Skip to content

Author

Junyi Peng

We have 2 of 17 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#human-computer interacti... Preprint Aug 2026

Learning to Prefer Reliably: Error-Augmented Emotion Preference Optimization with Calibrated Fusion

Experiments on the MER2026-EmoPrefer Challenge dataset and the error-augmented dataset demonstrate that EAPO improves emotion preference prediction and enhances the robustness of MLLM judges when evaluating fluent descriptions that conflict with the video's multimodal emotional evidence.

Zilong Huang, Junyi Peng, Junjie Li et al. · 0 citations
2026

HPQ: A Hybrid Framework for Joint Pruning and Quantization of Self-Supervised Speech Models

Despite achieving state-of-the-art accuracy in speaker verification (SV), large-scale self-supervised learning (SSL) speech models remain difficult to deploy on edge devices because of their computational and memory demands. Existing compression approaches improve efficiency through pruning and quantization, but usuall...

Junyi Peng, Lin Zhang, Jiangyu Han et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.