Related papers: Towards Foundation Models for Experimental Readout…
Cell-level dense prediction is central to computational pathology, but remains challenging due to fine-grained histological structures, strong domain shifts, and costly dense annotations. Existing ViT-based pathology foundation models rely…
Discrete diffusion language models (DDLMs) generate text by iteratively denoising categorical token sequences, while recent drifting methods for continuous generators suggest that part of this sampling-time correction can instead be…
Experiments at the future Electron Ion Collider require excellent hadron identification in a broad momentum range, in harsh conditions. A RICH capable to fulfill the PID requirements of the EIC could use MPGD-based photon detectors with…
We address the Continual Learning (CL) problem, wherein a model must learn a sequence of tasks from non-stationary distributions while preserving prior knowledge upon encountering new experiences. With the advancement of foundation models,…
The Booster Neutrino Experiment (MiniBooNE) searches for muon neutrino to electron neutrino oscillations using the ~1 GeV neutrino beam produced by the FNAL Booster synchrotron. The array of photomultiplier tubes (PMTs) lining the MiniBooNE…
We demonstrate in this paper that a generative model can be designed to perform classification tasks under challenging settings, including adversarial attacks and input distribution shifts. Specifically, we propose a conditional variational…
Fast and accurate data-driven prediction of molecular properties is pivotal to scientific advancements across myriad chemical domains. Deep learning methods have recently garnered much attention, despite their inability to outperform…
Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A…
High precision atomic data is indispensable for experiments involving studies of fundamental interactions, astrophysics, atomic clocks, plasma science, and others. We develop new parallel atomic structure codes and explore the difficulties…
Generating textual descriptions for images has been an attractive problem for the computer vision and natural language processing researchers in recent years. Dozens of models based on deep learning have been proposed to solve this problem.…
If a galactic supernova explosion occurs in the future, it will be critical to rapidly alert the community to the direction of the supernova by utilizing neutrino signals in order to enable the initiation of follow-up optical observations.…
Temporal causal representation learning is a powerful tool for uncovering complex patterns in observational studies, which are often represented as low-dimensional time series. However, in many real-world applications, data are…
We introduce QERNEL, a foundational neural wavefunction that variationally solves families of parameterized many-electron Hamiltonians and captures their ground states throughout parameter space within a single model. QERNEL combines…
Cerenkov technology is often the optimal choice for particle identification in high energy particle collision applications. Typically, the most challenging regime is at high pseudorapidity (forward) where particle identification must…
In the recent years, photonic Chern materials have attracted substantial interest as they feature topological edge states that are robust against disorder, promising to realize defect-agnostic integrated photonic crystal slab devices.…
Transformers operate as horizontal token-by-token scanners; at each generation step, attending to an ever-growing sequence of token-level states. This access pattern increases prefill latency and makes long-context decoding more…
We introduce a novel kernel-based framework for learning differential equations and their solution maps that is efficient in data requirements, in terms of solution examples and amount of measurements from each example, and computational…
The widespread success of foundation models in natural language processing and computer vision has inspired researchers to extend the concept to scientific machine learning and computational science. However, this position paper argues that…
Coherent elastic neutrino-nucleus scattering (CEvNS) opens new approaches for the search of new physics beyond the Standard Model. The NUCLEUS experiment aims to use the intense antineutrino flux produced from nuclear reactor cores to…
In this paper, we propose a novel tensor learning and coding model for third-order data completion. Our model is to learn a data-adaptive dictionary from the given observations, and determine the coding coefficients of third-order tensor…