-Based Reporting for Bearing Fault Diagnosis

arXiv:2607.22797v1 Announce Type: cross Abstract: Trustworthy deployment of AI-based diagnosis in safety-critical mechanical systems hinges on validation: whether a prediction can be checked against p

PIRL: From Open-Loop Exploration to Closed-Loop Reinforcement Learning [R]

local-air-machinelearning

TL;DR: Most RL post-training algorithms optimize the current batch and move on. But after an update, did the new policy actually become better? We introduce Policy Improvement Reinforcement Learning (

Poison to Detect: Detection of Targeted Overfitting in Federated Learning

arXiv:2509.11974v3 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative model training among clients without centralising data, making it a widely adopted privacy-enhan

QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation

arXiv:2607.22743v1 Announce Type: cross Abstract: Background and Objective: Automatic polyp segmentation supports computer-aided diagnosis and early colorectal cancer detec- tion. Centralized deep lea

Quality Action Assurance: Multimodal Verification of Examiner Claims in VR OSCEs

arXiv:2607.19063v2 Announce Type: replace Abstract: Objective Structured Clinical Examinations (OSCEs) are the gold standard for assessing clinical competence, yet scoring remains vulnerable to examin

QueenVIS: Rethinking Image-Only Training for Video Instance Segmentation via Query Enrichment

arXiv:2607.24598v1 Announce Type: new Abstract: Video instance segmentation (VIS) requires models to detect, segment, and track object identities across frames, and most methods enforce temporal consi

Real-Time Human-Centric World Modeling for Upper-Body Human-Object Interaction

arXiv:2607.23517v1 Announce Type: new Abstract: We present a real-time human-centric world model for upper-body interactive generation, aiming to synthesize coherent local world dynamics centered on a

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention

arXiv:2511.12940v2 Announce Type: replace Abstract: Recent advancements in video generation has shifted from bidirectional models for short videos to autoregressive ones for ultra long video generatio

ReflexTrack: A Feedback-Driven Agent for Training-Free Referring Video Object Segmentation

arXiv:2607.24098v1 Announce Type: new Abstract: Referring video object segmentation (RVOS) requires segmenting a target specified by natural language throughout a video. Recent agentic approaches comb