{"total":18,"rows":[{"id":"2412.21080","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","created":"2024-12-30","cited_by_count":19,"area":"mllm"},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18,"area":"mllm"},{"id":"2505.12632","title":"Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents","created":"2025-05-19","cited_by_count":14,"area":"mllm"},{"id":"2404.09933","title":"HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision","created":"2024-04-15","cited_by_count":9,"area":"mllm"},{"id":"2403.19811","title":"X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization","created":"2024-03-28","cited_by_count":6,"area":"mllm"},{"id":"2509.12145","title":"Open-ended Hierarchical Streaming Video Understanding with Vision Language Models","created":"2025-09-15","cited_by_count":6,"area":"mllm"},{"id":"2511.13261","title":"Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges","created":"2025-11-17","cited_by_count":5,"area":"mllm"},{"id":"2606.08615","title":"Harnessing Streaming Video in the Wild","created":"2026-06-07","cited_by_count":4,"area":"mllm"},{"id":"2511.21998","title":"Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?","created":"2025-11-27","cited_by_count":2,"area":"mllm"},{"id":"2411.15628","title":"ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos","created":"2024-11-23","cited_by_count":1,"area":"mllm"},{"id":"2512.10342","title":"CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates","created":"2025-12-11","cited_by_count":1,"area":"mllm"},{"id":"2607.02991","title":"GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video","created":"2026-07-03","cited_by_count":1,"area":"mllm"},{"id":"2607.05264","title":"SteelBench: Evaluating Vision-Language Models in Real-World Industrial Environments","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2509.22019","title":"EgoInstruct: An Egocentric Video Dataset of Face-to-face Instructional Interactions with Multi-modal LLM Benchmarking","created":"2025-09-26","cited_by_count":0,"area":"mllm"},{"id":"2603.22321","title":"From Instructions to Assistance: a Dataset Aligning Instruction Manuals with Assembly Videos for Evaluating Multimodal LLMs","created":"2026-03-20","cited_by_count":0,"area":"mllm"},{"id":"2604.00913","title":"Benchmarking and Mechanistic Analysis of Vision-Language Models for Cross-Depiction Assembly Instruction Alignment","created":"2026-04-01","cited_by_count":0,"area":"mllm"},{"id":"2607.10797","title":"Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos","created":"2026-07-12","cited_by_count":0,"area":"mllm"},{"id":"2610.14397","title":"RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work","created":"2026-10-09","cited_by_count":0,"area":"mllm"}],"next_cursor":null}