activity
20242026
collaborators

5 papers

cs.LG2026

Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecasting

Xingyu Zhang, Hanyun Du, Zeen Song +3

Most existing multivariate time series forecasting methods adopt an all-to-all paradigm that feeds all variable histories into a unified model to predict their future values withou…

cs.DC2026

HADIS: Hybrid Adaptive Diffusion Model Serving for Efficient Text-to-Image Generation

Qizheng Yang, Tung-I Chen, Siyu Zhao +2

Text-to-image diffusion models have achieved remarkable visual quality but incur high computational costs, making latency-aware, scalable deployment challenging. To address this, w…

cs.CV2025

Learning Invariant Causal Mechanism from Vision-Language Models

Zeen Song, Siyu Zhao, Xingyu Zhang +3

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, but its performance can degrade when fine-tuned in out-of-distribution (OOD) scenarios. We model the…

cs.LG2025

Reward Model Generalization for Compute-Aware Test-Time Reasoning

Zeen Song, Wenwen Qiang, Siyu Zhao +2

External test-time reasoning enhances large language models (LLMs) by decoupling generation and selection. At inference time, the model generates multiple reasoning paths, and an a…

cs.LG2024

Not All Frequencies Are Created Equal:Towards a Dynamic Fusion of Frequencies in Time-Series Forecasting

Xingyu Zhang, Siyu Zhao, Zeen Song +4

Long-term time series forecasting is a long-standing challenge in various applications. A central issue in time series forecasting is that methods should expressively capture long-…