# TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action

arXiv: https://arxiv.org/abs/2505.01583 · HTML: https://mlsanity.com/paper/2505.01583/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 57 of its 68 references that are in the map.
- First posted on arXiv 2 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 57)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2403.16999/) (2024)
- [Efficient Training of Language Models to Fill in the Middle](https://mlsanity.com/paper/2207.14255/) (2022)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound](https://mlsanity.com/paper/2201.02639/) (2022)
- [Query-Dependent Video Representation for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2303.13874/) (2023)
- [AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark](https://mlsanity.com/paper/2410.03051/) (2024)

## Built on by (most cited first, 14 of 14)

- [Kwai Keye-VL 1.5 Technical Report](https://mlsanity.com/paper/2509.01563/) (2025)
- [TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs](https://mlsanity.com/paper/2512.14698/) (2025)
- [MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding](https://mlsanity.com/paper/2505.20715/) (2025)
- [CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms](https://mlsanity.com/paper/2505.17020/) (2025)
- [ToSA: Token Merging with Spatial Awareness](https://mlsanity.com/paper/2506.20066/) (2025)
- [Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO](https://mlsanity.com/paper/2511.16669/) (2025)
- [Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models](https://mlsanity.com/paper/2510.05034/) (2025)
- [GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks](https://mlsanity.com/paper/2603.25864/) (2026)
- [What Happens When: Learning Temporal Orders of Events in Videos](https://mlsanity.com/paper/2512.08979/) (2025)
- [Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction](https://mlsanity.com/paper/2606.05769/) (2026)
- [BleedOrigin: Dynamic Bleeding Source Localization in Endoscopic Submucosal Dissection via Dual-Stage Detection and Tracking](https://mlsanity.com/paper/2507.15094/) (2025)
- [EventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction](https://mlsanity.com/paper/2510.21786/) (2025)
- [MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues](https://mlsanity.com/paper/2605.21954/) (2026)
- [EventLens: Event-Structure Reinforcement Learning for Video Understanding](https://mlsanity.com/paper/2610.16172/) (2026)

## Abstract (arXiv)

Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLMs). We propose TEMPURA (Temporal Event Masked Prediction and Understanding for Reasoning in Action), a two-stage training framework that enhances the video temporal understanding of VLMs. Inspired by infilling techniques in language modeling, TEMPURA first performs masked event prediction, learning to reconstruct missing events and generate step-by-step causal explanations from dense event annotations. It then learns video segmentation and dense captioning, decomposing videos into non-overlapping events with detailed, timestamp-aligned descriptions. We train TEMPURA on VER, our large-scale dataset of 500K videos annotated with temporally aligned event descriptions and structured reasoning steps. Experiments on video temporal grounding and highlight detection benchmarks show that TEMPURA substantially improves strong base VLMs across model families and scales, confirming that combining event-level reasoning with fine-grained temporal segmentation is an effective recipe for video temporal understanding.