# BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning

arXiv: https://arxiv.org/abs/2309.15785 · HTML: https://mlsanity.com/paper/2309.15785/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 51 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 30 of 42)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Expanding Language-Image Pretrained Models for General Video Recognition](https://mlsanity.com/paper/2208.02816/) (2022)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)

## Built on by (most cited first, 30 of 41)

- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [LongVLM: Efficient Long Video Understanding via Large Language Models](https://mlsanity.com/paper/2404.03384/) (2024)
- [The Revolution of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2402.12451/) (2024)
- [ST-LLM: Large Language Models Are Effective Temporal Learners](https://mlsanity.com/paper/2404.00308/) (2024)
- [MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens](https://mlsanity.com/paper/2404.03413/) (2024)
- [VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding](https://mlsanity.com/paper/2406.09418/) (2024)
- [VoCo-LLaMA: Towards Vision Compression with Large Language Models](https://mlsanity.com/paper/2406.12275/) (2024)
- [SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation](https://mlsanity.com/paper/2411.17646/) (2024)
- [A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming](https://mlsanity.com/paper/2404.16038/) (2024)
- [Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback](https://mlsanity.com/paper/2402.03746/) (2024)
- [Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM](https://mlsanity.com/paper/2412.09530/) (2024)
- [FreeVA: Offline MLLM as Training-Free Video Assistant](https://mlsanity.com/paper/2405.07798/) (2024)
- [LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models](https://mlsanity.com/paper/2408.14008/) (2024)
- [MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations](https://mlsanity.com/paper/2503.15871/) (2025)
- [PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance](https://mlsanity.com/paper/2411.02327/) (2024)
- [Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models](https://mlsanity.com/paper/2503.16036/) (2025)
- [UniVid: The Open-Source Unified Video Model](https://mlsanity.com/paper/2509.24200/) (2025)
- [VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding](https://mlsanity.com/paper/2312.02310/) (2023)
- [Enhancing Temporal Modeling of Video LLMs via Time Gating](https://mlsanity.com/paper/2410.05714/) (2024)
- [LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding](https://mlsanity.com/paper/2501.05067/) (2025)
- [Aligned Better, Listen Better for Audio-Visual Large Language Models](https://mlsanity.com/paper/2504.02061/) (2025)
- [Long Video Understanding with Learnable Retrieval in Video-Language Models](https://mlsanity.com/paper/2312.04931/) (2023)
- [VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding](https://mlsanity.com/paper/2504.07519/) (2025)
- [EgoM2P: Egocentric Multimodal Multitask Pretraining](https://mlsanity.com/paper/2506.07886/) (2025)
- [Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow](https://mlsanity.com/paper/2510.05836/) (2025)
- [Slot-VLM: SlowFast Slots for Video-Language Modeling](https://mlsanity.com/paper/2402.13088/) (2024)
- [ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding](https://mlsanity.com/paper/2602.16412/) (2026)
- [MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval](https://mlsanity.com/paper/2408.10575/) (2024)

## Abstract (arXiv)

The recent progress in Large Language Models (LLM) has spurred various advancements in image-language conversation agents, while how to build a proficient video-based dialogue system is still under exploration. Considering the extensive scale of LLM and visual backbone, minimal GPU memory is left for facilitating effective temporal modeling, which is crucial for comprehending and providing feedback on videos. To this end, we propose Branching Temporal Adapter (BT-Adapter), a novel method for extending image-language pretrained models into the video domain. Specifically, BT-Adapter serves as a plug-and-use temporal modeling branch alongside the pretrained visual encoder, which is tuned while keeping the backbone frozen. Just pretrained once, BT-Adapter can be seamlessly integrated into all image conversation models using this version of CLIP, enabling video conversations without the need for video instructions. Besides, we develop a unique asymmetric token masking strategy inside the branch with tailor-made training tasks for BT-Adapter, facilitating faster convergence and better results. Thanks to BT-Adapter, we are able to empower existing multimodal dialogue models with strong video understanding capabilities without incurring excessive GPU costs. Without bells and whistles, BT-Adapter achieves (1) state-of-the-art zero-shot results on various video tasks using thousands of fewer GPU hours. (2) better performance than current video chatbots without any video instruction tuning. (3) state-of-the-art results of video chatting using video instruction tuning, outperforming previous SOTAs by a large margin.