Dipankar Sarkar PRO
dipankarsarkar
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
upvoted a paper 44 minutes ago
PRISM-ฮ: Differential Subspace Steering for Prompt Highlighting in Large Language Models upvoted a paper about 1 hour ago
Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget upvoted a paper about 1 hour ago
Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMsOrganizations
