Bounded knowledge map
Recent connections
The 90 newest entries plus the curated synthesis cluster that connects ideas across the wiki.
107 nodes · 30 links. The server bounds this neighbourhood, so the browser never downloads or simulates the complete wiki graph.
107 nodes · 30 links shown. Hover or focus to isolate neighbours; select a node to open its source entry.
Linked entries
30 shownSyntheses
17 shownSynthesis: Arxiv-Cs-Lg10Synthesis: Arxiv-Cs-Ai10Synthesis: Arxiv-Cs-Cl9Synthesis: Arxiv-Cs-Cv7Wiki Lint Report — 2026-04-196Wiki Lint Report — 2026-04-126Wiki Lint Report — 2026-04-265Synthesis: Elon-Musk--X3Synthesis: Harrison-Chase--X2Synthesis: Swyx--X2Wiki Lint Report — 2026-07-19Wiki Lint Report — 2026-07-15Wiki Lint Report — 2026-07-05Wiki Lint Report — 2026-06-28Wiki Lint Report — 2026-06-22Wiki Lint Report — 2026-06-07Wiki Lint Report — 2026-05-03
Research
24 shownValidated Synthetic Patient Generation for Small Longitudinal Cohorts: Coagulation Dynamics Across PregnancyCan Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?Entropy-Centric Explainable AI for Remote Sensing Image SegmentationFARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic SegmentationTSCoNet: A Two-Stage Copula CNN-LSTM for Uncertainty-Aware Spatio-Temporal ForecastingSpectral Embeddings of Degree-alpha Laplacians in Random Dot Product GraphsMMArt A Multi-Perspective Multimodal Dataset for Visual Art UnderstandingRiemann GeoResolver: A Non-Euclidean Attention Framework from Euclidean Resolver to Hyperbolic-Spherical GeometryAccelerated Learning of High Dimensional Functions with a Tensor-Featured Training NetworkFaster Superword TokenizationLearning Disease-Sensitive Latent Interaction Graphs From Noisy Cardiac Flow MeasurementsDEFT: Data-Efficient Frequency-domain Top-k Sampling via Inverse Discrete Fourier Transform for Spatiotemporal Dynamical Systems ModelingUnlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-trainingSpecF2M: A Spectral-Aware Multi-task Network Estimating Axial Length and Refractive Error from Pediatric Fundus PhotographsOff-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does SoMultimodal Ambivalence and Hesitancy Recognition via Cross-Attention and Gated FusionOpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital PredistortionProjected climate memory and inherited warm-tail risk in accelerated European summer warmingExploring Semantic Stability Across Reviews in the Linux KernelShare First, Route What Remains: A Unified Framework for Token-Adaptive MoE ComputationDelays in Spiking Neural Networks: A State Space Model ApproachA Graph Neural Network--Guided Genetic Algorithm for Physical Internet Supply Chain Optimization under Cost UncertaintySelf-Correcting Long-Horizon Search Agents via Tree-Structured MemoryBeyond a Bag of Features: Set-Level Instability in Sparse Autoencoders
Safety
19 shownPredicting Space Groups of Double Perovskites by LLM with Dynamic Few-Shot LearningEfficient Hypergradient Descent for Inverse Reinforcement LearningAPCReg: Anatomical-Prior-Guided Coarse-to-Fine CBCT--IOS Registration via Multi-View Projection and Reliability-Controlled Residual CorrectionMitigating Bus Bunching with Reinforcement Learning Enhanced by Semantic Stop EmbeddingHidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action ModelsTemplated or fully Synthetic? Prompt construction as a confound in measuring LLM political stance beyond writing assistanceEvery Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and BiasesRethinking Data Efficiency in Industrial Dense Prediction: Pretraining Coherence, Not Inductive Bias, Determines ViTs Low-Data AdvantageSPOTting the Future: Lookahead Explanations for Deep Reinforcement LearningThreat-guided Policy-aware Scene Perturbation for Safe Autonomous Driving with Online Reinforcement LearningSafeCap: Improving LVLM Safety with Image Captioning Reinforcement LearningUPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective InterventionDual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic DialogueSBCO: Self-Supervised, Verifier-Grounded Harness Optimization For Planning AgentsPolicy Convergence and Divergence Across National and Within Regional AI Strategies: A Policy Design Element AnalysisThe Parser Already Knows: Lightweight Bias Correction in Constrained DecodingDreamer-SAC: Off-Policy Learning in Latent World Models for Sample-Efficient Autonomous DrivingEnhancing Automated Essay Scoring With Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-TrainingCritic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning
Agents
7 shownPay with confidence: How Solv Labs built verifiable, auditable agent payments on Amazon Bedrock AgentCore paymentsMEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom GraphOn Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models4D-WAM: 4D Consistent World Modeling for Autonomous DrivingDuplexWorld: Can voice agents help you get through the day?Seeing above the waves: A modular sensing framework for data acquisition at seaMIRA: Medical Image Reflection for Agentic Diagnosis
Model Releases
22 shownFormStruct-Bench:A Hierarchical and Diagnostic Benchmark for Table-Form Document Structure RecognitionReasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, and Optimization SelectsMeasure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT SystemsNutrition Data Infrastructure for the AI Era: Operationalizing FAIR for Agent-Mediated ResearchREDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent SystemsIdea for a deepseek-v4-flash-0731 backed automated research workflow to be leveraged via qwen3.6/3.8 27b for difficult tasks that require highly technical, not easy to find information.The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model LineagesTEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-ResolutionVibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inferenceA variational Bayes approach to inference for low-dimensional parameters in high-dimensional linear regressionImplicit representations are dead. Long live explicit primitives!Tested Nemotron 3.5 Lightning locally on coding, Hermes Agent and agentic workENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question AnsweringFlex-pi: A Multi-Stream World-Action Model with Compute FlexibilityCost-Efficient Estimation of General Abilities Across BenchmarksReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantizationb10375InSight-doc: Agentic Visual Perception for Long-Document UnderstandingTemporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge DistillationDegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation PredictionActionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique
Applications
5 shownDQS: A Low-Budget Query Strategy for Enhancing Unsupervised Data-driven Anomaly Detection Approaches***Lights, inference, action…*** I’m so happy to share that @sequoia has led the Seed in @previewio. Developers are flying in magical AI-nat…Self-Knowledge Retrieval Augmented Generation Framework for Patent MatchingAerial Layouting: Design and Control of a Compliant and Actuated End-Effector for Precise In-flight Marking on CeilingsFACT: Failure-Aware Causal Training for World-Action Models
Tutorials
2 shownLocal Ai
9 shownR4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric VideoFITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge GraphsLesion-Aware Adaptive Fourier Neural Operator for CT-to-PSMA PET Synthesis in Prostate CancerSafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak DefenseMultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level AlignmentThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered ScenesRetrieval-Corrected Conformal Prediction for Time SeriesRAG for regular users?Grid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity