Search

We present a novel neural algorithm for performing high-quality, high-resolution, real-time novel view synthesis. From a sparse set of input RGB images or videos streams, our network both reconstructs the 3D scene and renders novel views at 1080p resolution at 30fps on an NVIDIA A100. Our feed-forward network generalizes across a wide variety of datasets and scenes and produces state-of-the-art quality for a real-time method. Our quality approaches, and in some cases surpasses, the quality of some of the top offline methods. In order to achieve these results we use a novel combination of several key concepts, and tie them together into a cohesive and effective algorithm. We build on previous works that represent the scene using semi-transparent layers and use an iterative learned render-and-refine approach to improve those layers. Instead of flat layers, our method reconstructs layered depth maps (LDMs) that efficiently represent scenes with complex depth and occlusions. The iterative update steps are embedded in a multi-scale, UNet-style architecture to perform as much compute as possible at reduced resolution. Within each update step, to better aggregate the information from multiple input views, we use a specialized Transformer-based network component. This allows the majority of the per-input image processing to be performed in the input image space, as opposed to layer space, further increasing efficiency. Finally, due to the real-time nature of our reconstruction and rendering, we dynamically create and discard the internal 3D geometry for each frame, generating the LDM for each view. Taken together, this produces a novel and effective algorithm for view synthesis. Through extensive evaluation, we demonstrate that we achieve state-of-the-art quality at real-time rates. Project page: https://quark-3d.github.io/, Comment: SIGGRAPH Asia 2024 camera ready version; project page https://quark-3d.github.io/

Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. State-of-the-art influence functions, such as EK-FAC, often fail to accurately attribute abnormal model behavior to the specific poisoned training data responsible for the data poisoning attack. In addition, traditional unlearning algorithms often struggle to effectively remove the influence of poisoned samples, particularly when only a few affected examples can be identified. To address these challenge, we introduce $\Delta$-Influence, a novel approach that leverages influence functions to trace abnormal model behavior back to the responsible poisoned training data using as little as just one poisoned test example. $\Delta$-Influence applies data transformations that sever the link between poisoned training data and compromised test points without significantly affecting clean data. This allows $\Delta$-Influence to detect large negative shifts in influence scores following data transformations, a phenomenon we term as influence collapse, thereby accurately identifying poisoned training data. Unlearning this subset, e.g. through retraining, effectively eliminates the data poisoning. We validate our method across three vision-based poisoning attacks and three datasets, benchmarking against four detection algorithms and five unlearning strategies. We show that $\Delta$-Influence consistently achieves the best unlearning across all settings, showing the promise of influence functions for corrective unlearning. Our code is publicly available at: \url{https://github.com/andyisokay/delta-influence}, Comment: Accepted at NeurIPS Workshop on Attributing Model Behavior at Scale (ATTRIB @ NeurIPS 2024)

This monograph presents a theoretical background and a broad introduction to the Min-Max Framework for Majorization-Minimization (MM4MM), an algorithmic methodology for solving minimization problems by formulating them as min-max problems and then employing majorization-minimization. The monograph lays out the mathematical basis of the approach used to reformulate a minimization problem as a min-max problem. With the prerequisites covered, including multiple illustrations of the formulations for convex and non-convex functions, this work serves as a guide for developing MM4MM-based algorithms for solving non-convex optimization problems in various areas of signal processing. As special cases, we discuss using the majorization-minimization technique to solve min-max problems encountered in signal processing applications and min-max problems formulated using the Lagrangian. Lastly, we present detailed examples of using MM4MM in ten signal processing applications such as phase retrieval, source localization, independent vector analysis, beamforming and optimal sensor placement in wireless sensor networks. The devised MM4MM algorithms are free of hyper-parameters and enjoy the advantages inherited from the use of the majorization-minimization technique such as monotonicity., Comment: 84 pages, no figures, published in Foundations and Trends in Signal Processing: Vol. 18: No. 4, pp 310-389. http://dx.doi.org/10.1561/2000000129

