127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “research”

34,859 results

Research

GeoWorld: Geometric World Models

DGX agent

arXiv:2602.23058v2 Announce Type: replace Abstract: Energy-based predictive world models provide a powerful approach for multi-step visual planning by reasoning over latent energy landscapes rather th

researcharxiv-cs-cv

19 May 2026

Research

Search: “research”

GeoWorld: Geometric World Models

Gesture First, LLM-Assisted Voice Complement: Exploring Multimodal Robot 'Puppeteer' Teleoperation Via Virtual Counterpart in Augmented Reality

Global Automation Atlas

Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing

Glocal Smoothness: Line search and adaptive step sizes can help in theory too!

Gradient Dynamics of Attention: How Cross-Entropy Sculpts Bayesian Manifolds

GRAFT: Decoupling Ranking and Calibration for Survival Analysis

GraphMind: Theorem Selection and Conclusion Generation Framework with Dynamic GNN for LLM Reasoning

GraSP-VL: Length as a Semantic Granularity Interface for Vision-Language Representations

GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance

GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction

HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction

Haptic Rendering of Fractional-Order Viscoelasticity: Passivity and Rendering Fidelity

HexagonalWarriorMamba: Superior Threshold-Dependent Multi-label Classification of 12-Lead ECG Cardiac Abnormalities

Hierarchical Two-Stage Framework for Environment-Aware Long-Horizon Vessel Trajectory Prediction

High-dimensional Limit of SGD for Diagonal Linear Networks

Historical Knowledge Graphs for Global Maritime Estimated Time of Arrival

HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos

How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study

Human-Certified Module Repositories for the AI Age

Hybrid Quantum-Classical Neural Architecture Search

HyperVision: A Channel-Adaptive Ground-Based Hyperspectral Vision Pre-trained Backbone

Identify Then Project: Contrastive Learning of Latent Dynamics from Partial Observations with Port-Hamiltonian Structure

Image-to-Video Diffusion: From Foundations to Open Frontiers

Inducing Spatial Locality in Vision Transformers through the Training Protocol

Information-Theoretic Storage Cost in Sentence Comprehension

InstructAV2AV: Instruction-Guided Audio-Video Joint Editing

Integration of AI in Cybersecurity: Current Trends with a Focused Look at Intrusion Detection Applications

Inter-LPCM: Learning-based Inter-Frame Predictive Coding for LiDAR Point Cloud Compression

Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry

Iterative Chow Filtering for Learning with Distribution Shift

JSPG: Dynamic Dictionary Filtering via Joint Semantic-Pinyin-Glyph Retrieval for Chinese Contextual ASR

Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains

Language Acquisition Device in Large Language Models

Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement

Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design

Latent-IMH: Efficient Bayesian Inference for Inverse Problems with Approximate Operators

Learning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural Refinement

Learning in Position-Aware Multinomial Logit Bandits: From Multiplicative to General Position Effects

Learning Lifted Action Models from Traces with Minimal Information About Actions and States

Learning more physically realistic dynamics in machine-learning based weather forecasting with latent-space constraints

Learning Normal Representations for Blood Biomarkers

Learning over Positive and Negative Edges with Contrastive Message Passing

Learning Quantifiable Visual Explanations Without Ground-Truth

Learning spatially adaptive sparsity level maps for arbitrary convolutional dictionaries

Learning to Look Benign: Targeted Evasion of Malware Detectors via API Import Injection

Learning Unbiased Permutations via Flow Matching

Learning Variable-Length Tokenization for Generative Recommendation