Papers with multi-modal applications
Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large multi-modal models (LMMs) are revolutionizing the way machines interact with the world, unlocking new possibilities across multi-dimensional applications. |
| Approach: | They propose a parameter-efficient fine-tuning strategy that combines both . they find that parameter tuning methods distort the feature representation space . |
| Outcome: | The proposed strategy preserves representation space while limiting performance on downstream tasks. |
Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing self-supervised learning strategies focus on uni-modal applications . a recent study shows that multimodality is a major challenge for multi-modal systems . |
| Approach: | They propose two self-supervised pre-training methods that employ off-the-shelf multi-modal hate-speech data . they also incorporate multiple specialized pretext tasks to cater to complex multi-modity representation learning . |
| Outcome: | The proposed methods outperform the baseline self-supervised learning strategies on the Memotion challenge and the HarMeme task. |
OVEL: Online Video Entity Linking (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on Multi-modal Entity Linking focus on linking textual and visual mentions or offline videos’ mentions to entities in multi-modal knowledge bases. |
| Approach: | They propose a task called Online Video Entity Linking to establish connections between online videos and a knowledge base with high accuracy and timeliness. |
| Outcome: | The proposed method can establish connections between mentions in online videos and a knowledge base with high accuracy and timeliness. |
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture (2025.findings-emnlp)
Copied to clipboard
Xidong Wang, Dingjie Song, Shunian Chen, Junying Chen, Zhenyang Cai, Chen Zhang, Lichao Sun, Benyou Wang
| Challenge: | Long-context Large Language Models (MLLMs) are critical for video understanding and image analysis. |
| Approach: | They propose a hybrid architecture that integrates Mamba and Transformer blocks . they introduce data construction methods that capture both temporal and spatial dependencies . |
| Outcome: | The proposed model achieves competitive results across various benchmarks while maintaining high throughput and low memory consumption. |