A lightweight transformer predicts iconic gesture placement and intensity from text and emotion alone, outperforming GPT-4o on the BEAT2 dataset for real-time robot deployment.
Twifly: A data analysis framework for twitter
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
A lightweight one-block transformer architecture for EEG-based cognitive workload classification that uses under 0.5 million parameters and 0.02 GFLOPs.
Lightweight transformer fuses raw and spectral fNIRS representations via unified tokenization for competitive pain recognition on the AI4Pain dataset while remaining computationally compact.
citing papers explorer
-
Efficient Emotion-Aware Iconic Gesture Prediction for Robot Co-Speech
A lightweight transformer predicts iconic gesture placement and intensity from text and emotion alone, outperforming GPT-4o on the BEAT2 dataset for real-time robot deployment.
-
One-Block Transformer (1BT) for EEG-Based Cognitive Workload Assessment
A lightweight one-block transformer architecture for EEG-based cognitive workload classification that uses under 0.5 million parameters and 0.02 GFLOPs.
-
A Lightweight Transformer for Pain Recognition from Brain Activity
Lightweight transformer fuses raw and spectral fNIRS representations via unified tokenization for competitive pain recognition on the AI4Pain dataset while remaining computationally compact.