# Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding

arXiv: https://arxiv.org/abs/2403.16276 · HTML: https://mlsanity.com/paper/2403.16276/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 36 of its 60 references that are in the map.
- First posted on arXiv 24 Mar 2024.

## Placed in

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

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)
- [Learning to Answer Questions in Dynamic Audio-Visual Scenarios](https://mlsanity.com/paper/2203.14072/) (2022)
- [Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration](https://mlsanity.com/paper/2306.09093/) (2023)
- [End-to-end Temporal Action Detection with Transformer](https://mlsanity.com/paper/2106.10271/) (2021)
- [Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2007.10558/) (2020)
- [VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset](https://mlsanity.com/paper/2304.08345/) (2023)
- [End-to-End Dense Video Captioning with Parallel Decoding](https://mlsanity.com/paper/2108.07781/) (2021)
- [Caption Anything: Interactive Image Description with Diverse Multimodal Controls](https://mlsanity.com/paper/2305.02677/) (2023)
- [Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding](https://mlsanity.com/paper/2109.04872/) (2021)
- [Audio-Visual LLM for Video Understanding](https://mlsanity.com/paper/2312.06720/) (2023)
- [Generic Event Boundary Detection: A Benchmark for Event Segmentation](https://mlsanity.com/paper/2101.10511/) (2021)
- [ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System](https://mlsanity.com/paper/2304.14407/) (2023)
- [CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs](https://mlsanity.com/paper/2401.02582/) (2024)
- [Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs](https://mlsanity.com/paper/2310.00582/) (2023)
- [Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline](https://mlsanity.com/paper/2303.12930/) (2023)
- [Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training](https://mlsanity.com/paper/2303.00040/) (2023)

## Built on by (most cited first, 18 of 18)

- [VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction](https://mlsanity.com/paper/2501.01957/) (2025)
- [V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning](https://mlsanity.com/paper/2404.12353/) (2024)
- [VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity](https://mlsanity.com/paper/2503.11557/) (2025)
- [KinMo: Kinematic-aware Human Motion Understanding and Generation](https://mlsanity.com/paper/2411.15472/) (2024)
- [FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction](https://mlsanity.com/paper/2404.14715/) (2024)
- [AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video](https://mlsanity.com/paper/2508.03100/) (2025)
- [Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting](https://mlsanity.com/paper/2504.05541/) (2025)
- [FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs](https://mlsanity.com/paper/2601.13836/) (2026)
- [ChronusOmni: Improving Time Awareness of Omni Large Language Models](https://mlsanity.com/paper/2512.09841/) (2025)
- [Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment](https://mlsanity.com/paper/2412.00306/) (2024)
- [FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment](https://mlsanity.com/paper/2412.15023/) (2024)
- [RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language](https://mlsanity.com/paper/2505.17114/) (2025)
- [PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling](https://mlsanity.com/paper/2505.23155/) (2025)
- [What do MLLMs hear? Examining reasoning with text and sound components in Multimodal Large Language Models](https://mlsanity.com/paper/2406.04615/) (2024)
- [Exploring the Potential of Multimodal LLM with Knowledge-Intensive Multimodal ASR](https://mlsanity.com/paper/2406.10880/) (2024)
- [AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs](https://mlsanity.com/paper/2511.21251/) (2025)
- [Crab+: A Scalable and Unified Audio-Visual Scene Understanding Model with Explicit Cooperation](https://mlsanity.com/paper/2603.04128/) (2026)
- [Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning](https://mlsanity.com/paper/2607.02963/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable capabilities in natural language and multimodal domains. By fine-tuning multimodal LLMs with temporal annotations from well-annotated datasets, e.g., dense video captioning datasets, their temporal understanding capacity in video-language tasks can be obtained. However, there is a notable lack of untrimmed audio-visual video datasets with precise temporal annotations for events. This deficiency hinders LLMs from learning the alignment between time, audio-visual events, and text tokens, thus impairing their ability to temporally localize audio-visual events in videos. To address this gap, we introduce PU-VALOR, a comprehensive audio-visual dataset comprising over 114,000 pseudo-untrimmed videos with detailed temporal annotations. PU-VALOR is derived from the large-scale but coarse-annotated audio-visual dataset VALOR, through a subtle method involving event-based video clustering, random temporal scaling, and permutation. By fine-tuning a multimodal LLM on PU-VALOR, we developed AVicuna, a model capable of aligning audio-visual events with temporal intervals and corresponding text tokens. AVicuna excels in temporal localization and time-aware dialogue capabilities. Our experiments demonstrate that AVicuna effectively handles temporal understanding in audio-visual videos and achieves state-of-the-art performance on open-ended video QA, audio-visual QA, and audio-visual event dense localization tasks.