arXiv:2606. 19325v1 Announce Type: cross Abstract: Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings.
By Michael Finkelson, Daniel Segal, Eitan Richardson, Shahar Armon, Nani Goldring, Poriya Panet, Nir Zabari, Benjamin Brazowski, Or Patashnik, Yoav HaCohen
arXiv:2603. 18558v2 Announce Type: replace-cross Abstract: Long-form video question answering requires reasoning over extended temporal contexts, making frame selection a critical bottleneck for multi-modal large language models (MLLMs) bound by finite context windows.
By Dan Ben-Ami, Gabriele Serussi, Kobi Cohen, Chaim Baskin
Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. These systems operate within speech-only pipelines that produce clean vocal sequences without the ambient texture of real conversations.
Speaker recognition has advanced rapidly with large-scale training datasets, yet Vietnamese remains under-resourced, with existing corpora limited in scale and acoustic diversity. Most large-scale datasets rely on facial cues to link speech with speaker identities, restricting data collection to recordings where speakers appear on camera.
Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought (CoT) reasoning has become the dominant approach, with HumanOmniV2 and its IntentBench benchmark as a prominent reference point.
arXiv:2607. 11798v1 Announce Type: cross Abstract: Long-form audio description (AD) requires more than describing visible actions: it must preserve characters, events, relationships, and story context across scenes so that blind and low-vision (BLV) audiences can follow a film.
By Seung Hyun Hahm, Minh T. Dinh, SouYoung Jin