51 citations · 65 across the 23 of their papers we have counts for
26 papers
FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials
Viktor Zaverkin, Payman Goodarzi, Sergey V. Sukhomlinov +4
Machine-learned interatomic potentials extend atomistic simulations beyond the length- and timescales accessible to electronic-structure methods. However, the computational cost of…
GLASS: Global Latent Aggregation with Slot-based Set Decoding for Scalable All-Atom Crystal Generation
Hendrik Kraß, Seyed Mohamad Moosavi, Mathias Niepert
Generative models for crystals enable the discovery of novel structures, but scaling all-atom generation to larger systems such as metal--organic frameworks remains challenging. We…
Curvature-Aware Flow Matching for Molecular Structure Generation
Samir Darouich, Juliane Geisler, Jacob W. Toney +4
Generative models produce three-dimensional molecular structures with high geometric accuracy, yet they are trained on distributions of atomic coordinates without explicit access t…
Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing
Duc Minh Nguyen, Bao-Ngoc Dao, Tung M. Luu +15
Diffusion-based Vision-Language-Action (VLA) policies enable strong generalization in robotic manipulation, but remain sensitive to spurious visual correlations and noisy action ge…
Protein Fold Classification at Scale: Benchmarking and Pretraining
Dexiong Chen, Andrei Manolache, Mathias Niepert +1
Classifying protein topology is essential for deciphering biological function, but progress is held back by the lack of large-scale benchmarks that avoid duplicates and by models t…
SparseSAM: Structured Sparsification of Activations in Segment Anything Models
Hoai-Chau Tran, Chi H. Nguyen, Duy M. H. Nguyen +3
The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compressi…
Logical Guidance for the Exact Composition of Diffusion Models
Francesco Alesiani, Jonathan Warrell, Tanja Bien +3
We propose LOGDIFF (Logical Guidance for the Exact Composition of Diffusion Models), a guidance framework for diffusion models that enables principled constrained generation with c…
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
Duy M. H. Nguyen, Tuan A. Tran, Duong Nguyen +17
Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining.…
Beyond the Training Domain: Robust Generative Transition State Models for Unseen Chemistry
Samir Darouich, Jacob W. Toney, Weiliang Luo +3
Transition states (TSs) govern the rates and outcomes of chemical reactions, making their accurate prediction a central challenge in computational chemistry. Although recent machin…
How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
Tuan Anh Tran, Duy M. H. Nguyen, Hoai-Chau Tran +7
Recent advances in 3D point cloud transformers have led to state-of-the-art results in tasks such as semantic segmentation and reconstruction. However, these models typically rely…
S-Chain: Structured Visual Chain-of-Thought For Medicine
Khai Le-Duc, Duy M. H. Nguyen, Phuong T. H. Trinh +21
Faithful reasoning in medical vision-language models (VLMs) requires not only accurate predictions but also transparent alignment between textual rationales and visual evidence. Wh…
Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulations
Viktor Zaverkin, Matheus Ferraz, Francesco Alesiani +1
Universal machine-learned potentials promise transferable accuracy across compositional and vibrational degrees of freedom, yet their application to biomolecular simulations remain…
Adaptive Transition State Refinement with Learned Equilibrium Flows
Samir Darouich, Vinh Tong, Tanja Bien +2
Identifying transition states (TSs), the high-energy configurations that molecules pass through during chemical reactions, is essential for understanding and designing chemical pro…
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca +9
While machine learning on graphs has demonstrated promise in drug design and molecular property prediction, significant benchmarking challenges hinder its further progress and rele…
On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation
Nghiem T. Diep, Huy Nguyen, Chau Nguyen +5
The LLaMA-Adapter has recently emerged as an efficient fine-tuning technique for LLaMA models, leveraging zero-initialized attention to stabilize training and enhance performance.…
Adaptive Width Neural Networks
Federico Errica, Henrik Christiansen, Viktor Zaverkin +2
For almost 70 years, researchers have typically selected the width of neural networks' layers either manually or through automated hyperparameter tuning methods such as grid search…
ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
Duy M. H. Nguyen, Nghiem T. Diep, Trung Q. Nguyen +10
State-of-the-art medical multi-modal LLMs (med-MLLMs), such as LLaVA-Med and BioMedGPT, primarily depend on scaling model size and data volume, with training driven largely by auto…
Physics-Informed Weakly Supervised Learning for Interatomic Potentials
Makoto Takamoto, Viktor Zaverkin, Mathias Niepert
Machine learning plays an increasingly important role in computational chemistry and materials science, complementing computationally intensive ab initio and first-principles metho…
Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model
Duy M. H. Nguyen, An T. Le, Trung Q. Nguyen +7
Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and mi…
Accelerating Transformers with Spectrum-Preserving Token Merging
Hoai-Chau Tran, Duy M. H. Nguyen, Duy M. Nguyen +7
Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an…
Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
Viktor Zaverkin, Francesco Alesiani, Takashi Maruyama +5
The ability to perform fast and accurate atomistic simulations is crucial for advancing the chemical sciences. By learning from high-quality data, machine-learned interatomic poten…
Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
Duy M. H. Nguyen, Nina Lukashina, Tai Nguyen +7
A molecule's 2D representation consists of its atoms, their attributes, and the molecule's covalent bonds. A 3D (geometric) representation of a molecule is called a conformer and c…
Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
Federico Errica, Henrik Christiansen, Viktor Zaverkin +3
Long-range interactions are essential for the correct description of complex systems in many scientific fields. The price to pay for including them in the calculations, however, is…
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
Viktor Zaverkin, David Holzmüller, Henrik Christiansen +5
Efficiently creating a concise but comprehensive data set for training machine-learned interatomic potentials (MLIPs) is an under-explored problem. Active learning, which uses bias…