arXiv:2607. 29181v1 Announce Type: cross Abstract: Agentic assistants capable of proactive, personalized interactions require structured models of user intent and workflow.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2608. 13113v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video benchmarks.
arXiv:2606. 07433v1 Announce Type: cross Abstract: Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios.
Video provides a rich record of human behavior, interaction, and situated contexts, offering important evidence for understanding people and conducting human-centered research. As vision-language mode...
arXiv:2607. 11523v1 Announce Type: cross Abstract: When should an intelligent assistant speak up without being asked?
NextMe-800 is an approximately 800‑hour first‑person video dataset collected from a single volunteer over 126 days, featuring 1 Hz images, gaze, and audio. The data are captioned at five hierarchical abstraction levels—from atomic actions to major activities—enabling personalized action anticipation as an open‑vocabulary K‑step sequence prediction task. The authors also introduce NextAct, a 1,500‑point benchmark that combines NextMe‑800 with the multi‑person EgoLife dataset, and evaluate models using an embedding‑based soft edit distance to assess how well personal behavior can be anticipated across abstraction levels and prediction horizons.
When should an intelligent assistant speak up without being asked? Continuous egocentric video offers rich, evolving context that enables a new form of assistance: one that is proactive rather than merely reactive.