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 37 minutes ago
SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use upvoted a paper 38 minutes ago
DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation upvoted a paper 39 minutes ago
AutoMem: Automated Learning of Memory as a Cognitive SkillOrganizations
