6 citations · 10 across the 22 of their papers we have counts for
27 papers
RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning
Seungjun Moon, Subin Jeon, Sangwoo Kim +2
Recently, approaches that leverage human video datasets for robot policy training have become increasingly prevalent. However, most existing hand trackers regress pose from cropped…
Towards Robust Time Series Learning via Capacity-Centric Modulation
Siru Zhong, Senzhang Wang, James T. Kwok +1
Sample-level reliability heterogeneity is common in deep time series learning. Standard training pipelines apply a uniform regularization setting to all samples, which can under-re…
DrafTS: Time-Aware Decomposition with Residual Correction for Time Series Modeling
Yiqiu Liu, Siru Zhong, Zhiguang Wang +2
Real-world time series contain evolving underlying dynamics with irregular variations that lack stable temporal patterns and are often referred to as noise. Existing methods addres…
STORM-Bench: Evaluating Online Video QA under Evolving and Incomplete Evidence
Siru Zhong, Shenghan Tan, Rihong Yan +6
Reliable online video question answering requires tracking state transitions while selectively abstaining when visual evidence is insufficient. Existing benchmarks focus on static…
CompKV: Compensation-Aware KV Selection for Long-Context LLM Inference
Zhen Huang, Ruizhe Yao, Danyi Liu +8
Despite their strong performance, large language models (LLMs) are bottlenecked by KV cache memory traffic during long-context inference. Sparse attention is widely used to acceler…
PREM: Prefix-Steered Recurrent Memory for Long-Video Understanding
Siru Zhong, Qiongyan Wang, Xiaohui Lv +5
Long-video understanding must capture transient visual evidence under strict token budgets, yet existing methods compress frames, append memory tokens, or alter internal key-value…
EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards
Zhiqing Cui, Xinxiang Yin, Yihong Tang +11
Earth-system analysis reconstructs changing physical processes from observations that differ in source, scale, timing, and modality. Natural hazards make this work consequential be…
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…
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…
STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting
Sicong Lai, Yuehong Hu, Siru Zhong +3
Real-world traffic data exhibit heterogeneous spatial correlations and nonlinear temporal dynamics, posing substantial challenges for accurate spatio-temporal forecasting. Existing…
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…
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
Zhiqing Cui, Haotong Xie, Jiahao Yuan +11
Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so decom…
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…
Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting
Zhiqing Cui, Siru Zhong, Ming Jin +3
Global air quality forecasting grapples with extreme spatial heterogeneity and the poor generalization of existing transductive models to unseen regions. To tackle this, we propose…
Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models
Siru Zhong, Junjie Qiu, Yangyu Wu +7
Spatio-Temporal (ST) Foundation Models (STFMs) promise cross-dataset generalization, yet joint ST pretraining is computationally expensive and grapples with the heterogeneity of do…
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,…
OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting
Sisuo Lyu, Siru Zhong, Weilin Ruan +4
Time series forecasting is fundamental to diverse applications, with recent approaches leverage large vision models (LVMs) to capture temporal patterns through visual representatio…
Vision-Enhanced Time Series Forecasting via Latent Diffusion Models
Weilin Ruan, Siru Zhong, Haomin Wen +1
Diffusion models have recently emerged as powerful frameworks for generating high-quality images. While recent studies have explored their application to time series forecasting, t…
Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting
Siru Zhong, Weilin Ruan, Ming Jin +3
Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy. While text provides contextual understanding, it…
AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networks
Qiongyan Wang, Yutong Xia, Siru ZHong +6
Monitoring real-time air quality is essential for safeguarding public health and fostering social progress. However, the widespread deployment of air quality monitoring stations is…
Cross Space and Time: A Spatio-Temporal Unitized Model for Traffic Flow Forecasting
Weilin Ruan, Wenzhuo Wang, Siru Zhong +3
Predicting spatio-temporal traffic flow presents significant challenges due to complex interactions between spatial and temporal factors. Existing approaches often address these di…
Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting
Jianxiang Zhou, Erdong Liu, Wei Chen +2
Traffic forecasting has emerged as a crucial research area in the development of smart cities. Although various neural networks with intricate architectures have been developed to…
Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach
Huaiwu Zhang, Yutong Xia, Siru Zhong +5
The increasing number of vehicles highlights the need for efficient parking space management. Predicting real-time Parking Availability (PA) can help mitigate traffic congestion an…
UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation
Siru Zhong, Xixuan Hao, Yibo Yan +3
Urbanization challenges underscore the necessity for effective satellite image-text retrieval methods to swiftly access specific information enriched with geographic semantics for…