datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
AV-SpeakerBench
AV-SpeakerBench
Audiovisual QA benchmark with speaker-aware questions and aligned clips. This drop includes trimmed segments (audio-only, visual-only, audiovisual) plus annotations to probe fine-grained AV reasoning.
Project page: https://plnguyen2908.github.io/AV-SpeakerBench-project-page/
Code & benchmarks: https://github.com/plnguyen2908/AV-SpeakerBench
Paper: https://arxiv.org/abs/2512.02231
Files
test.csv - original annotations and metadata with clip paths… See the full description on the dataset page: https://huggingface.co/datasets/plnguyen2908/AV-SpeakerBench.AudioVisual-Benchmark-Evaluation
AudioVisual Benchmark Evaluation — evaluation subsets
Item-id lists for the audio-visual benchmark subsets used in our reported
evaluation tables.
Layout
<benchmark>/eval_subset.csv item ids evaluated in the paper
<benchmark>/media_index.csv id -> media filename(s)
<benchmark>/media/ the media files those ids refer to
eval_subset.csv holds a single id column keyed to the source benchmark
(question_id, idx, or index). media/ contains exactly the… See the full description on the dataset page: https://huggingface.co/datasets/plnguyen2908/AudioVisual-Benchmark-Evaluation.plndataset
LARI – Lightweight Adaptation for Response and Inquiry
Dataset Description
LARI is a native Question and Answer (QA) dataset in Brazilian Portuguese, composed of 464 context-question-answer trios validated by human experts. It was created to address the scarcity of native and educationally grounded benchmarks for Portuguese.
Unlike most QA resources available in Portuguese (derived from automatic translations of English datasets) LARI was built from content originally… See the full description on the dataset page: https://huggingface.co/datasets/jjuliar/plndataset.clean_dataset