Search

Bearing in mind the limited parametric knowledge of Large Language Models (LLMs), retrieval-augmented generation (RAG) which supplies them with the relevant external knowledge has served as an approach to mitigate the issue of hallucinations to a certain extent. However, uniformly retrieving supporting context makes response generation source-inefficient, as triggering the retriever is not always necessary, or even inaccurate, when a model gets distracted by noisy retrieved content and produces an unhelpful answer. Motivated by these issues, we introduce Semantic Uncertainty Guided Adaptive Retrieval (SUGAR), where we leverage context-based entropy to actively decide whether to retrieve and to further determine between single-step and multi-step retrieval. Our empirical results show that selective retrieval guided by semantic uncertainty estimation improves the performance across diverse question answering tasks, as well as achieves a more efficient inference., Comment: ICASSP2025

Gallium oxide is a novel advanced material gaining increasing attention for its unique combination of functional properties. It forms in several phases or polymorphs - {\alpha}, {\beta}, {\gamma}, and {\kappa} - having variable properties because of different lattice symmetries. Optical properties are of particular importance as they determine specific device applications and can also be used for phase identification. However, a direct comparison of optical polymorph signatures, including such critical parameters as bandgaps, is challenging due to the scattered, limited, or even absent data for certain phases in the literature. To address this issue, in the present work we systematically cross-correlate optical emission and absorption features of {\alpha}, {\beta}, {\gamma}, and {\kappa} thin films, as well as differently oriented {\beta}-phase bulk crystals and {\gamma}/{\beta} double polymorph structures. We demonstrate that the optical bandgap and emission features scale consistently across these polymorphs upon minimization of the methodological uncertainties. As a result, this work provides a comparative library of near- and far-field optical signatures of the polymorphs for use by the multidisciplinary research community working with gallium oxide., Comment: 17 pages, 14 figures, 4 tables

Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress, they often struggle to capture the causal and temporal dynamics inherent in complex video sequences. To address this limitation, we propose an enhanced framework that integrates a Causal-Temporal Reasoning Module (CTRM) into state-of-the-art LVLMs. CTRM comprises two key components: the Causal Dynamics Encoder (CDE) and the Temporal Relational Learner (TRL), which collectively encode causal dependencies and temporal consistency from video frames. We further design a multi-stage learning strategy to optimize the model, combining pre-training on large-scale video-text datasets, fine-tuning on causally annotated data, and contrastive alignment for better embedding coherence. Experimental results on standard benchmarks such as MSVD and MSR-VTT demonstrate that our method outperforms existing approaches in both automatic metrics (CIDEr, BLEU-4, ROUGE-L) and human evaluations, achieving more fluent, coherent, and relevant captions. These results validate the effectiveness of our approach in generating captions with enriched causal-temporal narratives.

Brain-computer interfaces (BCIs) have shown promise in enabling communication for individuals with motor impairments. Recent advancements like brain-to-speech technology aim to reconstruct speech from neural activity. However, decoding communication-related paradigms, such as imagined speech and visual imagery, using non-invasive techniques remains challenging. This study analyzes brain dynamics in these two paradigms by examining neural synchronization and functional connectivity through phase-locking values (PLV) in EEG data from 16 participants. Results show that visual imagery produces higher PLV values in visual cortex, engaging spatial networks, while imagined speech demonstrates consistent synchronization, primarily engaging language-related regions. These findings suggest that imagined speech is suitable for language-driven BCI applications, while visual imagery can complement BCI systems for users with speech impairments. Personalized calibration is crucial for optimizing BCI performance., Comment: 4 pages

Interpreting human neural signals to decode static speech intentions such as text or images and dynamic speech intentions such as audio or video is showing great potential as an innovative communication tool. Human communication accompanies various features, such as articulatory movements, facial expressions, and internal speech, all of which are reflected in neural signals. However, most studies only generate short or fragmented outputs, while providing informative communication by leveraging various features from neural signals remains challenging. In this study, we introduce a dynamic neural communication method that leverages current computer vision and brain-computer interface technologies. Our approach captures the user's intentions from neural signals and decodes visemes in short time steps to produce dynamic visual outputs. The results demonstrate the potential to rapidly capture and reconstruct lip movements during natural speech attempts from human neural signals, enabling dynamic neural communication through the convergence of computer vision and brain--computer interface., Comment: 4 pages, 2 figures, 1 table, Name of Conference: International Conference on Brain-Computer Interface

Many risk-sensitive applications require well-calibrated prediction sets over multiple, potentially correlated target variables, for which the prediction algorithm may report correlated non-conformity scores. In this work, we treat the scores as random vectors and aim to construct the prediction set accounting for their joint correlation structure. Drawing from the rich literature on multivariate quantiles and semiparametric statistics, we propose an algorithm to estimate the $1-\alpha$ quantile of the scores, where $\alpha$ is the user-specified miscoverage rate. In particular, we flexibly estimate the joint cumulative distribution function (CDF) of the scores using nonparametric vine copulas and improve the asymptotic efficiency of the quantile estimate using its influence function. The vine decomposition allows our method to scale well to a large number of targets. We report desired coverage and competitive efficiency on a range of real-world regression problems, including those with missing-at-random labels in the calibration set., Comment: 9 pages (+12 appendix), 11 figures, submitted to AISTATS 2025

