🔬 Applied Scientist & ML Specialist938 Problems · 127 Topics🌐 Linked to Tech Vault
TalentMe Science Depth: Universal Applied Science & ML Depth Problem Bank
938 end-to-end science depth, system design, transition bridge & BQ problems covering derivations, production trade-offs, pitfalls, and follow-ups.
🎯
Science Depth Mastery Tracker
0% MasteredLocally synced in your browser. Track, review, and master all 938 scientific & design topics.
Mastered: 0
Reviewing: 0
Unstarted: 136
🌐
Linked to TalentMe Tech Vault & MindmapsM5: NLP & Large Language Models
All 938 questions are directly linked to TalentMe's Tech Vault guides, atomic cards, and interactive mindmaps.
Found 24 in-depth questions
M5-001NLP & Large Language ModelsTokenization (BPE / WordPiece / Unigram)
EasyBPE Algorithm and Why It Is Widely Used in LLMs
⚡ One-Sentence Answer
M5-002NLP & Large Language ModelsTokenization (BPE / WordPiece / Unigram)
EasyComparison of BPE, WordPiece, and Unigram Tokenization
⚡ One-Sentence Answer
M5-003NLP & Large Language ModelsTokenization (BPE / WordPiece / Unigram)
MediumVocabulary Size Trade-offs in LLMs
⚡ One-Sentence Answer
M5-004NLP & Large Language ModelsTokenization (BPE / WordPiece / Unigram)
MediumImpact of Tokenizer on Downstream Metrics and Why Cross-Model Perplexity (PPL) Comparisons Are Unfair
⚡ One-Sentence Answer
M5-005NLP & Large Language ModelsTokenization (BPE / WordPiece / Unigram)
HardTokenizer Challenges in Multilingual and Code Domains
⚡ One-Sentence Answer
M5-006NLP & Large Language ModelsTokenization (BPE / WordPiece / Unigram)
HardVocabulary Expansion Techniques and Considerations
⚡ One-Sentence Answer
M5-007NLP & Large Language ModelsPretraining Objectives & Data Curation
EasyCausal Language Modeling (CLM) vs. Masked Language Modeling (MLM)
⚡ One-Sentence Answer
M5-008NLP & Large Language ModelsPretraining Objectives & Data Curation
EasyImpact of Data Quality and Mixture Ratios on Pre-training
⚡ One-Sentence Answer
M5-009NLP & Large Language ModelsPretraining Objectives & Data Curation
MediumData Deduplication Methods and Why It Matters in LLM Pre-training
⚡ One-Sentence Answer
M5-010NLP & Large Language ModelsPretraining Objectives & Data Curation
MediumCurriculum Learning and Data Ordering in LLM Pre-training
⚡ One-Sentence Answer
M5-011NLP & Large Language ModelsPretraining Objectives & Data Curation
HardSynthetic Data in Pre-training and Post-Training: Roles and Risks
⚡ One-Sentence Answer
M5-012NLP & Large Language ModelsPretraining Objectives & Data Curation
HardData Contamination and Its Impact on Benchmark Reliability
⚡ One-Sentence Answer
M5-013NLP & Large Language ModelsPretraining Objectives & Data Curation
MediumPre-training Domain Mixtures and the Role of the Annealing Phase
⚡ One-Sentence Answer
M5-014NLP & Large Language ModelsScaling Laws & Compute Allocation
EasyCore Conclusions of Kaplan vs. Chinchilla Scaling Laws
⚡ One-Sentence Answer
M5-015NLP & Large Language ModelsScaling Laws & Compute Allocation
EasyWhy Inference Costs Alter Compute-Optimal Scaling Choices
⚡ One-Sentence Answer
M5-016NLP & Large Language ModelsScaling Laws & Compute Allocation
MediumEmergent Abilities in Large Language Models and the Metric Discontinuity Debate
⚡ One-Sentence Answer
M5-017NLP & Large Language ModelsScaling Laws & Compute Allocation
MediumScaling Strategies Under Data-Constrained Regimes
⚡ One-Sentence Answer
M5-018NLP & Large Language ModelsScaling Laws & Compute Allocation
HardGuiding Hyperparameter and Architecture Choices via Scaling Laws
⚡ One-Sentence Answer
M5-019NLP & Large Language ModelsScaling Laws & Compute Allocation
HardPost-Training Scaling (RL and Test-Time Compute) vs. Pre-Training Scaling
⚡ One-Sentence Answer
M5-020NLP & Large Language ModelsInstruction Tuning & Supervised Fine-Tuning
EasySupervised Fine-Tuning (SFT) Objectives and Data Construction Principles
⚡ One-Sentence Answer
M5-021NLP & Large Language ModelsInstruction Tuning & Supervised Fine-Tuning
EasyLoss Masking and Sequence Packing in SFT Training
⚡ One-Sentence Answer
M5-022NLP & Large Language ModelsInstruction Tuning & Supervised Fine-Tuning
MediumCatastrophic Forgetting in SFT and Mitigation Strategies
⚡ One-Sentence Answer
M5-023NLP & Large Language ModelsInstruction Tuning & Supervised Fine-Tuning
MediumChain-of-Thought (CoT) Distillation: Benefits and Hallucination Risks
⚡ One-Sentence Answer
M5-024NLP & Large Language ModelsInstruction Tuning & Supervised Fine-Tuning
HardSFT Data Mixture and Multi-Task Balancing
⚡ One-Sentence Answer