Networks are designed to communicate, operate and allocate the tasks to the respective commodities. Operating the supercomputers became challenging, and it was handled by the network design commonly known as hypercube, denoted by $Q^n$. In a recent study, the hypercube networks were not enough to hold the parallel processors in the supercomputers. Thus, variants of hypercubes were discovered to produce an alternative to the hypercube. A new variant of the hypercube, the \textit{fractal cubic network}, can be used as the best alternative in the case of hypercubes, which was wrongly defined in [Eng. Sci. Technol. \textbf{18}(1) (2015) 32--41]. Arulperumjothi et al. recently corrected this definition and redefined the network in [Appl. Math. Comput. \textbf{452} (2023) 128037]. Our research investigates that the fractal cubic network is a \textit{rooted product} of two graphs. We try to determine its domination and resolving domination parameters, which could be applied to resource location and broadcasting-related problems.

Machine Learning and data mining techniques (i.e. supervised and unsupervised techniques) are used across domains to detect user safety violations. Examples include classifiers used to detect whether an email is spam or a web-page is requesting bank login information. However, existing ML/DM classifiers are limited in their ability to understand natural languages w.r.t the context and nuances. The aforementioned challenges are overcome with the arrival of Gen-AI techniques, along with their inherent ability w.r.t translation between languages, fine-tuning between various tasks and domains. In this manuscript, we provide a comprehensive overview of the various work done while using Gen-AI techniques w.r.t user safety. In particular, we first provide the various domains (e.g. phishing, malware, content moderation, counterfeit, physical safety) across which Gen-AI techniques have been applied. Next, we provide how Gen-AI techniques can be used in conjunction with various data modalities i.e. text, images, videos, audio, executable binaries to detect violations of user-safety. Further, also provide an overview of how Gen-AI techniques can be used in an adversarial setting. We believe that this work represents the first summarization of Gen-AI techniques for user-safety.

From CMB polarization data alone we reconstruct the CMB lensing power spectrum, comparable in overall constraining power to previous temperature-based reconstructions, and an unlensed E-mode power spectrum. The observations, taken in 2019 and 2020 with the South Pole Telescope (SPT) and the SPT-3G camera, cover 1500 deg$^2$ at 95, 150, and 220 GHz with arcminute resolution and roughly 4.9$\mu$K-arcmin coadded noise in polarization. The power spectrum estimates, together with systematic parameter estimates and a joint covariance matrix, follow from a Bayesian analysis using the Marginal Unbiased Score Expansion (MUSE) method. The E-mode spectrum at $\ell>2000$ and lensing spectrum at $L>350$ are the most precise to date. Assuming the $\Lambda$CDM model, and using only these SPT data and priors on $\tau$ and absolute calibration from Planck, we find $H_0=66.81\pm0.81$ km/s/Mpc, comparable in precision to the Planck determination and in 5.4$\sigma$ tension with the most precise $H_0$ inference derived via the distance ladder. We also find $S_8=0.850\pm0.017$, providing further independent evidence of a slight tension with low-redshift structure probes. The $\Lambda$CDM model provides a good simultaneous fit to the combined Planck, ACT, and SPT data, and thus passes a powerful test. Combining these CMB datasets with BAO observations, we find that the effective number of neutrino species, spatial curvature, and primordial helium fraction are consistent with standard model values, and that the 95% confidence upper limit on the neutrino mass sum is 0.075 eV. The SPT data are consistent with the somewhat weak preference for excess lensing power seen in Planck and ACT data relative to predictions of the $\Lambda$CDM model. We also detect at greater than 3$\sigma$ the influence of non-linear evolution in the CMB lensing power spectrum and discuss it in the context of the $S_8$ tension.(abridged), Comment: 28 pages, 21 figures + appendices

The detection of satellite thermal emission at millimeter wavelengths is presented using data from the 3rd-Generation receiver on the South Pole Telescope (SPT-3G). This represents the first reported detection of thermal emission from artificial satellites at millimeter wavelengths. Satellite thermal emission is shown to be detectable at high signal-to-noise on timescales as short as a few tens of milliseconds. An algorithm for downloading orbital information and tracking known satellites given observer constraints and time-ordered observatory pointing is described. Consequences for cosmological surveys and short-duration transient searches are discussed, revealing that the integrated thermal emission from all large satellites does not contribute significantly to the SPT-3G survey intensity map. Measured satellite positions are found to be discrepant from their two-line element (TLE) derived ephemerides up to several arcminutes which may present a difficulty in cross-checking or masking satellites from short-duration transient searches.

