Spatially-resolved images of debris disks are necessary to determine disk morphological properties and the scattering phase function (SPF) which quantifies the brightness of scattered light as a function of phase angle. Current high-contrast imaging instruments have successfully resolved several dozens of debris disks around other stars, but few studies have investigated trends in the scattered-light, resolved population of debris disks in a uniform and consistent manner. We have combined Karhunen-Loeve Image Projection (KLIP) with radiative-transfer disk forward modeling in order to obtain the highest quality image reductions and constrain disk morphological properties of eight debris disks imaged by the Gemini Planet Imager at H-band with a consistent and uniformly-applied approach. In describing the scattering properties of our models, we assume a common SPF informed from solar system dust scattering measurements and apply it to all systems. We identify a diverse range of dust density properties among the sample, including critical radius, radial width, and vertical width. We also identify radially narrow and vertically extended disks that may have resulted from substellar companion perturbations, along with a tentative positive trend in disk eccentricity with relative disk width. We also find that using a common SPF can achieve reasonable model fits for disks that are axisymmetric and asymmetric when fitting models to each side of the disk independently, suggesting that scattering behavior from debris disks may be similar to Solar System dust.

The advent of large language models (LLMs) revolutionized natural language processing applications, and running LLMs on edge devices has become increasingly attractive for reasons including reduced latency, data localization, and personalized user experiences. This comprehensive review examines the challenges of deploying computationally expensive LLMs on resource-constrained devices and explores innovative solutions across multiple domains. The paper investigates the development of on-device language models, their efficient architectures, including parameter sharing and modular designs, as well as state-of-the-art compression techniques like quantization, pruning, and knowledge distillation. Hardware acceleration strategies and collaborative edge-cloud deployment approaches are analyzed, highlighting the intricate balance between performance and resource utilization. Case studies of on-device language models from major mobile manufacturers demonstrate real-world applications and potential benefits. The review also addresses critical aspects such as adaptive learning, multi-modal capabilities, and personalization. By identifying key research directions and open challenges, this paper provides a roadmap for future advancements in on-device language models, emphasizing the need for interdisciplinary efforts to realize the full potential of ubiquitous, intelligent computing while ensuring responsible and ethical deployment. For a comprehensive review of research work and educational resources on on-device large language models (LLMs), please visit this https URL To download and run on-device LLMs, visit this https URL

The challenge of translating vast, multimodal biological data into predictive and mechanistic understanding of cellular function is a central theme in modern biology. Virtual cells, or digital cellular twins, have emerged as a critical paradigm to meet this challenge by creating integrative computational models of cellular processes. This review synthesizes the evolution and current state of the virtual cell, from foundational mechanistic frameworks like the Virtual Cell that employ deterministic and stochastic simulations to the recent transformative impact of artificial intelligence and foundation models. We examine the core technological pillars required to build these models, including the integration of various data types, such as single-cell and spatial omics, the spectrum of modeling approaches, and the bioengineering principles that connect simulation to application. We further discuss key applications, frameworks for model benchmarking and validation, and the significant hurdles that remain, including computational scalability, parameter inference, and ethical considerations, which provides a roadmap for development of predictive virtual cells that promise to revolutionize biomedical research and clinical practice.

The atmospheres of low-temperature brown dwarfs and gas giant planets are expected to contain the phosphine molecule, PH$_3$ However, previous observations have shown much lower abundances of this molecule than predicted by atmospheric chemistry models. We report JWST spectroscopic observations of phosphine in the atmosphere of the brown dwarf Wolf 1130C. Multiple absorption lines due to phosphine are detected around 4.3 ${\mu}$m, from which we calculate a phosphine abundance of 0.100$\pm$0.009 parts per million. This abundance is consistent with disequilibrium atmospheric chemistry models that reproduce the phosphine abundances in Jupiter and Saturn, and is much higher than abundances previously reported for other brown dwarfs or exoplanets.

We review lattice results related to pion, kaon, $D$-meson, $B$-meson, and nucleon physics with the aim of making them easily accessible to the nuclear and particle physics communities. More specifically, we report on the determination of the light-quark masses, the form factor $f_+(0)$ arising in the semileptonic $K \to \pi$ transition at zero momentum transfer, as well as the decay-constant ratio $f_K/f_\pi$ and its consequences for the CKM matrix elements $V_{us}$ and $V_{ud}$. We review the determination of the $B_K$ parameter of neutral kaon mixing as well as the additional four $B$ parameters that arise in theories of physics beyond the Standard Model. For the heavy-quark sector, we provide results for $m_c$ and $m_b$ as well as those for the decay constants, form factors, and mixing parameters of charmed and bottom mesons and baryons. These are the heavy-quark quantities most relevant for the determination of CKM matrix elements and the global CKM unitarity-triangle fit. We review the status of lattice determinations of the strong coupling constant $\alpha_s$. We review the determinations of nucleon charges from the matrix elements of both isovector and flavour-diagonal axial, scalar and tensor local quark bilinears, and momentum fraction, helicity moment and the transversity moment from one-link quark bilinears. We also review determinations of scale-setting quantities. Finally, in this review we have added a new section on the general definition of the low-energy limit of the Standard Model.

The integration of Large Language Models (LLMs) into robotics has unlocked unprecedented capabilities in high-level task planning. However, most current systems operate in an open-loop fashion, where LLMs act as one-shot planners, rendering them brittle and unable to adapt to unforeseen circumstances in dynamic physical environments. To overcome this limitation, this paper introduces the "Think, Act, Learn" (T-A-L) framework, a novel architecture that enables an embodied agent to autonomously learn and refine its policies through continuous interaction. Our framework establishes a closed-loop cycle where an LLM first "thinks" by decomposing high-level commands into actionable plans. The robot then "acts" by executing these plans while gathering rich, multimodal sensory feedback. Critically, the "learn" module processes this feedback to facilitate LLM-driven self-reflection, allowing the agent to perform causal analysis on its failures and generate corrective strategies. These insights are stored in an experiential memory to guide future planning cycles. We demonstrate through extensive experiments in both simulation and the real world that our T-A-L agent significantly outperforms baseline methods, including open-loop LLMs, Behavioral Cloning, and traditional Reinforcement Learning. Our framework achieves over a 97% success rate on complex, long-horizon tasks, converges to a stable policy in an average of just 9 trials, and exhibits remarkable generalization to unseen tasks. This work presents a significant step towards developing more robust, adaptive, and truly autonomous robotic agents.

Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To bridge this cognitive gap, we propose a novel framework that synergistically fuses a powerful Vision Foundation Model (VFM) for deep visual perception with a Large Language Model (LLM) serving as a knowledge-driven reasoning core. Our key technical innovation is a sophisticated fusion module, inspired by the Q-Former architecture, which distills complex spatiotemporal and object-centric visual features into a concise, language-aligned representation. This enables the LLM to effectively ground its inferential processes in direct visual evidence. The model is trained via a two-stage strategy, beginning with large-scale alignment pre-training on video-text data, followed by targeted instruction fine-tuning on a curated dataset designed to elicit advanced reasoning and prediction skills. Extensive experiments demonstrate that our model achieves state-of-the-art performance on multiple challenging benchmarks. Notably, it exhibits remarkable zero-shot generalization to unseen reasoning tasks, and our in-depth ablation studies validate the critical contribution of each architectural component. This work pushes the boundary of machine perception from simple recognition towards genuine cognitive understanding, paving the way for more intelligent and capable AI systems in robotics, human-computer interaction, and beyond.

Large Language Models (LLMs), despite their advanced linguistic capabilities, fundamentally lack an intuitive understanding of physical dynamics, which limits their effectiveness in real-world scenarios that require causal reasoning. In this paper, we introduce Causal World Model Induction (CWMI), a novel framework designed to embed an explicit model of causal physics within an LLM. Our approach incorporates a dedicated Causal Physics Module (CPM) and a new training objective called Causal Intervention Loss, encouraging the model to learn cause-and-effect relationships from multimodal data. By training the model to predict the outcomes of hypothetical interventions instead of merely capturing statistical correlations, CWMI develops a robust internal representation of physical laws. Experimental results show that CWMI significantly outperforms state-of-the-art LLMs on zero-shot physical reasoning tasks, including the PIQA benchmark and our newly proposed PhysiCa-Bench dataset. These findings demonstrate that inducing a causal world model is a critical step toward more reliable and generalizable AI systems.

Within 20 pc of the Sun there are currently 29 known cold brown dwarfs, sources with measured distances and an estimated effective temperature between that of Jupiter (170K) and ~500K. These sources are almost all isolated and are the closest laboratories we have for detailed atmospheric studies of giant planets formed outside the solar system. Here we report JWST observations of one such source, WISEA J153429.75-104303.3 (W1534), which we confirm is a substellar mass member of the Galactic halo with a metallicity <0.01xsolar. Its spectrum reveals methane (CH4), water (H2O), and silane (SiH4) gas. Although SiH4 is expected to serve as a key reservoir for the cloud-forming element Si in gas giant worlds, it eluded detection until now because it is removed from observable atmospheres by the formation of silicate clouds at depth. These condensates are favored with increasing metallicity, explaining why SiH4 remains undetected on well studied, metal-rich solar system worlds like Jupiter and Saturn. On the metal-poor world W1534, we detect a clear signature of SiH4 centered at ~4.55 microns with an abundance of 19+/-2 parts per billion (ppb). Our chemical modelling suggests that this SiH4 abundance may be quenched at ~kilobar levels just above the silicate cloud layers, whereupon vertical atmospheric mixing can transport SiH4 to the observable photosphere. The formation and detection of SiH4 demonstrates key coupled relationships between composition, cloud formation, and atmospheric mixing in cold brown dwarf and planetary atmospheres.

