Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations

• URL: http://arxiv.org/abs/2510.17313v3
• Date: Sat, 25 Oct 2025 02:21:56 GMT
• Title: Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations
• Authors: Tal Barami, Nimrod Berman, Ilan Naiman, Amos H. Hason, Rotem Ezra, Omri Azencot,
• Abstract summary: We introduce the first standardized benchmark for evaluating multi-factor sequential disentanglement across six diverse datasets.<n>We propose a post-hoc Latent Exploration Stage to automatically align latent dimensions with semantic factors, and introduce a Koopman-inspired model that achieves state-of-the-art results.<n>Our code is available on GitHub, and the datasets and trained models are available on Hugging Face.
• Score: 14.972702558607557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While real-world data involves multiple interacting semantic factors over time, prior work has mostly focused on simpler two-factor static and dynamic settings, primarily because such settings make data collection easier, thereby overlooking the inherently multi-factor nature of real-world data. We introduce the first standardized benchmark for evaluating multi-factor sequential disentanglement across six diverse datasets spanning video, audio, and time series. Our benchmark includes modular tools for dataset integration, model development, and evaluation metrics tailored to multi-factor analysis. We additionally propose a post-hoc Latent Exploration Stage to automatically align latent dimensions with semantic factors, and introduce a Koopman-inspired model that achieves state-of-the-art results. Moreover, we show that Vision-Language Models can automate dataset annotation and serve as zero-shot disentanglement evaluators, removing the need for manual labels and human intervention. Together, these contributions provide a robust and scalable foundation for advancing multi-factor sequential disentanglement. Our code is available on GitHub, and the datasets and trained models are available on Hugging Face.

Related papers

• Where is the multimodal goal post? On the Ability of Foundation Models to Recognize Contextually Important Moments [11.490236862362801]
  We study the ability of models to identify the most important sub-events in a video.<n>We evaluate models on their ability to distinguish between important and non-important sub-events in a game.
  arXiv  Detail & Related papers  (2026-01-22T21:40:08Z)
• Toward Purpose-oriented Topic Model Evaluation enabled by Large Language Models [0.8193467416247519]
  We introduce a purpose-oriented evaluation framework that employs nine Large Language Models (LLMs)-based metrics spanning four key dimensions of topic quality.<n>The framework is validated through adversarial and sampling-based protocols, and is applied across datasets spanning news articles, scholarly publications, and social media posts.
  arXiv  Detail & Related papers  (2025-09-08T18:46:08Z)
• ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation [51.297873393639456]
  ArtifactsBench is a framework for automated visual code generation evaluation.<n>Our framework renders each generated artifact and captures its dynamic behavior through temporal screenshots.<n>We construct a new benchmark of 1,825 diverse tasks and evaluate over 30 leading Large Language Models.
  arXiv  Detail & Related papers  (2025-07-07T12:53:00Z)
• RemoteSAM: Towards Segment Anything for Earth Observation [29.707796048411705]
  We aim to develop a robust yet flexible visual foundation model for Earth observation.<n>It should possess strong capabilities in recognizing and localizing diverse visual targets.<n>We present RemoteSAM, a foundation model that establishes new SoTA on several earth observation perception benchmarks.
  arXiv  Detail & Related papers  (2025-05-23T15:27:57Z)
• Survey of Large Multimodal Model Datasets, Application Categories and Taxonomy [2.294223504228228]
  Multimodal learning, a rapidly evolving field in artificial intelligence, seeks to construct more versatile and robust systems.<n>Inspired by the human ability to assimilate information through many senses, this method enables applications such as text-to-video conversion, visual question answering, and image captioning.<n>Recent developments in datasets that support multimodal language models (MLLMs) are highlighted in this overview.
  arXiv  Detail & Related papers  (2024-12-23T18:15:19Z)
• EBES: Easy Benchmarking for Event Sequences [17.277513178760348]
  Event Sequences (EvS) refer to sequential data characterized by irregular sampling intervals and a mix of categorical and numerical features.<n>EBES is a comprehensive benchmark for EvS classification with sequence-level targets.<n>It features standardized evaluation scenarios and protocols, along with an open-source PyTorch library that implements 9 modern models.
  arXiv  Detail & Related papers  (2024-10-04T13:03:43Z)
• An Integrated Data Processing Framework for Pretraining Foundation Models [57.47845148721817]
  Researchers and practitioners often have to manually curate datasets from difference sources. We propose a data processing framework that integrates a Processing Module and an Analyzing Module. The proposed framework is easy to use and highly flexible.
  arXiv  Detail & Related papers  (2024-02-26T07:22:51Z)
• StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data [129.92449761766025]
  We propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models. Our research includes comprehensive experiments conducted on various datasets.
  arXiv  Detail & Related papers  (2023-08-20T12:43:52Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• MSeg: A Composite Dataset for Multi-domain Semantic Segmentation [100.17755160696939]
  We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. We reconcile the generalization and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training.
  arXiv  Detail & Related papers  (2021-12-27T16:16:35Z)
• Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning [62.47593143542552]
  We describe a subset optimization approach for automatic dataset curation. We demonstrate that our approach finds videos with high audio-visual correspondence and show that self-supervised models trained on our data, despite being automatically constructed, achieve similar downstream performances to existing video datasets with similar scales.
  arXiv  Detail & Related papers  (2021-01-26T14:27:47Z)
• The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements [14.707930573950787]
  We present MuSe-CaR, a first of its kind multimodal dataset. The data is publicly available as it recently served as the testing bed for the 1st Multimodal Sentiment Analysis Challenge.
  arXiv  Detail & Related papers  (2021-01-15T10:40:37Z)
• Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations [67.4375210552593]
  We design experiments to understand an important but often ignored problem in visually grounded language generation. Given that humans have different utilities and visual attention, how will the sample variance in multi-reference datasets affect the models' performance? We show that it is of paramount importance to report variance in experiments; that human-generated references could vary drastically in different datasets/tasks, revealing the nature of each task.
  arXiv  Detail & Related papers  (2020-10-07T20:45:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.