Blog

a look inside my head

Literature Review: Adaptive Jailbreaking Strategies Based on the Semantic Understanding Capabilities of Large Language Models

5 min read · June 09, 2025

2025 · LLM Jailbreaking Adversarial AI AI Safety · research
Literature Review: Programming Refusal with Conditional Activation Steering

4 min read · May 28, 2025

2025 · LLM AI Alignment AI Safety Steering · research
Literature Review: Adversarial Search Engine Optimization for Large Language Models

5 min read · May 28, 2025

2025 · adversarial attacks llm search engines seo prompt injection preference manipulation · research
Literature Review: Group Think - Collaborating at Token Level Granularity

4 min read · May 28, 2025

2025 · Multi-Agent Systems Reasoning Token-Level · research
Literature Review: Enhancing Latent Computation in Transformers with Latent Tokens

4 min read · May 28, 2025

2025 · Parameter-Efficient-Tuning Transformers · research