Unlock: Attention Sinks and Retrieval Decay
Why evaluated transformer decoders disproportionately attend to initial tokens, how StreamingLLM uses that pattern for stable streaming inference, and how retrieval accuracy can vary with position inside the context window.
174 Prerequisites0 Mastered0 Working150 Gaps
Prerequisite mastery14%
Recommended probe
Chernoff Bounds is your weakest prerequisite with available questions. You haven't been assessed on this topic yet.
Attention Mechanism TheoryResearch
Not assessed11 questions
Forgetting Transformer (FoX)Research
No quiz
Sign in to track your mastery and see personalized gap analysis.