1 citations · 1 across the 5 of their papers we have counts for
5 papers
Nanbeige4.2-3B on Apple Silicon: Fixing Deployment Bugs and Decreasing Looped Transformer Memory Overhead
John T. Halloran
Nanbeige4.2-3B is a 3B-parameter agentic model built around a Looped Transformer (LT) that reuses one stack of layers for a second forward pass, adding effective depth without addi…
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
John T. Halloran, Noopur S. Bhatt
Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defe…
Training-Free Refusal of MCP Exploits via Retrieval-Augmented Generation
John T. Halloran
The model context protocol (MCP) has been widely adopted as an open standard enabling the seamless integration of generative AI agents. However, while LLM guardrails have significa…
Understanding the Effects of Safety Unalignment on Large Language Models
John T. Halloran
Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment…
Mamba State-Space Models Are Lyapunov-Stable Learners
John T. Halloran, Manbir Gulati, Paul F. Roysdon
Mamba state-space models (SSMs) have recently outperformed state-of-the-art (SOTA) Transformer large language models (LLMs) in various tasks and been widely adapted. However, a maj…