Related papers: Atoms as Language: VQ-Atom: Semantic Discretizatio…

Atom segmentation and localization, noise reduction and deblurring of atomic-resolution scanning transmission electron microscopy (STEM) images with high precision and robustness is a challenging task. Although several conventional…

Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping…

While most frontier models still use deterministic frequency-based tokenization algorithms such as byte-pair encoding (BPE), there has been significant recent work to design learned neural tokenizers. However, these schemes generally add to…

Molecular pretraining, which learns molecular representations over massive unlabeled data, has become a prominent paradigm to solve a variety of tasks in computational chemistry and drug discovery. Recently, prosperous progress has been…

Deep learning natural language processing models often use vector word embeddings, such as word2vec or GloVe, to represent words. A discrete sequence of words can be much more easily integrated with downstream neural layers if it is…

Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for…

Small-molecule foundation models are typically pretrained on standalone molecular data, unlike vision and language models that often benefit from cross-modal or relational supervision. Protein-ligand co-folding provides a molecular analogue…

Significant interests have recently risen in leveraging sequence-based large language models (LLMs) for drug design. However, most current applications of LLMs in drug discovery lack the ability to comprehend three-dimensional (3D)…

Post-training quantization (PTQ) has emerged as an effective technique for compressing large models and accelerating inference without retraining. While PTQ has been extensively studied in large language models (LLMs), its application to…

Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) for reliable predictions and real-world deployment. However, most existing methods are adapted from the LLM literature and primarily focus…

The vocabulary used by language models (LM) - defined by the tokenizer - plays a key role in text generation quality. However, its impact remains under-explored in radiology. In this work, we address this gap by systematically comparing…

The rapid advancement of speech generation technologies in the era of large language models (LLMs) has established discrete speech tokens as a foundational paradigm for speech representation. These tokens, characterized by their discrete,…

Recent advances in visual generation have emphasized the importance of Latent Generative Models (LGMs), which critically depend on effective visual tokenizers to bridge pixels and semantic representations. However, tokenizers constructed on…

First principles based exploration of chemical space deepens our understanding of chemistry, and might help with the design of new materials or experiments. Due to the computational cost of quantum chemistry methods and the immens number of…

Digital mapping of semantic features is essential for achieving interoperability between semantic communication and practical digital infrastructure. However, current research efforts predominantly concentrate on analog semantic…

Pattern recognition algorithms are commonly employed to simplify the challenging and necessary step of track reconstruction in sub-atomic physics experiments. Aiding in the discrimination of relevant interactions, pattern recognition seeks…

Traditional atomistic machine learning (ML) models serve as surrogates for quantum mechanical (QM) properties, predicting quantities such as dipole moments and polarizabilities, directly from compositions and geometries of atomic…

Training data attribution (TDA) methods ask which training documents are responsible for a model behavior. However, models often learn broad concepts shared across many examples. Moreover, existing TDA methods are supervised -- they require…

Molecular property prediction has gained significant attention due to its transformative potential in multiple scientific disciplines. Conventionally, a molecule graph can be represented either as a graph-structured data or a SMILES text.…

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains…