CycliST: A Video Language Model Benchmark for Reasoning on Cyclical State Transitions

• URL: http://arxiv.org/abs/2512.01095v1
• Date: Sun, 30 Nov 2025 21:28:41 GMT
• Title: CycliST: A Video Language Model Benchmark for Reasoning on Cyclical State Transitions
• Abstract summary: We present CycliST, a novel benchmark dataset designed to evaluate Video Language Models (VLM) on their ability for textual reasoning over cyclical state transitions.<n>We conduct extensive experiments with current state-of-the-art VLMs, both open-source and proprietary, and reveal their limitations in generalizing to cyclical dynamics.<n>Our results demonstrate that present-day VLMs struggle to reliably detect and exploit cyclic patterns, lack a notion of temporal understanding, and are unable to extract quantitative insights from scenes such as the number of objects in motion.
• Score: 35.80224795551762
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present CycliST, a novel benchmark dataset designed to evaluate Video Language Models (VLM) on their ability for textual reasoning over cyclical state transitions. CycliST captures fundamental aspects of real-world processes by generating synthetic, richly structured video sequences featuring periodic patterns in object motion and visual attributes. CycliST employs a tiered evaluation system that progressively increases difficulty through variations in the number of cyclic objects, scene clutter, and lighting conditions, challenging state-of-the-art models on their spatio-temporal cognition. We conduct extensive experiments with current state-of-the-art VLMs, both open-source and proprietary, and reveal their limitations in generalizing to cyclical dynamics such as linear and orbital motion, as well as time-dependent changes in visual attributes like color and scale. Our results demonstrate that present-day VLMs struggle to reliably detect and exploit cyclic patterns, lack a notion of temporal understanding, and are unable to extract quantitative insights from scenes, such as the number of objects in motion, highlighting a significant technical gap that needs to be addressed. More specifically, we find no single model consistently leads in performance: neither size nor architecture correlates strongly with outcomes, and no model succeeds equally well across all tasks. By providing a targeted challenge and a comprehensive evaluation framework, CycliST paves the way for visual reasoning models that surpass the state-of-the-art in understanding periodic patterns.

