Picture for Xinyu Yang

Xinyu Yang

Exploring Classical Piano Performance Generation with Expressive Music Variational AutoEncoder

Add code
Jul 02, 2025
Viaarxiv icon

Temporal-IRL: Modeling Port Congestion and Berth Scheduling with Inverse Reinforcement Learning

Add code
Jun 24, 2025
Viaarxiv icon

Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation

Add code
Jun 11, 2025
Viaarxiv icon

Flexible Operator Fusion for Fast Sparse Transformer with Diverse Masking on GPU

Add code
Jun 06, 2025
Viaarxiv icon

Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates

Add code
May 15, 2025
Viaarxiv icon

Seed1.5-VL Technical Report

Add code
May 11, 2025
Viaarxiv icon

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation

Add code
May 06, 2025
Viaarxiv icon

APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding

Add code
Feb 08, 2025
Viaarxiv icon

DeepSeek-V3 Technical Report

Add code
Dec 27, 2024
Figure 1 for DeepSeek-V3 Technical Report
Figure 2 for DeepSeek-V3 Technical Report
Figure 3 for DeepSeek-V3 Technical Report
Figure 4 for DeepSeek-V3 Technical Report
Viaarxiv icon

Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales

Add code
Dec 24, 2024
Viaarxiv icon