All Tags

23 tags

AI Agents Claude Code Context Engineering Feature Recovery Feature-Learning Fourier-Analysis Fourier-Features Grokking Group-Theory In-Context Learning Influence Functions Interpretability LLM LLM Tools Mechanistic-Interpretability Modular-Addition Reasoning Representation-Theory RLVR Self-Evolution Software Architecture Sparse Autoencoders Transformers
INFUSER: Influence-Guided Self-Evolution Improves Reasoning

INFUSER: Influence-Guided Self-Evolution Improves Reasoning

12 minute read
Neural Networks Provably Learn Group Representations: From Cyclic to Non-Abelian

Neural Networks Provably Learn Group Representations: From Cyclic to Non-Abelian

23 minute read
Inside Claude Code: A Source-Level Architectural Analysis

Inside Claude Code: A Source-Level Architectural Analysis

60 minute read
On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking

On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking

39 minute read
In-Context Linear Regression Demystified

In-Context Linear Regression Demystified

19 minute read
Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders

Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders

15 minute read

© 2025 - 2026 Y-Agent Research Blog