SpeakStream: Streaming Text-to-Speech with Interleaved Data.
CoRR, May, 2025
Reversal Blessing: Thinking Backward May Outpace Thinking Forward in Multi-choice Questions.
CoRR, February, 2025
Theory, Analysis, and Best Practices for Sigmoid Self-Attention.
,
,
,
,
,
,
,
,
,
,
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
dMel: Speech Tokenization made Simple.
CoRR, 2024
Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition.
CoRR, 2024
Decoding natural image stimuli from fMRI data with a surface-based convolutional network.
Proceedings of the Medical Imaging with Deep Learning, 2023
NeuroGen: Activation optimized image synthesis for discovery neuroscience.
NeuroImage, 2022
Personalized visual encoding model construction with small data.
CoRR, 2022
NeuroGen: activation optimized image synthesis for discovery neuroscience.
CoRR, 2021
3D No-Reference Image Quality Assessment via Transfer Learning and Saliency-Guided Feature Consolidation.
IEEE Access, 2019