AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Prototype-as-Prompt: Multimodal Sentiment Prototypes Endowing Large Language Models the Capability to Perform Multimodal Sentiment Analysis

Xianbing Zhao, Lan Luo, Hengyang Lu, Buzhou Tang

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace MSE with Prototype-as-Prompt soft promptsLlama-2-7B frozen LLM · CMU-MOSEIAcc-2: 86.74 -> 87.17Improved
replace MSE with Prototype-as-Prompt soft promptsChatGLM-6B frozen LLM · SIMS-V2Acc-2: 83.77 -> 84.75Improved
replace MSE with Prototype-as-Prompt soft promptsLlama-2-7B frozen LLM · SIMS-V2Acc-2: 75.53 -> 76.23Improved
replace MSE with Prototype-as-Prompt soft promptsChatGLM-6B frozen LLM · CHERMAAcc: 72.90 -> 75.33Improved
replace MSE with PaPQwen-1.5B frozen LLM · CMU-MOSEIAcc-2: 84.12 -> 86.00Improved
add cross-modal prototype alignment (CMD loss) (ablation)PaP (ChatGLM-6B) · CHERMAAcc-2: 74.01 -> 75.33Improved
add sentiment-aware prototype learning loss (ablation)PaP (ChatGLM-6B) · CHERMAAcc-2: 73.83 -> 75.33Improved
add distance-weighted prototype diversity regularization (ablation)PaP (ChatGLM-6B) · CHERMAAcc-2: 74.67 -> 75.33Improved
add sentiment-aware prototype learning loss (ablation)PaP (Llama-2-7B) · CHERMAAcc-2: 71.69 -> 72.70Improved
add cross-modal prototype alignment (ablation)PaP (Qwen-1.5B) · CHERMAAcc-2: 73.00 -> 73.93Improved
add diversity regularization (ablation)PaP (Qwen-1.5B) · CHERMAAcc-2: 73.47 -> 73.93Improved
choose LLM backbone Llama-2-7B instead of ChatGLM-6BPaP · SIMS-V2Acc-2: 84.75 -> 76.23Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy