2025
Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models.
CoRR, March, 2025
Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?
CoRR, March, 2025
EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts.
CoRR, February, 2025
PEEL the Layers and Find Yourself: Revisiting Inference-Time Data Leakage for Residual Neural Networks.
Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2025
Large Language Models can Become Strong Self-Detoxifiers.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
2024
Acceleration of Graph Neural Network-Based Prediction Models in Chemistry via Co-Design Optimization on Intelligence Processing Units.
,
,
,
,
,
,
,
,
,
,
,
,
J. Chem. Inf. Model., March, 2024
Attribute Graphs Underlying Molecular Generative Models: Path to Learning with Limited Data.
Trans. Mach. Learn. Res., 2024
Anniversary AI reflections.
Nat. Mac. Intell., 2024
Can Large Language Models Adapt to Other Agents In-Context?
CoRR, 2024
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs.
CoRR, 2024
SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection.
CoRR, 2024
Large Language Models can be Strong Self-Detoxifiers.
CoRR, 2024
Generation Constraint Scaling Can Mitigate Hallucination.
CoRR, 2024
Needle in the Haystack for Memory Based Large Language Models.
CoRR, 2024
GP-MoLFormer: A Foundation Model For Molecular Generation.
CoRR, 2024
Larimar: Large Language Models with Episodic Memory Control.
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
ProtIR: Iterative Refinement between Retrievers and Predictors for Protein Function Annotation.
CoRR, 2024
Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints.
CoRR, 2024
Structure-Informed Protein Language Model.
CoRR, 2024
Mapping Metaverse Research to the Sustainable Development Goal of Good Health and Well-Being.
IEEE Access, 2024
Multi-Scale Representation Learning for Protein Fitness Prediction.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Larimar: Large Language Models with Episodic Memory Control.
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Forty-first International Conference on Machine Learning, 2024
A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024
NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2024
2023
Physics-enhanced deep surrogates for partial differential equations.
Nat. Mac. Intell., December, 2023
The incentive gap in data work in the era of large models.
Nat. Mac. Intell., June, 2023
A Small Step Toward Generalizability: Training a Machine Learning Scoring Function for Structure-Based Virtual Screening.
,
,
,
,
,
,
,
,
,
,
J. Chem. Inf. Model., May, 2023
AI Maintenance: A Robustness Perspective.
Computer, February, 2023
Keeping Up with the Language Models: Robustness-Bias Interplay in NLI Data and Models.
CoRR, 2023
Equivariant Few-Shot Learning from Pretrained Models.
CoRR, 2023
Enhancing Protein Language Models with Structure-based Encoder and Pre-training.
CoRR, 2023
Physics-Inspired Protein Encoder Pre-Training via Siamese Sequence-Structure Diffusion Trajectory Prediction.
CoRR, 2023
Reprogramming Pretrained Language Models for Protein Sequence Representation Learning.
CoRR, 2023
Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
The Impact of Positional Encoding on Length Generalization in Transformers.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Efficient Equivariant Transfer Learning from Pretrained Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Reprogramming Pretrained Language Models for Antibody Sequence Infilling.
Proceedings of the International Conference on Machine Learning, 2023
Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction.
Proceedings of the International Conference on Machine Learning, 2023
Protein Representation Learning by Geometric Structure Pretraining.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
Direction Aware Positional and Structural Encoding for Directed Graph Neural Networks.
Proceedings of the IEEE International Conference on Acoustics, 2023
Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
2022
Large-scale chemical language representations capture molecular structure and properties.
Nat. Mac. Intell., December, 2022
Modified Galerkin method for Volterra-Fredholm-Hammerstein integral equations.
Comput. Appl. Math., September, 2022
Active Sampling of Multiple Sources for Sequential Estimation.
IEEE Trans. Signal Process., 2022
Explaining Artificial Intelligence Generation and Creativity: Human interpretability for novel ideas and artifacts.
IEEE Signal Process. Mag., 2022
Optimizing molecules using efficient queries from property evaluations.
Nat. Mach. Intell., 2022
Reducing Down(stream)time: Pretraining Molecular GNNs using Heterogeneous AI Accelerators.
CoRR, 2022
Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions.
CoRR, 2022
Reprogramming Large Pretrained Language Models for Antibody Sequence Infilling.
CoRR, 2022
AlphaFold Distillation for Improved Inverse Protein Folding.
CoRR, 2022
SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data.
CoRR, 2022
Causal Graphs Underlying Generative Models: Path to Learning with Limited Data.
CoRR, 2022
GT4SD: Generative Toolkit for Scientific Discovery.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2022
Learning Geometrically Disentangled Representations of Protein Folding Simulations.
CoRR, 2022
Accelerating Inhibitor Discovery for Multiple SARS-CoV-2 Targets with a Single, Sequence-Guided Deep Generative Framework.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2022
Cloud-Based Real-Time Molecular Screening Platform with MolFormer.
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2022
Towards Creativity Characterization of Generative Models via Group-Based Subset Scanning.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022
Biological Sequence Design with GFlowNets.
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the International Conference on Machine Learning, 2022
Data-Efficient Graph Grammar Learning for Molecular Generation.
