#robustml search results
Excited to announce our ICLR 2021 workshop on robust and reliable ML in the real world! CfP: sites.google.com/connect.hku.hk… Submission deadline: Feb 26th #RobustML #ICLR2021 #workshop
Wild new paper collects a set of naturally occuring adversarial examples for imagenet classifiers: densenet gets only 2% accuracy! arxiv.org/abs/1907.07174 #RobustML
Presented two works on Certified Robustness of Neural networks at #ICML2023 #robustml #certifiedml #optimization #xai @AdvMLICML23 @trustworthy_ml
A research question re #robustML: for medical #AI is it more useful a model that's 80% accurate on common (normal, usual) cases but 20% accurate on unusual, rare and anomalous cases (OoD), or the other way round? Scholarly warning: it's a tricky question. @EnricoCoiera @DrLukeOR
From all of us at the ELLIS RobustML Organising Committee, THANK YOU. Here's to the start of many more collaborations, discussions, and innovations in the world of RobustML! 🙌 #RobustML #ELLISWorkshop
Presenting new paper at #RobustML and #S2DOLAD Workshops at #ICLR2021 tomorrow We consider #NLProc with noisy labels(random, input-dependent) for text classification tasks by capturing noise in auxiliary noise model. Paper: arxiv.org/abs/2101.11214 With @goutham7r, V. Thumbe
For the last three months, Hannah from @Princeton was visiting us and conducting work in #RobustML and #UncertaintyEstimation. Hannah's research stay was made possible by the collaboration of @HIDAdigital and the Summer Work Program of #PrincetonU
We tasted the cake but it is still a dough. I will be happy to discuss reliable medical imaging at #RobustML #ICLR2021 workshop.
Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data deepai.org/publication/ta… by @Entodi et al. including @eloygeenjaar #SupervisedLearning #ComputerVision
deepai.org
Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI...
03/29/21 - Self-supervised learning has enabled significant improvements on natural image benchmarks. However, there is less work in the medi...
We will be presenting our works on concept-based explanations, robustness & disentanglement learning at the #ResponsibleAI #Weasel and #RobustML workshops at @iclr_conf tonight! (1/2)
Last month members of @DLRdatascience had the chance to attend @CambridgeEllis #ML Summer School. Besides many very insightful talks on #MachineLearning, we also got the chance to present and discuss our work on #RobustML and #DataFusion
Enjoyed the inspiring talks and discussions at the #RobustML workshop today!
We have a line-up of stellar speakers including Emmanuel Candes, Kevin Murphy @sirbayes & Aaditya Ramdas. Network, learn & collaborate with top ML minds! 🤝🧠 Registration closes on Aug 15. Don't miss out! Reserve your spot using the website link above. 2/n
RT @RICEric22: Excited to announce our ICLR 2021 workshop on robust and reliable ML in the real world! CfP: bit.ly/3bKRyRZ Submission deadline: Feb 26th #RobustML #ICLR2021 #workshop bit.ly/35Aw7yP #mw via @mldcmu #cmuai #mldcmu
As part of our model validation series, we just published our tutorial on Adversarial Robustness with #AdverTorch Black-box Estimators: bit.ly/3m7xUTX. We discuss how this new module of Advertorch can assess the robustness of any given ML model. #robustML #responsibleAI
🌍 Robustness doesn’t have to rely on group annotations: DPE diversity-promoting regularization can naturally uncover latent subgroups, improving fairness. 🔗 Blog: minhto2802.github.io/dpe4subpop 📄 Paper: openreview.net/pdf?id=qUTiOeM… #ICML2025 #MachineLearning #RobustML #Fairness (🧵 7/8)
4/4 We invite researchers to apply the framework across VLM architectures and share findings—could this become a standard safety‑verification tool for high‑stakes AI? #RobustML
CNNs are designed to process and classify images for computer vision and many other tasks. But slight modifications — say, a few darker pixels within an image — may cause a CNN to produce a drastically different classification. NOT a #robustML
Reliability is one of the metric of #RobustML MachieLearning is a two step process - Training step, Inferencing (production) step. Reliability metrics are required in both. A modern compute/software infrastructure will play a very important role in addition to data/methods.
The workshop, led by @cholmesuk, @samikaski & @yeewhye, provides a unique platform to discuss #RobustML ideas with the research community's pioneers. A splendid chance for collaboration awaits you. See you there! 🧳✈️🪩 #MLLeaders #ELLISWorkshop #MLCollaboration 4/n (n=4).
Safeguarding ML against adversarial meddling is a crucial need that often runs into impossibilities, eg online adversarial learning is computationally/statistically much harder than the iid setting. My group and I have been working on changing this! #NeurIPS2022 #RobustML
💡 Takeaway: Data selection isn’t neutral. When downsizing or compressing datasets, how we choose samples shapes downstream fairness & robustness outcomes. Read the full paper here 👉 arxiv.org/abs/2507.11690 #NeurIPS2025 #MachineLearning #RobustML #Coresets #AIethics
4/4 We invite researchers to apply the framework across VLM architectures and share findings—could this become a standard safety‑verification tool for high‑stakes AI? #RobustML
6/6 w/@LiuChenruo, @KenanTang, @YaoQin_UCSB, we hope this bridges two critical conversations—and inspires new ones. Looking forward to your thoughts. #AISafety #RobustML #TrustworthyAI #DistributionShift #MLTheory
The Robust And Secure Machine Learning Podcast is here youtube.com/playlist?list=… #RobustML #SecureML #MachineLearning #DeepLearning #AdversarialML #DeepLearning #ML #AI #LLMs
From all of us at the ELLIS RobustML Organising Committee, THANK YOU. Here's to the start of many more collaborations, discussions, and innovations in the world of RobustML! 🙌 #RobustML #ELLISWorkshop
Enjoyed the inspiring talks and discussions at the #RobustML workshop today!
