Sign in

iiinova is part of the Atmosphere — an open, public network where you own your identity.

Sai Prasanna

@saiprasanna.in
2.2K followers 689 following 287 posts

See(k)ing the surreal Causal World Models for Curious Robots @ University of Tübingen/Max Planck Institute for Intelligent Systems 🇩🇪 #reinforcementlearning #robotics #causality #meditation #vegan

PostsRepliesMedia
Sai Prasanna @saiprasanna.in · 10/09/2025
Use Beta NLL for regression when you also predict standard deviations, a simple change to NLL that works reliably better.
140 4
Sai Prasanna @saiprasanna.in · 27/03/2025
Freiburg
110 1
Sai Prasanna @saiprasanna.in · 27/03/2025
Tübingen
110 1
Sai Prasanna @saiprasanna.in · 01/03/2025
Imagine a task where you give a list of edges of a star graph, start and end node, and train a model with a teacher forcing you to predict the list of tokens in the path from the start to the end. (edge 1, edge 2 ...) (start, goal) (start, intermediate1, intermediate 2 .. .goal)
star graph illustrating the clever hans trick
100 1
Sai Prasanna @saiprasanna.in · 18/12/2024
V/LM AR glasses always had this Rick and Morty death crystals vibe to me.
Morty from Rick and morty with a blue death crystal embedded on head and text says "I do as crystal guides"
120 2
Sai Prasanna @saiprasanna.in · 01/12/2024
LMAO 🤣 blueskyroast.com/roast/saipra...
The spice level check contents from the linkThe dating app edition content from the link
010 1
Sai Prasanna @saiprasanna.in · 01/12/2024
Done :D
110 1
Sai Prasanna @saiprasanna.in · 26/11/2024
Arxiv sharing reminder pdf ❌ abs ✅
925141 251
Sai Prasanna @saiprasanna.in · 24/11/2024
Event poster made with so much creativity and love!
Poster saying Klammer Zwei (Name of the band) and crazy jazz creatures
000 0
Sai Prasanna @saiprasanna.in · 24/11/2024
Klammer Zwei: A Local Freiburg Jazz band, killing it 🔥
110 1
Sai Prasanna @saiprasanna.in · 23/11/2024
The cRSSM qualitatively extrapolates to unseen context values in terms of generated image samples. When presented a counterfactual cF, the decoded images from imagined latent states is conditioned on the counterfactual, showing disentanglement of the infered latent states.
120 2
Sai Prasanna @saiprasanna.in · 23/11/2024
We find the cRSSM consistently outperforming the following three settings, hidden: Dreamer trained on multiple contexts without the context being observable. concat: Concatenating context with observations. default: Dreamer trained only on default context.
110 1
Sai Prasanna @saiprasanna.in · 23/11/2024
Towards ZSG we introduce the novel contextual recurrent state-space model (cRSSM). It incorporates context into the world model of DreamerV3, allowing it to infer latent states which are (perhaps) disentangled from the context and also to predict latent dynamics/dream of many worlds.
120 2
Sai Prasanna @saiprasanna.in · 23/11/2024
The context comprises of parameters of a POMDP such as mass/length of a robot. It affects the dynamics and unlike (latent) states such as position/velocity, context does not change during an episode. We aim for ZSG to contexts in- and out-of-distribution.
110 1
Sai Prasanna @saiprasanna.in · 11/01/2024
I haven't used the Semanticscholar pdf reader a lot, but knew it has a highlighter. But now they have AI based auto-highlights!! Seems really rad, I will start using it in my workflow and report back if it's useful as I start to use it!
User interface of semantic scholar's research online paper reader
163 6