Anderson Schneider

Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization

Speculative Sampling for Parametric Temporal Point Processes

Learning To Acquire Resources in Competition

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design

Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel

Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting

TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster

SAS: Simulated Attention Score

TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster

Structural Knowledge Informed Continual Learning for Multivariate Time Series Forecasting