# CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion

arXiv: https://arxiv.org/abs/2402.05889 · HTML: https://mlsanity.com/paper/2402.05889/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 70 of its 82 references that are in the map.
- First posted on arXiv 8 Feb 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 70)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (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)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)

## Built on by (most cited first, 17 of 17)

- [From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities](https://mlsanity.com/paper/2412.11694/) (2024)
- [Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level](https://mlsanity.com/paper/2411.09921/) (2024)
- [When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning](https://mlsanity.com/paper/2602.08236/) (2026)
- [MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks](https://mlsanity.com/paper/2506.07016/) (2025)
- [Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs](https://mlsanity.com/paper/2503.23219/) (2025)
- [AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning](https://mlsanity.com/paper/2508.07470/) (2025)
- [Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators](https://mlsanity.com/paper/2505.18601/) (2025)
- [MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation](https://mlsanity.com/paper/2506.17113/) (2025)
- [Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering](https://mlsanity.com/paper/2410.09380/) (2024)
- [Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos](https://mlsanity.com/paper/2603.22529/) (2026)
- [AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding](https://mlsanity.com/paper/2512.16250/) (2025)
- [Vision-and-Language Navigation with Analogical Textual Descriptions in LLMs](https://mlsanity.com/paper/2509.25139/) (2025)
- [Towards Sparse Video Understanding and Reasoning](https://mlsanity.com/paper/2602.13602/) (2026)
- [Are Video Reasoning Models Ready to Go Outside?](https://mlsanity.com/paper/2603.10652/) (2026)
- [Continually Evolved Multimodal Foundation Models for Cancer Prognosis](https://mlsanity.com/paper/2501.18170/) (2025)
- [CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding](https://mlsanity.com/paper/2507.21888/) (2025)
- [Vulnerability-Aware Robust Multimodal Adversarial Training](https://mlsanity.com/paper/2511.18138/) (2025)

## Abstract (arXiv)

Despite impressive advancements in recent multimodal reasoning approaches, they are still limited in flexibility and efficiency, as these models typically process only a few fixed modality inputs and require updates to numerous parameters. This paper tackles these critical challenges and proposes CREMA, a generalizable, highly efficient, and modular modality-fusion framework that can incorporate any new modality to enhance video reasoning. We first augment multiple informative modalities (such as optical flow, 3D point cloud, audio, thermal heatmap, and touch map) from given videos without extra human annotation by leveraging sensors or existing pre-trained models. Next, we introduce a query transformer with multiple parameter-efficient modules associated with each accessible modality. It projects diverse modality features to the LLM token embedding space, allowing the model to integrate different data types for response generation. Furthermore, we propose a novel progressive multimodal fusion design supported by a lightweight fusion module and modality-sequential training strategy. It helps compress information across various assisting modalities, maintaining computational efficiency in the LLM while improving performance. We validate our method on 7 video-language reasoning tasks assisted by diverse modalities, including conventional VideoQA and Video-Audio/3D/Touch/Thermal QA, and achieve better/equivalent performance against strong multimodal LLMs, including OneLLM, BLIP-2, and SeViLA while reducing over 90% trainable parameters. We provide extensive analyses of CREMA, including the impact of each modality on reasoning domains, the design of the fusion module, and example visualizations.