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 about 2 hours ago
RecGPT-V3 Technical Report upvoted a paper about 3 hours ago
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources upvoted a paper about 4 hours ago
Agon: Competitive Cross-Model RL with Implicit Rival Grading of ReasoningOrganizations
