Search

The Bible, a product of an extensive and intricate process of oral-written transmission spanning centuries, obscures the contours of its earlier recensions. Debate rages over determining the existing layers and identifying the date of composition and historical background of the biblical texts. Traditional manual methodologies have grappled with authorship challenges through scrupulous textual criticism, employing linguistic, stylistic, inner-biblical, and historical criteria. Despite recent progress in computer-assisted analysis, many patterns still need to be uncovered in Biblical Texts. In this study, we address the question of authorship of biblical texts by employing statistical analysis to the frequency of words using a method that is particularly sensitive to deviations in frequencies associated with a few words out of potentially many. We aim to differentiate between three distinct authors across numerous chapters spanning the first nine books of the Bible. In particular, we examine 50 chapters labeled according to biblical exegesis considerations into three corpora (D, DtrH, and P). Without prior assumptions about author identity, our approach leverages subtle differences in word frequencies to distinguish among the three corpora and identify author-dependent linguistic properties. Our analysis indicates that the first two authors (D and DtrH) are much more closely related compared to P, a fact that aligns with expert assessments. Additionally, we attain high accuracy in attributing authorship by evaluating the similarity of each chapter with the reference corpora. This study sheds new light on the authorship of biblical texts by providing interpretable, statistically significant evidence that there are different linguistic characteristics of biblical authors and that these differences can be identified.

A multi-agent AI model is used to automate the discovery of new metallic alloys, integrating multimodal data and external knowledge including insights from physics via atomistic simulations. Our multi-agent system features three key components: (a) a suite of LLMs responsible for tasks such as reasoning and planning, (b) a group of AI agents with distinct roles and expertise that dynamically collaborate, and (c) a newly developed graph neural network (GNN) model for rapid retrieval of key physical properties. A set of LLM-driven AI agents collaborate to automate the exploration of the vast design space of MPEAs, guided by predictions from the GNN. We focus on the NbMoTa family of body-centered cubic (bcc) alloys, modeled using an ML-based interatomic potential, and target two key properties: the Peierls barrier and solute/screw dislocation interaction energy. Our GNN model accurately predicts these atomic-scale properties, providing a faster alternative to costly brute-force calculations and reducing the computational burden on multi-agent systems for physics retrieval. This AI system revolutionizes materials discovery by reducing reliance on human expertise and overcoming the limitations of direct all-atom simulations. By synergizing the predictive power of GNNs with the dynamic collaboration of LLM-based agents, the system autonomously navigates vast alloy design spaces, identifying trends in atomic-scale material properties and predicting macro-scale mechanical strength, as demonstrated by several computational experiments. This approach accelerates the discovery of advanced alloys and holds promise for broader applications in other complex systems, marking a significant step forward in automated materials design.

PRefLexOR (Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning) combines preference optimization with concepts from Reinforcement Learning to enable models to self-teach through iterative reasoning improvements. We propose a recursive learning approach that engages the model in multi-step reasoning, revisiting, and refining intermediate steps before producing a final output in training and inference phases. Through multiple training stages, the model first learns to align its reasoning with accurate decision paths by optimizing the log odds between preferred and non-preferred responses. During this process, PRefLexOR builds a dynamic knowledge graph by generating questions from random text chunks and retrieval-augmentation to contextualize relevant details from the entire training corpus. In the second stage, preference optimization enhances model performance by using rejection sampling to fine-tune reasoning quality by continually producing in-situ training data while masking the reasoning steps. Recursive optimization within a thinking token framework introduces iterative feedback loops, where the model refines reasoning, achieving deeper coherence, consistency, and adaptability. Implemented in small language models with only 3 billion parameters, we should that even tiny models can iteratively teach themselves to reason with greater depth and reflectivity. Our implementation is straightforward and can be incorporated into any existing pretrained LLM. We focus our examples on applications in biological materials science and demonstrate the method in a variety of case studies that range from in-domain to cross-domain applications. Using reasoning strategies that include thinking and reflection modalities we build a multi-agent recursive self-improving inference approach to successively improve responses via repeated sampling in inference time.

Recent advancements in head avatar rendering using Gaussian primitives have achieved significantly high-fidelity results. Although precise head geometry is crucial for applications like mesh reconstruction and relighting, current methods struggle to capture intricate geometric details and render unseen poses due to their reliance on similarity transformations, which cannot handle stretch and shear transforms essential for detailed deformations of geometry. To address this, we propose SurFhead, a novel method that reconstructs riggable head geometry from RGB videos using 2D Gaussian surfels, which offer well-defined geometric properties, such as precise depth from fixed ray intersections and normals derived from their surface orientation, making them advantageous over 3D counterparts. SurFhead ensures high-fidelity rendering of both normals and images, even in extreme poses, by leveraging classical mesh-based deformation transfer and affine transformation interpolation. SurFhead introduces precise geometric deformation and blends surfels through polar decomposition of transformations, including those affecting normals. Our key contribution lies in bridging classical graphics techniques, such as mesh-based deformation, with modern Gaussian primitives, achieving state-of-the-art geometry reconstruction and rendering quality. Unlike previous avatar rendering approaches, SurFhead enables efficient reconstruction driven by Gaussian primitives while preserving high-fidelity geometry.

In recent years there has been a lot of interest in the study of isometry invariant Poisson processes of $k$-flats in $d$-dimensional hyperbolic space $\mathbb{H}^d$, for $0\le k\le d-1$. A phenomenon that has no counterpart in euclidean geometry arises in the investigation of the total $k$-dimensional volume $F_r$ of the process inside a spherical observation window $B_r$ of radius $r$ when one lets $r$ tend to infinity. While $F_r$ is asymptotically normally distributed for $2k\leq d+1$, it has been shown to obey a nonstandard central limit theorem for $2k>d+1$. The intersection process of order $m$, for $d-m(d-k) \geq 0$, of the original process $\eta$ consists of all intersections of distinct flats $E_1,\ldots,E_m \in \eta$ with $\dim(E_1\cap\ldots\cap E_m) = d-m(d-k)$. For this intersection process, the total $d-m(d-k)$-dimensional volume $F^{(m)}_r$ of the process in $B_r$, again as $r \to \infty$, is of particular interest. For $2k \leq d+1$ it has been shown that $F^{(m)}_r$ is again asymptotically normally distributed. For $m \geq 2$, the limit is so far unknown, although it has been shown for certain $d$ and $k$ that it cannot be a normal distribution. We determine the limit distribution for all values of $d,k,m$. In addition, we establish explicit rates of convergence in the Kolmogorov distance and discuss properties of the limit distribution. Furthermore we show that the asymptotic covariance matrix of the vector $(F^{(1)}_r,\ldots,F^{(m)}_r)^\top$ has full rank when $2k < d+1$ and rank one when $2k \geq d+1$.

Over the last few decades, research institutions and funders have begun policies and programs that incentivize large-scale collaboration across institutions on focal research areas. Yet, few studies have evaluated the impact of those programs on research, particularly on timelines longer than a few years. Using the Canadian Institute for Advanced Research (CIFAR) as a case study, we examined the impacts of supporting a research program that convened experts across intuitions and countries for 40+ years. In this study, we used the Scopus bibliometric database to analyse publishing and citation trends within this team since its formation in 1986 and used nearest neighbour matching to compare these trends against authors across the globe with similar career characteristics to measure how effectively the CIFAR program Gravity & the Extreme Universe (CIFAR-GEU) has catalyzed collaborations and produced high quality research outputs. We found a greater degree of co-authorship within the CIFAR-GEU group compared to the Control group. We also found that the outputs generated by the CIFAR-GEU group had, overall, higher values for citation-based impact indicators (e.g., stronger metrics around citations, impact from international collaborations and reach beyond academia).

Speech is a fundamental aspect of human life, crucial not only for communication but also for cognitive, social, and academic development. Children with speech disorders (SD) face significant challenges that, if unaddressed, can result in lasting negative impacts. Traditionally, speech and language assessments (SLA) have been conducted by skilled speech-language pathologists (SLPs), but there is a growing need for efficient and scalable SLA methods powered by artificial intelligence. This position paper presents a survey of existing techniques suitable for automating SLA pipelines, with an emphasis on adapting automatic speech recognition (ASR) models for children's speech, an overview of current SLAs and their automated counterparts to demonstrate the feasibility of AI-enhanced SLA pipelines, and a discussion of practical considerations, including accessibility and privacy concerns, associated with the deployment of AI-powered SLAs., Comment: AAAI-FSS 24

Volumetric modeling and neural radiance field representations have revolutionized 3D face capture and photorealistic novel view synthesis. However, these methods often require hundreds of multi-view input images and are thus inapplicable to cases with less than a handful of inputs. We present a novel volumetric prior on human faces that allows for high-fidelity expressive face modeling from as few as three input views captured in the wild. Our key insight is that an implicit prior trained on synthetic data alone can generalize to extremely challenging real-world identities and expressions and render novel views with fine idiosyncratic details like wrinkles and eyelashes. We leverage a 3D Morphable Face Model to synthesize a large training set, rendering each identity with different expressions, hair, clothing, and other assets. We then train a conditional Neural Radiance Field prior on this synthetic dataset and, at inference time, fine-tune the model on a very sparse set of real images of a single subject. On average, the fine-tuning requires only three inputs to cross the synthetic-to-real domain gap. The resulting personalized 3D model reconstructs strong idiosyncratic facial expressions and outperforms the state-of-the-art in high-quality novel view synthesis of faces from sparse inputs in terms of perceptual and photo-metric quality., Comment: Siggraph Asia Conference Papers 2024

We describe the design and operation of a high-stability Fabry-Perot cavity, for laser stabilization in cavity quantum-electrodynamics experiments. Our design is based on an inexpensive and readily available uniaxial carbon-fiber reinforced polymer tube spacer, featuring an ultra-low thermal expansion coefficient. As a result, our $136\mathrm{mm}$-long cavity, which has a finesse of ${5160}$, shows a coefficient of thermal expansion of $1.6 \times 10^{-6}~\mathrm{K}^{-1}$. Enclosing it in a hermetic chamber at room-pressure and using a simple temperature stabilization, we observe absolute frequency excursions over a full day below $50~\mathrm{MHz}$ for a laser operating at $446.785\mathrm{THz}$. The frequency stability is limited by the imperfect thermal isolation from the environment and can be corrected using a built-in piezo-electric actuator. In addition, we discuss a different variant of this design and identify future improvements. Our system provides a cost-effective and robust solution for transferring laser stability over different wavelengths, as well as for linewidth reduction or spectral filtering of CW laser sources for applications in quantum science., Comment: 5 pages, 4 figures

Efficient and fast reconstruction of anatomical structures plays a crucial role in clinical practice. Minimizing retrieval and processing times not only potentially enhances swift response and decision-making in critical scenarios but also supports interactive surgical planning and navigation. Recent methods attempt to solve the medical shape reconstruction problem by utilizing implicit neural functions. However, their performance suffers in terms of generalization and computation time, a critical metric for real-time applications. To address these challenges, we propose to leverage meta-learning to improve the network parameters initialization, reducing inference time by an order of magnitude while maintaining high accuracy. We evaluate our approach on three public datasets covering different anatomical shapes and modalities, namely CT and MRI. Our experimental results show that our model can handle various input configurations, such as sparse slices with different orientations and spacings. Additionally, we demonstrate that our method exhibits strong transferable capabilities in generalizing to shape domains unobserved at training time.

A key challenge in artificial intelligence is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data. In this work, we present SciAgents, an approach that leverages three core concepts: (1) the use of large-scale ontological knowledge graphs to organize and interconnect diverse scientific concepts, (2) a suite of large language models (LLMs) and data retrieval tools, and (3) multi-agent systems with in-situ learning capabilities. Applied to biologically inspired materials, SciAgents reveals hidden interdisciplinary relationships that were previously considered unrelated, achieving a scale, precision, and exploratory power that surpasses traditional human-driven research methods. The framework autonomously generates and refines research hypotheses, elucidating underlying mechanisms, design principles, and unexpected material properties. By integrating these capabilities in a modular fashion, the intelligent system yields material discoveries, critique and improve existing hypotheses, retrieve up-to-date data about existing research, and highlights their strengths and limitations. Our case studies demonstrate scalable capabilities to combine generative AI, ontological representations, and multi-agent modeling, harnessing a `swarm of intelligence' similar to biological systems. This provides new avenues for materials discovery and accelerates the development of advanced materials by unlocking Nature's design principles.

The advancement of Large Language Models (LLMs) for domain applications in fields such as materials science and engineering depends on the development of fine-tuning strategies that adapt models for specialized, technical capabilities. In this work, we explore the effects of Continued Pretraining (CPT), Supervised Fine-Tuning (SFT), and various preference-based optimization approaches, including Direct Preference Optimization (DPO) and Odds Ratio Preference Optimization (ORPO), on fine-tuned LLM performance. Our analysis shows how these strategies influence model outcomes and reveals that the merging of multiple fine-tuned models can lead to the emergence of capabilities that surpass the individual contributions of the parent models. We find that model merging leads to new functionalities that neither parent model could achieve alone, leading to improved performance in domain-specific assessments. Experiments with different model architectures are presented, including Llama 3.1 8B and Mistral 7B models, where similar behaviors are observed. Exploring whether the results hold also for much smaller models, we use a tiny LLM with 1.7 billion parameters and show that very small LLMs do not necessarily feature emergent capabilities under model merging, suggesting that model scaling may be a key component. In open-ended yet consistent chat conversations between a human and AI models, our assessment reveals detailed insights into how different model variants perform and show that the smallest model achieves a high intelligence score across key criteria including reasoning depth, creativity, clarity, and quantitative precision. Other experiments include the development of image generation prompts based on disparate biological material design concepts, to create new microstructures, architectural concepts, and urban design based on biological materials-inspired construction principles.

Conway's Game of Life (Life), a well known algorithm within the broader class of cellular automata (CA), exhibits complex emergent dynamics, with extreme sensitivity to initial conditions. Modeling and predicting such intricate behavior without explicit knowledge of the system's underlying topology presents a significant challenge, motivating the development of algorithms that can generalize across various grid configurations and boundary conditions. We develop a decoder-only generative pretrained transformer (GPT) model to solve this problem, showing that our model can simulate Life on a toroidal grid with no prior knowledge on the size of the grid, or its periodic boundary conditions (LifeGPT). LifeGPT is topology-agnostic with respect to its training data and our results show that a GPT model is capable of capturing the deterministic rules of a Turing-complete system with near-perfect accuracy, given sufficiently diverse training data. We also introduce the idea of an `autoregressive autoregressor' to recursively implement Life using LifeGPT. Our results pave the path towards true universal computation within a large language model framework, synthesizing of mathematical analysis with natural language processing, and probing AI systems for situational awareness about the evolution of such algorithms without ever having to compute them. Similar GPTs could potentially solve inverse problems in multicellular self-assembly by extracting CA-compatible rulesets from real-world biological systems to create new predictive models, which would have significant consequences for the fields of bioinspired materials, tissue engineering, and architected materials design.

Using nonlinear simulations in two settings, we demonstrate that QG$^\mathrm{+1}$, a potential-vorticity (PV) based next-order-in-Rossby balanced model, captures several aspects of ocean submesoscale physics. In forced-dissipative 3D simulations under baroclinically unstable Eady-type background states, the statistical equilibrium turbulence exhibits long cyclonic tails and a plethora of rapidly-intensifying ageostrophic fronts. Despite that the model requires setting an explicit, small value for the fixed scaling Rossby number, the emergent flows are nevertheless characterized by $O(f)$ vorticity and convergence, as observed in upper-ocean submesoscale flows. Simulations of QG$^\mathrm{+1}$ under the classic strain-induced frontogenesis set-up show realistic frontal asymmetry and a finite time blow-up, quantitatively comparable to simulations of the semigeostrophic equations. The inversions in the QG$^\mathrm{+1}$ model are straightforward elliptic problems, allowing for the reconstruction of all flow fields from the PV and surface buoyancy, while avoiding the semigeostrophic coordinate transformation. Together, these results suggest QG$^\mathrm{+1}$ as a useful tool for studying upper-ocean submesoscale dynamics.

The design of alloys is a multi-scale problem that requires a holistic approach that involves retrieving relevant knowledge, applying advanced computational methods, conducting experimental validations, and analyzing the results, a process that is typically reserved for human experts. Machine learning (ML) can help accelerate this process, for instance, through the use of deep surrogate models that connect structural features to material properties, or vice versa. However, existing data-driven models often target specific material objectives, offering limited flexibility to integrate out-of-domain knowledge and cannot adapt to new, unforeseen challenges. Here, we overcome these limitations by leveraging the distinct capabilities of multiple AI agents that collaborate autonomously within a dynamic environment to solve complex materials design tasks. The proposed physics-aware generative AI platform, AtomAgents, synergizes the intelligence of large language models (LLM) the dynamic collaboration among AI agents with expertise in various domains, including knowledge retrieval, multi-modal data integration, physics-based simulations, and comprehensive results analysis across modalities that includes numerical data and images of physical simulation results. The concerted effort of the multi-agent system allows for addressing complex materials design problems, as demonstrated by examples that include autonomously designing metallic alloys with enhanced properties compared to their pure counterparts. Our results enable accurate prediction of key characteristics across alloys and highlight the crucial role of solid solution alloying to steer the development of advanced metallic alloys. Our framework enhances the efficiency of complex multi-objective design tasks and opens new avenues in fields such as biomedical materials engineering, renewable energy, and environmental sustainability.

During developmental processes such as embryogenesis, how a group of cells fold into specific structures, is a central question in biology that defines how living organisms form. Establishing tissue-level morphology critically relies on how every single cell decides to position itself relative to its neighboring cells. Despite its importance, it remains a major challenge to understand and predict the behavior of every cell within the living tissue over time during such intricate processes. To tackle this question, we propose a geometric deep learning model that can predict multicellular folding and embryogenesis, accurately capturing the highly convoluted spatial interactions among cells. We demonstrate that multicellular data can be represented with both granular and foam-like physical pictures through a unified graph data structure, considering both cellular interactions and cell junction networks. We successfully use our model to achieve two important tasks, interpretable 4-D morphological sequence alignment, and predicting local cell rearrangements before they occur at single-cell resolution. Furthermore, using an activation map and ablation studies, we demonstrate that cell geometries and cell junction networks together regulate local cell rearrangement which is critical for embryo morphogenesis. This approach provides a novel paradigm to study morphogenesis, highlighting a unified data structure and harnessing the power of geometric deep learning to accurately model the mechanisms and behaviors of cells during development. It offers a pathway toward creating a unified dynamic morphological atlas for a variety of developmental processes such as embryogenesis.

