相关论文: PhononBench:A Large-Scale Phonon-Based Benchmark f…

We present MaterialFigBench, a benchmark dataset designed to evaluate the ability of multimodal large language models (LLMs) to solve university-level materials science problems that require accurate interpretation of figures. Unlike…

Machine Learning (ML) has transformed many scientific fields, yet key applications still lack standardized benchmarks. Raman spectroscopy, a widely used technique for non-invasive molecular analysis, is one such field where progress is…

Mitigating low-frequency vibration or noise is of vital importance to both human health and mechanical engineering. Two-dimensional phononic crystal (PC) structures were proposed by attaching rubber and metallic cylinders on one or both…

Vibrational entropy plays a central role in determining phase stability and temperature dependent behavior in materials, yet its calculation from first-principles phonon methods remains computationally demanding. In this work, we combine…

Video-to-audio generation (V2A) is of increasing importance in domains such as film post-production, AR/VR, and sound design, particularly for the creation of Foley sound effects synchronized with on-screen actions. Foley requires…

Stably placing an object in a multi-object scene is a fundamental challenge in robotic manipulation, as placements must be penetration-free, establish precise surface contact, and result in a force equilibrium. To assess stability, existing…

Layout-guided text-to-image models offer greater control over the generation process by explicitly conditioning image synthesis on the spatial arrangement of elements. As a result, their adoption has increased in many computer vision…

Understanding the anharmonic phonon properties of crystal compounds -- such as phonon lifetimes and thermal conductivities -- is essential for investigating and optimizing their thermal transport behaviors. These properties also impact…

The rapid advancement of diffusion models, particularly Stable Diffusion 3.5, has enabled the generation of highly photorealistic synthetic images that pose significant challenges to existing detection methods. This paper presents…

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…

Research in AI4Science has shown promise in many science applications, including polymer design. However, current LLMs are ineffective in this problem space because: (i) most models lack polymer-specific knowledge, and (ii) existing aligned…

Phononic crystals (PnCs) are periodic engineered media that can customize the spatio-temporal characteristics of mechanical energy propagation. PnCs that additionally leverage precisely embedded defects can achieve robust energy…

Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence during training, while diffusion methods require multi-step…

The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the…

While machine-learned interatomic potentials (MLIPs) accelerate phonon dispersion calculations, merely identifying dynamical instabilities in computationally predicted materials is insufficient; automated pathways to resolve them are…

Predicting the stability of crystals is one of the central problems in materials science. Today, density functional theory (DFT) calculations are the computational tool of choice to obtain energies of crystals with quantitative accuracy.…

Breakthroughs in frontier theory often depend on the combination of concrete diagrammatic notations with rigorous logic. While multimodal large language models (MLLMs) show promise in general scientific tasks, current benchmarks often focus…

Defects are ubiquitous in solids and strongly influence materials' mechanical and functional properties. However, non-destructive characterization and quantification of defects, especially when multiple types coexist, remain a long-standing…

The discovery of novel solid-state materials, such as electrocatalysts, super-ionic conductors, or photovoltaic materials, plays a critical role in addressing various global challenges. It has, for instance, the potential to significantly…

Reliable long-term forecasting of Earth system dynamics is fundamentally limited by instabilities in current artificial intelligence (AI) models during extended autoregressive simulations. These failures often originate from inherent…