Shu Yao Profile
Shu Yao

@ZCODE0

Followers
27
Following
167
Media
2
Statuses
49

Incoming Assistant Professor @ AI Trust, HKUST (GZ)

Guangdong
Joined July 2014
Don't wanna be here? Send us removal request.
@ZCODE0
Shu Yao
10 months
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 https://t.co/uy8J0HqSU9 for more info and feel free to email for the application.
Tweet card summary image
yao.notion.site
Dr. Yao SHU (舒瑶) is now a tenure-track assistant professor of Artificial Intelligence Thrust at Hong Kong University of Science and Technology (Guangzhou), starting from April 8, 2025. He was...
1
0
2
@ZCODE0
Shu Yao
10 months
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: https://t.co/w80HmQ9PyL #AI #NLP #LLMs #Prompt #Robustness
0
0
1
@ZCODE0
Shu Yao
1 year
Follow is now a lifesaver for me!
0
0
0
@bryanklow
Bryan Kian Hsiang Low
1 year
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 @ https://t.co/IEtyi0dGLS
1
7
17
@bryanklow
Bryan Kian Hsiang Low
1 year
Visit the poster of @ZCODE0 @xiaoqiang_98 @Dai_Zh et al. on Federated #ZerothOrderOptimization at @icmlconf #ICML2024 Workshop on Differentiable Almost Everything (26 Jul, https://t.co/ogwPZwOaFe)! Paper: https://t.co/rwMyXC9dk7 #FederatedLearning
6
2
12
@bryanklow
Bryan Kian Hsiang Low
2 years
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: https://t.co/wsvUvM5oXi Code: https://t.co/nxk1q8w5IJ
1
4
14
@bryanklow
Bryan Kian Hsiang Low
2 years
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). https://t.co/rFgJNudTKM (1/n)
4
6
30
@bryanklow
Bryan Kian Hsiang Low
2 years
When using #ChatGPT, how do u decide what instruction to give it? https://t.co/6PNugtiN19 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
@bryanklow
Bryan Kian Hsiang Low
3 years
Congrats to @ZCODE0 for winning the best Ph.D. thesis award in 2023 @NUSComputing! His thesis topic is on #NeuralArchitectureSearch. URL: https://t.co/dFAoU9pylm
0
3
23
@bryanklow
Bryan Kian Hsiang Low
3 years
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: https://t.co/1tqv3N4PSU Present: https://t.co/z9rvSNBSyS
0
5
14
@bryanklow
Bryan Kian Hsiang Low
3 years
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: https://t.co/QUcHtB1a2Q Presentation: https://t.co/gh6aSXTWFk
1
3
12
@bryanklow
Bryan Kian Hsiang Low
3 years
1
9
27
@ZCODE0
Shu Yao
3 years
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.
@bryanklow
Bryan Kian Hsiang Low
3 years
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.
0
0
8
@bryanklow
Bryan Kian Hsiang Low
3 years
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
2
6
16
@bryanklow
Bryan Kian Hsiang Low
3 years
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
2
6
11
@bryanklow
Bryan Kian Hsiang Low
3 years
0
5
14