Copertina

Pro$^2$Assist: Continuous Step-Aware Proactive Assistance with Multimodal Egocentric Perception for Long-Horizon Procedural Tasks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Lilin, Yang, Bufang, Jiang, Siyang, Liu, Kaiwei, Hou, Kaiyuan, Fan, Yuang, Chen, Hongkai, Yan, Zhenyu, Jiang, Xiaofan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Human-Computer Interaction
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions
di: Yang, Bufang, et al.
Pubblicazione: (2025)

ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild
di: Yang, Bufang, et al.
Pubblicazione: (2025)

SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions
di: Yang, Bufang, et al.
Pubblicazione: (2024)

DrHouse: An LLM-empowered Diagnostic Reasoning System through Harnessing Outcomes from Sensor Data and Expert Knowledge
di: Yang, Bufang, et al.
Pubblicazione: (2024)

SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams
di: Yang, Bufang, et al.
Pubblicazione: (2026)

An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding
di: Jiang, Siyang, et al.
Pubblicazione: (2025)

TDBench: A Benchmark for Top-Down Image Understanding with Reliability Analysis of Vision-Language Models
di: Hou, Kaiyuan, et al.
Pubblicazione: (2025)

Exploring the Capabilities of LLMs for IMU-based Fine-grained Human Activity Understanding
di: Xu, Lilin, et al.
Pubblicazione: (2025)

PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices
di: Liu, Kaiwei, et al.
Pubblicazione: (2025)

A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
di: Jiang, Siyang, et al.
Pubblicazione: (2025)

Visualizing the Invisible: A Generative AR System for Intuitive Multi-Modal Sensor Data Presentation
di: Guo, Yunqi, et al.
Pubblicazione: (2024)

VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments
di: Yang, Bufang, et al.
Pubblicazione: (2024)

EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks
di: Liu, Lulin, et al.
Pubblicazione: (2026)

PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaboration
di: He, Chengbo, et al.
Pubblicazione: (2026)

DeepFeature: Iterative Context-aware Feature Generation for Wearable Biosignals
di: Liu, Kaiwei, et al.
Pubblicazione: (2025)

From Videos to Conversations: Egocentric Instructions for Task Assistance
di: Aggarwal, Lavisha, et al.
Pubblicazione: (2026)

EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams
di: Ran, Dongchuan, et al.
Pubblicazione: (2026)

ProMemAssist: Exploring Timely Proactive Assistance Through Working Memory Modeling in Multi-Modal Wearable Devices
di: Pu, Kevin, et al.
Pubblicazione: (2025)

ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents
di: Ding, Lei, et al.
Pubblicazione: (2026)

ProSec: Fortifying Code LLMs with Proactive Security Alignment
di: Xu, Xiangzhe, et al.
Pubblicazione: (2024)

ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response
di: Zhu, Xiaomeng, et al.
Pubblicazione: (2026)

ProGuard: Towards Proactive Multimodal Safeguard
di: Yu, Shaohan, et al.
Pubblicazione: (2025)

ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data
di: Tang, Yuanbo, et al.
Pubblicazione: (2026)

Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
di: Li, Zaijing, et al.
Pubblicazione: (2024)

LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks
di: Gao, Hengjian, et al.
Pubblicazione: (2026)

ReSPEC: A Framework for Online Multispectral Sensor Reconfiguration in Dynamic Environments
di: Liu, Yanchen, et al.
Pubblicazione: (2026)

RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users
di: Ye, Suyu, et al.
Pubblicazione: (2025)

AgentFold: Long-Horizon Web Agents with Proactive Context Management
di: Ye, Rui, et al.
Pubblicazione: (2025)

VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
di: Si, Shengyu, et al.
Pubblicazione: (2026)

Temporal Preferences in Language Models for Long-Horizon Assistance
di: Mazyaki, Ali, et al.
Pubblicazione: (2025)

AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance
di: Zhao, Yuyang, et al.
Pubblicazione: (2025)

ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation
di: Xue, Wei, et al.
Pubblicazione: (2026)

EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
di: Yu, Chengjun, et al.
Pubblicazione: (2026)

FlexiFly: Interfacing the Physical World with Foundation Models Empowered by Reconfigurable Drone Systems
di: Zhao, Minghui, et al.
Pubblicazione: (2024)

Generating Dialogues from Egocentric Instructional Videos for Task Assistance: Dataset, Method and Benchmark
di: Aggarwal, Lavisha, et al.
Pubblicazione: (2025)

Continual Multimodal Egocentric Activity Recognition via Modality-Aware Novel Detection
di: Lim, Wonseon, et al.
Pubblicazione: (2026)

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
di: Deng, Xiang, et al.
Pubblicazione: (2025)

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?
di: Lee, Hwiwon, et al.
Pubblicazione: (2026)

Large Language Models for Single-Step and Multi-Step Flight Trajectory Prediction
di: Luo, Kaiwei, et al.
Pubblicazione: (2025)

StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video
di: Li, Ao, et al.
Pubblicazione: (2026)