
Abhinav Shrivastava
@abhi2610
Followers
1K
Following
3K
Media
6
Statuses
438
Associate Professor, University of Maryland, College Park
Washington, DC
Joined May 2008
Speed up your diffusion models—with evolutionary caching!. Proud to share @AnirudAgg’s first paper (mentored by Matt Gwilliam)! ECAD uses evolutionary search to find Pareto-optimal schedules that speed up diffusion & boost quality—no retraining or tuning. Read the full 🧵below.
🧵 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. 🔗 #MachineLearning
0
3
28
RT @danh_trang: prompt engineering leveling up my parenting skills…. me: why don’t you want to eat?.kiddo (3 y/o): because i’m not hungry.m….
0
1
0
RT @mlevy1221: If you’re at #ICRA2025 come see us present P3-PO in the Representation Learning I session. Room 311 at 4:40.
0
1
0
RT @jbhuang0604: Brought to you by the amazing @umdcs students Seungjae Lee @JayLEE_0301, Daniel Ekpo (@daniekpo7), Haowen Liu, and my coll….
0
1
0
RT @jbhuang0604: Exploration is key for robots to generalize, especially in open-ended environments with vague goals and sparse rewards.….
0
24
0
RT @nikunj: I feel a little bit for the @GoogleDeepMind team. You build a world changing model and everyone is posting Ghibli-fied pictu….
0
216
0
RT @adityaag: Success isn't automatic. You always have to be "refounding". Few know this better than @satyanadella. I'm excited to share o….
0
23
0
RT @tomgoldsteincs: New open source reasoning model!. Huginn-3.5B reasons implicitly in latent space 🧠. Unlike O1 and R1, latent reasoning….
0
273
0
RT @adityaag: Over the last 11 years at @microsoft @satyanadella has had one of the greatest runs of any CEO, ever. I'm thrilled to announ….
0
40
0
RT @_sakshams_: 📢 Excited to announce LARP has been accepted to #ICLR2025 ! 🇸🇬 .Code and models are publicly available. Project page: http….
0
2
0
RT @coatol5: This past week has been an amazing blur. Last Wednesday at @southpkcommons' demo faire @bicro_ and I had the opportunity to pr….
0
3
0
RT @umdcs: 📢 Assistant Professor Ruohan Gao (@RuohanGao1) is joining @umdcs! His research centers on computer vision and machine learning,….
0
5
0
RT @_TianyeLi: @sharathgirish97 @amritamaz @abhi2610 @davedotluebke @shalinidemello @nvidia @NVIDIAAI @UofMaryland @amritamaz will present….
0
2
0
RT @_TianyeLi: 👑 QUEEN captures high-quality free-viewpoint videos and reduces the model size to 0.7 MB / frame while training in under 5 s….
0
2
0