Skip to content

Research

Page 64 of 166

An Enhanced Source-Free Unsupervised Domain Adaptation Framework for Cross-Dataset EEG Emotion Recognition via Predictive Coding and Test-Time Training

research note

An Enhanced Source-Free Unsupervised Domain Adaptation Framework for Cross-Dataset EEG Emotion Recognition via Predictive Coding and Test-Time Training

·8 min read·Md Niaz Imtiaz, Naimul Khan

This paper addresses the challenge of cross-dataset EEG-based emotion recognition under domain shifts caused by inter-subject variability and dataset differences

researchsource-free-domain-adaptationself-supervised-learningpredictive-codingeeg-emotion-recognition

Read note → Source paper ↗

HPRO — Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech

research note

HPRO — Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech

·9 min read·Sihang Nie, Xiaofen Xing, Rui Xing et al.

This paper addresses key limitations in emotional text-to-speech (TTS) models based on large language models (LLMs), particularly the common issue of flattened, averaged prosody caused by supervise…

researchemotional-text-to-speechhierarchical-reward-optimizationdifferentiable-reward-modellarge-language-models

Read note → Source paper ↗

Hybrid Quantum-Classical Neural Networks for Recognizing Quantum Phases

research note

Hybrid Quantum-Classical Neural Networks for Recognizing Quantum Phases

·8 min read·Colin Scarato, Johannes Knörzer, Markus K. Hoffmann et al.

This paper addresses the challenging problem of identifying quantum phases of matter, particularly topologically ordered phases such as those realized by the surface code, using quantum machine lea…

researchquantum-machine-learninghybrid-quantum-classicalquantum-phase-recognitionsuperconducting-qubits

Read note → Source paper ↗

Parameter Efficient Hybrid Transformer (PEHT) for Network Traffic Prediction via Dynamic Urban Congestion Integration

research note

Parameter Efficient Hybrid Transformer (PEHT) for Network Traffic Prediction via Dynamic Urban Congestion Integration

·7 min read·Abdolazim Rezaei, Mehdi Sookhak, Mahboobeh Haghparast

This paper addresses the challenging problem of accurate network traffic prediction in dynamic urban cellular networks by proposing the Parameter-Efficient Hybrid Transformer (PEHT)

researchnetwork-traffic-predictiontransformer-modelsparameter-efficient-learningmultimodal-fusion

Read note → Source paper ↗

Articles are CC BY 4.0 — feel free to quote with attribution