5 papers
Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting
Wan Zhang, Qinjie Lin, Chan Lee +3
Forecasting multiple time-series with high-dimensional covariates presents a core challenge: unifying common temporal patterns while retaining meaningful series-specific informatio…
Towards Sparse Video Understanding and Reasoning
Chenwei Xu, Zhen Ye, Shang Wu +8
We present \revise (\underline{Re}asoning with \underline{Vi}deo \underline{S}parsity), a multi-round agent for video question answering (VQA). Instead of uniformly sampling frames…
PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation
Shang Wu, Chenwei Xu, Zhuofan Xia +6
State-of-the-art text-to-video (T2V) generators frequently violate physical laws despite high visual quality. We show this stems from insufficient physical constraints in prompts r…
StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
Weijian Li, Hong-Yu Chen, Nabeel Rehemtulla +6
Current time series foundation model (TSFM) training corpora largely omit data with certain complexities like irregular temporal sampling. Astronomical time series of stellar fluxe…
Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism
Tim Tsz-Kit Lau, Weijian Li, Chenwei Xu +2
An appropriate choice of batch sizes in large-scale model training is crucial, yet it involves an intrinsic yet inevitable dilemma: large-batch training improves training efficienc…