Search Results for author:
Found 12 papers, 1 papers with code
Revisiting Funnel Transformers for Modern LLM Architectures with Comprehensive Ablations in Training and Inference Configurations
Transformer-based Large Language Models, which suffer from high computational costs, advance so quickly that techniques proposed to streamline earlier iterations are not guaranteed to benefit more modern models.
Factored Agents: Decoupling In-Context Learning and Memorization for Robust Tool Use
In this paper, we propose a novel factored agent architecture designed to overcome the limitations of traditional single-agent systems in agentic AI.
Project MPG: towards a generalized performance benchmark for LLM capabilities
There exists an extremely wide array of LLM benchmarking tasks, whereas oftentimes a single number is the most actionable for decision-making, especially by non-experts.
Time Series Viewmakers for Robust Disruption Prediction
Machine Learning guided data augmentation may support the development of technologies in the physical sciences, such as nuclear fusion tokamaks.
Offline Regularised Reinforcement Learning for Large Language Models Alignment
The canonical element of such datasets is for instance an LLM's response to a user's prompt followed by a user's feedback such as a thumbs-up/down.
Active Reinforcement Learning for Robust Building Control
Reinforcement learning (RL) is a powerful tool for optimal control that has found great success in Atari games, the game of Go, robotic control, and building optimization.
Continuous Convolutional Neural Networks for Disruption Prediction in Nuclear Fusion Plasmas
Grid decarbonization for climate change requires dispatchable carbon-free energy like nuclear fusion.
Machine Learning for Smart and Energy-Efficient Buildings
In this work, we review the ways in which machine learning has been leveraged to make buildings smart and energy-efficient.
Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning
We develop the first application of Personalized Federated Hypernetworks (PFH) to Reinforcement Learning (RL).
Multi-agent Reinforcement Learning
Personalized Federated Learning
+3
Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control
Optimizing prices for energy demand response requires a flexible controller with ability to navigate complex environments.
Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs
Our team is proposing to run a full-scale energy demand response experiment in an office building.
Using Meta Reinforcement Learning to Bridge the Gap between Simulation and Experiment in Energy Demand Response
Our team is proposing to run a full-scale energy demand response experiment in an office building.
