Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?
Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enabled interpretable description generation by jointly modeling video, audio, and language, etc. However, these performance improvements are often accompanied by an increase in model parameter size (e.g, at least 7B), which simultaneously incurs high computational costs and reduces inference efficiency, thereby hindering real-time deployment on resource-constrained platforms such as robots and mobile devices. This raises a fundamental question: do
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 58%Atomic-man007/Awesome_Multimodel_LLM →
- PossiblePossibly related (embedding) · 52%huggingface/transformers →
- PossiblePossibly related (embedding) · 50%sgl-project/sglang →
- PossiblePossibly related (embedding) · 49%modelscope/mcore-bridge →
- PossiblePossibly related (embedding) · 49%Large Tabular Models Excel Where LLMs Fail →
- LinkedLinked via arxiv author · 85%Kaiwen Zheng →
“Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?”
- LinkedLinked via arxiv author · 85%Junchen Fu →
“Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?”
- LinkedLinked via arxiv author · 85%Wenhao Deng →
“Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?”