Biomedical research requires large, diverse samples to produce unbiased results. Automated methods for matching variables across datasets can accelerate this process. Research in this area has been limited, primarily focusing on lexical matching and ontology based semantic matching. We aimed to develop new methods, leveraging large language models (LLM) and ensemble learning, to automate variable matching. Methods: We utilized data from two GERAS cohort (European and Japan) studies to develop variable matching methods. We first manually created a dataset by matching 352 EU variables with 1322 candidate JP variables, where matched variable pairs were positive and unmatched pairs were negative instances. Using this dataset, we developed and evaluated two types of natural language processing (NLP) methods, which matched variables based on variable labels and definitions from data dictionaries: (1) LLM-based and (2) fuzzy matching. We then developed an ensemble-learning method, using the Random Forest model, to integrate individual NLP methods. RF was trained and evaluated on 50 trials. Each trial had a random split (4:1) of training and test sets, with the model's hyperparameters optimized through cross-validation on the training set. For each EU variable, 1322 candidate JP variables were ranked based on NLP-derived similarity scores or RF's probability scores, denoting their likelihood to match the EU variable. Ranking performance was measured by top-n hit ratio (HRn) and mean reciprocal rank (MRR). Results:E5 performed best among individual methods, achieving 0.90 HR-30 and 0.70 MRR. RF performed better than E5 on all metrics over 50 trials (P less than 0.001) and achieved an average HR 30 of 0.98 and MRR of 0.73. LLM-derived features contributed most to RF's performance. One major cause of errors in automatic variable matching was ambiguous variable definitions within data dictionaries., Comment: 32 pages, 2 figures

Rare-earth emitters in solids are well-suited for implementing efficient, long-lived quantum memory coupled to integrated photonics for scalable quantum technologies. They are typically introduced as dopants in a solid-state host, but this introduces disorder and limits the available density of emitters. Stoichiometric materials can offer high densities with narrow optical linewidths. The regular spacing of emitters also opens possibilities for quantum information processing and collective effects. Here we show narrow optical linewidths in a layered stoichiometric crystalline material, NaEu(IO$_3$)$_4$. We observed an inhomogeneous linewidth of 2.2(1) GHz and a homogeneous linewidth of 120(4) kHz. Using spectral hole-burning techniques, we observe a hyperfine spin lifetime of 1.9(4) s. Furthermore, we demonstrate an atomic frequency comb delay of up to 800 ns.

The paper formalizes a version of parallel online directed acyclic graph (DAG) exploration, general enough to be readily mapped to many computational scenarios. In both the offline and online versions, vertices are weighted with the work units required for their processing, at least one parent must be completely processed before a child is processed, and at any given time only one processor can work on any given vertex. The online version has the following additional natural restriction: only after a vertex is processed, are its required work units or its children known. Using the Actor Model of parallel computation, it is shown that a natural class of parallel online algorithms meets a simple competitive ratio bound. We demonstrate and focus on the problem's occurrence in the scenario of energy landscape roadmapping or atlasing under pair-potentials, a highly compute-and-storage intensive modeling component integral to diverse applications involving soft-matter assembly. The method is experimentally validated using a C++ Actor Framework (CAF) software implementation built atop EASAL (Efficient Atlasing and Search of Assembly Landscapes), a substantial opensource software suite, running on multiple CPU cores of the HiperGator supercomputer, demonstrating linear speedup results.

