arXiv AI
Jun 6
Personal AI Agent for Camera Roll VQA
arXiv:2606. 05275v1 Announce Type: cross Abstract: We study the personal camera roll visual question answering setting.
Companion-style QA Assistance in Ego-Vision
BuddyVQA is a new benchmark for companion‑style question answering on egocentric streaming video, comprising 21.6K questions tied to 6K highlight moments across 1,012 long first‑person videos. It emphasizes two often overlooked aspects of daily first‑person QA: ego‑deictic expressions and interactively chained questions, requiring models to resolve visual pronouns and infer user intent within a long‑form streaming context. The authors propose MyBuddy, a multimodal chain‑of‑thought QA assistant that uses a question filter and multi‑level memory to efficiently retrieve visual and QA information, achieving significant performance gains on BuddyVQA and generalizing to other streaming and common video QA benchmarks.
Related stories
arXiv Machine Learning
Aug 3
EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment
arXiv:2604. 08342v2 Announce Type: replace Abstract: Long context egocentric video understanding has recently attracted significant research attention, with augmented reality (AR) highlighted as one of its most important application domains.
arXiv AI
Jun 30
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction
arXiv:2606. 29445v1 Announce Type: cross Abstract: Video understanding is a fundamental capability for multimodal intelligence, and recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance on Video Question Answering (VideoQA) benchmarks.
Hugging Face Trending Papers
Jul 13
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
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.
arXiv Machine Learning
Jul 7
Incentivizing Vision Language Models to Search for Long Video Question Answering
arXiv:2607. 02959v1 Announce Type: cross Abstract: We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-turn retrieval process.
arXiv AI
Aug 6
The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering
arXiv:2608. 04589v1 Announce Type: cross Abstract: EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize beyond common daily-life scenarios.
arXiv AI
Aug 14
EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory
arXiv:2608. 12627v1 Announce Type: cross Abstract: Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences.
arXiv AI
Jul 14
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
arXiv:2607. 11523v1 Announce Type: cross Abstract: When should an intelligent assistant speak up without being asked?
arXiv Computation and Language
Aug 27
EgoArgus: Benchmarking VLMs as Situational Assistants for Modality-Grounded User Supports
EgoArgus is a new, human‑annotated dataset that tests visual‑language models (VLMs) as situational assistants in five everyday dialogue‑video scenarios. It evaluates how well VLMs understand and decide when to intervene, especially when visual and textual cues are helpful, irrelevant, or conflicting. The study finds that current VLMs still struggle to reliably act as egocentric assistants and that existing modality‑bias mitigation methods offer limited improvement.
arXiv Computation and Language
Aug 31
MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering
MemoryCard is a video-memory-based augmentation framework designed to improve long-video question answering for Vision‑Language Models. It segments lengthy videos into semantically coherent units—each representing a distinct topic or event—by performing a self‑reading process over the video and aligned utterances. For each unit, the framework generates an event‑level video gist and selects representative visual moments, which are compiled into unified Memory Cards that are used for retrieval and answering questions, yielding up to a 21.8% relative accuracy improvement under comparable visual‑token budgets.
arXiv AI
3d ago
NoteVQA: Benchmarking VLMs on Real-Life Questions from Human Communities
NoteVQA is a new benchmark that collects 252 real‑life visual questions from the Chinese image‑sharing platform Xiaohongshu, covering 12 topics and 7 user intents. Each question is paired with a concise expert reference and a human‑audited interleaved answer that blends text and visual evidence. The study evaluates VLMs on short‑answer correctness and interleaved answer quality using a new AgenticInterleave framework and a 12‑dimensional IVR‑12 rubric, finding that even state‑of‑the‑art models achieve only about 53% accuracy and lag behind human references in content quality.
arXiv AI
Jun 9
MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention
arXiv:2606. 07639v1 Announce Type: cross Abstract: Video understanding is shifting from the offline paradigm -- taking a fully recorded video as input and producing a single answer after it ends -- toward real-time interaction, in which the model perceives new frames while still replying, revises its answer as new evidence appears, and remains silent when there is nothing to say.