Picture for Jason Li

Jason Li

Sandy

Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference

Add code
Sep 18, 2024
Viaarxiv icon

Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment

Add code
Jun 25, 2024
Viaarxiv icon

Mechanistic Interpretability of Binary and Ternary Transformers

Add code
May 27, 2024
Viaarxiv icon

zkLLM: Zero Knowledge Proofs for Large Language Models

Add code
Apr 24, 2024
Viaarxiv icon

SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation

Add code
Oct 13, 2023
Viaarxiv icon

AstroLLaMA: Towards Specialized Foundation Models in Astronomy

Add code
Sep 12, 2023
Figure 1 for AstroLLaMA: Towards Specialized Foundation Models in Astronomy
Figure 2 for AstroLLaMA: Towards Specialized Foundation Models in Astronomy
Figure 3 for AstroLLaMA: Towards Specialized Foundation Models in Astronomy
Viaarxiv icon

NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models

Add code
Apr 12, 2023
Viaarxiv icon

ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations

Add code
Feb 16, 2023
Viaarxiv icon

Modeling Human Eye Movements with Neural Networks in a Maze-Solving Task

Add code
Dec 20, 2022
Viaarxiv icon

Adapting TTS models For New Speakers using Transfer Learning

Add code
Oct 12, 2021
Figure 1 for Adapting TTS models For New Speakers using Transfer Learning
Figure 2 for Adapting TTS models For New Speakers using Transfer Learning
Viaarxiv icon