6 papers
Recursive Harness Self-Improvement
Hyunin Lee, Jinglue Xu, Jeffrey Seely +3
Under model--harness co-evolution, harnesses are not merely inference-time scaffolds but data-generating components whose execution traces can shape future foundation models. This…
Augmented Lagrangian Predictive Coding
Jeffrey Seely, Julian Gould
Predictive coding (PC) is a local-learning alternative to backpropagation (BP), training deep networks via local energy-minimization dynamics rather than a global backward pass. We…
Learning Multi-Agent Coordination via Sheaf-ADMM
Jeffrey Seely, Bartłomiej Cupiał, Llion Jones
We present a differentiable optimization framework for multi-agent coordination. An input is decomposed into overlapping local views, each processed by an agent that solves a conve…
Sheaf Cohomology of Linear Predictive Coding Networks
Jeffrey Seely
Predictive coding (PC) replaces global backpropagation with local optimization over weights and activations. We show that linear PC networks admit a natural formulation as cellular…
Sudoku-Bench: Evaluating creative reasoning with Sudoku variants
Jeffrey Seely, Yuki Imajuku, Tianyu Zhao +2
Existing reasoning benchmarks for large language models (LLMs) frequently fail to capture authentic creativity, often rewarding memorization of previously observed patterns. We add…
Continuous Thought Machines
Luke Darlow, Ciaran Regan, Sebastian Risi +2
Biological brains demonstrate complex neural activity, where neural dynamics are critical to how brains process information. Most artificial neural networks ignore the complexity o…