Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems
Journal ref AI for Science workshop at ICML 2024
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Improving Performance Prediction of Electrolyte Formulations with Transformer-based Molecular Representation Model
Comments Accepted in ML4LMS Workshop at ICML 2024
VarteX: Enhancing Weather Forecast through Distributed Variable Representation
Comments ICML 2024, Workshop on Machine Learning for Earth System Modeling
SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models
Comments To appear at ICML 2024
Efficient World Models with Context-Aware Tokenization
Comments ICML 2024
Compositional Image Decomposition with Diffusion Models
Comments ICML 2024, Webpage: https://energy-based-model.github.io/decomp-diffusion
A Fast Learning-Based Surrogate of Electrical Machines using a Reduced Basis
Journal ref AI for Science workshop at ICML (International Conference on Machine Learning ), Jul 2024, Viena, Austria
From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions
Comments 39 pages, 33 figures. ICML 2024 conference paper
Learning Modality Knowledge Alignment for Cross-Modality Transfer
Comments ICML 2024
Unified Uncertainties: Combining Input, Data and Model Uncertainty into a Single Formulation
Comments 4 pages, 3 figures, with appendix. LatinX in AI Research Workshop @ ICML 2024 Camera Ready
Learning to Remove Cuts in Integer Linear Programming
Comments International Conference on Machine Learning
SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching
Comments ICML 2024
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
Comments Accepted at ICML 2024; v2 updated to camera-ready version; Code available at https://github.com/MAGICS-LAB/OutEffHop; Models are on Hugging Face: https://huggingface.co/collections/magicslabnu/outeffhop-6610fcede8d2cda23009a98f
Thermometer: Towards Universal Calibration for Large Language Models
Comments Camera ready version for ICML 2024
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
Comments ICML 2024. Code is available at https://github.com/facebookresearch/MobileLLM
PGODE: Towards High-quality System Dynamics Modeling
Comments Accepted by ICML 2024
Expand-and-Cluster: Parameter Recovery of Neural Networks
Comments Accepted paper at ICML '24
Towards Compositionality in Concept Learning
Comments Accepted at ICML 2024. 26 pages, 10 figures
Graph Neural Networks for Emulation of Finite-Element Ice Dynamics in Greenland and Antarctic Ice Sheets
Comments 6 pages, 2 figures, submitted to the ICML 2024 Workshop on Machine Learning for Earth System Modeling
Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
Comments Published in ICML 2024
Are Protein Language Models Compute Optimal?
Comments Proceedings of the ICML 2024 Workshop on Accessible and Efficient Foundation Models for Biological Discovery, Vienna, Austria. 2024
Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models
Comments AI4Math workshop, ICML 2024
Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process
Comments Accepted to ICML 2024
Listening to the Noise: Blind Denoising with Gibbs Diffusion
Comments 12+9 pages, 7+5 figures, 1+1 tables; accepted to 2024 International Conference on Machine Learning; code: https://github.com/rubenohana/Gibbs-Diffusion
Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
Comments ICML 2024
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Comments Published at ICML 2024. Code for iDEM is available at https://github.com/jarridrb/dem
Single-Model Attribution of Generative Models Through Final-Layer Inversion
Comments Accepted at the Forty-first International Conference on Machine Learning [ICML2024]
Understanding and Diagnosing Deep Reinforcement Learning
Comments Published in ICML 2024
REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates
Comments Accepted paper at International Confrence on Machine Learning (ICML 2024). Visit our website: https://arshiaafzal.github.io/REST/
Scoreformer: A Surrogate Model For Large-Scale Prediction of Docking Scores
Comments Accepted at the 1st Machine Learning for Life and Material Sciences Workshop at ICML 2024