Related papers

• Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models [154.39583176906893]
  Large language models (MLs) have advanced understanding, they remain highly prone to hallucinations in scenes.<n>We argue this stems from a failure intemporal monitoring, the ability to persistently track object dynamic identities, states, and relations over time.<n>Existing benchmarks obscure this deficit relying on single final-answer queries that can often be resolved via local visual cues or statistical priors.
  arXiv  Detail & Related papers  (2026-05-09T14:32:36Z)
• Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gains [17.650604674194984]
  We argue that the current practice of evaluating AI/ML time-series forecasting models obscures real progress by overlooking the performance of efficient classical methods.<n>We demonstrate that these "standard" datasets often exhibit dominant autocorrelation patterns and seasonal cycles that can be effectively captured by simpler linear or statistical models.
  arXiv  Detail & Related papers  (2026-03-16T16:34:26Z)
• Single molecule localization microscopy challenge: a biologically inspired benchmark for long-sequence modeling [8.15111481608191]
  State space models (SSMs) have recently achieved strong performance on long sequence modeling tasks.<n>We introduce the Single Molecule Microscopy Challenge (PAM-C), a benchmark dataset consisting of ten SMLM simulations spanning dStorm and DNA-INT modalities.<n>Using a controlled subset of these simulations, we evaluate state space models and find that performance degrades substantially as temporal discontinuity.<n>These results highlight the need for sequence models better suited to sparse, irregular temporal processes encountered in real world scientific imaging data.
  arXiv  Detail & Related papers  (2026-03-11T20:50:01Z)
• Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs [54.502280390499756]
  We propose TimeWarp to create a targeted synthetic temporal dataset to fine-tune the model's responses to encourage it to focus on the given input video.<n>We demonstrate that when our method is applied to existing models, it significantly improves performance on temporal understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-04T21:48:40Z)
• THYME: Temporal Hierarchical-Cyclic Interactivity Modeling for Video Scene Graphs in Aerial Footage [11.587822611656648]
  We introduce the Temporal Hierarchical Cyclic Scene Graph (THYME) approach, which integrates hierarchical feature aggregation with cyclic temporal refinement to address limitations.<n>THYME effectively models multi-scale spatial context and enforces temporal consistency across frames, yielding more accurate and coherent scene graphs.<n>In addition, we present AeroEye-v1.0, a novel aerial video dataset enriched with five types of interactivity that overcomes the constraints of existing datasets.
  arXiv  Detail & Related papers  (2025-07-12T08:43:38Z)
• TopoCL: Topological Contrastive Learning for Time Series [1.8434042562191815]
  We propose Topological Contrastive Learning for time series (TopoCL)<n>TopoCL mitigates information loss by incorporating persistent homology.<n>We conduct experiments on four downstream tasks-classification, anomaly detection, forecasting, and transfer learning.
  arXiv  Detail & Related papers  (2025-02-05T06:37:35Z)
• Neural Persistence Dynamics [8.197801260302642]
  We consider the problem of learning the dynamics in the topology of time-evolving point clouds. Our proposed model - $textitNeural Persistence Dynamics$ - substantially outperforms the state-of-the-art across a diverse set of parameter regression tasks.
  arXiv  Detail & Related papers  (2024-05-24T17:20:18Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations [15.797295258800638]
  We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data. Our method relies on a continuous-time-dependent model of the series' evolution dynamics. A modulation mechanism, driven by a meta-learning algorithm, allows adaptation to unseen samples and extrapolation beyond observed time-windows.
  arXiv  Detail & Related papers  (2023-06-09T13:20:04Z)
• Leaping Into Memories: Space-Time Deep Feature Synthesis [93.10032043225362]
  We propose LEAPS, an architecture-independent method for synthesizing videos from internal models. We quantitatively and qualitatively evaluate the applicability of LEAPS by inverting a range of architectures convolutional attention-based on Kinetics-400.
  arXiv  Detail & Related papers  (2023-03-17T12:55:22Z)
• Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series [18.885471782270375]
  NCDSSM employs auxiliary variables to disentangle recognition from dynamics, thus requiring amortized inference only for the auxiliary variables. We propose three flexible parameterizations of the latent dynamics and an efficient training objective that marginalizes the dynamic states during inference. Empirical results on multiple benchmark datasets show improved imputation and forecasting performance of NCDSSM over existing models.
  arXiv  Detail & Related papers  (2023-01-26T18:45:04Z)
• TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning [79.77010271213695]
  We propose a novel video self-supervised learning framework named Temporal Contrastive Graph Learning (TCGL) Our TCGL integrates the prior knowledge about the frame and snippet orders into graph structures, i.e., the intra-/inter- snippet Temporal Contrastive Graphs (TCG) To generate supervisory signals for unlabeled videos, we introduce an Adaptive Snippet Order Prediction (ASOP) module.
  arXiv  Detail & Related papers  (2021-12-07T09:27:56Z)
• Learning Temporal Dynamics from Cycles in Narrated Video [85.89096034281694]
  We propose a self-supervised solution to the problem of learning to model how the world changes as time elapses. Our model learns modality-agnostic functions to predict forward and backward in time, which must undo each other when composed. We apply the learned dynamics model without further training to various tasks, such as predicting future action and temporally ordering sets of images.
  arXiv  Detail & Related papers  (2021-01-07T02:41:32Z)
• Unsupervised Video Decomposition using Spatio-temporal Iterative Inference [31.97227651679233]
  Multi-object scene decomposition is a fast-emerging problem in learning. We show that our model has a high accuracy even without color information. We demonstrate the decomposition, segmentation prediction capabilities of our model and show that it outperforms the state-of-the-art on several benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-25T22:57:17Z)

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.