Bose Lab
Selected works

Publications

2026
Normalizing Flow Maps
F. M. Ruscio*, T. J. Hitge*, Z. Peng, D. Rehman, Z. W. Blasingame, M. M. Bronstein, N. M. Boffi, A. Tong, A. J. Bose
NeurIPS 2026 STODY Workshop (Oral)
2026
Fixed-Point Rates for Self-Distillation of Flow Maps
T. Stanic, Q. Bertrand, A. J. Bose, G. Gidel
NeurIPS 2026 STODY Workshop
2026
On the Stability and Convergence of Flow Map Training
I. Nath, M. Massias, A. J. Bose, G. Gidel, Q. Bertrand
NeurIPS 2026 STODY Workshop
2026
Steered Not Stirred: Effective Tilting in Generative Models using Surrogate Reward Mixing
A. Sargood, O. Gallup, G. Maierhofer, N. Ghenassia, P. Duckworth, K. Sinkovics, A. J. Bose
NeurIPS 2026 STODY Workshop
2026
Few-step Cofolding with All-Atom Flow Maps
G. Scarpellini, R. Shprints, P. Holderrieth, J. Nam, P. Murugan, R. Gomez-Bombarelli, T. Jaakola, M. Al-Shedivat, N. M. Boffi, A.J. Bose
NeurIPS 2026 (Spotlight)
2026
Learned Relay Representations for Forward-Thinking Discrete Diffusion Models
B. Rozonoyer, J. Minniti, D. Patel, N. Band, A. J. Bose, T. G. J. Rudner, A. McCallum
Preprint 2026
2026
Aligning Flow Map Policies with Optimal Q-Guidance
C. Ziakas, A. Russo, A.J. Bose
NeurIPS 2026
2026
Coupling Models for One-Step Discrete Generation
F. Z. Peng, A.J. Bose, A.R. Zhang, A. Tong
NeurIPS 2026
2026
Autoregressive Boltzmann Generators
D. Rehman, C. Tan, A.J. Bose†, A. Tong†
ICML 2026 (Spotlight)
2026
General Multimodal Protein Design Enables DNA-Encoding of Chemistry
J. Rector-Brooks*, T. Lambert*, M. Skreta*, D. Roth*, ..., C.H. Liu*
Preprint 2026
2026
OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction
E. Jin*, A. Nica*, K. Lee, A. J. Bose, M. Galkin, S. Miret, J. Rector-Brooks, A. Tong, M. Bronstein, F. H. Arnold, C.H. Liu
ICLR 2026
2026
Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds
O. Davis, M. Albergo, N. Boffi, M. Bronstein, A. J. Bose
ICLR 2026
2026
Planner Aware Path Learning in Diffusion Language Models Training
F. Z. Peng*, Z. Bezemek*, J. Rector-Brooks, S. Zhang, Anru R. Zhang, J, M. Bronstein, A. Tong†, A. J. Bose†
ICLR 2026 (Oral)
2026
Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators
D. Rehman, O. Davis, J. Lu, J. Tang, M. Bronstein, Y. Bengio, A. Tong†, A. J. Bose†
ICLR 2026
2025
Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
T. Akhound-Sadegh*, J. Lee*, A. J. Bose, V. De Bortoli, A. Doucet, M. Bronstein, D. Beaini, S. Ravanbakhsh, K. Neklyudov†, A. Tong†
NeurIPS 2025 (Spotlight)
2025
Path Planning for Masked Diffusion Model Sampling
F. Z. Peng*, Z. Bezemek*, S. Patel, J. Rector-Brooks, A. J. Bose, A. Tong†, P Chatterjee†
Preprint 2025
2025
RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis
R. Yadav, Q. Yan, G. Wolf, A. J. Bose, R. Liao
NeurIPS 2025
2025
Curly Flow Matching For Learning Non-Gradient Field Dynamics
K. Petrović, L. Atanackovic, V. Morro, K. Kapusniak, M. Bronstein, A. J. Bose†, A Tong†
NeurIPS 2025
2025
Scalable Equilibrium Sampling with Sequential Boltzmann Generators
C. B. Tan*, A. J. Bose*, C. Lin, L. Klein, M. Bronstein, A. Tong
ICML 2025
2025
The Superposition of Diffusion Models
M. Skreta*, L. Atanackovic*, A. J. Bose, A. Tong, K. Neklyudov
ICLR 2025 (Spotlight)
2025
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
J. Rector-Brooks, M. Hasan, Z. Peng, Z. Quinn, C. Liu, S. Mittal, N. Dziri, M. Bronstein, Y. Bengio, P. Chatterjee, A. Tong†, A. J. Bose†
ICLR 2025
2024
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation
G. Huguet*, J. Vuckovic*, K. Fatras, E. Thibodeau-Laufer, P. Lemos, R. Islam, C. Liu, J. Rector-Brooks, T. Akhound-Sadegh, M. Bronstein, A. Tong†, A. J. Bose†
NeurIPS 2024
2024
Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
D. Ferbach, Q. Bertrand, A. J. Bose, G. Gidel
NeurIPS 2024 (Spotlight)
2024
Metric Flow Matching for Smooth Interpolations on the Data Manifold
K. Kapusniak, P. Potaptchik, T. Reu, L. Zhang, A. Tong, M. Bronstein, A. J. Bose, F. D. Giovanni
NeurIPS 2024
2024
Fisher Flow Matching for Generative Modeling over Discrete Data
O. Davis, S. Kessler, M. Petrache, I. I. Ceylan, M. Bronstein, A. J. Bose
NeurIPS 2024
2024
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
T. Akhound-Sadegh*, J. Rector-Brooks*, A.J. Bose*, S. Mittal, P. Lemos, C.H. Liu, M. Sendera, S. Ravanbaksh, G. Gidel, Y. Bengio, N. Malkin, A. Tong
ICML 2024
2024
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
A. J. Bose*, T. Akhound-Sadegh*, K. Fatras, G. Huguet, J. Rector-Brooks, C.H. Liu, A.C. Nica, M. Korablyov, M. Bronstein, A. Tong
ICLR 2024 (Spotlight)
2024
On the Stability of Iterative Retraining of Generative Models on their own Data
Q. Bertrand, A. J. Bose, A. Duplessis, M. Jiralerspong, G. Gidel
ICLR 2024 (Spotlight)
2023
EDGI: Equivariant Diffusion for Planning with Embodied Agents
J. Bremer*, A. J. Bose*, P. de Haan, T. Cohen
NeurIPS 2023
2023
Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
M. Jiralerspong, A. J. Bose, G. Gidel
NeurIPS 2023
2023
A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
D. Ferbach*, C. Tsirigotis*, G. Gidel, A.J. Bose
ICLR 2023
2022
Riemannian Diffusion Models
C.W. Huang*, M. Aghajohari*, A.J. Bose, P. Panangaden, A. Courville
NeurIPS 2022
2022
Controllable Generative Modeling via Causal Reasoning
A.J. Bose, R. Monti, A. Grover
TMLR 2022
2022
Equivariant Finite Normalizing Flows
A.J. Bose, I. Kobyzev, M. Brubaker
Preprint 2022
2022
Matching Normalizing Flows and Probability Paths on Manifolds
H. Ben-Hamu*, S. Cohen*, A.J. Bose, B. Amos, M. Nickel, A. Grover, R. Chen, Y. Lipman
ICML 2022
2022
Online Adversarial Attacks
A. Mladenović*, A.J. Bose*, H. Berard*, W.L. Hamilton, S. Lacoste-Julien, P. Vincent, G.Gidel
ICLR 2022
2021
Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding
N. Dziri, A. Madotto, O. Zaiane, A.J. Bose
EMNLP 2021
2020
Adversarial Example Games
A.J. Bose*, G. Gidel*, H. Berard*, A. Cianflone, P. Vincent, S. Lacoste-Julien, W.L. Hamilton
NeurIPS 2020
2020
Structure Aware Negative Sampling in Knowledge Graphs
K. Ahrabian, A. Feizi, Y. Salehi, W. L. Hamilton, A. J. Bose
EMNLP 2020
2020
Latent Variable Modelling with Hyperbolic Normalizing Flows
A. J. Bose, A. Smofsky, R. Liao, P. Panangaden, W. L. Hamilton
ICML 2020
2019
Meta-Graph: Few Shot Link Prediction via Meta Learning
A. J. Bose, A. Jain, P. Molino, W. L. Hamilton
Preprint (Unpublished)
2019
Compositional Fairness Constraints for Graph Embeddings
A. J. Bose, W. L. Hamilton
ICML 2019
2019
Discrete off-policy policy gradient using continuous relaxations
A. Cianflone, Z. Ahmed, R. Islam, A. J. Bose, W. L. Hamilton
RLDM 2019
2019
A Cross-Domain Transferable Neural Coherence Model
X. Peng, H. Saghir, J. Kang, T. Long, A. J. Bose, Y. Cao, J. Cheung
ACL 2019
2018
Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization
A. J. Bose, P. Aarabi
IEEE MMSP 2018 (Best Paper Runner-Up)
2018
Adversarial Contrastive Estimation
A. J. Bose*, Y. Cao*, H. Ling*
ACL 2018 (Oral)