Large language models (LLMs) show strong reasoning via chain-of-thought (CoT) prompting, but the process is opaque, which makes verification, debugging, and control difficult in high-stakes settings. We present Vis-CoT, a human-in-the-loop framework that converts linear CoT text into an interactive reasoning graph. Users can visualize the logical flow, identify flawed steps, and intervene by pruning incorrect paths and grafting new, user-defined premises. This shifts interaction from passive observation to active collaboration, steering models toward more accurate and trustworthy conclusions. Across GSM8K and StrategyQA, Vis-CoT improves final-answer accuracy by up to 24 percentage points over non-interactive baselines. A user study also shows large gains in perceived usability and trust. Vis-CoT points to a practical path for more reliable, understandable, and collaborative reasoning by combining LLMs with targeted human oversight.

Recent JWST/NIRSpec observations have revealed strong methane emission at 3.326 microns in the $\approx$482 K brown dwarf CWISEP J193518.59$-$154620.3 (W1935). Atmospheric modeling suggests the presence of a $\approx$300 K thermal inversion in its upper atmosphere, potentially driven by auroral activity. We present an extension of the retrieved spectra of W1935 with and without inversion spanning 1--20 microns, to identify thermal inversion-sensitive spectral features and explore the origin of the object's peculiar characteristics. Our analysis indicates that atmospheric heating contributes approximately 15% to the bolometric luminosity. The model with inversion predicts an additional similar-strength methane emission feature at 7.7 microns and tentative ammonia emission features in the mid-infrared. Wavelengths beyond $\sim$2 microns are significantly influenced by the inversion, except for the 4.1--5.0 microns CO$_2$ and CO features that originate from atmospheric layers deeper than the region where the inversion occurs. W1935 appears as an outlier in Spitzer/IRAC mid-infrared color-magnitude diagrams (CMDs) based on the $m_{\rm Ch1}-m_{\rm Ch2}$ (IRAC 3.6 microns $-$ 4.5 microns) color, but exhibits average behavior in all other combinations that trace clear sequences. This anomaly is likely due to the Ch2 filter probing vertical mixing-sensitive CO$_2$ and CO features that do not correlate with temperature or spectral type. We find that the thermal inversion tends to produce bluer $m_{\rm Ch1}-m_{\rm Ch2}$ colors, so the overluminous and/or redder position of W1935 in diagrams involving this color cannot be explained by the thermal inversion. This analysis provides insights into the intriguing dispersion of cold brown dwarfs in mid-infrared CMDs and sheds light on their spectral diversity.

We introduce Soft Kernel Interpolation (SoftKI), a method that combines aspects of Structured Kernel Interpolation (SKI) and variational inducing point methods, to achieve scalable Gaussian Process (GP) regression on high-dimensional datasets. SoftKI approximates a kernel via softmax interpolation from a smaller number of interpolation points learned by optimizing a combination of the SoftKI marginal log-likelihood (MLL), and when needed, an approximate MLL for improved numerical stability. Consequently, it can overcome the dimensionality scaling challenges that SKI faces when interpolating from a dense and static lattice while retaining the flexibility of variational methods to adapt inducing points to the dataset. We demonstrate the effectiveness of SoftKI across various examples and show that it is competitive with other approximated GP methods when the data dimensionality is modest (around 10).

We study aspects of Jackiw-Teitelboim (JT) quantum gravity in two-dimensional nearly de Sitter (dS) spacetime, as well as pure de Sitter quantum gravity in three dimensions. These are each theories of boundary modes, which include a reparameterization field on each connected component of the boundary as well as topological degrees of freedom. In two dimensions, the boundary theory is closely related to the Schwarzian path integral, and in three dimensions to the quantization of coadjoint orbits of the Virasoro group. Using these boundary theories we compute loop corrections to the wavefunction of the universe, and investigate gravitational contributions to scattering. Along the way, we show that JT gravity in dS$_2$ is an analytic continuation of JT gravity in Euclidean AdS$_2$, and that pure gravity in dS$_3$ is a continuation of pure gravity in Euclidean AdS$_3$. We define a genus expansion for de Sitter JT gravity by summing over higher genus generalizations of surfaces used in the Hartle-Hawking construction. Assuming a conjecture regarding the volumes of moduli spaces of such surfaces, we find that the de Sitter genus expansion is the continuation of the recently discovered AdS genus expansion. Then both may be understood as coming from the genus expansion of the same double-scaled matrix model, which would provide a non-perturbative completion of de Sitter JT gravity.