Attention is a key factor for successful learning, with research indicating strong associations between (in)attention and learning outcomes. This dissertation advanced the field by focusing on the automated detection of attention-related processes using eye tracking, computer vision, and machine learning, offering a more objective, continuous, and scalable assessment than traditional methods such as self-reports or observations. It introduced novel computational approaches for assessing various dimensions of (in)attention in online and classroom learning settings and addressing the challenges of precise fine-granular assessment, generalizability, and in-the-wild data quality. First, this dissertation explored the automated detection of mind-wandering, a shift in attention away from the learning task. Aware and unaware mind wandering were distinguished employing a novel multimodal approach that integrated eye tracking, video, and physiological data. Further, the generalizability of scalable webcam-based detection across diverse tasks, settings, and target groups was examined. Second, this thesis investigated attention indicators during online learning. Eye-tracking analyses revealed significantly greater gaze synchronization among attentive learners. Third, it addressed attention-related processes in classroom learning by detecting hand-raising as an indicator of behavioral engagement using a novel view-invariant and occlusion-robust skeleton-based approach. This thesis advanced the automated assessment of attention-related processes within educational settings by developing and refining methods for detecting mind wandering, on-task behavior, and behavioral engagement. It bridges educational theory with advanced methods from computer science, enhancing our understanding of attention-related processes that significantly impact learning outcomes and educational practices., Comment: Doctoral thesis

One persistent obstacle in industrial quality inspection is the detection of anomalies. In real-world use cases, two problems must be addressed: anomalous data is sparse and the same types of anomalies need to be detected on previously unseen objects. Current anomaly detection approaches can be trained with sparse nominal data, whereas domain generalization approaches enable detecting objects in previously unseen domains. Utilizing those two observations, we introduce the hybrid task of domain generalization on sparse classes. To introduce an accompanying dataset for this task, we present a modification of the well-established MVTec AD dataset by generating three new datasets. In addition to applying existing methods for benchmark, we design two embedding-based approaches, Spatial Embedding MLP (SEMLP) and Labeled PatchCore. Overall, SEMLP achieves the best performance with an average image-level AUROC of 87.2 % vs. 80.4 % by MIRO. The new and openly available datasets allow for further research to improve industrial anomaly detection., Comment: Accepted as extended abstract in CVPR 2024 workshop VAND 2.0

We find the turbulent energy spectrum of weakly interacting 2D internal gravity waves without relying on the hydrostatic approximation. This spectrum is an exact solution of the kinetic equation after the shear modes are removed, and it agrees with the oceanic Garrett-Munk spectrum for frequencies large compared to the Coriolis frequency and vertical scales small compared to the depth of the ocean. Among a continuous family of solutions to the kinetic equation, we show that the turbulent solution is the special solution with non zero angular dependent radial flux. Our solution provides an interesting insight of how turbulent energy cascade proceeds in anisotropic systems - similarly to isotropic turbulence it is self-similar in scale, but its angular part is peaked along the curve of vanishing frequency., Comment: 6 pages, 4 figures

We report a mixture of expert strategy to create fine-tuned large language models using a deep layer-wise token-level approach based on low-rank adaptation (LoRA). Starting with a set of pre-trained LoRA adapters, our gating strategy uses the hidden states to dynamically mix adapted layers, allowing the resulting X-LoRA model to draw upon different capabilities and create never-before-used deep layer-wise combinations to solve tasks. The design is inspired by the biological principles of universality and diversity, where neural network building blocks are reused in different hierarchical manifestations. Hence, the X-LoRA model can be easily implemented for any existing large language model (LLM) without a need for modifications of the underlying structure. We develop a tailored X-LoRA model that offers scientific capabilities including forward/inverse analysis tasks and enhanced reasoning capability, focused on biomaterial analysis, protein mechanics and design. The impact of this work include access to readily expandable and adaptable models with strong domain knowledge and the capability to integrate across areas of knowledge. Featuring experts in biology, mathematics, reasoning, bio-inspired materials, mechanics and materials, chemistry, protein biophysics, mechanics and quantum-mechanics based molecular properties, we conduct a series of physics-focused case studies. We examine knowledge recall, protein mechanics forward/inverse tasks, protein design, adversarial agentic modeling including ontological knowledge graph construction, as well as molecular design. The model is capable not only of making quantitative predictions of nanomechanical properties of proteins or quantum mechanical molecular properties, but also reasons over the results and correctly predicts likely mechanisms that explain distinct molecular behaviors.

We present Cephalo, a series of multimodal vision large language models (V-LLMs) designed for materials science applications, integrating visual and linguistic data for enhanced understanding. A key innovation of Cephalo is its advanced dataset generation method. Cephalo is trained on integrated image and text data from thousands of scientific papers and science-focused Wikipedia data demonstrates can interpret complex visual scenes, generate precise language descriptions, and answer queries about images effectively. The combination of a vision encoder with an autoregressive transformer supports multimodal natural language understanding, which can be coupled with other generative methods to create an image-to-text-to-3D pipeline. To develop more capable models from smaller ones, we report both mixture-of-expert methods and model merging. We examine the models in diverse use cases that incorporate biological materials, fracture and engineering analysis, protein biophysics, and bio-inspired design based on insect behavior. Generative applications include bio-inspired designs, including pollen-inspired architected materials, as well as the synthesis of bio-inspired material microstructures from a photograph of a solar eclipse. Additional model fine-tuning with a series of molecular dynamics results demonstrate Cephalo's enhanced capabilities to accurately predict statistical features of stress and atomic energy distributions, as well as crack dynamics and damage in materials.

A fundamental problem of out-of-equilibrium physics is the speed at which the order parameter grows upon crossing a phase transition. Here, we investigate the dynamics of ordering in a Fermi gas undergoing a density-wave phase transition induced by quenching of long-range, cavity-mediated interactions. We observe in real-time the exponential rise of the order parameter and track its growth over several orders of magnitude. Remarkably, the growth rate is insensitive to the contact interaction strength from the ideal gas up to the unitary limit and can exceed the Fermi energy by an order of magnitude, in quantitative agreement with a linearized instability analysis. We then generalize our results to linear interaction ramps, where deviations from the adiabatic behaviour are captured by a simple dynamical ansatz. Our study offers a paradigmatic example of the interplay between non-locality and non-equilibrium dynamics, where universal scaling behaviour emerges despite strong interactions at the microscopic level., Comment: 14 pages, 7 figures

We consider the motion of a circularly-moving perturber in a self-gravitating, collisional system with spherically symmetric density profile. We concentrate on the singular isothermal sphere which, despite its pathological features, admits a simple polarization function in linear response theory. This allows us to solve for the acoustic wake trailing the perturber and the resulting dynamical friction, in the limit where the self-gravity of the response can be ignored. In steady-state and for subsonic velocities $v_p

