Arvind singhania biography of rory

  • Arvind Kumar Singhania founded

    • Advances in Neural Information Processing Systems 37 (NeurIPS 2024)

    Edited by: A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang

    Main Conference Track  Datasets and Benchmarks Track
    • MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable ConvergenceIonut-Vlad Modoranu, Mher Safaryan, Grigory Malinovsky, Eldar Kurtić, Thomas Robert, Peter Richtarik, Dan Alistarh
    • GITA: Graph to Visual and Textual Integration for Vision-Language Graph ReasoningYanbin Wei, Shuai Fu, Weisen Jiang, Zejian Zhang, Zhixiong Zeng, Qi Wu, James T. Kwok, Yu Zhang
    • How does PDE order affect the convergence of PINNs?Chang hoon Song, Yesom Park, Myungjoo Kang
    • Fair Wasserstein CoresetsZikai Xiong, Niccolo Dalmasso, Shubham Sharma, Freddy Lecue, Daniele Magazzeni, Vamsi Potluru, Tucker Balch, Manuela M. Veloso
    • Improved Regret for Bandit Convex Optimization with Delayed FeedbackYuanyu Wan, Chang Yao, Mingli Song, Lijun Zhang
    • Enhancing Chess Reinforcement Learning with Graph RepresentationTomas Rigaux, Hisashi Kashima
    • Mixtures of Experts for Audio-Visual LearningYing Cheng, Yang Li, Junjie He, Rui Feng
    • Learning Place Cell Representations and Context-Dependent RemappingMarkus Pettersen, Frederik Rogge, Mikkel Lepperød
    • Robust Sparse Regression with Non-Isotropic DesignsChih-Hung Liu, Gleb Novikov
    • Training-Free Adaptive Diffusion with Bounded Difference Approximation StrategyHancheng Ye, Jiakang Yuan, Renqiu Xia, Xiangchao Yan, Tao Chen, Junchi Yan, Botian Shi, Bo Zhang
    • Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMsXuan Zhang, Chao Du, Tianyu Pang, Qian Liu, Wei Gao, Min Lin
    • Decompose, Analyze and Rethink: Solving Intricate Problems with Human-like Reasoning CycleShangzi Xue, Zhenya Huang, Jiayu Liu, Xin Lin, Yuting Ning, Binbin Jin, Xin Li, Qi Liu
    • UQ-Guided Hyperparameter Optimization for Iterative LearnersJiesong Liu, Feng Zhang, Jiawei Guan, Xipen

    Beyond Pass or Fail: Multi-Dimensional Benchmarking of Foundation Models for Goal-based Mobile UI Navigation

    Dezhi Ran Key Lab of HCST (PKU), MOE; SCSPeking UniversityBeijingChinadezhiran@pku.edu.cn, Mengzhou Wu School of EECS, Peking UniversityBeijingChinawmz@stu.pku.edu.cn, Hao Yu School of Software and Microelectronics, Peking UniversityBeijingChinayh0315@pku.edu.cn, Yuetong Li The University of ChicagoChicagoUSAyuetong@uchicago.edu, Jun Ren University of Texas at DallasDallasUSAjxr210020@utdallas.edu, Yuan Cao School of EECS, Peking UniversityBeijingChinacao˙yuan21@stu.pku.edu.cn, Xia Zeng Tencent Inc.ShenzhenChinaxiazeng@tencent.com, Haochuan Lu Tencent Inc.ShenzhenChinahudsonhclu@tencent.com, Zexin Xu University of Texas at DallasDallasUSAZexin.xu@utdallas.edu, Mengqian Xu East China Normal UniversityShanghaiChinaxmq@stu.ecnu.edu.cn, Ting Su East China Normal UniversityShanghaiChinatsu@sei.ecnu.edu.cn, Liangchao Yao Tencent Inc.ShenzhenChinaclarkyao@tencent.com, Ting Xiong Tencent Inc.ShenzhenChinacandyxiong@tencent.com, Wei Yang University of Texas at DallasDallasUSAwei.yang@utdallas.edu, Yuetang Deng Tencent Inc.ShenzhenChinayuetangdeng@tencent.com, Assaf Marron Dept. of Computer Science and Applied MathematicsWeizmann Institute of ScienceRehovotIsraelAssaf.Marron@weizmann.ac.il, David Harel Dept. of Computer Science and Applied MathematicsWeizmann Institute of ScienceRehovotIsraeldavid.harel@weizmann.ac.il and Tao Xie Key Lab of HCST (PKU), MOE; SCSPeking UniversityBeijingChinataoxie@pku.edu.cn

    Abstract.

    Recent advances of foundation models (FMs) have made navigating mobile applications (apps) based on high-level goal instructions within reach, with significant industrial applications such as UI testing. While existing benchmarks evaluate FM-based UI navigation using the binary pass/fail metric, they have two major limitations: they cannot reflect the complex nature of mobile UI navigation where FMs may fail for various reasons (e.g., misunderstandin

    SCTS Annual Meeting 2024: Abstracts

    • Meeting Abstracts
    • Open access
    • Published:

    Journal of Cardiothoracic Surgeryvolume 19, Article number: 702 (2025) Cite this article

    • 2038 Accesses

    • 2 Altmetric

    • Metrics details

    A1 Surgical prehabilitation in an acute tertiary centre: an evaluation

    Melissa Taylor

    University Hospitals Bristol and Weston, Bristol, United Kingdom

    Correspondence: Melissa Taylor

    Journal of Cardiothoracic Surgery 2024, 19(2):A1

    Objective: The aim of this study is to evaluate the impact of a physiotherapy led prehabilitation program on functional capacity, strength and health related quality of life in patients undergoing major surgery at UHBW.

    Methods: A service evaluation of quantitative measures. In 2019, UHBW set up a physiotherapy led prehabilitation service to those listed for major surgery. Assessment screened for physical, nutritional and psychological risk factors. Personalised exercise programs, targeted nutritional, smoking, alcohol and wellbeing support were provided. Interventions were delivered both face to face and virtually. Strength, functional capacity and health related quality of life were measured by the 30 s sit to stand test, grip strength and EQ-5D-5L.

    Results: 795 patients were enrolled in the prehabilitation programme between 15th June 2021 and 5th January 2023. Mean age 67 years. 380 (48%) patients were on a thoracic pathway. Other specialities included colorectal (20%) upper gastrointestinal (7%), hepatobiliary (9%), head and neck (5%) and gynaecology (5%). Data shows a significant improvement in 30 s sit to stand score, mean difference + 2.9 (P < 0.01) n = 305. No significant change in grip strength, mean difference -0.4 kg (P 0.42) n = 99. A significant Improvement in EQ-5D-5L index score. + 0.05 (P < 0.01) n = 325.

    Conclusion: A physiotherapy led prehabilitation programme can improve functional capacity and health related quality of life in patients prior to major surgery, e

    .

  • Location: San Francisco Bay Area ·
  • Abstract. Ensuring that Large Language Models