Test Time Compute

concepts · 1 notes linked

Related: Shanghai AI Laboratory · Deepseek R1 · GPT-4O · Large Language Models · Reinforcement Learning · Chain Of Thought

Notes

• Can 1B LLM Surpass 405B LLM? Optimizing Computation for Small LLMs to Outperform Larger Models — Test-time scaling lets small LLMs outperform much larger models