Author name cluster

Yushi Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Andrew M. Bean
Ryan Othniel Kearns
Angelika Romanou
Franziska Sofia Hafner
Harry Mayne
Jan Batzner
Negar Foroutan Eghlidi
Chris Schmitz

Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstract and complex phenomena such as safety' and robustness' requires strong construct validity, that is, having measures that represent what matters to the phenomenon. With a team of 29 expert reviewers, we conduct a systematic review of 445 LLM benchmarks from leading conferences in natural language processing and machine learning. Across the reviewed articles, we find patterns related to the measured phenomena, tasks, and scoring metrics which undermine the validity of the resulting claims. To address these shortcomings, we provide eight key recommendations and detailed actionable guidance to researchers and practitioners in developing LLM benchmarks.

PDF Details

IROS Conference 2025 Conference Paper

Unidirectional Point-Voxel Fusion for Enhanced 3D Single Object Tracking

Yuyu Jiang
Baojie Fan
Yushi Yang
Jinrong Du
Ying Yao

Sparse point-based trackers struggle with texture-less and incomplete point clouds. Conversely, dense voxel-based trackers have richer spatial and semantic information, but filtering out interference from complex backgrounds remains a challenge. Additionally, there is still a gap between point and voxel-based trackers in exploiting their complementary strengths. To address these issues, we propose UTracker, which uses unidirectional point-voxel fusion to construct a bridge between point and voxel tracking features, enabling them to complement and enhance each other. Specifically, we design template-enhanced unidirectional attention (TEUA) and historical template fusion (HTF), which enable unidirectional interaction from historical templates to the search area in the point branch, retaining the pure template features. Then, a point-guided adaptive feature transformer (PGAFT) is developed to unidirectionally enhance the interaction between point and voxel features. Extensive experiments demonstrate that UTracker achieves superior performance, reaching an average accuracy of 89. 5%, 72. 58%, and 63. 4% on the KITTI, NuScenes, and Waymo Open Dataset, respectively.

Details

IROS Conference 2024 Conference Paper

Enhancing 3D Single Object Tracking with Efficient Point Cloud Segmentation

Yushi Yang
Baojie Fan
Yuyu Jiang
Wuyang Zhou
Dong Chen
Hongxin Xu

3D single object tracking (SOT) based on point cloud has attracted much attention due to its important role in machine vision and autonomous driving. Recently, M 2 -Track proposes a two-stage tracking structure centered on motion, but they ignore the effect of segmentation errors in sparse point cloud scenarios, which hinder the ability of networks to accurately represent tracking targets. To solve the problems, we propose an efficient 3D single object tracker (Abbr. EST) that can effectively segment point cloud features. Firstly, the proposed fusion segmentation module makes up for the feature loss caused by the downsampling strategy and enhances the ability of the network to recognize foreground points. In addition, the global embedded module is used to further focus on the crucial features of the target. This module provides global information by using residual networks and adding background information. Numerous experiments conducted on KITTI and NuScenes benchmarks show that EST achieves superior point cloud tracking in both performance and efficiency.

Details