Facial expression classification remains a challenging task due to the high dimensionality and inherent complexity of facial image data. This paper presents Hy-Facial, a hybrid feature extraction framework that integrates both deep learning and traditional image processing techniques, complemented by a systematic investigation of dimensionality reduction strategies. The proposed method fuses deep features extracted from the Visual Geometry Group 19-layer network (VGG19) with handcrafted local descriptors and the scale-invariant feature transform (SIFT) and Oriented FAST and Rotated BRIEF (ORB) algorithms, to obtain rich and diverse image representations. To mitigate feature redundancy and reduce computational complexity, we conduct a comprehensive evaluation of dimensionality reduction techniques and feature extraction. Among these, UMAP is identified as the most effective, preserving both local and global structures of the high-dimensional feature space. The Hy-Facial pipeline integrated VGG19, SIFT, and ORB for feature extraction, followed by K-means clustering and UMAP for dimensionality reduction, resulting in a classification accuracy of 83. 3\% in the facial expression recognition (FER) dataset. These findings underscore the pivotal role of dimensionality reduction not only as a pre-processing step but as an essential component in improving feature quality and overall classification performance.

In recent work we computed the path integral of three-dimensional gravity with negative cosmological constant on spaces which are topologically a torus times an interval. Here we employ a modular bootstrap to show that the amplitude is completely fixed by consistency conditions and a few basic inputs from gravity. This bootstrap is notably for an ensemble of CFTs, rather than for a single instance. We also compare the 3d gravity result with the Narain ensemble. The former is well-approximated at low temperature by a random matrix theory ansatz, and we conjecture that this behavior is generic for an ensemble of CFTs at large central charge with a chaotic spectrum of heavy operators.

The proliferation of mobile devices and online interactions have been threatened by different cyberattacks, where phishing attacks and malicious Uniform Resource Locators (URLs) pose significant risks to user security. Traditional phishing URL detection methods primarily rely on URL string-based features, which attackers often manipulate to evade detection. To address these limitations, we propose a novel graph-based machine learning model for phishing URL detection, integrating both URL structure and network-level features such as IP addresses and authoritative name servers. Our approach leverages Loopy Belief Propagation (LBP) with an enhanced convergence strategy to enable effective message passing and stable classification in the presence of complex graph structures. Additionally, we introduce a refined edge potential mechanism that dynamically adapts based on entity similarity and label relationships to further improve classification accuracy. Comprehensive experiments on real-world datasets demonstrate our model's effectiveness by achieving F1 score of up to 98.77\%. This robust and reproducible method advances phishing detection capabilities, offering enhanced reliability and valuable insights in the field of cybersecurity.

We review lattice results related to pion, kaon, $D$-meson, $B$-meson, and nucleon physics with the aim of making them easily accessible to the nuclear and particle physics communities. More specifically, we report on the determination of the light-quark masses, the form factor $f_+(0)$ arising in the semileptonic $K \to \pi$ transition at zero momentum transfer, as well as the decay constant ratio $f_K/f_\pi$ and its consequences for the CKM matrix elements $V_{us}$ and $V_{ud}$. Furthermore, we describe the results obtained on the lattice for some of the low-energy constants of $SU(2)_L\times SU(2)_R$ and $SU(3)_L\times SU(3)_R$ Chiral Perturbation Theory. We review the determination of the $B_K$ parameter of neutral kaon mixing as well as the additional four $B$ parameters that arise in theories of physics beyond the Standard Model. For the heavy-quark sector, we provide results for $m_c$ and $m_b$ as well as those for the decay constants, form factors, and mixing parameters of charmed and bottom mesons and baryons. These are the heavy-quark quantities most relevant for the determination of CKM matrix elements and the global CKM unitarity-triangle fit. We review the status of lattice determinations of the strong coupling constant $\alpha_s$. We consider nucleon matrix elements, and review the determinations of the axial, scalar and tensor bilinears, both isovector and flavor diagonal. Finally, in this review we have added a new section reviewing determinations of scale-setting quantities.