← 🧠 Foundations of LLMs & GenAINEXT IN FOUNDATIONS OF LLMS & GENAITraining Reasoning Models: RLVR, PRM vs ORM→
Core
Inference-Time Compute and Reasoning Models
Inference-time (test-time) compute is the idea that spending more computation at generation, longer chains of thought, sampling multiple attempts, or search, reliably improves answers on hard problems, a scaling axis distinct from making the model bigger. Reasoning models (o1/R1-style) are trained, often via RL on verifiable rewards, to produce long internal reasoning and exploit this. Applied-AI interviews probe it because it changed how hard problems are solved and introduced a real latency/cost trade-off: route easy queries to fast models, reserve reasoning models for genuinely hard ones.
a free account unlocks the core curriculum tier · no card
COURSES COVERING THIS TOPIC
No lesson covers this one directly yet. These teach the surrounding topic from the beginning.
RELATED CONCEPTS
PRACTICE THIS IN REAL QUESTIONS
LLM & GenAI FundamentalsHow are reasoning models (o1/R1-style) trained, and what is test-time compute scaling?→LLM & GenAI FundamentalsWhat are small language models (SLMs) and reasoning models (LRMs), and when do you choose each?→LLM & GenAI FundamentalsWalk through GRPO's implementation: group sampling, advantage normalization, and the failure modes you watch for.→ML Infrastructure & GPUsReasoning models made your traffic decode-heavy: 30k thinking tokens per request. What changes in your serving stack?→LLM & GenAI FundamentalsWhat is RLVR (reinforcement learning with verifiable rewards), and why does it work for reasoning models?→System Design for AI in ProductionSize the GPU fleet for an internal LLM assistant: 2,000 employees, 8K context. How many cards, and should you self-host at all?→
COMPANIES THAT ASSUME THIS