We have a line-up of stellar speakers including Emmanuel Candes, Kevin Murphy @sirbayes & Aaditya Ramdas. Network, learn & collaborate with top ML minds! 🤝🧠 Registration closes on Aug 15. Don't miss out! Reserve your spot using the website link above. 2/n
Join us for the ELLIS RobustML workshop this September featuring an all-star line-up of speakers. Don't miss the chance to engage in meaningful discussions and forge collaborations with pioneers in robust ML! 🤖🛡️ #ELLISRobustML #RobustML
Excited to co-organise the inaugural ELLIS RobustML workshop at Aalto University, Finland on September 23-24, with a fantastic line-up of speakers! Workshop website: sites.google.com/view/ellis-rob… ELLIS Programme website: ellis.eu/programs/robus… #ELLISRobustMLWorkshop
Join us for the 1st ELLIS Robust Machine Learning Workshop! 🗓️Sept 23-24, 2023 🧭 @AaltoUniversity in Espoo, Finland 🚨 Register by Aug. 15, submit an abstract by Sept 4, 2023 🔗 sites.google.com/view/ellis-rob… #ELLISRobustMLWorkshop #RobustML #ELLISWorkshop
Presented two works on Certified Robustness of Neural networks at #ICML2023 #robustml #certifiedml #optimization #xai @AdvMLICML23 @trustworthy_ml
🧵6/6 For more details, please check our paper arxiv.org/pdf/2301.12576… and project tongwu2020.github.io/tongwu/tta_ris…. Grateful for my excellent collaborators: Feiran Jia @Xiangyu28527122 @JiachenWang97 @VSehwag_ Saeed Mahloujifar @prateekmittal_ #TrustworthyAI #RobustML #AISafety
Safeguarding ML against adversarial meddling is a crucial need that often runs into impossibilities, eg online adversarial learning is computationally/statistically much harder than the iid setting. My group and I have been working on changing this! #NeurIPS2022 #RobustML
Excited to announce our ICLR 2021 workshop on robust and reliable ML in the real world! CfP: sites.google.com/connect.hku.hk… Submission deadline: Feb 26th #RobustML #ICLR2021 #workshop
Presented two works on Certified Robustness of Neural networks at #ICML2023 #robustml #certifiedml #optimization #xai @AdvMLICML23 @trustworthy_ml
Wild new paper collects a set of naturally occuring adversarial examples for imagenet classifiers: densenet gets only 2% accuracy! arxiv.org/abs/1907.07174 #RobustML
For the last three months, Hannah from @Princeton was visiting us and conducting work in #RobustML and #UncertaintyEstimation. Hannah's research stay was made possible by the collaboration of @HIDAdigital and the Summer Work Program of #PrincetonU
From all of us at the ELLIS RobustML Organising Committee, THANK YOU. Here's to the start of many more collaborations, discussions, and innovations in the world of RobustML! 🙌 #RobustML #ELLISWorkshop
Last month members of @DLRdatascience had the chance to attend @CambridgeEllis #ML Summer School. Besides many very insightful talks on #MachineLearning, we also got the chance to present and discuss our work on #RobustML and #DataFusion
A research question re #robustML: for medical #AI is it more useful a model that's 80% accurate on common (normal, usual) cases but 20% accurate on unusual, rare and anomalous cases (OoD), or the other way round? Scholarly warning: it's a tricky question. @EnricoCoiera @DrLukeOR
Presenting new paper at #RobustML and #S2DOLAD Workshops at #ICLR2021 tomorrow We consider #NLProc with noisy labels(random, input-dependent) for text classification tasks by capturing noise in auxiliary noise model. Paper: arxiv.org/abs/2101.11214 With @goutham7r, V. Thumbe
RT @RICEric22: Excited to announce our ICLR 2021 workshop on robust and reliable ML in the real world! CfP: bit.ly/3bKRyRZ Submission deadline: Feb 26th #RobustML #ICLR2021 #workshop bit.ly/35Aw7yP #mw via @mldcmu #cmuai #mldcmu
As part of our model validation series, we just published our tutorial on Adversarial Robustness with #AdverTorch Black-box Estimators: bit.ly/3m7xUTX. We discuss how this new module of Advertorch can assess the robustness of any given ML model. #robustML #responsibleAI
Something went wrong.
Something went wrong.
United States Trends
- 1. Northern Lights 45.7K posts
- 2. #Aurora 9,707 posts
- 3. #DWTS 53.2K posts
- 4. #chaggie 3,929 posts
- 5. Carmilla 2,295 posts
- 6. #huskerdust 7,649 posts
- 7. MIND-BLOWING 36.9K posts
- 8. #RHOSLC 7,279 posts
- 9. AI-driven Web3 1,025 posts
- 10. H-1B 35.9K posts
- 11. Justin Edwards 2,499 posts
- 12. Superb 23K posts
- 13. Sabonis 6,261 posts
- 14. Louisville 18.2K posts
- 15. SPECTACULAR 25.7K posts
- 16. Creighton 2,333 posts
- 17. Andy 61K posts
- 18. Gonzaga 3,029 posts
- 19. Cleto 2,613 posts
- 20. H1-B 4,187 posts