Blog

a look inside my head

Literature Review: Persona Vectors: Monitoring and Controlling Character Traits in Language Models

3 min read · October 21, 2025

2025 · Activation Steering Representation Learning Alignment AI Robustness LLM · research
Literature Review: Fresh in Memory: Training-Order Recency is Linearly Encoded in Language Model Activations

3 min read · October 21, 2025

2025 · Representation Learning Interpretability LLM · research
Literature Review: REFRAG — Rethinking RAG-Based Decoding

4 min read · October 21, 2025

2025 · RAG LLM Representation Learning · research
Literature Review: Shutdown Resistance in Large Language Models

3 min read · October 18, 2025

2025 · Decepton AI Alignment Trustworthy AI LLM · research
Literature Review: Uni-LoRA — One Vector is All You Need

3 min read · October 18, 2025

2025 · Parameter Efficient Fine-Tuning LoRA PEFT LLM Adaptation Representation Learning · research