6 papers
Local Synaptic Rules Can Implement a SIGReg Gradient Without Backpropagation
Martin Andrews
We prove that two canonical local synaptic learning rules, the potentiation arm of spike-timing-dependent plasticity (STDP) and homeostatic plasticity (instantiated here via fl…
Reinforcement Learning for Long-Horizon Multi-Turn Search Agents
Vivek Kalyan, Martin Andrews
Large Language Model (LLM) agents can leverage multiple turns and tools to solve complex tasks, with prompt-based approaches achieving strong performance. This work demonstrates th…
GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization
Martin Andrews, Sam Witteveen
Optimizing GPU kernels for high performance is a complex task, often demanding deep architectural knowledge, extensive profiling, and iterative experimentation. This challenge is a…
A Reasoning-Based Approach to Cryptic Crossword Clue Solving
Martin Andrews, Sam Witteveen
Cryptic crossword clues are challenging language tasks for which new test sets are released daily by major newspapers on a global basis. Each cryptic clue contains both the definit…
Capturing Sparks of Abstraction for the ARC Challenge
Martin Andrews
Excellent progress has been made recently in solving ARC Challenge problems. However, it seems that new techniques may be required to push beyond 60% accuracy. Even commercial Larg…
Proving that Cryptic Crossword Clue Answers are Correct
Martin Andrews, Sam Witteveen
Cryptic crossword clues are challenging cognitive tasks, for which new test sets are released on a daily basis by multiple international newspapers. Each cryptic clue contains both…