Search Results for author: Vikas Garg

Found 24 papers, 6 papers with code

Predicting deliberative outcomes

no code implementations ICML 2020 Vikas Garg, Tommi Jaakkola

Our games take as input, e. g., UN resolution to be voted on, and map such contexts to initial strategies, player utilities, and interactions.

Structured Prediction

Predicting deliberative outcomes

no code implementations ICML 2020 Vikas Garg, Tommi Jaakkola

Our games take as input, e. g., UN resolution to be voted on, and map such contexts to initial strategies, player utilities, and interactions.

Structured Prediction

Diffusion Models as Cartoonists! The Curious Case of High Density Regions

no code implementations2 Nov 2024 Rafał Karczewski, Markus Heinonen, Vikas Garg

We investigate what kind of images lie in the high-density regions of diffusion models.

Denoising

Diffusion Twigs with Loop Guidance for Conditional Graph Generation

1 code implementation31 Oct 2024 Giangiacomo Mercatali, Yogesh Verma, Andre Freitas, Vikas Garg

We introduce a novel score-based diffusion framework named Twigs that incorporates multiple co-evolving flows for enriching conditional generation tasks.

Graph Generation

ACE: Abstractions for Communicating Efficiently

no code implementations30 Sep 2024 Jonathan D. Thomas, Andrea Silvi, Devdatt Dubhashi, Vikas Garg, Moa Johansson

On the symbolic side, we draw on work from library learning for proposing abstractions.

What Ails Generative Structure-based Drug Design: Too Little or Too Much Expressivity?

no code implementations12 Aug 2024 Rafał Karczewski, Samuel Kaski, Markus Heinonen, Vikas Garg

Several generative models with elaborate training and sampling procedures have been proposed recently to accelerate structure-based drug design (SBDD); however, perplexingly, their empirical performance turns out to be suboptimal.

Attribute Drug Design

Topological Neural Networks go Persistent, Equivariant, and Continuous

no code implementations5 Jun 2024 Yogesh Verma, Amauri H Souza, Vikas Garg

Topological Neural Networks (TNNs) incorporate higher-order relational information beyond pairwise interactions, enabling richer representations than Graph Neural Networks (GNNs).

Property Prediction

Alignment is Key for Applying Diffusion Models to Retrosynthesis

no code implementations27 May 2024 Najwa Laabid, Severi Rissanen, Markus Heinonen, Arno Solin, Vikas Garg

Retrosynthesis, the task of identifying precursors for a given molecule, can be naturally framed as a conditional graph generation task.

Graph Generation Retrosynthesis

Heteroscedastic Preferential Bayesian Optimization with Informative Noise Distributions

no code implementations23 May 2024 Marshal Arijona Sinaga, Julien Martinelli, Vikas Garg, Samuel Kaski

Such a model can be seamlessly integrated into the acquisition function, thus leading to candidate design pairs that elegantly trade informativeness and ease of comparison for the human expert.

Bayesian Optimization Informativeness

Employing Federated Learning for Training Autonomous HVAC Systems

no code implementations1 May 2024 Fredrik Hagström, Vikas Garg, Fabricio Oliveira

They have been shown to outperform classical controllers in terms of energy cost and consumption, as well as thermal comfort.

Federated Learning Transfer Learning

Graph4GUI: Graph Neural Networks for Representing Graphical User Interfaces

no code implementations21 Apr 2024 Yue Jiang, Changkong Zhou, Vikas Garg, Antti Oulasvirta

Present-day graphical user interfaces (GUIs) exhibit diverse arrangements of text, graphics, and interactive elements such as buttons and menus, but representations of GUIs have not kept up.

ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs

1 code implementation15 Apr 2024 Yogesh Verma, Markus Heinonen, Vikas Garg

Climate and weather prediction traditionally relies on complex numerical simulations of atmospheric physics.

Uncertainty Quantification Weather Forecasting

Field-based Molecule Generation

no code implementations24 Feb 2024 Alexandru Dumitrescu, Dani Korpela, Markus Heinonen, Yogesh Verma, Valerii Iakovlev, Vikas Garg, Harri Lähdesmäki

This work introduces FMG, a field-based model for drug-like molecule generation.

Algebraic Positional Encodings

2 code implementations26 Dec 2023 Konstantinos Kogkalidis, Jean-Philippe Bernardy, Vikas Garg

We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches.

Compositional Sculpting of Iterative Generative Processes

1 code implementation NeurIPS 2023 Timur Garipov, Sebastiaan De Peuter, Ge Yang, Vikas Garg, Samuel Kaski, Tommi Jaakkola

A key challenge in composing iterative generative processes, such as GFlowNets and diffusion models, is that to realize the desired target distribution, all steps of the generative process need to be coordinated, and satisfy delicate balance conditions.

AbODE: Ab Initio Antibody Design using Conjoined ODEs

no code implementations31 May 2023 Yogesh Verma, Markus Heinonen, Vikas Garg

Antibodies are Y-shaped proteins that neutralize pathogens and constitute the core of our adaptive immune system.

Graph Matching Protein Folding

Modular Flows: Differential Molecular Generation

no code implementations12 Oct 2022 Yogesh Verma, Samuel Kaski, Markus Heinonen, Vikas Garg

Generating new molecules is fundamental to advancing critical applications such as drug discovery and material synthesis.

Density Estimation Drug Discovery

Provably expressive temporal graph networks

1 code implementation29 Sep 2022 Amauri H. Souza, Diego Mesquita, Samuel Kaski, Vikas Garg

Specifically, novel constructions reveal the inadequacy of MP-TGNs and WA-TGNs, proving that neither category subsumes the other.

Why GANs are overkill for NLP

no code implementations19 May 2022 David Alvarez-Melis, Vikas Garg, Adam Tauman Kalai

We show that, while it may seem that maximizing likelihood is inherently different than minimizing distinguishability, this distinction is largely artificial and only holds for limited models.

Text Generation

Generative Models for Graph-Based Protein Design

1 code implementation ICLR Workshop DeepGenStruct 2019 John Ingraham, Vikas Garg, Regina Barzilay, Tommi Jaakkola

Engineered proteins offer the potential to solve many problems in biomedicine, energy, and materials science, but creating designs that succeed is difficult in practice.

Protein Design Protein Folding

Supervising Unsupervised Learning

no code implementations NeurIPS 2018 Vikas Garg

We introduce a framework to transfer knowledge acquired from a repository of (heterogeneous) supervised datasets to new unsupervised datasets.

Clustering Zero-Shot Learning

Local Aggregative Games

no code implementations NeurIPS 2017 Vikas Garg, Tommi Jaakkola

Aggregative games provide a rich abstraction to model strategic multi-agent interactions.

Learning Tree Structured Potential Games

no code implementations NeurIPS 2016 Vikas Garg, Tommi Jaakkola

Many real phenomena, including behaviors, involve strategic interactions that can be learned from data.

Adaptivity to Local Smoothness and Dimension in Kernel Regression

no code implementations NeurIPS 2013 Samory Kpotufe, Vikas Garg

We present the first result for kernel regression where the procedure adapts locally at a point $x$ to both the unknown local dimension of the metric and the unknown H\{o}lder-continuity of the regression function at $x$.

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.