arxiv:2606.27396
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 21 minutes ago
Simplified Sparse Attention via Gist Tokens upvoted a paper 21 minutes ago
AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents upvoted a paper 22 minutes ago
SWE-Together: Evaluating Coding Agents in Interactive User SessionsOrganizations