Proceedings of the Tenth International Conference on Learning Representations, 2022
Augmenting Molecular Deep Generative Models with Topological Data Analysis Representations.
Proceedings of the IEEE International Conference on Acoustics, 2022
Knowledge Graph Generation From Text.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022
Fourier Representations for Black-Box Optimization over Categorical Variables.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
2021
Sample-Efficient Generation of Novel Photo-acid Generator Molecules using a Deep Generative Model.
CoRR, 2021
Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination.
CoRR, 2021
Benchmarking deep generative models for diverse antibody sequence design.
CoRR, 2021
Physics-enhanced deep surrogates for PDEs.
CoRR, 2021
Towards Interpreting Zoonotic Potential of Betacoronavirus Sequences With Attention.
CoRR, 2021
Do Large Scale Molecular Language Representations Capture Important Structural Information?
CoRR, 2021
Gi and Pal Scores: Deep Neural Network Generalization Statistics.
CoRR, 2021
Towards creativity characterization of generative models via group-based subset scanning.
CoRR, 2021
Predicting Deep Neural Network Generalization with Perturbation Response Curves.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Best Arm Identification in Contaminated Stochastic Bandits.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Active Binary Classification of Random Fields.
Proceedings of the IEEE International Symposium on Information Theory, 2021
Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design.
Proceedings of the 38th International Conference on Machine Learning, 2021
Active Estimation From Multimodal Data.
Proceedings of the IEEE International Conference on Acoustics, 2021
ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021
Self-Progressing Robust Training.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021
2020
Reprogramming Language Models for Molecular Representation Learning.
CoRR, 2020
Characterizing the Latent Space of Molecular Deep Generative Models with Persistent Homology Metrics.
CoRR, 2020
Explaining Chemical Toxicity using Missing Features.
CoRR, 2020
Active learning of deep surrogates for PDEs: Application to metasurface design.
CoRR, 2020
Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2020
Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models.
CoRR, 2020
Optimizing Mode Connectivity via Neuron Alignment.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models.
,
,
,
,
,
,
,
,
,
,
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Combinatorial Black-Box Optimization with Expert Advice.
Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020
Toward a neuro-inspired creative decoder.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020
Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness.
Proceedings of the 8th International Conference on Learning Representations, 2020
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets.
Proceedings of the 8th International Conference on Learning Representations, 2020
Improving Efficiency in Large-Scale Decentralized Distributed Training.
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020
DualTKB: A Dual Learning Bridge between Text and Knowledge Base.
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020
Learning Implicit Text Generation via Feature Matching.
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020
2019
Projection and multi projection methods for nonlinear integral equations on the half-line.
J. Comput. Appl. Math., 2019
Decentralized Parallel Algorithm for Training Generative Adversarial Nets.
CoRR, 2019
Toward A Neuro-inspired Creative Decoder.
CoRR, 2019
Interactive Visual Exploration of Latent Space (IVELS) for peptide auto-encoder model selection.
Proceedings of the Deep Generative Models for Highly Structured Data, 2019
Superconvergence of Iterated Galerkin Method for a Class of Nonlinear Fredholm Integral Equations.
Proceedings of the Recent Advances in Intelligent Information Systems and Applied Mathematics, 2019
2018
Discrete Legendre spectral Galerkin method for Urysohn integral equations.
Int. J. Comput. Math., 2018
PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences.
CoRR, 2018
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
2017
Neurology-as-a-Service for the Developing World.
CoRR, 2017
Automated brain state identification using graph embedding.
Proceedings of the 2017 International Workshop on Pattern Recognition in Neuroimaging, 2017
2016
Legendre Spectral Projection Methods for Fredholm-Hammerstein Integral Equations.
J. Sci. Comput., 2016
Erratum to: Discrete Legendre spectral projection methods for Fredholm-Hammerstein integral equations [J. Comput. Appl. Math 278 (2015) 293-305].
J. Comput. Appl. Math., 2016
Corrigendum to: "Convergence analysis of discrete legendre spectral projection methods for hammerstein integral equations of mixed type" Applied Mathematics and Computation Volume 265, 15 August 2015, Pages 574-601.
Appl. Math. Comput., 2016
2015
Discrete Legendre spectral projection methods for Fredholm-Hammerstein integral equations.
J. Comput. Appl. Math., 2015
Convergence analysis of discrete legendre spectral projection methods for hammerstein integral equations of mixed type.
Appl. Math. Comput., 2015
2014
Comparative study of metamodelling techniques in building energy simulation: Guidelines for practitioners.
Simul. Model. Pract. Theory, 2014
Legendre spectral projection methods for Urysohn integral equations.
J. Comput. Appl. Math., 2014
2011
Modeling mutations of influenza virus with IBM Blue Gene.
IBM J. Res. Dev., 2011
2009
Free energy simulations reveal a double mutant avian H5N1 virus hemagglutinin with altered receptor binding specificity.
J. Comput. Chem., 2009
2006
Low-dimensional, free-energy landscapes of protein-folding reactions by nonlinear dimensionality reduction.
Proc. Natl. Acad. Sci. USA, 2006