Posts
14 posts
Multi-head Latent Attention and KV Cache Compression
Embedding Inversion Attacks
MoE Load Balancing and Gradient Interference
LLM Agent Memory Poisoning
LLM Jailbreaks and Automated Red Teaming
OpenAI o1 and DeepSeek-R1 Reasoning Models
An Overview of Diffusion Language Models
Output Guardrails, Observability, and the Right to Erasure
Egress Gateway Defense
Defenses at the Agent, RAG, and MCP Layers
Input-Side PII Anonymization and Reversible Mapping
How Personal Data Leaks, and What Data Governance Has to Cover
Toolformer
Transformer Architecture and LLM Serving Optimization