AIConfPaper
← Search

Anuroop Sriram

13 accepted papers

2025

Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching

Aaron J Havens, Benjamin Kurt Miller, Bing Yan, Carles Domingo-Enrich, Anuroop Sriram, Daniel S. Levine +7
ICML 2025poster

We introduce Adjoint Sampling, a highly scalable and efficient algorithm for learning diffusion processes that sample from unnormalized densities, or energy functions. It is the first on-policy approach that allows significantly more gradient updates than the number of energy evaluations and model s…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

All-atom Diffusion Transformers: Unified generative modelling of molecules and materials

Chaitanya K. Joshi, Xiang Fu, Yi-Lun Liao, Vahe Gharakhanyan, Benjamin Kurt Miller, Anuroop Sriram +1
ICML 2025poster

Diffusion models are the standard toolkit for generative modelling of 3D atomic systems. However, for different types of atomic systems -- such as molecules and materials -- the generative processes are usually highly specific to the target system despite the underlying physics being the same. We in…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective

Neta Shaul, Itai Gat, Marton Havasi, Daniel Severo, Anuroop Sriram, Peter Holderrieth +3
ICLR 2025oral

The design space of discrete-space diffusion or flow generative models are significantly less well-understood than their continuous-space counterparts, with many works focusing only on a simple masked construction. In this work, we aim to take a holistic approach to the construction of discrete gene…

Cited by 4Source ↗PDF ↗Scholar ↗
2025

UMA: A Family of Universal Models for Atoms

Brandon M Wood, Misko Dzamba, Xiang Fu, Meng Gao, Muhammed Shuaibi, Luis Barroso-Luque +12
NeurIPS 2025spotlight

The ability to quickly and accurately compute properties from atomic simulations is critical for advancing a large number of applications in chemistry and materials science including drug discovery, energy storage, and semiconductor manufacturing. To address this need, we present a family of Univers…

Cited by 0Source ↗Scholar ↗
2024

Fine-Tuned Language Models Generate Stable Inorganic Materials as Text

Nate Gruver, Anuroop Sriram, Andrea Madotto, Andrew Gordon Wilson, C. Lawrence Zitnick, Zachary Ward Ulissi
ICLR 2024poster

We propose fine-tuning large language models for generation of stable materials. While unorthodox, fine-tuning large language models on text-encoded atomistic data is simple to implement yet reliable, with around 90\% of sampled structures obeying physical constraints on atom positions and charges.…

Cited by 77Source ↗PDF ↗code ↗Scholar ↗
2024

FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions

Anuroop Sriram, Benjamin Kurt Miller, Ricky T. Q. Chen, Brandon M Wood
NeurIPS 2024poster

Material discovery is a critical area of research with the potential to revolutionize various fields, including carbon capture, renewable energy, and electronics. However, the immense scale of the chemical space makes it challenging to explore all possible materials experimentally. In this paper, we…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2024

FlowMM: Generating Materials with Riemannian Flow Matching

Benjamin Kurt Miller, Ricky T. Q. Chen, Anuroop Sriram, Brandon M Wood
ICML 2024poster

Crystalline materials are a fundamental component in next-generation technologies, yet modeling their distribution presents unique computational challenges. Of the plausible arrangements of atoms in a periodic lattice only a vanishingly small percentage are thermodynamically stable, which is a key i…

Cited by 34Source ↗PDF ↗Scholar ↗
2022

Spherical Channels for Modeling Atomic Interactions

C. Lawrence Zitnick, Abhishek Das, Adeesh Kolluru, Janice Lan, Muhammed Shuaibi, Anuroop Sriram +2
NeurIPS 2022accept

Modeling the energy and forces of atomic systems is a fundamental problem in computational chemistry with the potential to help address many of the world’s most pressing problems, including those related to energy scarcity and climate change. These calculations are traditionally performed using Dens…

Cited by 73Source ↗PDF ↗code ↗Scholar ↗
2022

Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations

Anuroop Sriram, Abhishek Das, Brandon M Wood, Siddharth Goyal, C. Lawrence Zitnick
ICLR 2022poster

Recent progress in Graph Neural Networks (GNNs) for modeling atomic simulations has the potential to revolutionize catalyst discovery, which is a key step in making progress towards the energy breakthroughs needed to combat climate change. However, the GNNs that have proven most effective for this t…

Cited by 33Source ↗PDF ↗Scholar ↗
2020

GrappaNet: Combining Parallel Imaging With Deep Learning for Multi-Coil MRI Reconstruction

Anuroop Sriram, Jure Zbontar, Tullie Murrell, C. Lawrence Zitnick, Aaron Defazio, Daniel K. Sodickson
CVPR 2020poster

Magnetic Resonance Image (MRI) acquisition is an inherently slow process which has spurred the development of two different acceleration methods: acquiring multiple correlated samples simultaneously (parallel imaging) and acquiring fewer samples than necessary for traditional signal processing metho…

Cited by 136PDF ↗code ↗Scholar ↗
2018

COLD FUSION: TRAINING SEQ2SEQ MODELS TOGETHER WITH LANGUAGE MODELS

Anuroop Sriram, Heewoo Jun, Sanjeev Satheesh, Adam Coates
ICLR 2018workshop

Sequence-to-sequence (Seq2Seq) models with attention have excelled at tasks which involve generating natural language sentences such as machine translation, image captioning and speech recognition. Performance has further been improved by leveraging unlabeled data, often in the form of a language mo…

Cited by 358Source ↗Scholar ↗
2018

Robust Speech Recognition Using Generative Adversarial Networks

Anuroop Sriram, Heewoo Jun, Yashesh Gaur, Sanjeev Satheesh
ICASSP 2018accepted

This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by learning to map noisy audio to the same embedding space as that of…

Cited by 0Source ↗Scholar ↗
2016

Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin

Dario Amodei, Sundaram Ananthanarayanan, Rishita Anubhai, Jingliang Bai, Eric Battenberg, Carl Case +63
ICML 2016poster

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech–two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of s…

Cited by 4031Source ↗PDF ↗code ↗Scholar ↗