vrm
- Karma
- 58
- Created
- 9 years ago
About
CTO @ TensorZero, previously worked on RL, fusion, and robotics at Carnegie Mellon, data & analytics at KKR, and robot learning at Stanfordvirajm.com
Recent Submissions
- 1. ▲ Ask HN: What do you recommend for test observability?
- 2. ▲ Improving Cursor Tab with RL (cursor.com)
- 3. ▲ Automatically Evaluating AI Coding Assistants with Each Git Commit (tensorzero.com)
- 4. ▲ Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Tree Search (arxiv.org)
- 5. ▲ Think of LLM Applications as POMDPs – Not Agents (tensorzero.com)
- 6. ▲ An experimental design perspective on model-based reinforcement learning (blog.ml.cmu.edu)
- 7. ▲ Spinlaunch with Basic Physics [pdf] (virajrmehta.com)
- 8. ▲ Data breach allowed Stanford applicants to view others’ information (stanforddaily.com)
- 9. ▲ Simple Random Search provides a competitive approach to RL (arxiv.org)