Related papers: BRIDGE: Branching Ratio Inquiry/Decay Generated Ev…
Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalability challenge is that verified synthesis requires consistent artifacts across several coupled…
Recently, there is a need for a general-purpose event generator of decays of an elementary particle or a hadron to a state of higher multiplicity ($N > 2$) that is simple to use and universal. We present the structure of such a library to…
Business Document Information Extraction (BDIE) is the problem of transforming a blob of unstructured information (raw text, scanned documents, etc.) into a structured format that downstream systems can parse and use. It has two main tasks:…
We present a study for the generation of events from a physical process with deep generative models. The simulation of physical processes requires not only the production of physical events, but also to ensure these events occur with the…
We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of points that are disparate and high-magnitude when…
We have just entered an era of precision measurements for $B_s$-decay observables. A characteristic feature of the $B_s$-meson system is $B^0_s$--$\bar B^0_s$ mixing, which exhibits a sizable decay width difference. The latter feature leads…
Coarse-mask local image editing asks a model to modify a user-indicated region while preserving the surrounding scene. In practice, however, rough masks often become unintended shape priors: instead of serving as flexible edit support, the…
Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs, is a critical step in the temporal complex event schema induction task.…
Diffusion-based generative graph models have been proven effective in generating high-quality small graphs. However, they need to be more scalable for generating large graphs containing thousands of nodes desiring graph statistics. In this…
Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge.…
Recent advances in EEG-based BCI technologies have revealed the potential of brain-to-robot collaboration through the integration of sensing, computing, communication, and control. In this paper, we present BRIEDGE as an end-to-end system…
Universal image restoration is a critical task in low-level vision, requiring the model to remove various degradations from low-quality images to produce clean images with rich detail. The challenges lie in sampling the distribution of…
Grain Boundary (GB) deformation mechanisms such as Sliding (GBS) and Opening (GBO) are prevalent in alloys at high homologous temperatures but are hard to capture quantitatively. We propose an automated procedure to quantify 3D GB…
To assess the knowledge proficiency of a learner, multiple choice question is an efficient and widespread form in standard tests. However, the composition of the multiple choice question, especially the construction of distractors is quite…
Recently developed deep neural models like NetGAN, CELL, and Variational Graph Autoencoders have made progress but face limitations in replicating key graph statistics on generating large graphs. Diffusion-based methods have emerged as…
Gas transport and other complex real-world challenges often require solving and controlling partial differential equations (PDEs) defined on graph structures, which typically demand substantial memory and computational resources. The Random…
We propose to apply several gradient estimation techniques to enable the differentiation of programs with discrete randomness in High Energy Physics. Such programs are common in High Energy Physics due to the presence of branching processes…
The computer code DECAY4 is developed to generate initial energy, time and angular distributions of particles emitted in radioactive decays of nuclides and nuclear (atomic) deexcitations. Data for description of nuclear and atomic decay…
Gradient-enhanced Kriging (GE-Kriging) is a well-established surrogate modelling technique for approximating expensive computational models. However, it tends to get impractical for high-dimensional problems due to the size of the inherent…
Despite the success of deep learning for text and image data, tree-based ensemble models are still state-of-the-art for machine learning with heterogeneous tabular data. However, there is a significant need for tabular-specific…