local ai

arXiv:2605.27965v1 Announce Type: new Abstract: Reasoning models often generate long traces in which useful self-correction and unproductive revision are hard to distinguish. We study this distinction

arXiv:2602.02417v2 Announce Type: replace Abstract: Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-

This project uses Stable Diffusion AI to generate D&D character artwork from uploaded character sheets , streamlining the character creation process for tabletop gamers. The AI-generated avatars make

Ollama v0.30.0-rc29 is a pre-release version that changes the architecture to directly support llama.cpp instead of building on top of GGML, and adds compatibility with the GGUF file format. MLX is us

arXiv:2605.27435v1 Announce Type: cross Abstract: Deploying large language models (LLMs) on mobile devices increasingly relies on heterogeneous execution, yet no prior study has systematically charact

arXiv:2605.27997v1 Announce Type: cross Abstract: Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-leve

arXiv:2602.17443v2 Announce Type: replace Abstract: Multi-turn LLM evaluation is typically reported as a single win-rate scalar, conflating distinct capabilities. We introduce AIDG (Adversarial Inform

As enterprises confront rising memory and storage costs alongside mounting pressure to run AI workloads on-premises, the fundamental architecture of the private cloud data center is changing beneath t

The search results do not contain specific details about release b9354. Based on the context from the llama.cpp project, b9354 is a build release of llama.cpp, a C/C++ implementation for running large

b9360 is a release of llama.cpp published May 27, 2026 that includes a fix for environment variable names to have the LLAMA_ARG_ prefix . The release includes prebuilt binaries for multiple platforms

The search didn't provide specific details about release b9365. Based on the GitHub repository pattern and context, b9365 is a build release of llama.cpp, which is a C/C++ implementation for enabling

b9368 is an intermediate build release of llama.cpp, a C/C++ implementation for efficient LLM inference on consumer hardware. The release follows the project's rapid development cycle where multiple b

arXiv:2605.27044v1 Announce Type: new Abstract: Early battery degradation trajectory forecasting (BDTF), which predicts the full-life state-of-health trajectory from early operational data, is critica

arXiv:2605.26645v1 Announce Type: new Abstract: LLM-based knowledge-graph question answering (KGQA) delegates graph traversal to language models, turning each question into a sequence of local relatio

arXiv:2605.26675v1 Announce Type: cross Abstract: CART random forests are among the most widely used modern predictive methods, with well-documented empirical success. Yet, at the mechanistic level, t

arXiv:2605.26304v1 Announce Type: new Abstract: Collaborative navigation of heterogeneous robots in unknown environments poses significant challenges due to sensing, communication, and computational l

→ Creativity dial (Raw → High) to trade prompt adherence for aesthetic depth → Style reference image input → Moodboard conditioning for consistent art direction across a body of work KREA 2 Large + Me

arXiv:2512.18540v2 Announce Type: replace-cross Abstract: We study distributed control of networked systems through reinforcement learning, where neural policies must be simultaneously scalable, expre

arXiv:2605.26119v1 Announce Type: cross Abstract: Industrial Edge AI programs often begin with the model and only later confront the platform. That sequencing is attractive because it allows early dem

arXiv:2505.16942v2 Announce Type: replace Abstract: Recent optical flow estimation methods often employ local cost sampling from a dense all-pairs correlation volume. This results in quadratic computa

arXiv:2605.26305v1 Announce Type: new Abstract: This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows. Both systems leverage a hybrid Local Body, Remote

arXiv:2511.06625v5 Announce Type: replace-cross Abstract: Low-dose chest computed tomography (LDCT) captures pulmonary and cardiac structures in a single scan, enabling joint assessment of lung and ca

arXiv:2605.26615v1 Announce Type: new Abstract: Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed te

arXiv:2605.27351v1 Announce Type: new Abstract: 3D editing is a fundamental capability for scalable 3D content creation. While image editing has rapidly evolved toward large-scale feedforward generati

arXiv:2605.26190v1 Announce Type: cross Abstract: This paper presents the HRVConformer, a novel deep learning architecture for the classification of hypoxic-ischemic encephalopathy (HIE) using the ins

arXiv:2408.05560v2 Announce Type: replace Abstract: Stochastic gradient updates are widely used for their efficiency and scalability, but their effective step sizes can depend strongly on feature scal

arXiv:2605.26252v1 Announce Type: new Abstract: Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of pas

KREA 2 Image, KREA's foundational image generation model trained from scratch with adjustable creativity and style parameters, has been integrated as a partner node within ComfyUI. This integration al

arXiv:2603.03711v3 Announce Type: replace Abstract: Local Differential Privacy (LDP) is the gold standard trust model for privacy-preserving machine learning by guaranteeing privacy at the data source

Lipdub (by Lightricks) Input a text prompt dialogue to dub/translate a characters speech. https://links.comfy.org/4v8Tr00 Obscura Remova (by WepeNerd) Used as occlusion removal, haze cleanup, foregrou

arXiv:2605.26756v1 Announce Type: new Abstract: Diffusion models can unintentionally memorize training samples, raising concerns about privacy and copyright. While recent methods can detect memorizati

Enterprises are adopting an agentic AI PC strategy as Copilot+ PCs shift AI workloads from expensive cloud inference to secure, high-performance on-device processing. As agentic AI moves from experime

arXiv:2605.26444v1 Announce Type: new Abstract: Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection l

arXiv:2605.26842v1 Announce Type: cross Abstract: The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to pro

New skill from K-Dense: LiteParse in Scientific Agent Skills — built for fast, local research paper ingestion. Your AI co-scientist can now: * Parse PDFs and supplementary files on your machine (no do

arXiv:2605.26399v1 Announce Type: new Abstract: Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typ

arXiv:2605.26870v1 Announce Type: cross Abstract: Background: Large language models are typically evaluated as models, benchmarks, or short conversational episodes. Less is known about what happens wh

arXiv:2602.20475v2 Announce Type: replace-cross Abstract: The High-Luminosity Large Hadron Collider (HL-LHC) at CERN will produce unprecedented datasets capable of revealing fundamental properties of

arXiv:2510.01833v2 Announce Type: replace Abstract: Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local de

arXiv:2510.18668v2 Announce Type: replace-cross Abstract: The vast majority of cardiovascular diseases may be preventable if early signs and risk factors are detected. Cardiovascular monitoring with b

arXiv:2605.26784v1 Announce Type: cross Abstract: Standard on-policy reinforcement learning relies on heuristic clipping to enforce trust regions, but this mechanism imposes a severe cost by indiscrim

arXiv:2604.04940v2 Announce Type: replace Abstract: Designing effective heuristics for NP-hard combinatorial optimization problems remains challenging and often requires substantial domain expertise.

arXiv:2605.26861v1 Announce Type: new Abstract: Image geo-localization aims to determine where a photograph was taken, a task that often requires more than recognizing visible landmarks. Human experts

arXiv:2605.27314v1 Announce Type: new Abstract: Reactive control is often considered insufficient for multi-objective tasks because conflicting objectives give rise to local minima. We argue this limi

Dreamverse is an AI video generation engine that produces 30 seconds of 1080p video in 4.5 seconds on a single GPU , making it significantly faster than existing systems like Sora. It provides a creat

arXiv:2605.26571v1 Announce Type: new Abstract: Federated learning enables collaborative model training without sharing raw data, but its performance can degrade substantially under heterogeneous clie