Picture for Siyuan Feng

Siyuan Feng

Airport Delay Prediction with Temporal Fusion Transformers

May 14, 2024
Viaarxiv icon

Emerging Platforms Meet Emerging LLMs: A Year-Long Journey of Top-Down Development

Add code
Apr 14, 2024
Viaarxiv icon

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

Add code
Feb 19, 2024
Viaarxiv icon

Dynamic Adjustment of Matching Radii under the Broadcasting Mode: A Novel Multitask Learning Strategy and Temporal Modeling Approach

Dec 09, 2023
Viaarxiv icon

Relax: Composable Abstractions for End-to-End Dynamic Machine Learning

Nov 01, 2023
Viaarxiv icon

PolyVoice: Language Models for Speech to Speech Translation

Add code
Jun 13, 2023
Figure 1 for PolyVoice: Language Models for Speech to Speech Translation
Figure 2 for PolyVoice: Language Models for Speech to Speech Translation
Figure 3 for PolyVoice: Language Models for Speech to Speech Translation
Figure 4 for PolyVoice: Language Models for Speech to Speech Translation
Viaarxiv icon

Efficient Neural Music Generation

Add code
May 25, 2023
Figure 1 for Efficient Neural Music Generation
Figure 2 for Efficient Neural Music Generation
Figure 3 for Efficient Neural Music Generation
Figure 4 for Efficient Neural Music Generation
Viaarxiv icon

Language-universal phonetic encoder for low-resource speech recognition

Add code
May 19, 2023
Figure 1 for Language-universal phonetic encoder for low-resource speech recognition
Figure 2 for Language-universal phonetic encoder for low-resource speech recognition
Figure 3 for Language-universal phonetic encoder for low-resource speech recognition
Figure 4 for Language-universal phonetic encoder for low-resource speech recognition
Viaarxiv icon

Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition

May 19, 2023
Figure 1 for Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition
Figure 2 for Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition
Figure 3 for Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition
Figure 4 for Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition
Viaarxiv icon

A multi-functional simulation platform for on-demand ride service operations

Add code
Mar 22, 2023
Figure 1 for A multi-functional simulation platform for on-demand ride service operations
Figure 2 for A multi-functional simulation platform for on-demand ride service operations
Figure 3 for A multi-functional simulation platform for on-demand ride service operations
Figure 4 for A multi-functional simulation platform for on-demand ride service operations
Viaarxiv icon