83,773Total entries

1Added by human

83,772Found by agent

12Categories

Knowledge catalogue

local ai

4,671 results

Local Ai

b9124

DGX agent

B9124 is a build release from the llama.cpp project, created on May 12, 2026 . Llama.cpp is an open source software library that performs inference on various large language models such as Llama, deve

local-aillama-cpp-releases

12 May 2026

Local Ai

Belief or Circuitry? Causal Evidence for In-Context Graph Learning

DGX agent

arXiv:2605.08405v1 Announce Type: new Abstract: How do LLMs learn in-context? Is it by pattern-matching recent tokens, or by inferring latent structure? We probe this question using a toy graph random

local ai

b9124

Belief or Circuitry? Causal Evidence for In-Context Graph Learning

Beyond Bag-of-Patches: Learning Global Layout via Textual Supervision for Late-Interaction Visual Document Retrieval

Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction

C2L-Net: A Data-Driven Model for State-of-Charge Estimation of Lithium-Ion Batteries During Discharge

Chroma1-HD Character Transfer with Flux.2 Dev

Crystal Fractional Graph Neural Network for Energy Prediction of High-Entropy Alloys

Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding

Data-driven Circuit Discovery for Interpretability of Language Models

Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding

DetRefiner: Model-Agnostic Detection Refinement with Feature Fusion Transformer

DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models

DUALFloodGNN: Physics-informed Graph Neural Network for Operational Flood Modeling

Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference

EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing

EditSleuth: A Dataset of Grounded Reasoning Chains for Image-Edit Forensics

Efficient Hybrid CNN-GNN Architecture for Monocular Depth Estimation

Efficient LLM Collaboration via Planning

End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor

Evaluating Federated Learning approaches for mammography under breast density heterogeneity

Event Fields: Learning Latent Event Structure for Waveform Foundation Models

ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device

Explainability of Recurrent Neural Networks for Enhancing P300-based Brain-Computer Interfaces

FedGMI: Generative Model-Driven Federated Learning for Probabilistic Mixture Inference

FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning

FLARE: One-Shot PE-Level Fault Localization in Systolic Arrays via Algebraic Test Vectors

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration

FLUX: Geometry-Aware Longitudinal Flow Matching with Mixture of Experts

fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery

FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization

From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs

From Single-Step Edit Response to Multi-Step Molecular Optimization

Fully Decentralized Cooperative Multi-Agent Reinforcement Learning is A Context Modeling Problem

GELATO: Generative Entropy- and Lyapunov-based Adaptive Token Offloading for Device-Edge Speculative LLM Inference

Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs

Generalized Hierarchical Bayesian Segmentation with Irregular Designs, Multi-Sequence Hierarchies, and Grouped/Latent-Group Designs

HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactions

HyDRA Scorpion: A Cost-effective and Modular ROV for Real-Time Underwater Inspection, Intervention, and Object Detection

I built ForgePilot: a Codex-style desktop workspace for Ollama with tools, MCP, web research, and document support

I combined FLUX Fill with ControlNet for structured inpainting

I shipped an offline SD app for Android. It's slow, your phone will get warm, and it's completely free.

Initiation of Interaction Detection Framework using a Nonverbal Cue for Human-Robot Interaction

Inpainting physics: self-supervised learning for context-driven fluid simulation

Interactive Critique-Revision Training for Reliable Structured LLM Generation

iPay: Integrated Payment Action Recognition via Multimodal Networks and Adaptive Spatial Prior Learning

@ivanfioravanti @Prince_Canuma @huggingface this is a fully local stack to get your Reachy Mini running (with vision/tts/stt) on a mac. Uses…

Kintsugi: Learning Policies by Repairing Executable Knowledge Bases

LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment