AI Wiki — Knowledge Base

Geometric Observability Index: An Operator-Theoretic Framework for Per-Feature Sensitivity, Weak Observability, and Dynamic Effects in SE(3) Pose Estimation

arXiv:2602.05582v2 Announce Type: replace Abstract: We introduce the Geometric Observability Index (GOI), a per-feature sensitivity measure for pose estimation on SE(3). For a Gauss-Newton curvature m

model-releasesarxiv-cs-cv

7 Jul 2026

Search: “index”

From Relaxed Indexability to Exact Indexability: A t-Step Approach for Partially Observable Restless Bandits

RL-Index: Reinforcement Learning for Retrieval Index Reasoning

Mycelium-Index: A Streaming Approximate Nearest Neighbor Index with Myelial Edge Decay, Traffic-Driven Reinforcement, and Adaptive Living Hierarchy

LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing

MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference

Self-Evolving Search Index

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Poisoning Attacks on the PGM-index

Index SLM Technical Report

PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention

MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval

ColBERTSaR: Sparsified ColBERT Index via Product Quantization

SPIN: Shadow Predictive Indexer for Sparse Attention

Symmetry-Aware Feature Learning: A Polynomial Separation for Multi-Index Models

Self-Indexing Attention for Compression-Compatible Sparse Long-Context LLM Inference

Reducing Redundancy in Whole-Slide Image Patching for Scalable Indexing and Retrieval

Index-Translate: A Multilingual Translation Model Family -- Text, Speech, Controlled Dubbing, and Long-Document Translation

Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry

Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval

NeuRoute: Logit-Guided Neural Routing for Billion-Scale Vector Search with Sub-Hour Index Construction

A Persona-based Rate Action Index

CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval

Physics-Informed Neural Networks for Computing the Morse Index of the Critical Catenoid

What's the Point? Spatial Grammar & Index Resolution for Sign Language Processing

Subspace Aggregation Query and Index Generation for Multidimensional Resource Space Model

PRIME: Pre-Retrieval Index Modeling Enhancement for Structured Document Retrieval-Real

Scalable extensions to given-data Sobol' index estimators

Indexing: the Beginning and the End

Restless bandits with imperfect binary feedback: PCL-indexability analysis and computation

Segmentation-Guided Spatial Indexing for Generalizable and Explainable Deepfake Detection

Optimal Regret for Single Index Bandits

MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search

Low-Rank Single-Index Bandits with Unknown Links: From Matrices to Tensors

Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach

Unleash LLMs Potential for Sequential Recommendation by Coordinating Dual Dynamic Index Mechanism

Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG

When Generated Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception

Global Index on Responsible AI 2026 : Conceptual Framework and Methodology

Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature

Characterizing Bias in Post-Bandit Inference under Index Algorithms

The C-index illusion: discrimination without calibration in published survival models

LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention

Geometric Observability Index: An Operator-Theoretic Framework for Per-Feature Sensitivity, Weak Observability, and Dynamic Effects in SE(3) Pose Estimation

A Skill-Based AI Agentic Pipeline for Library of Congress Subject Indexing

MINT: Multi-Vector Search Index Tuning

Restless Bandits with Individual Penalty Constraints: A New Near-Optimal Index Policy and How to Learn It

Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM

Video Evidence Indexing: Learning Where to Look from Video Previews for Token-Budgeted Long-Video Question Answering