{"total":16,"rows":[{"id":"2606.04970","title":"Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance","created":"2026-06-03","cited_by_count":7,"area":null},{"id":"2607.11523","title":"Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos","created":"2026-07-13","cited_by_count":5,"area":null},{"id":"2607.13298","title":"FOLIO: Focused Semantic Memory for Streaming Video Understanding","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2603.04592","title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2608.02392","title":"GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2602.15707","title":"Proactive Conversational Assistant for a Procedural Manual Task based on Audio and IMU","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2606.04743","title":"TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.06991","title":"Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.09547","title":"Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2604.08062","title":"From Gaze to Guidance: Interpreting and Adapting to Users' Cognitive Needs with Multimodal Gaze-Aware AI Assistants","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2608.25561","title":"EgoArgus: Benchmarking VLMs as Situational Assistants for Modality-Grounded User Supports","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.07099","title":"Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.21371","title":"RobotEQ-Video: A Video-Centric Benchmark for Social Proactive Intelligence with World-State Taxonomy","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2610.05013","title":"EMBER-Bench: Benchmarking Cross-Event Causal Memory in Long-Horizon Embodied Tasks","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05775","title":"InteractionBench: A Real-Time Interaction Benchmark for Streaming Video Systems","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.16967","title":"Proactive Physical AI through Continuous Observation and Timely Intervention","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}