The paper introduces an automated pipeline that converts educational videos into structured summaries and high‑quality question‑answer pairs. It uses FFmpeg for audio extraction, Whisper for speech recognition, BART for transcript summarization, and Llama‑3.1‑8BInstruct for generating and self‑verifying QA pairs. The verified pairs form a synthetic dataset that fine‑tunes the Llama model via LoRA, producing a domain‑specific question generator without manual annotation.
Bengali, spoken by over 230 million people, remains severely under-resourced in spoken language research. Existing open Bengali ASR corpora are confined to short, read or crowd-sourced speech and lack...
Lipi-Ghor is a large-scale, weakly-supervised Bengali speech corpus containing 885 hours of audio from 998 YouTube videos across 17 domains, each annotated in SSTT format with speaker diarization and timestamps. It is the first Bengali corpus to combine extensive coverage with speaker-diarized, long-form audio annotations, and the authors provide a replicable pipeline for building similar resources in other languages. The dataset includes a human-annotated gold evaluation split and is released under CC‑BY‑4.0, with raw audio withheld.
arXiv:2606. 14762v1 Announce Type: cross Abstract: As video content continues to expand across educational platforms, recorded lectures, and live-streamed entertainment, the need for efficient and structured analysis of long-form footage has increased \cite{1}.
LF-VideoQA is a new dataset for long‑form, open‑ended question answering over narrative videos, built around theory‑of‑mind questions that require reasoning across scenes averaging 23 minutes. It contains over 6,300 question‑answer‑rubric triples generated automatically from annotated screenplays and validated by humans. The dataset challenges current vision‑language models, showing that even oracle models fall short and that visual evidence is essential for answering these questions.
arXiv:2511. 05550v3 Announce Type: replace-cross Abstract: Large audio language models (LALMs) leverage multimodal representations to generate open-ended answers to natural language queries about audio.
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.
arXiv:2606. 14591v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) have shown strong performance on a wide range of audio understanding tasks, yet they still struggle with complex audio reasoning.
Video-IFBench is a new benchmark designed to evaluate how well multimodal large language models (MLLMs) follow user-specified instructions in video understanding tasks. It introduces an instruction taxonomy with four templates—single-task, multi-task, selection, and nested—covering 32 task types and 39 constraint categories that span semantic and format requirements. The benchmark was built using a semi-automatic pipeline that combines MLLMs, programmatic processing, and human verification, producing 1.5K samples, and a large-scale evaluation of over 20 recent MLLMs shows that instruction following remains difficult, especially for complex constraints and conditional structures.
arXiv:2606. 03635v1 Announce Type: cross Abstract: Understanding short online videos involves more than identifying visible objects and actions; video makers often include an underlying message or purpose in the clip.
arXiv:2606. 07924v1 Announce Type: cross Abstract: This paper presents our system description for the 2nd Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR).
arXiv:2502. 16584v2 Announce Type: replace-cross Abstract: Recent advancements in audio tokenization have significantly enhanced the integration of audio capabilities into large language models (LLMs).
arXiv:2505.13520v2 Announce Type: replace-cross Abstract: Textbook question answering (TQA) is a complex task, requiring the interpretation of complex multimodal context. Although recent advances hav...