Pran-Ker/gpu-mode-trimul
Reinforcement Learning • Updated
Prannay Hebbar
Pran-Ker
AI & ML interests
Post-Training, Agents, Program Synthesis
Recent Activity
authored a paper about 15 hours ago
SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work? authored a paper 9 days ago
SIA: Self Improving AI with Harness & Weight UpdatesOrganizations
None yet