Quasars are bright active galactic nuclei powered by the accretion of matter around supermassive black holes at the center of galaxies. Their stochastic brightness variability depends on the physical properties of the accretion disk and black hole. The upcoming Rubin Observatory Legacy Survey of Space and Time (LSST) is expected to observe tens of millions of quasars, so there is a need for efficient techniques like machine learning that can handle the large volume of data. Quasar variability is believed to be driven by an X-ray corona, which is reprocessed by the accretion disk and emitted as UV/optical variability. We are the first to introduce an auto-differentiable simulation of the accretion disk and reprocessing. We use the simulation as a direct component of our neural network to jointly model the driving variability and reprocessing to fit simulated LSST 10-year quasar light curves. The driving variability is reconstructed using a latent stochastic differential equation, a physically motivated, generative deep learning method that can model continuous-time stochastic dynamics. By embedding these physical processes into our network, we achieve a model that is more robust and interpretable. We also use transformers to scale our model to tens of millions of parameters. We demonstrate how our model outperforms a Gaussian process regression baseline and can infer accretion disk parameters and time delays between wavebands, even for out-of-distribution driving signals. Our approach provides a powerful and scalable framework that can be adapted to solve other inverse problems in multivariate time series with irregular sampling., Comment: 31 pages, 19 figures

Disorder-induced ordering and unprecedentedly high radiation tolerance in $\gamma$-phase of gallium oxide is a recent spectacular discovery at the intersection of the fundamental physics and electronic applications. Importantly, by far, these data were collected with initial samples in form of the thermodynamically stable $\beta$-phase of this material. Here, we investigate these phenomena starting instead from already metastable $\alpha$-phase and explain radically new trend occurring in the system. We argue that in contrast to that in $\beta$-to-$\gamma$ disorder-induced transitions, the O sublattice in $\alpha$-phase exhibits hexagonal close-packed structure, so that to activate $\alpha$-to-$\gamma$ transformation significant structural rearrangements are required in both Ga and O sublattices. Moreover, consistently with theoretical predictions, $\alpha$-to-$\gamma$ phase transformation requires accumulation of the substantial tensile strain to initiate otherwise impossible lattice glides. Thus, we explain the experimentally observed trends in term of the combination of disorder and strain governing the process. Finally, and perhaps most amazingly, we demonstrate atomically abrupt $\alpha$/$\gamma$ interfaces paradoxically self-organized out of the stochastic disorder., Comment: 9 pages, 4 figures, under peer review

Agricultural meteorological recommendations are crucial for enhancing crop productivity and sustainability by providing farmers with actionable insights based on weather forecasts, soil conditions, and crop-specific data. This paper presents a novel approach that leverages large language models (LLMs) and prompt engineering to improve the accuracy and relevance of these recommendations. We designed a multi-round prompt framework to iteratively refine recommendations using updated data and feedback, implemented on ChatGPT, Claude2, and GPT-4. Our method was evaluated against baseline models and a Chain-of-Thought (CoT) approach using manually collected datasets. The results demonstrate significant improvements in accuracy and contextual relevance, with our approach achieving up to 90\% accuracy and high GPT-4 scores. Additional validation through real-world pilot studies further confirmed the practical benefits of our method, highlighting its potential to transform agricultural practices and decision-making., Comment: 10 pages

Machine learning (ML) has demonstrated significant promise in accelerating drug design. Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model predicting the target property of interest. The model predictions are used to determine which designs to evaluate in the lab, and the model is updated on the new measurements to inform the next cycle of decisions. A key challenge is that the experimental feedback from each cycle inspires changes in the candidate proposal or experimental protocol for the next cycle, which lead to distribution shifts. To promote robustness to these shifts, we must account for them explicitly in the model training. We apply domain generalization (DG) methods to classify the stability of interactions between an antibody and antigen across five domains defined by design cycles. Our results suggest that foundational models and ensembling improve predictive performance on out-of-distribution domains. We publicly release our codebase extending the DG benchmark ``DomainBed,'' and the associated dataset of antibody sequences and structures emulating distribution shifts across design cycles.

Diffusion models have demonstrated remarkable performance in generation tasks. Nevertheless, explaining the diffusion process remains challenging due to it being a sequence of denoising noisy images that are difficult for experts to interpret. To address this issue, we propose the three research questions to interpret the diffusion process from the perspective of the visual concepts generated by the model and the region where the model attends in each time step. We devise tools for visualizing the diffusion process and answering the aforementioned research questions to render the diffusion process human-understandable. We show how the output is progressively generated in the diffusion process by explaining the level of denoising and highlighting relationships to foundational visual concepts at each time step through the results of experiments with various visual analyses using the tools. Throughout the training of the diffusion model, the model learns diverse visual concepts corresponding to each time-step, enabling the model to predict varying levels of visual concepts at different stages. We substantiate our tools using Area Under Cover (AUC) score, correlation quantification, and cross-attention mapping. Our findings provide insights into the diffusion process and pave the way for further research into explainable diffusion mechanisms., Comment: 22 pages, published in Expert Systems with Applications

This article introduces idMotif, a visual analytics framework designed to aid domain experts in the identification of motifs within protein sequences. Motifs, short sequences of amino acids, are critical for understanding the distinct functions of proteins. Identifying these motifs is pivotal for predicting diseases or infections. idMotif employs a deep learning-based method for the categorization of protein sequences, enabling the discovery of potential motif candidates within protein groups through local explanations of deep learning model decisions. It offers multiple interactive views for the analysis of protein clusters or groups and their sequences. A case study, complemented by expert feedback, illustrates idMotif's utility in facilitating the analysis and identification of protein sequences and motifs., Comment: IEEE CGA