Publications (12)
Representation Collapse in Sequential Post-Training of Large Language Models
Yichen Liu, Mingyu Chen, Hao Wang +7
Large language models are now adapted through chains of post-training stages rather than through a single instruction-tuning pass. This paper studies whether such sequential post-t…
Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation
Jian Jiang, Chenxi Lin, Yiming Gu +24
Surgical scene understanding demands not only accurate predictions but also interpretable reasoning that surgeons can verify against clinical expertise. However, existing surgical…
Experimental demonstration of broadband absorption enhancement in partially aperiodic silicon nanohole structures
Chenxi Lin, Luis Javier MartÃnez, Michelle L. Povinelli
We report the design, fabrication, and optical absorption measurement of silicon membranes patterned with partially aperiodic nanohole structures. We demonstrate excellent agreemen…
AlignSurvey: A Comprehensive Benchmark for Human Preferences Alignment in Social Surveys
Chenxi Lin, Weikang Yuan, Zhuoren Jiang +5
Understanding human attitudes, preferences, and behaviors through social surveys is essential for academic research and policymaking. Yet traditional surveys face persistent challe…
Attention-augmented Spatio-Temporal Segmentation for Land Cover Mapping
Rahul Ghosh, Praveen Ravirathinam, Xiaowei Jia +3
The availability of massive earth observing satellite data provide huge opportunities for land use and land cover mapping. However, such mapping effort is challenging due to the ex…
Clustering augmented Self-Supervised Learning: Anapplication to Land Cover Mapping
Rahul Ghosh, Xiaowei Jia, Chenxi Lin +2
Collecting large annotated datasets in Remote Sensing is often expensive and thus can become a major obstacle for training advanced machine learning models. Common techniques of ad…
SCD: A Stacked Carton Dataset for Detection and Segmentation
Jinrong Yang, Shengkai Wu, Lijun Gou +5
Carton detection is an important technique in the automatic logistics system and can be applied to many applications such as the stacking and unstacking of cartons, the unloading o…
Recurrent Alignment with Hard Attention for Hierarchical Text Rating
Chenxi Lin, Jiayu Ren, Guoxiu He +3
While large language models (LLMs) excel at understanding and generating plain text, they are not tailored to handle hierarchical text structures or directly predict task-specific…
Early- and in-season crop type mapping without current-year ground truth: generating labels from historical information via a topology-based approach
Chenxi Lin, Liheng Zhong, Xiao-Peng Song +3
Land cover classification in remote sensing is often faced with the challenge of limited ground truth. Incorporating historical information has the potential to significantly lower…
Carton dataset synthesis method for domain shift based on foreground texture decoupling and replacement
Lijun Gou, Shengkai Wu, Jinrong Yang +4
One major impediment in rapidly deploying object detection models for industrial applications is the lack of large annotated datasets. We currently have presented the Sacked Carton…
Surg: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence
Zhitao Zeng, Mengya Xu, Jian Jiang +13
Surgical intelligence has the potential to improve the safety and consistency of surgical care, yet most existing surgical AI frameworks remain task-specific and struggle to genera…
Mapping smallholder cashew plantations to inform sustainable tree crop expansion in Benin
Leikun Yin, Rahul Ghosh, Chenxi Lin +9
Cashews are grown by over 3 million smallholders in more than 40 countries worldwide as a principal source of income. As the third largest cashew producer in Africa, Benin has near…