ATProto Browser

Experimental browser for the Atmosphere

Post

Preprint Alert 🚀 Can we simultaneously learn transformation-invariant and transformation-equivariant representations with self-supervised learning? TL;DR Yes! This is possible via simple predictive learning & architectural inductive biases – without extra loss terms and predictors! 🧵 (1/10)

May 14, 2025, 12:52 PM

Loading post...

{
  "$type": "app.bsky.feed.like",
  "subject": {
    "cid": "bafyreifqqqdzemi5l5ppbcjk4eimy7kjfhoehoszykjlgpkwbpskzs32fu",
    "uri": "at://did:plc:226ezbiltrd56rp2mqyd4fye/app.bsky.feed.post/3lp525hequc2p"
  },
  "createdAt": "2025-05-14T18:29:06.377Z"
}