Publications (9)
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Wei Huang, Yi Ge, Shuai Yang +11
We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs). While RL is essential for LLMs' reasoning capabilities, it is resource-i…
R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
Tianyu Fu, Yi Ge, Yichen You +6
Large Language Models (LLMs) achieve impressive reasoning capabilities at the cost of substantial inference overhead, posing substantial deployment challenges. Although distilled S…
A Linear LMP Model for Active and Reactive Power with Power Loss
Yanghao Yu, Qingchun Hou, Yi Ge +2
Pricing the reactive power is more necessary than ever before because of the increasing challenge of renewable energy integration on reactive power balance and voltage control. How…
Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following
Tianyi Xiong, Yi Ge, Ming Li +13
Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences.…
Weighted Bayesian Gaussian Mixture Model for Roadside LiDAR Object Detection
Tianya Zhang, Yi Ge, Peter J. Jin
Background modeling is widely used for intelligent surveillance systems to detect moving targets by subtracting the static background components. Most roadside LiDAR object detecti…
Optimal convergence rates in the averaging principle for slow-fast SPDEs driven by multiplicative noise
Yi Ge, Xiaobin Sun, Yingchao Xie
In this paper, we study a class of slow-fast stochastic partial differential equations with multiplicative Wiener noise. Under some appropriate conditions, we prove the slow compon…
Unimodal-uniform Constrained Wasserstein Training for Medical Diagnosis
Xiaofeng Liu, Xu Han, Yukai Qiao +2
The labels in medical diagnosis task are usually discrete and successively distributed. For example, the Diabetic Retinopathy Diagnosis (DR) involves five health risk levels: no DR…
Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training
Xiaofeng Liu, Yuzhuo Han, Song Bai +6
Semantic segmentation (SS) is an important perception manner for self-driving cars and robotics, which classifies each pixel into a pre-determined class. The widely-used cross entr…
Study on Dynamic Matching and Dynamic Characteristics of Hydrostatic Transmission System of Forklift Truck
An Ying, Yi Ge, Liu Guoliang +4
In the fields of agricultural machinery, construction equipment, and special-purpose vehicles, hydrostatic transmission (HST) drive systems have witnessed a significant increase in…