CinePile 2.0 - Making Stronger Datasets with Adversarial Refinement
CinePile 2.0 is a new video question-answering benchmark and dataset designed to evaluate long-form video understanding in multimodal models. The dataset uses adversarial refinement techniques to reduce spurious correlations and improve question difficulty, making it harder for models to answer correctly without genuine video comprehension. It targets a known weakness in existing video benchmarks where models can exploit language priors rather than visual content.
Related guides (3)
Related events (8)
Docmatix: A Large-Scale Dataset for Document Visual Question Answering
Hugging Face released Docmatix, a large-scale dataset designed for Document Visual Question Answering (DocVQA) tasks. The dataset aims to address the scarcity of high-quality training data for document understanding in multimodal models. It is intended to improve fine-tuning of vision-language models on document comprehension tasks.
Benchmark for view-level visual evidence identification in multi-view MLLMs for autonomous driving
A new arXiv preprint introduces a multi-view visual question answering benchmark targeting evidence-source identification in autonomous driving scenarios. Given six synchronized NuScenes camera views and a question, models must identify which camera view supports the answer — not just produce a correct answer. The 122-pair benchmark spans causality, counterfactual reasoning, and intent prediction, and exposes grounding failures that answer-only evaluation misses. The work addresses a meaningful gap between answer accuracy and correct visual grounding in safety-critical multimodal systems.
FineVideo: Behind the Scenes — HuggingFace Video Dataset Release
HuggingFace published a behind-the-scenes account of FineVideo, a curated dataset aimed at advancing video understanding in AI/ML models. The post details the data collection, annotation, and curation methodology used to build the dataset. FineVideo is positioned as a resource for training and evaluating multimodal video models.
Build Awesome Datasets for Video Generation
Hugging Face published a blog post on constructing high-quality datasets for video generation models. The post likely covers data collection, preprocessing, and curation pipelines relevant to training video diffusion or generation systems. This is a practical tooling and methodology guide aimed at practitioners working on video AI.
Moment-Video: Benchmark Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
Moment-Video is a new benchmark of 1,000 human-verified video-QA pairs designed to evaluate how well video multimodal large language models (MLLMs) handle brief, localized visual events that may span only a few frames. The benchmark covers 7 domains and 25 subcategories across four task types: Temporal Occurrence, Temporal Counting, Action Description, and Temporal Reasoning. Evaluation of 33 proprietary and open-source models reveals severe deficiencies: the best model (Seed-2.0-Pro) achieves only 39.6% accuracy, while most open-source models score below 25%. Diagnostic analyses show that denser frame sampling helps but does not resolve the bottleneck, pointing to fundamental limitations in how current video MLLMs represent and preserve transient visual evidence.
Survey: Human-View Video Understanding with MLLMs — Watch, Remember, Reason Framework
A new arXiv survey paper proposes a unified 'human-view' framework for analyzing multimodal LLM-based video understanding, organized around three functional abilities: watching (perception), remembering (memory), and reasoning. The authors introduce a formulation characterizing video understanding systems by perceptual representations, memory states, reasoning traces, and predictions, then survey methods, datasets, and benchmarks across these dimensions. The work covers challenges including spatio-temporal perception, long-video processing, streaming understanding, and faithful reasoning, with application domains spanning egocentric, sports, medical, and narrative video.
OmniAgent: POMDP-based active perception agent for long video understanding with test-time scaling
Researchers introduce OmniAgent, a multimodal agent that reformulates long video understanding as a POMDP-based iterative Observation-Thought-Action cycle, selectively distilling audio-visual cues into persistent textual memory rather than processing all frames uniformly. The system uses Agentic Supervised Fine-Tuning and a novel reinforcement learning method (TAURA) with turn-level entropy for credit assignment. OmniAgent demonstrates positive test-time scaling and achieves state-of-the-art open-source results across ten benchmarks, with its 7B model outperforming Qwen2.5-VL-72B on LVBench (50.5% vs. 47.3%).
WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata
WikiVQABench is a new human-curated VQA benchmark that requires external knowledge beyond visual perception, constructed by combining Wikipedia images, captions, and Wikidata structured knowledge with LLM-generated question candidates reviewed by human annotators. The benchmark evaluates knowledge-intensive reasoning in vision-language models, covering 15 VLMs ranging from 256M to 90B parameters. Accuracy spans 24.7% to 75.6%, indicating meaningful discrimination across model scales. The dataset and code are publicly released.