10 papers
Cross-Embodiment Causal Transfer from Human Videos to Robot Manipulation
Xingyu Zhang, Yingchao Li, Peizheng Guo +3
Scaling robot manipulation models requires large amounts of interaction data, yet collecting diverse real-robot experience remains costly. Human manipulation videos, in contrast, p…
CAG-WAM: Causal Action-Gain World Action Models for Robot Manipulation
Peizheng Guo, Cheng Zhang, Xingyu Zhang +2
World Action Models (WAMs) combine action generation with future prediction, allowing predicted futures to support action evaluation and robot decision making. However, the future…
GUPO: Gradient Uncertainty-aware Policy Optimization for Post-Training Large Language Models
Peizheng Guo, Jianqi Zhang, Xingyu Zhang +4
Group Relative Policy Optimization (GRPO) has become a widely used approach for post-training Large Language Models (LLMs) for reasoning. In GRPO, the group gradients induced by di…
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…
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…
Hypergraph and Latent ODE Learning for Multimodal Root Cause Localization in Microservices
Xin Liu, Yuhang He, Sichen Zhao +2
Root cause localization in cloud native microservice systems requires modeling complex service dependencies, irregular temporal dynamics, and heterogeneous observability data. We p…
LAtent Phase Inference from Short time sequences using SHallow REcurrent Decoders (LAPIS-SHRED)
Yuxuan Bao, Xingyue Zhang, J. Nathan Kutz
Reconstructing full spatio-temporal dynamics from sparse observations in both space and time remains a central challenge in complex systems, as measurements can be spatially incomp…
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…
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-…
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…