Related papers: Unifying Polymer Modeling and Design via a Conform…
Open-sourcing foundation models (FMs) enables broad reuse but also exposes model trainers to economic and safety risks from unrestricted downstream fine-tuning. We address this problem by building non-fine-tunable foundation models: models…
Molecular conformation generation (MCG) is a fundamental and important problem in drug discovery. Many traditional methods have been developed to solve the MCG problem, such as systematic searching, model-building, random searching,…
Foundation models have revolutionized natural language processing through a ``train once, deploy anywhere'' paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining. Access to a Physics Foundation…
The code of nature, embedded in DNA and RNA genomes since the origin of life, holds immense potential to impact both humans and ecosystems through genome modeling. Genomic Foundation Models (GFMs) have emerged as a transformative approach…
With the rapid advancement of generative models, associated privacy concerns have attracted growing attention. To address this, researchers have begun adapting machine unlearning techniques from traditional classification models to…
Contemporary large language models (LLMs), such as GPT-4 and Llama, have harnessed extensive computational power and diverse text corpora to achieve remarkable proficiency in interpreting and generating domain-specific content, including…
World models based on video generation demonstrate remarkable potential for simulating interactive environments but face persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and…
Modern data-driven tools are transforming application-specific polymer development cycles. Surrogate models that can be trained to predict the properties of new polymers are becoming commonplace. Nevertheless, these models do not utilize…
We present a systematic evaluation of representation learning objectives for particle physics within a unified framework. Our study employs a shared transformer-based particle-cloud encoder with standardized preprocessing, matched sampling,…
We present a three-dimensional foundation model for polycrystalline materials based on a masked autoencoder trained via large-scale self-supervised learning. The model is pretrained on $100{,}000$ voxelized synthetic face-centered cubic…
Molecular conformer generation (MCG) is an important task in cheminformatics and drug discovery. The ability to efficiently generate low-energy 3D structures can avoid expensive quantum mechanical simulations, leading to accelerated virtual…
Molecular property prediction and generative design via deep learning models has been the subject of intense research given its potential to accelerate development of new, high-performance materials. More recently, these workflows have been…
General-purpose 3D modeling in chemistry encompasses molecules and materials, requiring both generative and predictive capabilities. However, most existing AI approaches are optimized for a single domain (molecules or materials) and a…
A coarse-grained simulation model eliminates microscopic degrees of freedom and represents a polymer by a simplified structure. A priori, two classes of coarse-grained models may be distinguished: those which are designed for a specific…
Polymers are attractive in applications like flexible electronics and thermal interface materials due to their mechanical compliance and processability. However, conventional polymers have low thermal conductivity (TC), limiting their heat…
Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work,…
Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for representing the 3D surfaces of an object class. In this context, we identify an interesting question that has previously not received research attention: is it…
Time-series analysis plays a pivotal role across a range of critical applications, from finance to healthcare, which involves various tasks, such as forecasting and classification. To handle the inherent complexities of time-series data,…
Matrix-free nanocomposites made from polymer grafted nanoparticles (PGN) represent a paradigm shift in materials science because they greatly improve nanoparticle dispersion and offer greater tunability over rheological and mechanical…
A brief review of our recent studies aiming at a better understanding of the scaling behaviour of polymers in disordered environments is given. The main emphasis is on a simple generic model where the polymers are represented by…