Tags

Transformer (8)

• Transformer Notes (VIII): Frontier Applications 2025-12-20
• Transformer Notes (VII): Deployment Optimization 2025-12-20
• Transformer Notes (VI): Evaluation and Benchmarks 2025-12-20
• Transformer Notes (V): Training Techniques 2025-12-20
• Transformer Notes (IV): Mixture of Experts Architecture 2025-12-20
• Transformer Notes (III): Attention Mechanisms 2025-12-20
• Transformer Notes (II): Core Components 2025-12-20
• Transformer Notes (I): Fundamentals 2025-12-20

RLHF (4)

• RL Notes (6): LLM Alignment (Part 2) 2025-12-19
• RL Notes (5): LLM Alignment (Part 1) 2025-12-19
• LLM-RL Training Stability: Root Cause Analysis and Solutions 2025-12-19
• Why is LoRA Effective in RL Fine-tuning? An Information Bandwidth Perspective 2025-12-19

Inference (3)

• Speculative Decoding: A Complete Guide to Principles, Methods, and Speedup Analysis 2026-01-05
• Nondeterminism in LLM Inference: Root Cause Analysis and Batch Invariance Solutions 2025-12-24
• Transformer Notes (VII): Deployment Optimization 2025-12-20

Reasoning (2)

• Train Long, Think Short: A Survey on LLM Reasoning Length Control 2025-12-31
• Transformer Notes (VIII): Frontier Applications 2025-12-20

PPO (2)

• RL Notes (3): Policy-Based RL 2025-12-19
• LLM-RL Training Stability: Root Cause Analysis and Solutions 2025-12-19

LLM (2)

• Speculative Decoding: A Complete Guide to Principles, Methods, and Speedup Analysis 2026-01-05
• Nondeterminism in LLM Inference: Root Cause Analysis and Batch Invariance Solutions 2025-12-24

GRPO (2)

• Train Long, Think Short: A Survey on LLM Reasoning Length Control 2025-12-31
• Entropy Control in LLM-RL: A Systematic Survey from Entropy Collapse to Exploration 2025-12-23

Efficiency (2)

• Speculative Decoding: A Complete Guide to Principles, Methods, and Speedup Analysis 2026-01-05
• Train Long, Think Short: A Survey on LLM Reasoning Length Control 2025-12-31

Alignment (2)

• RL Notes (6): LLM Alignment (Part 2) 2025-12-19
• RL Notes (5): LLM Alignment (Part 1) 2025-12-19

Training (1)

• Transformer Notes (V): Training Techniques 2025-12-20

Speculative Decoding (1)

• Speculative Decoding: A Complete Guide to Principles, Methods, and Speedup Analysis 2026-01-05

Reproducibility (1)

• Nondeterminism in LLM Inference: Root Cause Analysis and Batch Invariance Solutions 2025-12-24

RLVR (1)

• Entropy Control in LLM-RL: A Systematic Survey from Entropy Collapse to Exploration 2025-12-23

Negative Samples (1)

• Entropy Control in LLM-RL: A Systematic Survey from Entropy Collapse to Exploration 2025-12-23

Multimodal (1)

• Transformer Notes (VIII): Frontier Applications 2025-12-20

MoE (1)

• Transformer Notes (IV): Mixture of Experts Architecture 2025-12-20

MCTS (1)

• RL Notes (4): Model-Based Methods & MARL 2025-12-19

Evaluation (1)

• Transformer Notes (VI): Evaluation and Benchmarks 2025-12-20

Entropy (1)

• Entropy Control in LLM-RL: A Systematic Survey from Entropy Collapse to Exploration 2025-12-23

Determinism (1)

• Nondeterminism in LLM Inference: Root Cause Analysis and Batch Invariance Solutions 2025-12-24

DQN (1)

• RL Notes (2): Value-Based RL 2025-12-19

CUDA (1)

• Nondeterminism in LLM Inference: Root Cause Analysis and Batch Invariance Solutions 2025-12-24

Batch Invariance (1)

• Nondeterminism in LLM Inference: Root Cause Analysis and Batch Invariance Solutions 2025-12-24

Attention (1)

• Transformer Notes (III): Attention Mechanisms 2025-12-20

AlphaZero (1)

• RL Notes (4): Model-Based Methods & MARL 2025-12-19

RL (10)

• Train Long, Think Short: A Survey on LLM Reasoning Length Control 2025-12-31
• Entropy Control in LLM-RL: A Systematic Survey from Entropy Collapse to Exploration 2025-12-23
• RL Notes (6): LLM Alignment (Part 2) 2025-12-19
• RL Notes (5): LLM Alignment (Part 1) 2025-12-19
• RL Notes (4): Model-Based Methods & MARL 2025-12-19
• RL Notes (3): Policy-Based RL 2025-12-19
• RL Notes (2): Value-Based RL 2025-12-19
• RL Notes (1): Fundamentals 2025-12-19
• LLM-RL Training Stability: Root Cause Analysis and Solutions 2025-12-19
• Why is LoRA Effective in RL Fine-tuning? An Information Bandwidth Perspective 2025-12-19