Postdoc & RA positions in #DataCentricAI Collaborative ML/#FederatedLearning #DataValuation Incentive-Aware Mechanism Design #MachineUnlearning NUS Computing See groups.google.com/u/2/g/ml-news/… #ICML2023 #ICLR2023 #AAAI2023 #IJCAI2023 #UAI2023 #AISTATS2023 Meet me @ #NeurIPS2022

To fairly trade off betw payoff & model rewards in collaborative ML, the #NeurIPS2022 work of qphong Bryan Kian Hsiang Low patrick jaillet refines #ShapleyValue into a conditional variant representing pairwise payoff flows betw parties. #FederatedLearning #DataValuation

The #NeurIPS2022 work of Dai Zhongxiang Shu Yao Bryan Kian Hsiang Low patrick jaillet introduces theoretically grounded batch #BayesianOptimization algorithms using #DeepNeuralNetworks (DNNs) as the surrogate function that can handle categorical, high-dimensional, or image inputs. #NeuralTangentKernel

This is the first unified theoretical study to explain why existing training-free NAS algorithms perform well in practice and how to further improve them. We believe this work can help/inspire existing training-free NAS and also the follow-ups to behave more soundly in practice.

Congrats Lam Chi Thanh (Steve) Xinyi Xu Sebastian Tay weicong Wu Zhaoxuan Flint Xiaofeng Fan qphong Dai Zhongxiang Shu Yao Arun Verma chuan-sheng patrick jaillet. Accepted papers @ #AISTATS2023 #ICLR2023: Zeroth-Order Optimization #BayesianOptimization #ActiveLearning #FederatedLearning #AI4Science

The #ICLR2023 work of Shu Yao Dai Zhongxiang weicong Arun Verma patrick jaillet Bryan Kian Hsiang Low proposes a query-efficient Zeroth-Order Optimization algo w. trajectory-informed derivative est. #BayesianOptimization #GaussianProcess Paper: openreview.net/pdf?id=n1bLgxH… Present: iclr.cc/virtual/2023/p…

The #ICLR2023 work of Dai Zhongxiang Shu Yao Arun Verma Flint Xiaofeng Fan Bryan Kian Hsiang Low patrick jaillet proposes the first federated neural contextual bandit algorithm (1/N). #FederatedLearning #BayesianOptimization Paper: openreview.net/pdf?id=38m4h8H… Presentation: iclr.cc/virtual/2023/p…

Postdoc & RA positions in #AutoML #ActiveLearning #BayesianOptimization #NeuralArchitectureSearch #ReinforcementLearning #MultiAgentRL #AutoRL NUS Computing See groups.google.com/u/2/g/ml-news/… #ICLR2023 #AAAI2023 #IJCAI2023 #UAI2023 #AISTATS2023 #NeurIPS2023 Meet me @ #ICML2023

Congrats to Shu Yao for winning the best Ph.D. thesis award in 2023 NUS Computing! His thesis topic is on #NeuralArchitectureSearch. URL: comp.nus.edu.sg/~lowkh/pubs/ph…

Congrats! to Rachael Sim Sebastian Tay Xinyi Xu greg Lam Chi Thanh (Steve) Arun Verma Dai Zhongxiang Shu Yao qphong @nghiaht87 yehong chuan-sheng patrick jaillet Accepted papers NeurIPS Conference #NeurIPS2023: #ShapleyValue #DataValuation #FederatedLearning #BayesianOptimization #AI4Science

When using #ChatGPT, how do u decide what instruction to give it? xqlin98.github.io/INSTINCT/ Joint work on Automatic Prompting with Lin Xiaoqiang Wu Zhaoxuan Dai Zhongxiang Hu.Wenyang Shu Yao see-kiong patrick jaillet. #LLM #LLMs #PromptEngineering #GenerativeAI (1/n)

Congrats! Gregory Lau Apivich H. (Kaotoo) He Zhenfeng Sebastian Tay Wu Zhaoxuan Rui Qiao qphong ruth Dai Zhongxiang @ZCODE patrick jaillet Accepted ICLR 2026 #ICLR2024: #ShapleyValue #DataValuation #FederatedLearning #BayesianOptimization #NeuralArchitectureSearch #NeuralTangentKernel #AI4Science

Our research group & collaborators have put together 4 chapters in the #FederatedLearning: Theory and Practice book: fairness (ch.8), #DataValuation (ch.15) & incentives (ch.16) in #FederatedLearning, and federated sequential decision making (ch.14). sciencedirect.com/book/978044319… (1/n)

The #ICLR2024 ICLR 2026 work of He Zhenfeng Dai Zhongxiang @ZCODE introduces RoBoT🤖 to robustify and boost training-free #NeuralArchitectureSearch. Join us @ Poster Session 6 May 9 Thu 4:30PM Halle B #250 Paper: openreview.net/pdf?id=qPloNoD… Code: github.com/hzf1174/RoBoT

Visit the poster of Shu Yao Lin Xiaoqiang Dai Zhongxiang et al. on Federated #ZerothOrderOptimization at ICML Conference #ICML2024 Workshop on Differentiable Almost Everything (26 Jul, differentiable.xyz)! Paper: differentiable.xyz/papers-2024/pa… #FederatedLearning

The #EMNLP2024 EMNLP 2025 (findings) position paper of Xinyi Xu Wu Zhaoxuan Rui Qiao Arun Verma Pang Wei Koh et al. proposes a data-centric viewpoint of AI research, focusing on #LLM #LLMs. Check it out @ arxiv.org/abs/2406.14473

Follow is now a lifesaver for me!

LLMs struggling with prompt variations? 🤔 PAFT (Prompt-Agnostic Fine-Tuning) to the rescue! 🚀 We fine-tune for robustness, achieving state-of-the-art performance. Read the paper: arxiv.org/abs/2502.12859 #AI #NLP #LLMs #Prompt #Robustness