# CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms

arXiv: https://arxiv.org/abs/2505.17020 · HTML: https://mlsanity.com/paper/2505.17020/

## Key facts

- Cited by 11 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 75 of its 82 references that are in the map.
- First posted on arXiv 22 May 2025.

## 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 75)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [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)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (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)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?](https://mlsanity.com/paper/2403.14624/) (2024)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)

## Built on by (most cited first, 11 of 11)

- [MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning](https://mlsanity.com/paper/2506.05331/) (2025)
- [VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning](https://mlsanity.com/paper/2512.22315/) (2025)
- [Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs](https://mlsanity.com/paper/2512.16584/) (2025)
- [Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking](https://mlsanity.com/paper/2505.20199/) (2025)
- [Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models](https://mlsanity.com/paper/2604.08545/) (2026)
- [LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning](https://mlsanity.com/paper/2605.22012/) (2026)
- [SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs](https://mlsanity.com/paper/2602.06040/) (2026)
- [TrajTok: Learning Trajectory Tokens enables better Video Understanding](https://mlsanity.com/paper/2602.22779/) (2026)
- [MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning](https://mlsanity.com/paper/2603.12266/) (2026)
- [Progressive Scaling Visual Object Tracking](https://mlsanity.com/paper/2505.19990/) (2025)
- [You Only Forward Once: An Efficient Compositional Judging Paradigm](https://mlsanity.com/paper/2511.16600/) (2025)

## Abstract (arXiv)

The advent of Large Multimodal Models (LMMs) has significantly enhanced Large Language Models (LLMs) to process and interpret diverse data modalities (e.g., image and video). However, as input complexity increases, particularly with long video sequences, the number of required tokens has grown significantly, leading to quadratically computational costs. This has made the efficient compression of video tokens in LMMs, while maintaining performance integrity, a pressing research challenge. In this paper, we introduce CrossLMM, decoupling long video sequences from LMMs via a dual cross-attention mechanism, which substantially reduces visual token quantity with minimal performance degradation. Specifically, we first implement a significant token reduction from pretrained visual encoders through a pooling methodology. Then, within LLM layers, we employ a visual-to-visual cross-attention mechanism, wherein the pooled visual tokens function as queries against the original visual token set. This module enables more efficient token utilization while retaining fine-grained informational fidelity. In addition, we introduce a text-to-visual cross-attention mechanism, for which the text tokens are enhanced through interaction with the original visual tokens, enriching the visual comprehension of the text tokens. Comprehensive empirical evaluation demonstrates that our approach achieves comparable or superior performance across diverse video-based LMM benchmarks, despite utilizing substantially fewer computational resources.