5 papers
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment
Yang Tian, Rui Wang, Xumeng Wen +5
Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide lim…
Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains
Jiawen Zhang, Zhenwei Zhang, Shun Zheng +3
Time-Series Foundation Models (TSFMs) are rapidly transitioning from research prototypes to core components of critical decision-making systems, driven by their impressive zero-sho…
Deep Self-Evolving Reasoning
Zihan Liu, Shun Zheng, Xumeng Wen +3
Long-form chain-of-thought reasoning has become a cornerstone of advanced reasoning in large language models. While recent verification-refinement frameworks have enabled proprieta…
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Xumeng Wen, Zihan Liu, Shun Zheng +9
Recent advancements in long chain-of-thought (CoT) reasoning, particularly through the Group Relative Policy Optimization algorithm used by DeepSeek-R1, have led to significant int…
Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models
Xumeng Wen, Shun Zheng, Zhen Xu +2
Recent studies have shown that large language models (LLMs), when customized with post-training on tabular data, can acquire general tabular in-context learning (TabICL) capabiliti…