127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “deployment”

12,448 results

Research

World Action Models: A Survey

DGX agent

arXiv:2606.20781v1 Announce Type: cross Abstract: World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large v

researcharxiv-cs-cv

23 Jun 2026

Model Releases

Search: “deployment”

World Action Models: A Survey

Zero-Shot Vision-Language Models for Classroom Engagement Recognition: A Benchmark Study of Prompt Sensitivity and Cross-Dataset Generalization

A Multi-Modal Sensor Fusion Instrument for Measuring Regional Human Mobility: The Distributed Human Data Engine (DHDE)

A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models

AerialClaw: An Open-Source Framework for LLM-Driven Autonomous Aerial Agents

ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing

Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline

AVIS: Adaptive Test-Time Scaling for Vision-Language Models

Benchmarking Large Language Models for Safety Data Extraction

Detecting AI-Generated Content on Social Media with Multi-modal Language Models

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling

Fast-SDE: Efficient Single-Microphone Sound Source Distance Estimation in Reverberant Environments

Fast Speech Foundation Model Distillation Using Interleaved Stacking

Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data

GLACIER: A Multimodal Student-Teacher Foundation Model for Molecular Property Prediction

Human-Guided Agentic AI for Multimodal Clinical Prediction: Lessons from the AgentDS Healthcare Benchmark

Illumination-Robust Camera-Based Heart-Rate Estimation for Physiological Sensing in Robots

Knowing When to Ask: Self-Gated Clarification for Hierarchical Language Agents

Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

Learning Unions of Convex Sets via Invertible Latent Decomposition for Path Planning

MedCTA: A Benchmark for Clinical Tool Agents

MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching

MobileFineTuner: A Mobile-Native Framework for On-Device LLM Fine-Tuning in Real-World Embedded AI Applications

MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation

Performance Analysis of YOLOv11 and YOLOv8 for Mixed Traffic Object Detection under Adverse Weather Conditions in Developing Countries

Physics-Distilled Neural Network enabled by Large Language Models for Manufacturing Process-Property Predictive Modeling

PIGEON: VLM-Driven Object Navigation via Points of Interest Selection

PLUME: Probabilistic Latent Unified World Modeling and Parameter Estimation for Multi-Finger Manipulation

Point Cloud Segmentation for Autonomous Clip Positioning in Laparoscopic Cholecystectomy on a Phantom

SAFER-Nav: Enhancing Safety for Visual Robot Navigation via Segmentation-Aware Fine-Tuning

Semantic Grading of Written Answers in Low-Resource Language Bangla Using a Fine-Tuned Lightweight Language Model

SR-LIO++: LiDAR-Inertial Odometry and Quantized Mapping with Caching-Aware Sweep Reconstruction

TacCoRL: Integrating Tactile Feedback into VLA via Simulation

Using Explainability as a Training-Time Reliability Signal for Efficient ECG Classification

ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation

When Generic Prompt Improvements Hurt: Evaluation-Driven Iteration for LLM Applications

When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval

XPR: An Extensible Cross-Platform Point-Based Differentiable Renderer

A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation

A Source Domain is All You Need: Source-Only Cross-OS Transfer Learning for APT Anomaly Detection via Semantic Alignment and Optimal Transport

A Spiking Neural Architecture for Coordinating Arm and Locomotor Control

Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models

AgniNav: Configuration-Driven Cross-Embodiment Local Planning for Robot Navigation

Alignment Defends LLMs from Property Inference Attacks

ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents

Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations