Hugging Face's logo
Dipankar Sarkar's picture
🏗️ Building on HF

Dipankar Sarkar PRO

dipankarsarkar
4 794 165
issdandavis's profile picture TravisMuhlestein's profile picture gouc's profile picture
·
https://www.dipankar.cc

AI & ML interests

Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.

Recent Activity

liked a model 40 minutes ago
Unseen1980/daedalus-150m-instruct
upvoted a paper 40 minutes ago
Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference
repliedto appvoid's post 41 minutes ago
Byte-level state-space models. That sounded pretty scary for a scientist decades ago. Now we have: 1. Knowledge that deeper layers train smoothly. 2. Knowledge that Transformers work but is quadratic on sequence length. 3. Knowledge that SSMs work even better. Numerically unstable sometimes. 4. Speculative-decoding. 5. Open high-quality data. 6. Knowledge that KD works. It slowly feels like is no longer a bad idea.
View all activity

Organizations

Skelf Research's profile picture Neul Labs's profile picture Cognisoc's profile picture Incredlabs's profile picture