Ani Aggarwal (@AnirudAgg) profile picture

i try to teach computer to see

San Francisco, CA
Joined July 2014
Photo by Ani Aggarwal (@AnirudAgg)Photo by Ani Aggarwal (@AnirudAgg)Photo by Ani Aggarwal (@AnirudAgg)Photo by Ani Aggarwal (@AnirudAgg)Photo by Ani Aggarwal (@AnirudAgg)Photo by Ani Aggarwal (@AnirudAgg)Photo by Ani Aggarwal (@AnirudAgg)Photo by Ani Aggarwal (@AnirudAgg)Photo by Ani Aggarwal (@AnirudAgg)Photo by Ani Aggarwal (@AnirudAgg)
🧵 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
2
1
2
13
2,038
Super excited to present our work on efficient upsampling of ViT, VAE, and any other latent features!
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/uplift/
5
1
18
2,756
🦖 Pixel 🦕 dense 🦖 DINO 🦕 features and image super resolution 🖼️!! #CVPR2026
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/UPLiF… Paper: arxiv.org/abs/2601.17950 Website: cs.umd.edu/~mwalmer/uplift/
1
4
117
🎉 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! 🇧🇷
🧵 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
1
2
80
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-upsamp…
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]
2
2
3
385
Technically more than one line of code 😁
2
31
Ani Aggarwal retweeted
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]
8
51
3
388
19,409
ECAD discovers more intricate caching schedules than heuristics can design. This PixArt-α schedule produced the previous images (using 20 diffusion steps)! Red = cached components, gray = recomputed.
1
1
97
Super grateful to co-authors @abhi2610 & Matthew Gwilliam. Preprint, code, and more results: aniaggarwal.github.io/ecad. Feedback greatly appreciated! 👇
2
95