Previously, I led research and engineering efforts during my time at IBM Research, Amazon A9, and Microsoft Research. I received a PhD in Computer Science (EECS) from MIT, where I worked closely with Tommi Jaakkola (PhD supervisor), Regina Barzilay, Stefanie Jegelka and Cynthia Rudin. While at MIT, I was closely associated with the Machine Learning for Pharmaceutical Discovery and Synthesis (MLPDS) Consortium, and also served as a BP Technologies Energy Fellow. I also collaborated extensively with Adam Kalai, Ofer Dekel, and Lin Xiao. Before moving to Boston, I spent two wonderful years in Chicago, working with Raquel Urtasun (M.S. supervisor), Sanja Fidler, Risi Kondor, and John Lafferty.

My research interests span (geometric and topological) deep learning, dynamical and control systems (e.g., world models), (discrete, multimodal, foundational) generative models, physics-inspired models (e.g., for weather forecasting), learning and reasoning under (evolving) constraints (e.g., pertaining to symmetry, resource, safety, scalability, missing data, uncertainty), and ML for Science. I am particularly passionate about advancing the state of the art for applications in biodesign (e.g., drug discovery, material design), computer vision, language understanding, and process automation.

I'm a firm believer in, and proponent of, rigorous and reproducible science. Our group maintains code for our recent projects here. I've also closely supervised and mentored more than 100 students, researchers, and engineers in both academic and industrial settings over two decades. Helping nurture their talents and witnessing their amazing accomplishments has been particularly satisfying.


