533 citations · 584 across the 21 of their papers we have counts for
23 papers
SMat-Attention: Structured Long-Context Sequence Modeling
Emile Anand, Abdullah Ateyeh, Archer Wang +1
Long-context sequence models face a fundamental tradeoff: softmax attention uses flexible token-level interactions at quadratic cost, whereas linear attention obtains linear-time t…
Fast, Accurate, and Scalable Fermionic Neural Networks via Translation Equivariance
David D. Dai, Yen-Ting Lin, Marin Soljačić
We demonstrate that designing a neural quantum state to be an exact eigenstate of the Hamiltonian's symmetries significantly improves both training speed and final variational ener…
Can AI Follow In Einstein's Footsteps?
Michael Shalyt, Nathan Regev, Marin Soljačić +1
AI is accelerating physics discovery, but perhaps away from Einstein-level theory building. To understand this gap, we must recognize a striking trend: while being very successful,…
End-to-End Optimization of Incoherent Imaging for Classification Under Detector-Limited Readout
Archer Wang, Joshua Chen, Sachin Vaidya +1
End-to-end co-optimization of optical front-ends (e.g. metasurfaces) and neural network back-ends has been widely applied to imaging tasks, yet a formalism characterizing when and…
Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
Zixin Jessie Chen, Zhuo Chen, Archer Wang +4
Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as r…
TraversalBench: Challenging Paths to Follow for Vision Language Models
Clara Petrova, Zhuo Chen, Marin Soljačić
Vision-language models (VLMs) perform strongly on multimodal benchmarks, but their ability to follow complex visual paths remains under-tested. We introduce TraversalBench, a contr…
A Framework for Closed-Loop Robotic Assembly, Alignment and Self-Recovery of Precision Optical Systems
Seou Choi, Sachin Vaidya, Caio Silva +4
Robotic automation has transformed scientific workflows in domains such as chemistry and materials science, yet free-space optics, which is a high precision domain, remains largely…
Unsupervised Decomposition and Recombination with Discriminator-Driven Diffusion Models
Archer Wang, Emile Anand, Yilun Du +1
Decomposing complex data into factorized representations can reveal reusable components and enable synthesizing new samples via component recombination. We investigate this in the…
Active learning for photonic crystals
Ryan Lopez, Charlotte Loh, Rumen Dangovski +1
Active learning for photonic crystals explores the integration of analytic approximate Bayesian last layer neural networks (LL-BNNs) with uncertainty-driven sample selection to acc…
Learning simple heuristic rules for classifying materials based on chemical composition
Andrew Ma, Marin Soljačić
In the past decade, there has been a significant interest in the use of machine learning approaches in materials science research. Conventional deep learning approaches that rely o…
LM: Mutual Information Scaling Law for Long-Context Language Modeling
Zhuo Chen, Oriol Mayné i Comas, Zhuotao Jin +2
We present a universal theoretical framework for understanding long-context language modeling based on a bipartite mutual information scaling law that we rigorously verify in natur…
Predicting band gap from chemical composition: A simple learned model for a material property with atypical statistics
Andrew Ma, Owen Dugan, Marin Soljačić
In solid-state materials science, substantial efforts have been devoted to the calculation and modeling of the electronic band gap. While a wide range of ab initio methods and mach…
OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step
Owen Dugan, Donato Manuel Jimenez Beneto, Charlotte Loh +3
Despite significant advancements in text generation and reasoning, Large Language Models (LLMs) still face challenges in accurately performing complex arithmetic operations. Langua…
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
Zhuo Chen, Rumen Dangovski, Charlotte Loh +3
We propose Quantum-informed Tensor Adaptation (QuanTA), a novel, easy-to-implement, fine-tuning method with no inference overhead for large-scale pre-trained language models. By le…
KAN: Kolmogorov-Arnold Networks
Ziming Liu, Yixuan Wang, Sachin Vaidya +5
Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have…
TENG: Time-Evolving Natural Gradient for Solving PDEs With Deep Neural Nets Toward Machine Precision
Zhuo Chen, Jacob McCarran, Esteban Vizcaino +2
Partial differential equations (PDEs) are instrumental for modeling dynamical systems in science and engineering. The advent of neural networks has initiated a significant shift in…
Photonic probabilistic machine learning using quantum vacuum noise
Seou Choi, Yannick Salamin, Charles Roques-Carmes +7
Probabilistic machine learning utilizes controllable sources of randomness to encode uncertainty and enable statistical modeling. Harnessing the pure randomness of quantum vacuum n…
Multimodal Foundation Models for Material Property Prediction and Discovery
Viggo Moro, Charlotte Loh, Rumen Dangovski +7
Artificial intelligence is transforming computational materials science, improving the prediction of material properties, and accelerating the discovery of novel materials. Recentl…
ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation
Zhuo Chen, Laker Newhouse, Eddie Chen +2
Quantum many-body physics simulation has important impacts on understanding fundamental science and has applications to quantum materials design and quantum technology. However, du…
Topological electromagnetic waves in dispersive and lossy plasma crystals
Chen Qian, Yue Jiang, Jicheng Jin +4
Topological photonic crystals, which offer topologically protected and back-scattering-immune transport channels, have recently gained significant attention for both scientific and…
Model Stitching: Looking For Functional Similarity Between Representations
Adriano Hernandez, Rumen Dangovski, Peter Y. Lu +1
Model stitching (Lenc & Vedaldi 2015) is a compelling methodology to compare different neural network representations, because it allows us to measure to what degree they may be in…
Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries
Charlotte Loh, Seungwook Han, Shivchander Sudalairaj +5
Deep ensembles (DE) have been successful in improving model performance by learning diverse members via the stochasticity of random initialization. While recent works have attempte…
QuACK: Accelerating Gradient-Based Quantum Optimization with Koopman Operator Learning
Di Luo, Jiayu Shen, Rumen Dangovski +1
Quantum optimization, a key application of quantum computing, has traditionally been stymied by the linearly increasing complexity of gradient calculations with an increasing numbe…