Ani Aggarwal

@AnirudAgg

Vision AI researcher | Applying for 2026 PhD | CS + Math from UMD | I like vision

San Francisco, CA

aniaggarwal.github.io

Joined July 2014

Following

Followers

Replies Media

Pinned
Ani Aggarwal
@AnirudAgg
Jun 19, 2025
🧵 Your DiT, faster Introducing ECAD: we reframe diffusion model caching as multi-objective optimization and evolve Pareto-optimal schedules via a genetic algorithm—achieving 4.47 FID gain at 2.58× speedup, with no retraining or tuning. 🔗 aniaggarwal.github.io/ecad #MachineLearning
Ani Aggarwal
@AnirudAgg
Jun 6
Super excited to present our work on efficient upsampling of ViT, VAE, and any other latent features!
Matthew Walmer
@MatthewWalmer
Jun 6
We’re looking forward to presenting UPLiFT at #CVPR2026! Efficiently extract pixel-dense features from pretrained backbones like DINOv3. We’ll be at the final poster session on Sunday (6/7) from 3:30-5:30pm at Poster 474, so please come by! Website: cs.umd.edu/~mwalmer/uplif…
Ani Aggarwal
@AnirudAgg
Feb 23
🦖 Pixel 🦕 dense 🦖 DINO 🦕 features and image super resolution 🖼️!! #CVPR2026
Matthew Walmer
@MatthewWalmer
Feb 23
Excited to announce that UPLiFT has been accepted to #CVPR2026! You can also try out UPLiFT right now to extract pixel-dense DINOv3 features with our pretrained models linked below! Code: github.com/mwalmer-umd/UP… Paper: arxiv.org/abs/2601.17950 Website: cs.umd.edu/~mwalmer/uplif…
Ani Aggarwal
@AnirudAgg
Jan 28
🎉 Thrilled to share that my first research paper has been accepted to #ICLR2026! 🎉 I’ll be attending in person in Rio and would love to connect with others! 🇧🇷
Ani Aggarwal
@AnirudAgg
Jun 19, 2025
🧵 Your DiT, faster Introducing ECAD: we reframe diffusion model caching as multi-objective optimization and evolve Pareto-optimal schedules via a genetic algorithm—achieving 4.47 FID gain at 2.58× speedup, with no retraining or tuning. 🔗 aniaggarwal.github.io/ecad #MachineLearning
Ani Aggarwal
@AnirudAgg
Jan 28
Super excited to announce our paper! Upsample any latents (DINO, VAE, etc.) in linear time (compared to quadratic cross attention). Our models are all available on Hugging Face and Torch Hub with just one line of code! (please star the GitHub repo 🥺) huggingface.co/UPLiFT-upsampl…
Matthew Walmer
@MatthewWalmer
Jan 27
We’re excited to announce UPLiFT, our lightweight, pixel-dense feature upsampler. UPLiFT boosts feature density, preserves semantics, and has better efficiency scaling than recent SOTA methods. See all links in the thread below. Coauthors: @_sakshams_ @AnirudAgg @abhi2610 🧵[1/6]