Here, we present the 1UVA catalog of time variable ultraviolet (UV) sources. We describe a new analysis pipeline, the VAriable Source Clustering Analysis (VASCA). We apply the pipeline to 10 years of data from the GALaxy Evolution eXplorer (GALEX) satellite. We analyse a sky area of 302 deg$^2$ , resulting in the detection of 4202 time-variable UV sources. We cross correlate these sources with multi-frequency data from the Gaia satellite and the SIMBAD database, finding an association for 3655 sources. The source sample is dominated by Active Galactic Nuclei ($\approx$73 %) and stars ($\approx$24 %). We look at UV and multi-frequency properties of these sources, focusing on the stellar population. We find UV variability for four White Dwarfs. One of them, WD J004917.14-252556.81, has recently been found to be the most massive pulsating White Dwarf. Its Spectral Energy Distribution shows no sign of a stellar companion. The observed flux variability is unexpected and difficult to explain., Comment: Accepted for publication in Astronomy and Astrophysics. The 1UVA catalog will be made available via the Strasbourg astronomical Data Center (CDS). The article has 13 pages and contains 11 figures

We conducted measurements of $K^- + {^3{\rm He}} \to \pi \!Y \!N + N'$ reactions using a $1~{\rm GeV}/c$ $K^-$-beam, with the objective of understanding the broad decay width of $\bar{K} \!N \!N$ (approximately twice as broad as that of $\Lambda(1405)$ considered to be the $\bar{K} \!N$ quasi-bound state). We successfully reproduced distributions of the $\pi \! Y \! N$ invariant mass and momentum transfer for $\pi \! Y \! N$ using model fitting functions for $\bar{K} \!N \!N$ formation and quasi-free $\bar{K}$ absorption (${\rm QF}_{\bar{K}-{\rm abs}}$) processes. The model can describe the experimental data quite well, and four $\bar{K} \! N \! N \to \pi \! Y \! N $ cross-sections were obtained. The results indicate that mesonic decay is the dominant decay branch of $\bar{K} \! N \! N$. The results also suggest that $\Gamma_{\pi \Lambda N} \sim \Gamma_{\pi \Sigma N}$, which indicates that the $I_{\bar{K} \! N}=1$ absorption channel, in addition to the $I_{\bar{K} \! N}=0$ absorption channel, substantially contribute to the $\bar{K} \! N \! N$ decay, making the $\bar{K} \! N \! N$ state approximately twice as unstable as $\Lambda$(1405).

Classroom observation protocols standardize the assessment of teaching effectiveness and facilitate comprehension of classroom interactions. Whereas these protocols offer teachers specific feedback on their teaching practices, the manual coding by human raters is resource-intensive and often unreliable. This has sparked interest in developing AI-driven, cost-effective methods for automating such holistic coding. Our work explores a multimodal approach to automatically estimating encouragement and warmth in classrooms, a key component of the Global Teaching Insights (GTI) study's observation protocol. To this end, we employed facial and speech emotion recognition with sentiment analysis to extract interpretable features from video, audio, and transcript data. The prediction task involved both classification and regression methods. Additionally, in light of recent large language models' remarkable text annotation capabilities, we evaluated ChatGPT's zero-shot performance on this scoring task based on transcripts. We demonstrated our approach on the GTI dataset, comprising 367 16-minute video segments from 92 authentic lesson recordings. The inferences of GPT-4 and the best-trained model yielded correlations of r = .341 and r = .441 with human ratings, respectively. Combining estimates from both models through averaging, an ensemble approach achieved a correlation of r = .513, comparable to human inter-rater reliability. Our model explanation analysis indicated that text sentiment features were the primary contributors to the trained model's decisions. Moreover, GPT-4 could deliver logical and concrete reasoning as potential teacher guidelines. Our findings provide insights into using advanced, multimodal techniques for automated classroom observation, aiming to foster teacher training through frequent and valuable feedback., Comment: Accepted as a full paper by the 25th International Conference on Artificial Intelligence in Education (AIED 2024)

We introduce a novel framework for 3D human avatar generation and personalization, leveraging text prompts to enhance user engagement and customization. Central to our approach are key innovations aimed at overcoming the challenges in photo-realistic avatar synthesis. Firstly, we utilize a conditional Neural Radiance Fields (NeRF) model, trained on a large-scale unannotated multi-view dataset, to create a versatile initial solution space that accelerates and diversifies avatar generation. Secondly, we develop a geometric prior, leveraging the capabilities of Text-to-Image Diffusion Models, to ensure superior view invariance and enable direct optimization of avatar geometry. These foundational ideas are complemented by our optimization pipeline built on Variational Score Distillation (VSD), which mitigates texture loss and over-saturation issues. As supported by our extensive experiments, these strategies collectively enable the creation of custom avatars with unparalleled visual quality and better adherence to input text prompts. You can find more results and videos in our website: https://syntec-research.github.io/MagicMirror

Successful learning depends on learners' ability to sustain attention, which is particularly challenging in online education due to limited teacher interaction. A potential indicator for attention is gaze synchrony, demonstrating predictive power for learning achievements in video-based learning in controlled experiments focusing on manipulating attention. This study (N=84) examines the relationship between gaze synchronization and self-reported attention of learners, using experience sampling, during realistic online video learning. Gaze synchrony was assessed through Kullback-Leibler Divergence of gaze density maps and MultiMatch algorithm scanpath comparisons. Results indicated significantly higher gaze synchronization in attentive participants for both measures and self-reported attention significantly predicted post-test scores. In contrast, synchrony measures did not correlate with learning outcomes. While supporting the hypothesis that attentive learners exhibit similar eye movements, the direct use of synchrony as an attention indicator poses challenges, requiring further research on the interplay of attention, gaze synchrony, and video content type.

