Hi guys! I am extremely honored to join the AI Thrust at HKUST (GZ) as an Assistant Professor in April 2025. I am recruiting Ph.D. and MPhil students for Fall 2025. Visit my personal website yao.notion.site for more info and feel free to email for the application.
1
2
157
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
1
74
Shu Yao retweeted
20 Sep 2024
The #EMNLP2024 @emnlpmeeting (findings) position paper of @michael_xinyi @WuZhaoxuan @ray_qiaorui @arun_v3rma @PangWeiKoh et al. proposes a data-centric viewpoint of AI research, focusing on #LLM #LLMs.
Check it out @ arxiv.org/abs/2406.14473
1
7
17
1,994
Shu Yao retweeted
20 Jul 2024
Visit the poster of @ZCODE0 @xiaoqiang_98 @Dai_Zh et al. on Federated #ZerothOrderOptimization at @icmlconf #ICML2024 Workshop on Differentiable Almost Everything (26 Jul, differentiable.xyz)!
Paper: differentiable.xyz/papers-20…
#FederatedLearning
6
2
12
557
Shu Yao retweeted
6 May 2024
The #ICLR2024 @iclr_conf work of @he_zhenfeng @Dai_Zh @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=qPloNo…
Code: github.com/hzf1174/RoBoT
1
4
14
863
Shu Yao retweeted
3 Mar 2024
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/97804… (1/n)
4
6
30
2,122
Shu Yao retweeted
16 Jan 2024
Congrats! @greglau @apivich_h @he_zhenfeng @insebtion @WuZhaoxuan @ray_qiaorui @qphong ruth @Dai_Zh @ZCODE @pjaillet
Accepted @iclr_conf #ICLR2024: #ShapleyValue #DataValuation #FederatedLearning #BayesianOptimization #NeuralArchitectureSearch #NeuralTangentKernel #AI4Science
3
8
37
3,074
Shu Yao retweeted
5 Oct 2023
When using #ChatGPT, how do u decide what instruction to give it?
xqlin98.github.io/INSTINCT/
Joint work on Automatic Prompting with @xiaoqiang_98 @WuZhaoxuan @Dai_Zh @_Hu_Wenyang @ZCODE0 see-kiong @pjaillet.
#LLM #LLMs #PromptEngineering #GenerativeAI (1/n)
2
6
19
3,269
Shu Yao retweeted
22 Sep 2023
Congrats! to @RachaelSim2 @insebtion @michael_xinyi greg @chi_thanh_lam @arun_v3rma @Dai_Zh @ZCODE0 @qphong @nghiaht87 yehong chuan-sheng @pjaillet
Accepted papers @NeurIPSConf #NeurIPS2023: #ShapleyValue #DataValuation #FederatedLearning #BayesianOptimization #AI4Science
7
8
46
5,066
Shu Yao retweeted
31 May 2023
Congrats to @ZCODE0 for winning the best Ph.D. thesis award in 2023 @NUSComputing!
His thesis topic is on #NeuralArchitectureSearch.
URL: comp.nus.edu.sg/~lowkh/pubs/…
3
23
986
Shu Yao retweeted
18 May 2023
Postdoc & RA positions in #AutoML #ActiveLearning #BayesianOptimization #NeuralArchitectureSearch #ReinforcementLearning #MultiAgentRL #AutoRL @NUSComputing
See groups.google.com/u/2/g/ml-n…
#ICLR2023 #AAAI2023 #IJCAI2023 #UAI2023 #AISTATS2023 #NeurIPS2023
Meet me @ #ICML2023
2
9
18
4,205
Shu Yao retweeted
30 Apr 2023
The #ICLR2023 work of @ZCODE0 @Dai_Zh weicong @arun_v3rma @pjaillet @bryanklow proposes a query-efficient Zeroth-Order Optimization algo w. trajectory-informed derivative est. #BayesianOptimization #GaussianProcess
Paper: openreview.net/pdf?id=n1bLgx…
Present: iclr.cc/virtual/2023/poster/…
5
14
890
Shu Yao retweeted
30 Apr 2023
The #ICLR2023 work of @Dai_Zh @ZCODE0 @arun_v3rma @Flint_xf_Fan @bryanklow @pjaillet proposes the first federated neural contextual bandit algorithm (1/N).
#FederatedLearning #BayesianOptimization
Paper: openreview.net/pdf?id=38m4h8…
Presentation: iclr.cc/virtual/2023/poster/…
1
3
12
738
Shu Yao retweeted
21 Jan 2023
Congrats @chi_thanh_lam @michael_xinyi @insebtion weicong @WuZhaoxuan @Flint_xf_Fan @qphong @Dai_Zh @ZCODE0 @arun_v3rma chuan-sheng @pjaillet. Accepted papers @ #AISTATS2023 #ICLR2023: Zeroth-Order Optimization #BayesianOptimization #ActiveLearning #FederatedLearning #AI4Science
1
9
27
2,840
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.
28 Nov 2022
To understand and boost gradient-based #TrainingFree #NeuralArchitectureSearch algorithms, the #NeurIPS2022 work of @ZCODE0 @Dai_Zh @WuZhaoxuan @bryanklow provides the first unified theoretical study and principled improvement for them based on theory of #NeuralTangentKernel.
8
Shu Yao retweeted
28 Nov 2022
The #NeurIPS2022 work of @Dai_Zh @ZCODE0 @bryanklow @pjaillet introduces theoretically grounded batch #BayesianOptimization algorithms using #DeepNeuralNetworks (DNNs) as the surrogate function that can handle categorical, high-dimensional, or image inputs. #NeuralTangentKernel
15 Sep 2022
Congrats!!! to @qphong @Dai_Zh @ZCODE0 @WuZhaoxuan @bryanklow @pjaillet for their accepted papers on #BayesianOptimization #NeuralArchitectureSearch #ShapleyValue #FederatedLearning #DataValuation at #NeurIPS2022:
2
6
16
Shu Yao retweeted
28 Nov 2022
To fairly trade off betw payoff & model rewards in collaborative ML, the #NeurIPS2022 work of @qphong @bryanklow @pjaillet refines #ShapleyValue into a conditional variant representing pairwise payoff flows betw parties. #FederatedLearning #DataValuation
15 Sep 2022
Congrats!!! to @qphong @Dai_Zh @ZCODE0 @WuZhaoxuan @bryanklow @pjaillet for their accepted papers on #BayesianOptimization #NeuralArchitectureSearch #ShapleyValue #FederatedLearning #DataValuation at #NeurIPS2022:
2
6
11
Shu Yao retweeted
3 Nov 2022
Postdoc & RA positions in #DataCentricAI Collaborative ML/#FederatedLearning #DataValuation Incentive-Aware Mechanism Design #MachineUnlearning
@NUSComputing
See groups.google.com/u/2/g/ml-n…
#ICML2023 #ICLR2023 #AAAI2023 #IJCAI2023 #UAI2023 #AISTATS2023
Meet me @ #NeurIPS2022
5
14
Shu Yao retweeted
3 Nov 2022
Postdoc & RA positions in Learning with Less Data: #AutoML pipeline #ActiveLearning #BayesianOptimization #NeuralArchitectureSearch
@NUSComputing
See groups.google.com/u/2/g/ml-n…
#ICML2023 #ICLR2023 #AAAI2023 #IJCAI2023 #UAI2023 #AISTATS2023
Meet me @ #NeurIPS2022
5
20