Mark Coates

One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration

A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic

Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling

It Takes Two: Your GRPO Is Secretly DPO

PhyloTextDiff: Text-Based Discrete Diffusion for Generative Phylogenetic Inference

Is the acquisition worth the cost? Surrogate losses for Consistent Two-stage Classifiers

C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning

Hint Marginalization for Improved Reasoning in Large Language Models

When to retrain a machine learning model

When to retrain a machine learning model

SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting