J. B. Jiao
YOU?
Author Swipe
View article: MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models
MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models Open
As a prominent data modality task, time series forecasting plays a pivotal role in diverse applications. With the remarkable advancements in Large Language Models (LLMs), the adoption of LLMs as the foundational architecture for time serie…
View article: Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning
Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning Open
Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of i…
View article: An Exploratory Study on a Potential Biomarker for Seizures in Autoimmune Encephalitis
An Exploratory Study on a Potential Biomarker for Seizures in Autoimmune Encephalitis Open
Specific clinical and laboratory features are closely associated with seizures in AE. Increased PB eosinophil counts may serve as a novel biomarker for seizure risk in AE patients.
View article: Search for $η_{1}(1855)$ in $χ_{cJ}\toηηη^{\prime}$ decays
Search for $η_{1}(1855)$ in $χ_{cJ}\toηηη^{\prime}$ decays Open
Based on a sample of $2.7\times10^{9}$ $ψ(3686)$ events collected by the BESIII detector operating at the BEPCII collider, an analysis of the decay $ψ(3686)\toγχ_{cJ}, χ_{cJ}\toηηη^{\prime}$ is performed. The decay modes $χ_{c1}$ and $χ_{c…
View article: MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding
MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding Open
Even in the era of rapid advances in large models, video understanding remains a highly challenging task. Compared to texts or images, videos commonly contain more information with redundancy, requiring large models to properly allocate at…