ManySpace
English Giriş yap Kayıt ol

Yapay ZekâUzmanlıkAIML-LM-026

Reasoning Models and Test-Time Compute

Spending more computation at inference, through long reasoning traces, sampling and verification, and RL on verifiable rewards.

Bu konunun henüz Türkçe çevirisi yok, bu yüzden İngilizce gösteriliyor.

Zorluk
5 / 5
Önem
3 / 5
Çalışma süresi
1–2 sa
Çalışma türü
Karma

Neden önemli

The learner can distinguish chain-of-thought prompting, best-of-n sampling with a verifier, and RL-trained reasoning, and state what each scales.

Bu konuya giden rota

Rota AIML-LM-026
What Is a Model? Rational Agents and Task Environments Tasks: Regression, Classification, and Beyond Features and Targets Agent and Environment Classification Framing Linear Regression I: Prediction and Residuals Embeddings Tokens and Tokenization Return and Discounting Policies Scores and Logits Loss and Fitting: Squared Error Similarity in Vector Space Markov Decision Processes Multiclass Scores and Softmax Autoregression Objective Functions and Empirical Risk Query, Key, Value Policy Optimization Gradient Descent in Machine Learning Next-Token Prediction Similarity Scores Stochastic and Mini-batch Optimization Weighted Aggregation Self-Attention Policy Gradients: REINFORCE Context and Conditioning Prompting and In-Context Learning Reasoning Models and Test-Time Compute