Leveraging generative Artificial Intelligence (AI), we have transformed a dataset comprising 1,000 scientific papers into an ontological knowledge graph. Through an in-depth structural analysis, we have calculated node degrees, identified communities and connectivities, and evaluated clustering coefficients and betweenness centrality of pivotal nodes, uncovering fascinating knowledge architectures. The graph has an inherently scale-free nature, is highly connected, and can be used for graph reasoning by taking advantage of transitive and isomorphic properties that reveal unprecedented interdisciplinary relationships that can be used to answer queries, identify gaps in knowledge, propose never-before-seen material designs, and predict material behaviors. We compute deep node embeddings for combinatorial node similarity ranking for use in a path sampling strategy links dissimilar concepts that have previously not been related. One comparison revealed structural parallels between biological materials and Beethoven's 9th Symphony, highlighting shared patterns of complexity through isomorphic mapping. In another example, the algorithm proposed a hierarchical mycelium-based composite based on integrating path sampling with principles extracted from Kandinsky's 'Composition VII' painting. The resulting material integrates an innovative set of concepts that include a balance of chaos/order, adjustable porosity, mechanical strength, and complex patterned chemical functionalization. We uncover other isomorphisms across science, technology and art, revealing a nuanced ontology of immanence that reveal a context-dependent heterarchical interplay of constituents. Graph-based generative AI achieves a far higher degree of novelty, explorative capacity, and technical detail, than conventional approaches and establishes a widely useful framework for innovation by revealing hidden connections.

This work addresses flexibility in deep learning by means of transductive reasoning. For adaptation to new data and tasks, e.g., in continual learning, existing methods typically involve tuning learnable parameters or complete re-training from scratch, rendering such approaches unflexible in practice. We argue that the notion of separating computation from memory by the means of transduction can act as a stepping stone for solving these issues. We therefore propose PARMESAN (parameter-free memory search and transduction), a scalable method which leverages a memory module for solving dense prediction tasks. At inference, hidden representations in memory are being searched to find corresponding patterns. In contrast to other methods that rely on continuous training of learnable parameters, PARMESAN learns via memory consolidation simply by modifying stored contents. Our method is compatible with commonly used architectures and canonically transfers to 1D, 2D, and 3D grid-based data. The capabilities of our approach are demonstrated at the complex task of continual learning. PARMESAN learns by 3-4 orders of magnitude faster than established baselines while being on par in terms of predictive performance, hardware-efficiency, and knowledge retention., Comment: preprint, 25 pages, 7 figures

We present SpaceHopper, a three-legged, small-scale robot designed for future mobile exploration of asteroids and moons. The robot weighs 5.2kg and has a body size of 245mm while using space-qualifiable components. Furthermore, SpaceHopper's design and controls make it well-adapted for investigating dynamic locomotion modes with extended flight-phases. Instead of gyroscopes or fly-wheels, the system uses its three legs to reorient the body during flight in preparation for landing. We control the leg motion for reorientation using Deep Reinforcement Learning policies. In a simulation of Ceres' gravity (0.029g), the robot can reliably jump to commanded positions up to 6m away. Our real-world experiments show that SpaceHopper can successfully reorient to a safe landing orientation within 9.7 degree inside a rotational gimbal and jump in a counterweight setup in Earth's gravity. Overall, we consider SpaceHopper an important step towards controlled jumping locomotion in low-gravity environments., Comment: To be published in the 2024 IEEE International Conference on Robotics and Automation

The Fermi All-sky Variability Analysis (FAVA) provides a photometric alternative for identifying week-long gamma-ray flares across the entire sky while being independent of any diffuse Galactic or isotropic emission model. We reviewed 779 weeks of Fermi-LAT data analyzed by FAVA to estimate the rate and origin of Galactic gamma-ray flares, and to search for new variable Galactic gamma-ray transients. We report an estimated yearly rate of ~8.5 Galactic gamma-ray flares/year with ~1 flare/year coming from unknown sources. Out of the known gamma-ray sources that are spatially coincident with these detected flares, we report gamma-ray flares for six of them for the first time. All six are classified as pulsars, or a source of unknown nature but which positionally overlaps with known supernova remnants or pulsar wind nebulae. This potentially means these sites are tentative candidates to be the second known site of a variable gamma-ray pulsar wind nebula (PWN), after the famous Crab Nebula's PWN. Additionally, we identify 9 unassociated flares that are unlikely to have originated from known gamma-ray sources., Comment: Submitted to ApJ Feb. 28 2024. Minor edits in Section 4 and 5 for clarity. 26 pages, 6 figures, 5 Tables

Designing de novo proteins beyond those found in nature holds significant promise for advancements in both scientific and engineering applications. Current methodologies for protein design often rely on AI-based models, such as surrogate models that address end-to-end problems by linking protein structure to material properties or vice versa. However, these models frequently focus on specific material objectives or structural properties, limiting their flexibility when incorporating out-of-domain knowledge into the design process or comprehensive data analysis is required. In this study, we introduce ProtAgents, a platform for de novo protein design based on Large Language Models (LLMs), where multiple AI agents with distinct capabilities collaboratively address complex tasks within a dynamic environment. The versatility in agent development allows for expertise in diverse domains, including knowledge retrieval, protein structure analysis, physics-based simulations, and results analysis. The dynamic collaboration between agents, empowered by LLMs, provides a versatile approach to tackling protein design and analysis problems, as demonstrated through diverse examples in this study. The problems of interest encompass designing new proteins, analyzing protein structures and obtaining new first-principles data -- natural vibrational frequencies -- via physics simulations. The concerted effort of the system allows for powerful automated and synergistic design of de novo proteins with targeted mechanical properties. The flexibility in designing the agents, on one hand, and their capacity in autonomous collaboration through the dynamic LLM-based multi-agent environment on the other hand, unleashes great potentials of LLMs in addressing multi-objective materials problems and opens up new avenues for autonomous materials discovery and design.

Sewage sludge, a biosolid product of wastewater processing, is an often-overlooked source of rich organic waste. Hydrothermal processing (HTP), which uses heat and pressure to convert biomass into various solid, liquid, and gaseous products, has shown promise in converting sewage sludge into new materials with potential application in biofuels, asphalt binders, and bioplastics. In this study we focus on hydrochar, the carbonaceous HTP solid phase, and investigate its use as a bio-based filler in additive manufacturing technologies. We explore the impact of HTP and subsequent thermal activation on chemical and structural properties of sewage sludge and discuss the role of atypical metallic and metalloid dopants in organic material processing. In additive manufacturing composites, although the addition of hydrochar generally decreases mechanical performance, we show that toughness and strain can be recovered with hierarchical microstructures, much like biological materials that achieve outstanding properties by architecting relatively weak building blocks.

Multicellular self-assembly into functional structures is a dynamic process that is critical in the development and diseases, including embryo development, organ formation, tumor invasion, and others. Being able to infer collective cell migratory dynamics from their static configuration is valuable for both understanding and predicting these complex processes. However, the identification of structural features that can indicate multicellular motion has been difficult, and existing metrics largely rely on physical instincts. Here we show that using a graph neural network (GNN), the motion of multicellular collectives can be inferred from a static snapshot of cell positions, in both experimental and synthetic datasets.

