collaborators

18 papers

astro-ph.SR2026

The Production of Electron-Capture Elements in Thermonuclear Supernovae: Theory vs. Observations

S. Shiber, P. Hoeflich, T. Mera +9

Type Ia supernovae (SNe Ia) explosively destroy carbon-oxygen white dwarfs (WDs) in multiple stellar systems. They produce approximately 50% of the iron-group elements in the Unive…

cs.CV2026

Contrastive On-Policy Distillation

Jiacheng Ruan, Jun Tang, Wenzhen Yuan +5

On-policy Distillation (OPD) supervises a student model on trajectories sampled from its own policy by minimizing the divergence between the output distributions of the teacher and…

cs.CV2026

ExFusion: Efficient Transformer Training via Multi-Experts Fusion

Jiacheng Ruan, Daize Dong, Xiaoye Qu +5

Mixture-of-Experts (MoE) models substantially improve performance by increasing the capacity of dense architectures. However, directly training MoE models requires considerable com…

cs.CV2026

MMGist: A Comprehensive Multimodal Benchmark for 2027

Wenzhen Yuan, Jiacheng Ruan, Wutao Xiong +3

We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effective…

cs.CY2026

From Motion Signals to Insights: A Unified Framework for Student Behavior Analysis and Feedback in Physical Education Classes

Xian Gao, Jiacheng Ruan, Jingsheng Gao +4

Analyzing student behavior in educational scenarios is crucial for enhancing teaching quality and student engagement. Existing AI-based models often rely on classroom video footage…

cs.CV2026

BasketHAR: A Multimodal Dataset for Human Activity Recognition and Sport Analysis in Basketball Training Scenarios

Xian Gao, Haoyue Zhang, Zongyun Zhang +3

Human Activity Recognition (HAR) involves the automatic identification of user activities and has gained significant research interest due to its broad applicability. Most HAR syst…