Integrating the traffic science with representation learning for city-wide network congestion prediction von Zheng, Wenqing, Yang, Hao (Frank), Cai, Jiarui, Wang, Peihao, Jiang, Xuan, Du, Simon Shaolei, Wang, Yinhai, Wang, Zhangyang

Volltext

Robust Offline Reinforcement Learning -- Certify the Confidence Interval von Yao, Jiarui, Du, Simon Shaolei

Volltext bestellen

Offline Multi-task Transfer RL with Representational Penalization von Bose, Avinandan, Du, Simon Shaolei, Fazel, Maryam

Volltext bestellen

On Erroneous Agreements of CLIP Image Embeddings von Li, Siting, Koh, Pang Wei, Du, Simon Shaolei

Volltext bestellen

Transformers are Efficient Compilers, Provably von Zhai, Xiyu, Zhou, Runlong, Zhang, Liao, Du, Simon Shaolei

Volltext bestellen

Robust Offline Reinforcement Learning -- Certify the Confidence Interval von Yao, Jiarui, Du, Simon Shaolei

Volltext

CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning von Wang, Yiping, Chen, Yifang, Yan, Wendan, Fang, Alex, Zhou, Wenjing, Jamieson, Kevin, Du, Simon Shaolei

Volltext bestellen

Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning von Wang, Yiping, Chen, Yifang, Yan, Wendan, Jamieson, Kevin, Du, Simon Shaolei

Volltext bestellen

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning von Zhou, Zhaoyi, Zhu, Chuning, Zhou, Runlong, Cui, Qiwen, Gupta, Abhishek, Du, Simon Shaolei

Volltext bestellen

Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning von Chen, Yifang, Wang, Shuohang, Yang, Ziyi, Sharma, Hiteshi, Karampatziakis, Nikos, Yu, Donghan, Jamieson, Kevin, Du, Simon Shaolei, Shen, Yelong

Volltext bestellen

Offline Multi-task Transfer RL with Representational Penalization von Bose, Avinandan, Du, Simon Shaolei, Fazel, Maryam

Volltext

On Erroneous Agreements of CLIP Image Embeddings von Li, Siting, Pang Wei Koh, Du, Simon Shaolei

Volltext

Transformers are Efficient Compilers, Provably von Zhai, Xiyu, Zhou, Runlong, Liao, Zhang, Du, Simon Shaolei

Volltext

A Benchmark for Low-Switching-Cost Reinforcement Learning von Xu, Shusheng, Liang, Yancheng, Li, Yunfei, Du, Simon Shaolei, Wu, Yi

Volltext bestellen

LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning von Zhang, Jifan, Chen, Yifang, Canal, Gregory, Mussmann, Stephen, Das, Arnav M, Bhatt, Gantavya, Zhu, Yinglun, Bilmes, Jeffrey, Du, Simon Shaolei, Jamieson, Kevin, Nowak, Robert D

Volltext bestellen

Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning von Wang, Yiping, Chen, Yifang, Yan, Wendan, Jamieson, Kevin, Du, Simon Shaolei

Volltext

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning von Zhou, Zhaoyi, Zhu, Chuning, Zhou, Runlong, Cui, Qiwen, Gupta, Abhishek, Du, Simon Shaolei

Volltext

Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning von Chen, Yifang, Wang, Shuohang, Yang, Ziyi, Sharma, Hiteshi, Karampatziakis, Nikos, Yu, Donghan, Jamieson, Kevin, Du, Simon Shaolei, Shen, Yelong

Volltext

Hypothesis Transfer Learning via Transformation Functions von Du, Simon Shaolei, Koushik, Jayanth, Singh, Aarti, Poczos, Barnabas

Volltext bestellen

LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning von Zhang, Jifan, Chen, Yifang, Canal, Gregory, Mussmann, Stephen, Das, Arnav M, Bhatt, Gantavya, Zhu, Yinglun, Bilmes, Jeffrey, Du, Simon Shaolei, Jamieson, Kevin, Nowak, Robert D

Volltext