Bounded knowledge map
Recent connections
Explicit wiki links among recent Local Ai entries.
90 nodes · 0 links. The server bounds this neighbourhood, so the browser never downloads or simulates the complete wiki graph.
90 nodes · 0 links shown. Hover or focus to isolate neighbours; select a node to open its source entry.
◯
No links inside this recent set
Try another category, or browse entries to follow links beyond this bounded view.
Local Ai
90 shownGlobal Consistency Repair for Natural-Language Claim SetsHide and Seek: HIDE Concepts to SEEK explanations for black box modelsEnriched Holomorphic Neural Networks for 2D and 3D Laplace ProblemsCORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV CachesA Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for ReasoningHAFixAgent: History-Aware Agentic Program RepairSpatial Context or Memory? Sizing the Inputs of Neural Surrogates for Partially Observed FieldsUser Trajectory Prediction Unifying Global and Local Temporal InformationExploring Attention Sinks in Text-to-Image Transformers from Diffusion and Autoregressive ModelsBeyond the Final Embedding: Retrieving Memories from Token-Level EvidenceTrajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RLPartiGen: Part-Aware Representations for Language-Conditioned Humanoid Motion GenerationProbabilistic Ship Trajectory Forecasting using Transformer Models on AIS DataA Local Agentic AI Framework to Generate Edge Case Scenarios for Safety AssuranceStructural Automata for Neural Semantic ParsingAgentic Peer-to-Peer Networks: From Content Distribution to Capability and Action SharingDoes Location Matter? A Black-Box Causal Audit Reveals Model-Dependent Audio Grounding in LALM HallucinationScaling Agentic Data for Long-Horizon Terminal IntelligenceAPEX: Asynchronous Prefix Denoising for Extreme CompressionEfficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture SearchGeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMsContinually Post-training Small Models via Synthetic Self-distillationReceipt scanner that runs a fine-tuned 0.8B vision model on the phone (free) - detailed cost trackingDP-MIND: Differentially private memory-guided Long context InferenceDeltaLLM: Delta-Key Sparse Attention for Edge LLMsNot Just an Evaluation: A Case Study of Discourse Particle Sensitivity in Language ModelsSemantic Views: Certified Reuse of LLM Labels Across Semantic QueriesMachine Unlearning for Federated Socially Fair k-Means ClusteringDistributed Harmonic-Covariance Feedback for Hole Closure in Planar Robot SwarmsM5 Ultra 256GB or 2x DGX Spark? Which one?I built a lightweight tool that automatically frees up VRAM for gaming and restores your local LLMs afterward2x 3090, 3x 3060 potential (smart and informed) future upgrade paths (send help)Typesafe ai raised 870m $ on hype (jev)microsoft doubles down on local ai with nvidia, but with a costRecommendations for Local AI Long-Term Memory and User Personalization ModulesWe built Many Agents give AI agents their own cloud computers and let them work for you 🚀The '10th Juror': Open-Set Standpoint Screening for Bureaucratic Bias DetectionSepGen: Multi-Stem Audio-Video Separation and Generation in a Single ModelThe Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission GateS^3Geo: Structure-Semantic Synergistic Learning for Cross-View Geo-LocalizationFed-GRPO: Reward-Signal-Driven Federated Group Relative Policy OptimizationBoosting the Local Invariance for Better Adversarial TransferabilityFinsler Flow Matching: Dynamics-Aware Geodesic Interpolation for Single-Snapshot Trajectory InferenceCharacterizing Overconfident Failure in LLM-Based Code GenerationI made a Mac app that uses your Ollama models to answer questions from your own folders, with the exact sentence citedFedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge EditingScalable Hierarchical Graph Generation via Soft Community StructureA 24KB stand-alone HTML-LLM that can generate consistent storiesScalable AI Uncertainty Quantification via Generalized Laplace Active SubspacesPhonological Interference in Multilingual Speech ModelsBridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight MigrationSatFix: Absolute Visual Localization of UAVs in Satellite Maps from a Single Oblique ImageDynamic Free-Rider Detection in Cross-Silo Federated Learning via Simulated Attack PatternsCensus-Based Population Autonomy For Distributed Robotic TeamingLlamaTale v0.43.0 - MCP Server for story creationQwen3.8 27b with 200K ctx + MTP on 12GB Ampere CardsWorldCast: Distributed Multiplayer World ModelsGitHub - google-ai-edge/ml-drift: GPU-Accelerated AI/ML InferenceTrajectory-Guided Fault Localization for Agent Skill EvolutionPower Side-Channel Membership Inference Attack on Embedded Machine LearningEpyc inference rigsLLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action LocalizationQwen3.8-27B: 159 tok/s on R9700, 64 tok/s on Strix HaloAtomWorld-Mirror: Macro-Step World Modeling of Critical Evolution Backbones for Materials DynamicsEfficient and Generalizable Archetypal Analysis for Discrete DataClass Machine Unlearning for Complex Data via Concepts Inference and Data PoisoningF^3NO: Frequency-Decomposed Finite-Time Flow-map Neural Operators with Cross-Scale Conditioning[Paper] Stepped MoE: Segment-Level Routing with Configurable Inference ComplexityCausal-fate dynamics of unrealized influenceTraceRelay: Attention-Aligned Recurrence over Rolling TracesPoint-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud RepresentationLarge Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP SystemOpen-Vocabulary Audio-Visual Event Localization via Complex-Valued Fusionembeddinggemma-2 MLX only?PointVGGT: Zero-Shot Multiview RGB-D Point Cloud Registration with Visual Geometry Foundation PriorsHIVE: Open Source Research Tool w/ ConfidenceLocal Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge PretrainingNot Every Change Is Necessary: Recoverable Drift in Large Language Model UnlearningPMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy LearningEvent-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational AgentsLooking Inside LLMs: Small-World Connectivity as a Signature of Reasoning PerformanceLearning Kilometer-Scale Weather Prediction with Global-Regional AlignmentSkillContrast: Difference-Guided Text Selection for Agent Skill RerankingEvidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMsDVD: Dynamic Vector Decoding for Efficient MLLM-based PerceptionHI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High ResolutionBudgeted Multi-Source Counterfactual Annotation for Off-Policy EvaluationConformal Data Contamination Tests for In-distribution Data AcquisitionWhen Scene Text Hijacks the Scene: Uncovering, Exploiting, and Mitigating Rendered-Text Semantic Leakage in Image Generation ModelsLearning Which Correspondences to Trust: Confidence-Weighted Event-Camera Localization in LiDAR Maps