works on

From the 1 of 14 linked papers with an AI index.

collaborators

14 papers

cs.AI2026

LiveHouse-TS: An Open-world Living Benchmark for Time Series Foundation Models

Haomin Wen, Ziyu Zhou, Qingxiang Liu +2

Time Series Foundation Models (TSFMs) have recently emerged as a highly promising paradigm for cross-domain zero-shot forecasting. However, existing evaluation protocols predominan…

cs.CV2026

Ground, Cover, and Refine: Evidence-Centric Frame Selection for Long-Video Question Answering

Fan Wei, Siru Zhong, Runmin Dong +3

Long-video question answering requires identifying sparse yet critical evidence from videos containing thousands of frames under a constrained visual-token budget. Existing methods…

cs.LG2026

STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting

Sicong Lai, Yuehong Hu, Siru Zhong +3

The paper introduces STKAN, a spatio‑temporal forecasting model that uses Kolmogorov‑Arnold network modules with Taylor‑polynomial approximations for spatial and temporal token mix…

cs.LG2026

TS-Memory: Plug-and-Play Memory for Time Series Foundation Models

Sisuo Lyu, Siru Zhong, Tiegang Chen +6

Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remain…

cs.AI2026

DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting

Siru Zhong, Yiqiu Liu, Zhiqing Cui +4

Deep time series models are vulnerable to noisy data ubiquitous in real-world applications. Existing robustness strategies either prune data or rely on costly prior quantification,…

cs.LG2026

Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting

Siru Zhong, Zhao Meng, Haohuan Fu +3

Local temporal patterns in real-world time series continuously shift, rendering globally shared transformations suboptimal. Current deep forecasting models, despite their scale and…