TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal Models

• URL: http://arxiv.org/abs/2602.18884v1
• Date: Sat, 21 Feb 2026 16:10:52 GMT
• Title: TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal Models
• Authors: Zhenkun Gao, Xuhong Wang, Xin Tan, Yuan Xie,
• Abstract summary: We introduce TPRU, a large-scale dataset sourced from diverse embodied scenarios.<n>TPRU is systematically designed to cultivate temporal reasoning through three complementary tasks.<n>We leverage TPRU with a reinforcement learning (RL) fine-tuning methodology, specifically targeting the enhancement of resource-efficient models.
• Score: 16.203071396170284
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs), particularly smaller, deployable variants, exhibit a critical deficiency in understanding temporal and procedural visual data, a bottleneck hindering their application in real-world embodied AI. This gap is largely caused by a systemic failure in training paradigms, which lack large-scale, procedurally coherent data. To address this problem, we introduce TPRU, a large-scale dataset sourced from diverse embodied scenarios such as robotic manipulation and GUI navigation. TPRU is systematically designed to cultivate temporal reasoning through three complementary tasks: Temporal Reordering, Next-Frame Prediction, and Previous-Frame Review. A key feature is the inclusion of challenging negative samples, compelling models to transition from passive observation to active, cross-modal validation. We leverage TPRU with a reinforcement learning (RL) fine-tuning methodology, specifically targeting the enhancement of resource-efficient models. Experiments show our approach yields dramatic gains: on our manually curated TPRU-Test, the accuracy of TPRU-7B soars from 50.33\% to 75.70\%, a state-of-the-art result that significantly outperforms vastly larger baselines, including GPT-4o. Crucially, these capabilities generalize effectively, demonstrating substantial improvements on established benchmarks. The codebase is available at https://github.com/Stephen-gzk/TPRU/ .

Related papers

• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision [11.159231524113764]
  Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs)<n>In this paper, we propose the textbfGuided Verifier framework to address these structural limitations.<n>We develop a specialized data synthesis pipeline targeting multimodal hallucinations, constructing textbfCoRe dataset of process-level negatives and textbfCorrect-guide textbfReasoning trajectories to train the guided verifier.
  arXiv  Detail & Related papers  (2026-02-04T07:38:42Z)
• Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs [22.76757502541604]
  We introduce PIP: a Parallel Inference Paradigm for Key Information Extraction (KIE)<n>Our approach reformulates the problem by using "[mask]" tokens as placeholders for all target values, enabling their simultaneous generation in a single forward pass.<n> Experimental results show that our PIP-models achieve a 5-36x inference speedup with negligible performance degradation compared to traditional autoregressive base models.
  arXiv  Detail & Related papers  (2026-01-27T13:45:30Z)
• Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs [78.09559830840595]
  We present the first systematic study on quantizing diffusion-based language models.<n>We identify the presence of activation outliers, characterized by abnormally large activation values.<n>We implement state-of-the-art PTQ methods and conduct a comprehensive evaluation.
  arXiv  Detail & Related papers  (2025-08-20T17:59:51Z)
• Perception-Aware Policy Optimization for Multimodal Reasoning [79.56070395437898]
  A major source of error in current multimodal reasoning lies in the perception of visual inputs.<n>We propose PAPO, a novel policy gradient algorithm that encourages the model to learn to perceive while learning to reason.<n>We observe a substantial reduction of 30.5% in perception errors, indicating improved perceptual capabilities with PAPO.
  arXiv  Detail & Related papers  (2025-07-08T23:22:34Z)
• R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning [69.72249695674665]
  We propose a robust test-time prompt tuning (R-TPT) for vision-language models (VLMs)<n>R-TPT mitigates the impact of adversarial attacks during the inference stage.<n>We introduce a plug-and-play reliability-based weighted ensembling strategy to strengthen the defense.
  arXiv  Detail & Related papers  (2025-04-15T13:49:31Z)
• PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection [68.8373788348678]
  Visual instruction tuning adapts pre-trained Multimodal Large Language Models to follow human instructions.<n>PRISM is the first training-free framework for efficient visual instruction selection.<n>It reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines.
  arXiv  Detail & Related papers  (2025-02-17T18:43:41Z)
• A Bayesian Approach to Data Point Selection [24.98069363998565]
  Data point selection (DPS) is becoming a critical topic in deep learning. Existing approaches to DPS are predominantly based on a bi-level optimisation (BLO) formulation. We propose a novel Bayesian approach to DPS.
  arXiv  Detail & Related papers  (2024-11-06T09:04:13Z)
• TimeSieve: Extracting Temporal Dynamics through Information Bottlenecks [31.10683149519954]
  We propose an innovative time series forecasting model TimeSieve. Our approach employs wavelet transforms to preprocess time series data, effectively capturing multi-scale features. Our results validate the effectiveness of our approach in addressing the key challenges in time series forecasting.
  arXiv  Detail & Related papers  (2024-06-07T15:58:12Z)
• Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures [18.592350352298553]
  We introduce LightTS, a light deep learning architecture merely based on simple-based structures. Compared with the existing state-of-the-art methods, LightTS demonstrates better performance on five of them and comparable performance on the rest. LightTS is robust and has a much smaller variance in forecasting accuracy than previous SOTA methods in long sequence forecasting tasks.
  arXiv  Detail & Related papers  (2022-07-04T04:03:00Z)
• Transformer Hawkes Process [79.16290557505211]
  We propose a Transformer Hawkes Process (THP) model, which leverages the self-attention mechanism to capture long-term dependencies. THP outperforms existing models in terms of both likelihood and event prediction accuracy by a notable margin. We provide a concrete example, where THP achieves improved prediction performance for learning multiple point processes when incorporating their relational information.
  arXiv  Detail & Related papers  (2020-02-21T13:48:13Z)

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.