Interested in AI & startups.
Joined August 2019
- Tweets8
- Following230
- Followers79
- Likes3.2K
Ishaan Javali retweeted
Happy to share that our work “1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities” was accepted to #NeurIPS2025 as an Oral Presentation!
Grateful to my amazing collaborators @IJ_Apps @m_bortkiewicz @ben_eysenbach 🥳
1/ While most RL methods use shallow MLPs (~2–5 layers), we show that scaling up to 1000-layers for contrastive RL (CRL) can significantly boost performance, ranging from doubling performance to 50x on a diverse suite of robotic tasks.
Webpage+Paper+Code: wang-kevin3290.github.io/sca…
Check out this new paper by @kevin_wang3290, myself, @m_bortkiewicz, @tomasztrzcinsk1, and
@ben_eysenbach!
We show a method for scaling Contrastive RL, leading to significant performance improvements.
1/ While most RL methods use shallow MLPs (~2–5 layers), we show that scaling up to 1000-layers for contrastive RL (CRL) can significantly boost performance, ranging from doubling performance to 50x on a diverse suite of robotic tasks.
Webpage+Paper+Code: wang-kevin3290.github.io/sca…
Ishaan Javali retweeted
1/ While most RL methods use shallow MLPs (~2–5 layers), we show that scaling up to 1000-layers for contrastive RL (CRL) can significantly boost performance, ranging from doubling performance to 50x on a diverse suite of robotic tasks.
Webpage+Paper+Code: wang-kevin3290.github.io/sca…
Ishaan Javali retweeted
We (@RohitDilip8 @AlexBeatson @IJ_Apps + I) won 2nd place & the @trychroma prize at the @scale_AI GenAI hackathon w/ Protex: the protein therapeutics universe is immense, we focus the search space w/ @OpenAI & @Meta ESM embeddings of InterPro, Chroma vector db, InfoNCE & @vercel
Just applied to @theresidency!
I'm excited about meeting fellow builders and working on innovative ideas near the Bay Area.
