Ir para o conteúdo

Kanaka Rajan

@kanakarajanphd.bsky.social did:plc:nemx43ymm6toi4fqil4gqbev

Associate Professor at Harvard & Kempner Institute. Applying computational frameworks & machine learning to decode multi-scale neural processes. Marathoner. Rescue dog mom. https://www.rajanlab.com/

No Bluesky desde

Seguidores
3.785
Seguindo
248
Posts
61
Dias nos rankings
0

Resumo

Kanaka Rajan (@kanakarajanphd.bsky.social) é um usuário do Bluesky desde 11 setembro 2023. Tem 3.785 seguidores, segue 248 contas e publicou 61 posts.

Aparições nos rankings

Os melhores dias em que posts desta conta entraram na lista diária do Debya.

Esta conta ainda não apareceu em um ranking diário.

Posts curtidos recentemente

Curtidas públicas da rede Bluesky.

  • Ann Huang@annhuang42.bsky.social

    📄 Paper: arxiv.org/abs/2609.38081 🌐 Page: ann-huang-0.github.io/Hessian-null... 💻 Code: github.com/Ann-Huang-0/hessian-null-space-continuation w/ my awesome team 🌟 @neurostrow.bsky.social, @hansonlu.bsky.social @wtredman.bsky.social, @leokoz8.bsky.social, @kanakarajanphd.bsky.social (12/12)

    Ver post
  • Ann Huang@annhuang42.bsky.social

    Overall, HNC finds diverse mechanisms with matched function around a single trained network. This opens the door to mechanistic analysis of solution spaces, to separating task demands from optimizer bias, and to a principled basis for reward auditing, model merging, editing and fine-tuning (11/12)

    Ver post
  • Ann Huang@annhuang42.bsky.social

    📐 HNC also measures loss-landscape geometry. The Hessian captures the local geometry around one network; the null space walk tracks how it changes along the way. Bigger models have more flat directions, while harder tasks have fewer. The directions HNC follows get stiffer on harder tasks. (10/12)

    Ver post
  • Ann Huang@annhuang42.bsky.social

    HNC can also uncover reward hacking! In the AI Safety Gridworld boat race, we start with policies that correctly follow the track. Preserving proxy reward (+3 for entering an arrow tile clockwise), HNC walks find the known exploit: hopping on and off one tile without net clockwise progress (9/12)

    Ver post
  • Ann Huang@annhuang42.bsky.social

    Applied to RL, HNC searches for different policies while preserving a reward surrogate. An odor-tracking agent shifts from zigzagging across a plume to smoothly following its edge—a distinct navigation strategy at comparable return 🪰(8/12)

    Ver post

Entre para ver mais

Contas que bloqueia

No Bluesky, bloqueios são registros públicos.

Esta conta não bloqueia ninguém.