Wang Ruohan

ML Research Scientist, Institute for Infocomm Research, A*STAR, ex-@AWS

[Wang Ruohan @WRuohan]

https://t.co/cu3qoGXG8l

[Wang Ruohan @WRuohan]

The results in turn provide a theoretical perspective towards why pre-trained models are robust few-shot learners. #fewshotlearning #pretraining (3/3)

[Wang Ruohan @WRuohan]

Happy that our paper "Robust Meta-Representation Learning via Global Label Inference and Classification" with Isak Falk, Massi Pontil and Carlo Ciliberto has been accepted to PAMI. check it out at https://t.co/2HJHRisiIJ (1/3)

[Wang Ruohan @WRuohan]

The paper builds upon our previous work "The Role of Global Labels in Few-Shot Classification and How to Infer Them" from Nuerips 2021. We show that standard pre-training is a special instance of meta-learning, but with improved convergence rate. (2/3)

[Wang Ruohan @WRuohan]

@DHLParcelUK where is my parcel? The tracking says it's due to be delivered yesterday. But the only tracking status is "parcel collected". The shipment number is 51083231832860. The parcel is extremely important.

[Wang Ruohan @WRuohan]

Our paper "The Role of Global Labels in Few-Shot Classification and How to Infer Them" with Massi Pontil and Carlo Ciliberto has been accepted to #NeurIPS2021. Check it out at https://t.co/JiyxOUQ4mn

[Wang Ruohan @WRuohan]

Our paper "Structured Prediction for Conditional #MetaLearning" with @YiannisDemiris and Carlo Ciliberto has been accepted to #NeurIPS2020. We will release the updated version of the paper soon. An earlier version is at https://t.co/TssGDctQNv.

[Wang Ruohan @WRuohan]

@ChannelFireball The lack of legacy events is extremely disappointing.

[Wang Ruohan @WRuohan]

Our paper Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation (https://t.co/pSyOicwlPB) has been accepted to ICML 2019. We propose a new take on imitation learning without adversarial training of the reward function.

[Wang Ruohan @WRuohan]

Our paper Real-Time Workload Classification during Driving using HyperNetworks (https://t.co/oUWKSUYifG) has been accepted for IROS 2018. Our proposed architecture is designed to tackle noisy and dynamic data like gaze patterns.

[Wang Ruohan @WRuohan]

@AndrewYNg No limit hold'em and Ms Pac-Man

[Wang Ruohan @WRuohan]

@jimmfleming Thank you for MAGAN on arxivst. I'm the author of the paper, code at https://t.co/7mJOReI4P5

[Wang Ruohan @WRuohan]

MAGAN: Margin Adaptation for Adversarial Networks, our new paper on auto-encoder based GAN.

https://t.co/SRhekdiudi
https://t.co/7mJOReI4P5

[Wang Ruohan @WRuohan]

Why large-batch learning fails.
https://t.co/EJqyJc90nd