Select Publications
N. Laabid and V. Garg. Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning. (Preprint)
S. Gupta(+), S. Kansal(+), S. Jegelka, P. Isola, and V. Garg. Canonicalizing Multimodal Contrastive Representation Learning. (Preprint) (Blogpost)
Y. Verma, M. Heinonen, and V. Garg. Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation. (Preprint)
S.-Y. Yu(+), J.-W. Wang(+), M. Horii, M. Tomizuka, and V. Garg. Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control, RA-L, 2026. (Preprint) (Demo videos)
H. Scheufele(+), P. Blohm(+), and V. Garg. Temperature Scaling in Discrete Sequence (Language) Models, ICML, 2026. (PDF)
A. Gupta(+), P. Barabanshchikova(+), V. Garg, S. Kaski, and T. Jaakkola. A Game-Theoretic Method for Fairly Composing Diffusion Models, ICML, 2026 (Spotlight). (PDF)
M. Krahn(+), L. Bastian(+), V. Garg(++), B. Schuller(++), and T. Birdal(++). Collapsed Effective Operators for Higher-order Structures, ICML, 2026. (PDF)
R. Karczewski, M. Heinonen, A. Pouplin, S. Hauberg, and V. Garg. The Spacetime of Diffusion Models: An Information Geometry Perspective, ICLR, 2026 (Oral). (PDF) (Blogpost)
P. Blohm and V. Garg. Composition of Pretrained Diffusion Models: A Logic-Based Calculus, ICLR, 2026. (PDF)
F. Ruiz-Mazo and V. Garg. Frozen Priors, Fluid Forecasts: Prequential Uncertainty for Low-Data Deployment with Pretrained Generative Models, ICLR, 2026. (PDF)
M. Ji(+), I. Roy(+), and V. Garg. Contraction and Hourglass Persistence for Learning on Graphs, Simplices, and Cells, ICLR, 2026. (PDF) (Poster)
A. Akbari, A. H. Souza, and V. Garg. The Logical Expressiveness of Topological Neural Networks, ICLR, 2026. (PDF)
M. Ji, A. H. Souza, and V. Garg. On topological descriptors for graph products, NeurIPS, 2025. (PDF)
M. Ji, A. H. Souza, and V. Garg. Graph Persistence goes Spectral, NeurIPS, 2025. (PDF)
R. Karczewski, M. Heinonen, and V. Garg. Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models, ICML, 2025. (PDF) (Blogpost)
Y. Verma, A. H. Souza, and V. Garg. Positional Encoding meets Persistent Homology on Graphs, ICML, 2025. (PDF)
R. Karczewski, S. Kaski, M. Heinonen, and V. Garg. What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much?, AISTATS, 2025 (Oral). (PDF) (Poster)
R. Karczewski, M. Heinonen, and V. Garg. Diffusion Models as Cartoonists! The Curious Case of High Density Regions, ICLR, 2025. (PDF) (Poster)
N. Laabid(+), S. Rissanen(+), M. Heinonen, A. Solin, and V. Garg. Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models, ICLR, 2025. (PDF) (Blogpost) (Poster)
A. Dumitrescu et al. E(3)-equivariant models cannot learn chirality: Field-based molecular generation, ICLR, 2025. (PDF)
Y. Verma, A. Bharti, and V. Garg. Robust Simulation-Based Inference under Missing Data via Neural Processes, ICLR, 2025. (PDF)
T. Silva, R. B. Alves, E. de Souza da Silva, A. H. Souza, V. Garg, S. Kaski, and D. Mesquita. When do GFlowNets learn the right distribution?, ICLR, 2025 (Spotlight). (PDF)
T. Silva, A. H. Souza, O. Rivasplata, V. Garg, S. Kaski, and D. Mesquita. Generalization and Distributed Learning of GFlowNets, ICLR, 2025. (PDF)
V. Garg. Generative AI for graph-based drug design: Recent advances and the way forward, Current Opinion in Structural Biology, 2024. (PDF)
K. Kogkalidis, J.-P. Bernardy, and V. Garg. Algebraic Positional Encodings, NeurIPS, 2024 (Spotlight). (PDF)
G. Mercatali(+), Y. Verma(+), A. Freitas, and V. Garg. Diffusion Twigs with Loop Guidance for Conditional Graph Generation, NeurIPS, 2024. (PDF)
T. A. Pham and V. Garg. What do Graph Neural Networks learn? Insights from Tropical Geometry, NeurIPS, 2024. (PDF)
K. Brilliantov, A. H. Souza, and V. Garg. Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond, NeurIPS, 2024. (PDF)
Y. Verma, A. H. Souza, and V. Garg. Topological Neural Networks go Persistent, Equivariant, and Continuous, ICML, 2024. (PDF)
R. Karczewski, A. H. Souza, and V. Garg. On the Generalization of Equivariant Graph Neural Networks, ICML, 2024. (PDF)
Y. Verma, M. Heinonen, and V. Garg. ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs, ICLR, 2024 (Oral). (PDF) (Blogpost) (Poster)
Y. Jiang, C. Zhou, V. Garg(++), and A. Oulasvirta(++). Graph4GUI: Graph Neural Networks for Representing Graphical User Interfaces, CHI, 2024. (PDF)
J. Immonen(+), A. H. Souza(+), and V. Garg. Going beyond persistent homology using persistent homology, NeurIPS, 2023 (Oral). (PDF)
T. Garipov, S. De Peuter, G. Yang, V. Garg, S. Kaski, and T. Jaakkola. Compositional Sculpting of Iterative Generative Processes, NeurIPS, 2023. (PDF)
Y. Verma, M. Heinonen, and V. Garg. AbODE: Ab initio antibody design using conjoined ODEs, ICML, 2023. (PDF) (Blogpost) (Poster)
I. Moflic, V. Garg, and A. Paler. Graph Neural Network Autoencoders for Efficient Quantum Circuit Optimisation, APS, 2023. (PDF)
D. Alvarez-Melis (+*), V. Garg(+*), and A. Kalai (+*). Are GANs overkill for NLP?, NeurIPS, 2022 (Spotlight). (PDF)
Y. Verma, S. Kaski, M. Heinonen, and V. Garg. Modular Flows: Differential Molecular Generation, NeurIPS, 2022. (PDF) (Blogpost) (Poster)
A. H. Souza, D. Mesquita, S. Kaski, and V. Garg. Provably expressive temporal graph networks, NeurIPS, 2022. (PDF)
G. Mercatali, A. Freitas, and V. Garg. Symmetry-induced Disentanglement on Graphs, NeurIPS, 2022. (PDF)
V. Garg(*), A. Kalai(*), K. Ligett(*), and S. Wu(*). Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization, AISTATS, 2021 (Oral). (PDF)
V. Garg, S. Jegelka, and T. Jaakkola. Generalization and Representational Limits of Graph Neural Networks, ICML, 2020. (PDF)
V. Garg and T. Jaakkola. Predicting deliberative outcomes, ICML, 2020. (PDF)
J. Ingraham, V. Garg, R. Barzilay, and T. Jaakkola. Generative Models for Graph-Based Protein Design, NeurIPS, 2019. (PDF) (Code)
V. Garg and T. Jaakkola. Solving graph compression via optimal transport, NeurIPS, 2019. (PDF)
V. Garg and T. Pichkhadze. Online Markov Decoding: Lower Bounds and Near-Optimal Approximation Algorithms, NeurIPS, 2019. (PDF)
V. Garg, O. Dekel, and L. Xiao. Learning SMaLL Predictors, NeurIPS, 2018. (PDF)
V. Garg and A. Kalai. Supervising Unsupervised Learning, NeurIPS, 2018 (Spotlight). (PDF) (Poster)
V. Garg, L. Xiao, and O. Dekel. Sparse Multi-Prototype Classification, UAI, 2018. (PDF)
V. Garg and T. Jaakkola. Local Aggregative Games, NeurIPS, 2017. (PDF)
V. Garg and T. Jaakkola. Learning Tree Structured Potential Games, NeurIPS, 2016. (PDF)
V. Garg, C. Rudin, and T. Jaakkola. CRAFT: ClusteR-specific Assorted Feature selecTion, AISTATS, 2016. (PDF) (Code)
S. Shankar, V. Garg, and R. Cipolla. Deep Carving: Discovering Visual Attributes by Carving Deep Neural Nets, CVPR, 2015. (PDF)
R. Kondor, N. Teneva, and V. Garg. Multiresolution Matrix Factorization, ICML, 2014. (PDF)
V. Garg, T. S. Jayram, and B. Narayanaswamy. Online Optimization with Dynamic Temporal Uncertainty, AAAI, 2013. (PDF)
S. Kpotufe and V. Garg. Adaptivity to Local Smoothness and Dimension in Kernel Regression, NeurIPS, 2013. (PDF)
V. Garg, M. N. Murty, and Y. Narahari. Biobjective Clustering (BiGC) Based on Cooperative Game Theory, TKDE, 2013. (PDF)
P. Agrawal(+), V. Garg(+), and R. Narayanam. Link Label Prediction in Signed Social Networks, IJCAI, 2013. (PDF)
V. Garg, A. Narang, and S. Bhattacherjee. Real-Time Memory Efficient Data Redundancy Removal, CIKM, 2010. (PDF)
[(+/++): Equal Contribution, (*): Alphabetical Order]