8 papers
Structural Plasticity as Active Inference: A Biologically-Inspired Architecture for Homeostatic Control
Brennen A. Hill
Traditional neural networks, while powerful, rely on biologically implausible learning mechanisms such as global backpropagation. This paper introduces the Structurally Adaptive Pr…
HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning
Brennen Hill
The adaptation of large language models (LLMs) to specialized reasoning tasks is fundamentally constrained by computational resources. Parameter-Efficient Fine-Tuning (PEFT) method…
Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs
Brennen Hill, Surendra Parla, Venkata Abhijeeth Balabhadruni +2
The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and c…
Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents
Brennen Hill
Recent advances in agent development have focused on scaling model size and raw interaction data, mirroring successes in large language models. However, for complex, long-horizon m…
The Physical Basis of Prediction: World Model Formation in Neural Organoids via an LLM-Generated Curriculum
Brennen Hill
The capacity of an embodied agent to understand, predict, and interact with its environment is fundamentally contingent on an internal world model. This paper introduces a novel fr…
Co-Evolving Complexity: An Adversarial Framework for Automatic MARL Curricula
Brennen Hill
The advancement of general-purpose intelligent agents is intrinsically linked to the environments in which they are trained. While scaling models and datasets has yielded remarkabl…