Regression analyses based on transformations of cumulative incidence functions are often adopted when modeling and testing for treatment effects in clinical trial settings involving competing and semi-competing risks. Common frameworks include the Fine-Gray model and models based on direct binomial regression. Using large sample theory we derive the limiting values of treatment effect estimators based on such models when the data are generated according to multiplicative intensity-based models, and show that the estimand is sensitive to several process features. The rejection rates of hypothesis tests based on cumulative incidence function regression models are also examined for null hypotheses of different types, based on which a robustness property is established. In such settings supportive secondary analyses of treatment effects are essential to ensure a full understanding of the nature of treatment effects. An application to a palliative study of individuals with breast cancer metastatic to bone is provided for illustration.

Quantitative measurement of crystals in high-resolution images allows for important insights into underlying material characteristics. Deep learning has shown great progress in vision-based automatic crystal size measurement, but current instance segmentation methods reach their limits with images that have large variation in crystal size or hard to detect crystal boundaries. Even small image segmentation errors, such as incorrectly fused or separated segments, can significantly lower the accuracy of the measured results. Instead of improving the existing pixel-wise boundary segmentation methods, we propose to use an instance-based segmentation method, which gives more robust segmentation results to improve measurement accuracy. Our novel method enhances flow maps with a size-aware multi-scale attention module. The attention module adaptively fuses information from multiple scales and focuses on the most relevant scale for each segmented image area. We demonstrate that our proposed attention fusion strategy outperforms state-of-the-art instance and boundary segmentation methods, as well as simple average fusion of multi-scale predictions. We evaluate our method on a refractory raw material dataset of high-resolution images with large variation in crystal size and show that our model can be used to calculate the crystal size more accurately than existing methods., Comment: has been accepted for publication in IEEE Transactions on Instrumentation and Measurement

Solving mechanics problems using numerical methods requires comprehensive intelligent capability of retrieving relevant knowledge and theory, constructing and executing codes, analyzing the results, a task that has thus far mainly been reserved for humans. While emerging AI methods can provide effective approaches to solve end-to-end problems, for instance via the use of deep surrogate models or various data analytics strategies, they often lack physical intuition since knowledge is baked into the parametric complement through training, offering less flexibility when it comes to incorporating mathematical or physical insights. By leveraging diverse capabilities of multiple dynamically interacting large language models (LLMs), we can overcome the limitations of conventional approaches and develop a new class of physics-inspired generative machine learning platform, here referred to as MechAgents. A set of AI agents can solve mechanics tasks, here demonstrated for elasticity problems, via autonomous collaborations. A two-agent team can effectively write, execute and self-correct code, in order to apply finite element methods to solve classical elasticity problems in various flavors (different boundary conditions, domain geometries, meshes, small/finite deformation and linear/hyper-elastic constitutive laws, and others). For more complex tasks, we construct a larger group of agents with enhanced division of labor among planning, formulating, coding, executing and criticizing the process and results. The agents mutually correct each other to improve the overall team-work performance in understanding, formulating and validating the solution. Our framework shows the potential of synergizing the intelligence of language models, the reliability of physics-based modeling, and the dynamic collaborations among diverse agents, opening novel avenues for automation of solving engineering problems.

We highlight a non-canonical yet natural choice of variables for an efficient derivation of a kinetic equation for the energy density in non-isotropic systems, including internal gravity waves on a vertical plane, inertial and Rossby waves. The existence of a second quadratic invariant simplifies the kinetic equation and leads to extra conservation laws for resonant interactions. We analytically determine the scaling of the radial turbulent energy spectrum. Our findings suggest the existence of an inverse energy cascade of internal gravity waves, from small to large scales, in practically relevant scenarios.

Transformer neural networks show promising capabilities, in particular for uses in materials analysis, design and manufacturing, including their capacity to work effectively with both human language, symbols, code, and numerical data. Here we explore the use of large language models (LLMs) as a tool that can support engineering analysis of materials, applied to retrieving key information about subject areas, developing research hypotheses, discovery of mechanistic relationships across disparate areas of knowledge, and writing and executing simulation codes for active knowledge generation based on physical ground truths. When used as sets of AI agents with specific features, capabilities, and instructions, LLMs can provide powerful problem solution strategies for applications in analysis and design problems. Our experiments focus on using a fine-tuned model, MechGPT, developed based on training data in the mechanics of materials domain. We first affirm how finetuning endows LLMs with reasonable understanding of domain knowledge. However, when queried outside the context of learned matter, LLMs can have difficulty to recall correct information. We show how this can be addressed using retrieval-augmented Ontological Knowledge Graph strategies that discern how the model understands what concepts are important and how they are related. Illustrated for a use case of relating distinct areas of knowledge - here, music and proteins - such strategies can also provide an interpretable graph structure with rich information at the node, edge and subgraph level. We discuss nonlinear sampling strategies and agent-based modeling applied to complex question answering, code generation and execution in the context of automated force field development from actively learned Density Functional Theory (DFT) modeling, and data analysis.

Through evolution, nature has presented a set of remarkable protein materials, including elastins, silks, keratins and collagens with superior mechanical performances that play crucial roles in mechanobiology. However, going beyond natural designs to discover proteins that meet specified mechanical properties remains challenging. Here we report a generative model that predicts protein designs to meet complex nonlinear mechanical property-design objectives. Our model leverages deep knowledge on protein sequences from a pre-trained protein language model and maps mechanical unfolding responses to create novel proteins. Via full-atom molecular simulations for direct validation, we demonstrate that the designed proteins are novel, and fulfill the targeted mechanical properties, including unfolding energy and mechanical strength, as well as the detailed unfolding force-separation curves. Our model offers rapid pathways to explore the enormous mechanobiological protein sequence space unconstrained by biological synthesis, using mechanical features as target to enable the discovery of protein materials with superior mechanical properties.

