Search Results for author:
Found 26 papers, 13 papers with code
Collaborative Evolutionary Reinforcement Learning
Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks.
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination
Training policies solely on the team-based reward is often difficult due to its sparsity.
Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
For deep neural network accelerators, memory movement is both energetically expensive and can bound computation.
Safety Aware Reinforcement Learning (SARL)
Since the safe agent effectively abstracts a task-independent notion of safety via its action probabilities, it can be ported to modulate multiple policies solving different tasks within the given environment without further training.
Learning Intrinsic Symbolic Rewards in Reinforcement Learning
We show that the discovered dense rewards are an effective signal for an RL policy to solve the benchmark tasks.
Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization
In this work, we present a flexible and scalable framework for automated mixed-precision quantization that concurrently optimizes task performance, memory compression, and compute savings through multi-objective evolutionary computing.
Multi-Objective GFlowNets
We study the problem of generating diverse candidates in the context of Multi-Objective Optimization.
The Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Science
We present the Open MatSci ML Toolkit: a flexible, self-contained, and scalable Python-based framework to apply deep learning models and methods on scientific data with a specific focus on materials science and the OpenCatalyst Dataset.
PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design
Catalyst materials play a crucial role in the electrochemical reactions involved in numerous industrial processes key to this transition, such as renewable energy storage and electrofuel synthesis.
Group SELFIES: A Robust Fragment-Based Molecular String Representation
We introduce Group SELFIES, a molecular string representation that leverages group tokens to represent functional groups or entire substructures while maintaining chemical robustness guarantees.
Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model
Our findings indicate that the simple similarity metric employed by retrievers is insufficient for retrieving all the necessary statements for reasoning.
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
On downstream tasks, ProtST enables both supervised learning and zero-shot prediction.
FAENet: Frame Averaging Equivariant GNN for Materials Modeling
Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to specific symmetries.
MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling
Our experiments in this low-resource training setting show that language models pretrained on scientific text outperform BERT trained on general text.
Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node.
MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling
We propose MatSci ML, a novel benchmark for modeling MATerials SCIence using Machine Learning (MatSci ML) methods focused on solid-state materials with periodic crystal structures.
EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations
In addition to our thorough evaluation and analysis on eight existing datasets based on the benchmarking literature, we release two new benchmark datasets, propose four new metrics, and three challenging tasks.
Ranked #1 on
Formation Energy
on GeTe
Searching for High-Value Molecules Using Reinforcement Learning and Transformers
Reinforcement learning (RL) over text representations can be effective for finding high-value policies that can search over graphs.
On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions
The use of machine learning for material property prediction and discovery has traditionally centered on graph neural networks that incorporate the geometric configuration of all atoms.
HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science
We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee).
Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance
KREED's top-1 predictions identify the correct 3D structure with >98% accuracy on the QM9 and GEOM datasets when provided with substitution coordinates of all heavy atoms with natural isotopic abundance.
Towards equilibrium molecular conformation generation with GFlowNets
Sampling diverse, thermodynamically feasible molecular conformations plays a crucial role in predicting properties of a molecule.
A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
In these graphs, the geometric attributes transform according to the inherent physical symmetries of 3D atomic systems, including rotations and translations in Euclidean space, as well as node permutations.
Are LLMs Ready for Real-World Materials Discovery?
Given those shortcomings, we outline a framework for developing Materials Science LLMs (MatSci-LLMs) that are grounded in materials science knowledge and hypothesis generation followed by hypothesis testing.
Are large language models superhuman chemists?
Large language models (LLMs) have gained widespread interest due to their ability to process human language and perform tasks on which they have not been explicitly trained.
Optimizing Multiagent Cooperation via Policy Evolution and Shared Experiences
Training policies solely on the team-based reward is often difficult due to its sparsity.
