Related papers: MolDA: Molecular Understanding and Generation via …

Molecular dynamics (MD) is a powerful approach for modelling molecular systems, but it remains computationally intensive on spatial and time scales of many macromolecular systems of biological interest. To explore the opportunities offered…

Autoregressive (AR) vision-language models (VLMs) have long dominated multimodal understanding, reasoning, and graphical user interface (GUI) grounding. Recently, discrete diffusion vision-language models (DVLMs) have shown strong…

Molecular optimization (MO) is a crucial stage in drug discovery in which task-oriented generated molecules are optimized to meet practical industrial requirements. Existing mainstream MO approaches primarily utilize external property…

The molecular large language models have garnered widespread attention due to their promising potential on molecular applications. However, current molecular large language models face significant limitations in understanding molecules due…

End-to-end autonomous driving systems based on vision-language-action (VLA) models integrate multimodal sensor inputs and language instructions to generate planning and control signals. While autoregressive large language models and…

Large language models (LLMs) predominantly use autoregressive (AR) approaches, but masked diffusion models (MDMs) are emerging as viable alternatives. A key challenge in comparing AR and MDM paradigms is their typical architectural…

In this report, we introduce MammothModa, yet another multi-modal large language model (MLLM) designed to achieve state-of-the-art performance starting from an elementary baseline. We focus on three key design insights: (i) Integrating…

The integration of deep learning, particularly AI-Generated Content, with high-quality data derived from ab initio calculations has emerged as a promising avenue for transforming the landscape of scientific research. However, the challenge…

Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain underexplored. Existing methods compromise by producing either low-resolution meshes or coarse…

Autoregressive (AR) language models enforce a fixed left-to-right generation order, creating a fundamental limitation when the required output structure conflicts with natural reasoning (e.g., producing answers before explanations due to…

Since its foundations, more than one hundred years ago, the field of structural biology has strived to understand and analyze the properties of molecules and their interactions by studying the structure that they take in 3D space. However,…

The integration of molecular and natural language representations has emerged as a focal point in molecular science, with recent advancements in Language Models (LMs) demonstrating significant potential for comprehensive modeling of both…

Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose \textbf{VDLM}, a modular variable diffusion language model that separates semantic planning from…

Multimodal recommender systems (MRS) integrate heterogeneous user and item data, such as text, images, and structured information, to enhance recommendation performance. The emergence of large language models (LLMs) introduces new…

We propose a method to fuse frozen text-only large language models (LLMs) with pre-trained image encoder and decoder models, by mapping between their embedding spaces. Our model demonstrates a wide suite of multimodal capabilities: image…

Vision-language-action models (VLAs) have shown generalization capabilities in robotic manipulation tasks by inheriting from vision-language models (VLMs) and learning action generation. Most VLA models focus on interpreting vision and…

Large language model (LLM)-based text-to-speech (TTS) systems achieve remarkable naturalness via autoregressive (AR) decoding, but require N sequential steps to generate N speech tokens. We present LLaDA-TTS, which replaces the AR LLM with…

Large Language Models (LLMs) have shown impressive performance across various domains, but their ability to perform molecular reasoning remains underexplored. Existing methods mostly rely on general-purpose prompting, which lacks…

Despite their ability to understand chemical knowledge, large language models (LLMs) remain limited in their capacity to propose novel molecules with desired functions (e.g., drug-like properties). In addition, the molecules that LLMs…

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end…