collaborators

14 papers

cs.LG2026

Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models

Jianqi Zhang, Xingyu Zhang, Zeen Song +3

Time series forecasting (TSF) plays an important role in a wide range of real-world applications. Recently, time series foundation models (TSFMs), pretrained on large-scale dataset…

cs.LG2026

Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting

Xingyu Zhang, Jingyao Wang, Xin Yu +4

Time series forecasting often suffers from over-smoothing, especially when future dynamics are multi-modal. Forecasts may follow the coarse trend of the observed future, but fail t…

cs.LG2026

From Shallow to Deep: Pinning Semantic Intent via Causal GRPO

Shuyi Zhou, Zeen Song, Wenwen Qiang +4

Large Language Models remain vulnerable to adversarial prefix attacks (e.g., ``Sure, here is'') despite robust standard safety. We diagnose this vulnerability as Shallow Safety Ali…

cs.LG2026

Adaptive Uncertainty-Aware Tree Search for Robust Reasoning

Zeen Song, Zihao Ma, Wenwen Qiang +2

Inference-time reasoning scaling has significantly advanced the capabilities of Large Language Models (LLMs) in complex problem-solving. A prevalent approach involves external sear…

cs.CL2026

Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs

Yao Zhou, Zeen Song, Wenwen Qiang +4

Safety alignment mechanisms in Large Language Models (LLMs) often operate as latent internal states, obscuring the model's inherent capabilities. Building on this observation, we m…

cs.CV2026

Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective

Zeen Song, Wenwen Qiang, Changwen Zheng +2

Video contrastive learning (V-CL) has emerged as a popular framework for unsupervised video representation learning, demonstrating strong results in tasks such as action classifica…