News

Feb, 2024
Our paper "DeiT-LT:Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets" got accepted to CVPR\'24. Project Page is available [here](https://rangwani-harsh.github.io/DeiT-LT/)

Feb, 2024
Invited Talk on "Learning from Limited and Imperfect Data" at IEEE Deep-Tech Seminar.

Feb, 2024
Serving as reviewer in ECCV\'24.

January, 2024
Our paper on "Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Metrics" got accepted to ICLR\'24 for a **Spotlight (Top-5%)** presentation. Pre-print is available [here](https://openreview.net/pdf?id=rxVBKhyfSo).

December, 2023
Serving as reviewer for ICML\'24.

November, 2023
Organizing the [Adobe-IISc GenAI Workshop](https://adobe-genai-workshop.github.io/)

October, 2023
Our paper on "Inducing Smoothness Regularization in Federated Learning" got accepted to WACV\'24. Pre-print is available [here](https://openaccess.thecvf.com/content/WACV2024/papers/Yashwanth_Minimizing_Layerwise_Activation_Norm_Improves_Generalization_in_Federated_Learning_WACV_2024_paper.pdf).

October, 2023
Attended ICCV\'23 in Paris. Thanks to Google and Kotak AI Centre for travel grants.

September, 2023
Serving as reviewer for AAAI\'24 and ICLR\' 24.

August, 2023
Talk at Adobe Research about our recent CVPR 2023 and NeurIPS 2022 Works.

July, 2023
Served as Volunteer for organizing NicoloFest at COLT\'23.

June-August, 2023
Research Internship at Adobe Research, working on a Text-2-Image Generative Diffusion Models project.

August, 2023
Research talk at CDS Department Expo, IISc Bangalore.

July, 2023
Our paper on "Strata-NeRF, Neural Radiance fields for Stratified Scenes", got accepted at ICCV\'23.

June, 2023
Our paper on "Optimizing Non-Decomposable Objectives with Mixup Fine-Tuning", got accepted at [Differentiable Almost Everything Workshop](https://differentiable.xyz/) at ICML\'23. Preprint is available [here](https://differentiable.xyz/papers/paper_28.pdf)!

May, 2023
Our paper "Certified Adversarial Robustness Within Multiple Perturbation Bounds" was selected for **oral presentation (top 7.8%)** at [3rd AdvART Workshop](https://robustart.github.io/) at CVPR\'23.

May, 2023
Awarded the Google Travel Grant 2023, for attending CVPR\'23. Thanks Google!

April, 2023
We released our works "NoisyTwins, Class-Consistent and Diverse Image Generation through StyleGANs" accepted at CVPR\'23 and "Certified Adversarial Robustness Within Multiple Perturbation Bounds" appearing at CVPRW\'23 on Arxiv. Checkout publication page for details.

April, 2023
Serving as reviewer for NeurIPS\'23, ICCV\'23 and FGVC\'23

April, 2023
Giving an invited talk on our work "Cost-Sensitive Self-Training for Non-Decomposable Metrics" at [IISc EECS Symposium](https://eecs.iisc.ac.in/EECS2023/) in AI/ML track. Do tune in case you are attending!

February, 2023
Invited for presentation of our work "Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data" at [ACM-ARCS 2023](https://event.india.acm.org/ARCS/#arcs-schedule). Thanks ACM-India!

January, 2023
Presented our work on "Cost-Sensitive Self-Training for Non-Decomposable Metrics" at [Microsoft-Wadhwani-Penn Workshop](https://trust-ai-workshop.github.io/) on Trustworthy AI.

January, 2023
Selected for participation in Research Week With Google.

December, 2022
Talk on our work "Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data" at ACML 2022 workshop on [Weakly Supervised Learning](https://wsl-workshop.github.io/acml22.html). ([Slides](https://rangwani-harsh.github.io/Saddle-LongTail-NeurIPS-ACML-Talk.pdf))

October, 2022
Recieved travel grants from Pratiksha Trust and ACM/IARCS for attending ECCV'22.

September, 2022
Papers on "SAM for escaping saddle point for long-tailed learning" and "Cost-Sensitive Self-Training for Non-Decomposable Metrics" got accepted at NeurIPS'22.

August, 2022
Our work on "A Closer Look at Smoothness in Domain Adversarial Training" got accepted at OOD-CV Workshop for **spotlight presentation**.

July, 2022
Papers on "Group Spectral Regularization for GANs" and "Hierarchial Semantic Regularization for StyleGANs" got accepted at ECCV'22.