For centuries, researchers have sought out ways to connect disparate areas of knowledge. While early scholars (Galileo, da Vinci, etc.) were experts across fields, specialization has taken hold later. With the advent of Artificial Intelligence, we can now explore relationships across areas (e.g., mechanics-biology) or disparate domains (e.g., failure mechanics-art). To achieve this, we use a fine-tuned Large Language Model (LLM), here for a subset of knowledge in multiscale materials failure. The approach includes the use of a general-purpose LLM to distill question-answer pairs from raw sources followed by LLM fine-tuning. The resulting MechGPT LLM foundation model is used in a series of computational experiments to explore its capacity for knowledge retrieval, various language tasks, hypothesis generation, and connecting knowledge across disparate areas. While the model has some ability to recall knowledge from training, we find that LLMs are particularly useful to extract structural insights through Ontological Knowledge Graphs. These interpretable graph structures provide explanatory insights, frameworks for new research questions, and visual representations of knowledge that also can be used in retrieval-augmented generation. Three versions of MechGPT are discussed, featuring different sizes from 13 billion to 70 billion parameters, and reaching context lengths of more than 10,000 tokens. This provides ample capacity for sophisticated retrieval augmented strategies, as well as agent-based modeling where multiple LLMs interact collaboratively and/or adversarially, the incorporation of new data from the literature or web searches, as well as multimodality.

Inventory matching is a standard mechanism/auction for trading financial stocks by which buyers and sellers can be paired. In the financial world, banks often undertake the task of finding such matches between their clients. The related stocks can be traded without adversely impacting the market price for either client. If matches between clients are found, the bank can offer the trade at advantageous rates. If no match is found, the parties have to buy or sell the stock in the public market, which introduces additional costs. A problem with the process as it is presently conducted is that the involved parties must share their order to buy or sell a particular stock, along with the intended quantity (number of shares), to the bank. Clients worry that if this information were to leak somehow, then other market participants would become aware of their intentions and thus cause the price to move adversely against them before their transaction finalizes. We provide a solution, Prime Match, that enables clients to match their orders efficiently with reduced market impact while maintaining privacy. In the case where there are no matches, no information is revealed. Our main cryptographic innovation is a two-round secure linear comparison protocol for computing the minimum between two quantities without preprocessing and with malicious security, which can be of independent interest. We report benchmarks of our Prime Match system, which runs in production and is adopted by J.P. Morgan. The system is designed utilizing a star topology network, which provides clients with a centralized node (the bank) as an alternative to the idealized assumption of point-to-point connections, which would be impractical and undesired for the clients to implement in reality. Prime Match is the first secure multiparty computation solution running live in the traditional financial world., Comment: 27 pages, 7 figures, USENIX Security 2023

In a gaseous medium, dynamical friction (DF) reaches a maximum when the orbital speed of a (point-like) perturber moving on a circular orbit is close to the sound speed. Therefore, in a quasi-steady state, eccentric orbits of perturbers approaching the sound barrier (from below) should rapidly circularize as they experience the strongest drag at pericenter passage. To investigate this effect, we extend the solution of Desjacques et al. 2022 for circular DF in a uniform gaseous medium to eccentric Keplerian orbits. We derive an approximation to the steady-state DF force, which is valid for eccentricities as high as $e=0.9$ in a limited range of Mach number around the transition to supersonic regime. We validate our analytical result with 3-dimensional simulations of the gas density response. Although gaseous DF generally dissipates orbital energy, we find that it can be directed along the motion of the perturber near pericenter passage when the eccentricity is $e\gtrsim 0.9$. We apply our results to compute the long-time evolution of the orbital parameters. Most trajectories tend to circularize as the perturber moves into the supersonic regime. However, orbits with eccentricities $e\gtrsim 0.8$ below the sound barrier experience a slight increase in eccentricity as they loose orbital energy. Possible extensions to our analytical approach are also discussed., Comment: 12 pages, 7 figures; Comments welcome

Reversible crosslinkers can enable several desirable mechanical properties, such as improved toughness and self-healing, when incorporated in polymer networks for bioengineering and structural applications. In this work, we performed coarse-grained molecular dynamics to investigate the effect of the energy landscape of reversible crosslinkers on the dynamic mechanical properties of crosslinked polymer network hydrogels. We report that, for an ideal network, the energy potential of the crosslinker interaction drives the viscosity of the network, where a stronger potential results in a higher viscosity. Additional topographical analyses reveal a mechanistic understanding of the structural rearrangement of the network as it deforms and indicate that as the number of defects increases in the network, the viscosity of the network increases. As an important validation for the relationship between the energy landscape of a crosslinker chemistry and the resulting dynamic mechanical properties of a crosslinked ideal network hydrogel, this work enhances our understanding of deformation mechanisms in polymer networks that cannot easily be revealed by experiment and reveals design ideas that can lead to better performance of the polymer network at the macroscale.

NeRFs have enabled highly realistic synthesis of human faces including complex appearance and reflectance effects of hair and skin. These methods typically require a large number of multi-view input images, making the process hardware intensive and cumbersome, limiting applicability to unconstrained settings. We propose a novel volumetric human face prior that enables the synthesis of ultra high-resolution novel views of subjects that are not part of the prior's training distribution. This prior model consists of an identity-conditioned NeRF, trained on a dataset of low-resolution multi-view images of diverse humans with known camera calibration. A simple sparse landmark-based 3D alignment of the training dataset allows our model to learn a smooth latent space of geometry and appearance despite a limited number of training identities. A high-quality volumetric representation of a novel subject can be obtained by model fitting to 2 or 3 camera views of arbitrary resolution. Importantly, our method requires as few as two views of casually captured images as input at inference time., Comment: In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Spider silks are remarkable materials characterized by superb mechanical properties such as strength, extensibility and lightweightedness. Yet, to date, limited models are available to fully explore sequence-property relationships for analysis and design. Here we propose a custom generative large-language model to enable design of novel spider silk protein sequences to meet complex combinations of target mechanical properties. The model, pretrained on a large set of protein sequences, is fine-tuned on ~1,000 major ampullate spidroin (MaSp) sequences for which associated fiber-level mechanical properties exist, to yield an end-to-end forward and inverse generative strategy. Performance is assessed through: (1), a novelty analysis and protein type classification for generated spidroin sequences through BLAST searches, (2) property evaluation and comparison with similar sequences, (3) comparison of molecular structures, as well as, and (4) a detailed sequence motif analyses. We generate silk sequences with property combinations that do not exist in nature, and develop a deep understanding the mechanistic roles of sequence patterns in achieving overarching key mechanical properties (elastic modulus, strength, toughness, failure strain). The model provides an efficient approach to expand the silkome dataset, facilitating further sequence-structure analyses of silks, and establishes a foundation for synthetic silk design and optimization.