activity
20242026
collaborators

6 papers

cs.NE2026

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…

cs.CL2025

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…

cs.LG2025

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…

cs.CL2025

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…

cs.CL2024

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…

cs.CL2024

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…