Publications (88)
Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning
Zhe Yang, Damai Dai, Peiyi Wang +1
Large Language Models (LLMs) have recently gained the In-Context Learning (ICL) ability with the models scaling up, allowing them to quickly adapt to downstream tasks with only a f…
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
Bofei Gao, Feifan Song, Zhe Yang +17
Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks like GSM8K or MATH ar…
On Anticipated backward stochastic differential equations with Markov chain noise
Zhe Yang, Robert J. Elliott
In 2013, Lu and Ren \cite {luren} considered anticipated backward stochastic differential equations driven by finite state, continuous time Markov chain noise and established the e…
UMRE: A Unified Monotonic Transformation for Ranking Ensemble in Recommender Systems
Zhengrui Xu, Zhe Yang, Zhengxiao Guo +5
Industrial recommender systems commonly rely on ensemble sorting (ES) to combine predictions from multiple behavioral objectives. Traditionally, this process depends on manually de…
SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering
Zhe Yang, Wenrui Li, Guanghui Cheng
The Audio-Visual Question Answering (AVQA) task holds significant potential for applications. Compared to traditional unimodal approaches, the multi-modal input of AVQA makes featu…
CrossRoI: Cross-camera Region of Interest Optimization for Efficient Real Time Video Analytics at Scale
Hongpeng Guo, Shuochao Yao, Zhe Yang +2
Video cameras are pervasively deployed in city scale for public good or community safety (i.e. traffic monitoring or suspected person tracking). However, analyzing large scale vide…