Blog

a look inside my head

Literature Review: Beyond the 80/20 Rule – High-Entropy Minority Tokens Drive Effective RL for LLM Reasoning

4 min read · June 14, 2025

2025 · LLM Reinforcement Learning Entropy Reasoning · research
Literature Review: Auto-Patching: Enhancing Multi-Hop Reasoning in Language Models

7 min read · June 14, 2025

2025 · LLM Reasoning Interpretability Mechanistic Interpretability · research
Literature Review: Thinkless: LLM Learns When to Think

4 min read · June 09, 2025

2025 · Reinforcement Learning LLM Chain-of-Thought Policy Optimization · research
Literature Review: DASH: Input-Aware Dynamic Layer Skipping for Efficient LLM Inference with Markov Decision Policies

4 min read · June 09, 2025

2025 · LLM Layer Skipping Model Compression · research
Literature Review: Gaming Tool Preferences in Agentic LLMs

4 min read · June 09, 2025

2025 · Agentic AI LLM Tool Selection Adversarial AI Function Calling AI Security · research