Chao Li

VELR: Efficient Video Reward Feedback via Ensemble Latent Reward Models

A Dynamic Multiscale Anti-Aliasing Network for Time Series Forecasting

Joint Multi-Scale Forecasting with FFT and Gumbel Sampling

SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance

TCAN: An Asymmetry Modeling Network for Time Series Forecasting

Bit-by-Bit: Progressive QAT with Outlier Channel Splitting for Stable Low-Bit LLMs

Multivariate Time Series Anomaly Detection with Idempotent Reconstruction