This study presents an innovative dynamic weighting knowledge distillation (KD) framework tailored for efficient Earth observation (EO) image classification (IC) in resource-constrained settings. Utilizing EfficientViT and MobileViT as teacher models, this framework enables lightweight student models, particularly ResNet8 and ResNet16, to surpass 90% in accuracy, precision, and recall, adhering to the stringent confidence thresholds necessary for reliable classification tasks. Unlike conventional KD methods that rely on static weight distribution, our adaptive weighting mechanism responds to each teacher model's confidence, allowing student models to prioritize more credible sources of knowledge dynamically. Remarkably, ResNet8 delivers substantial efficiency gains, achieving a 97.5% reduction in parameters, a 96.7% decrease in FLOPs, an 86.2% cut in power consumption, and a 63.5% increase in inference speed over MobileViT. This significant optimization of complexity and resource demands establishes ResNet8 as an optimal candidate for EO tasks, combining robust performance with feasibility in deployment. The confidence-based, adaptable KD approach underscores the potential of dynamic distillation strategies to yield high-performing, resource-efficient models tailored for satellite-based EO applications. The reproducible code is accessible on our GitHub repository., Comment: Under revisions

Earth observation (EO) systems are essential for mapping, catastrophe monitoring, and resource management, but they have trouble processing and sending large amounts of EO data efficiently, especially for specialized applications like agriculture and real-time disaster response. This paper presents a novel framework for semantic communication in EO satellite networks, aimed at enhancing data transmission efficiency and system performance through cognitive processing techniques. The proposed system leverages Discrete Task-Oriented Joint Source-Channel Coding (DT-JSCC) and Semantic Data Augmentation (SA) integrate cognitive semantic processing with inter-satellite links, enabling efficient analysis and transmission of multispectral imagery for improved object detection, pattern recognition, and real-time decision-making. Cognitive Semantic Augmentation (CSA) is introduced to enhance a system's capability to process and transmit semantic information, improving feature prioritization, consistency, and adaptation to changing communication and application needs. The end-to-end architecture is designed for next-generation satellite networks, such as those supporting 6G, demonstrating significant improvements in fewer communication rounds and better accuracy over federated learning., Comment: 8 Pages, 5 figures, Magazine. arXiv admin note: substantial text overlap with arXiv:2409.15246

Each request in LLM inference goes through two phases: compute-bound prefill and memory-bandwidth-bound decode. To improve GPU utilization, recent systems use hybrid batching that combines the prefill and decode phases of different requests into the same batch. Hybrid batching works well for linear operations as it amortizes the cost of loading model weights from HBM. However, attention computation in hybrid batches remains inefficient because existing attention kernels are optimized for either prefill or decode. In this paper, we present POD-Attention -- the first GPU kernel that efficiently computes attention for hybrid batches. POD-Attention aims to maximize the utilization of both compute and memory bandwidth by carefully allocating the GPU's resources such that prefill and decode operations happen concurrently on the same multiprocessor. We integrate POD-Attention in a state-of-the-art LLM inference scheduler Sarathi-Serve. POD-Attention speeds up attention computation by up to 75% (mean 28%) and increases LLM serving throughput by up to 22% in offline inference. In online inference, POD-Attention enables lower time-to-first-token (TTFT), time-between-tokens (TBT), and request execution latency versus Sarathi-Serve.

This manuscript summarizes work on the Capsule Vision Challenge 2024 by MISAHUB. To address the multi-class disease classification task, which is challenging due to the complexity and imbalance in the Capsule Vision challenge dataset, this paper proposes CASCRNet (Capsule endoscopy-Aspp-SCR-Network), a parameter-efficient and novel model that uses Shared Channel Residual (SCR) blocks and Atrous Spatial Pyramid Pooling (ASPP) blocks. Further, the performance of the proposed model is compared with other well-known approaches. The experimental results yield that proposed model provides better disease classification results. The proposed model was successful in classifying diseases with an F1 Score of 78.5% and a Mean AUC of 98.3%, which is promising given its compact architecture., Comment: 8 pages, 4 figures

Gen-AI techniques are able to improve understanding of context and nuances in language modeling, translation between languages, handle large volumes of data, provide fast, low-latency responses and can be fine-tuned for various tasks and domains. In this manuscript, we present a comprehensive overview of the applications of Gen-AI techniques in the finance domain. In particular, we present the opportunities and challenges associated with the usage of Gen-AI techniques. We also illustrate the various methodologies which can be used to train Gen-AI techniques and present the various application areas of Gen-AI technologies in the finance ecosystem. To the best of our knowledge, this work represents the most comprehensive summarization of Gen-AI techniques within the financial domain. The analysis is designed for a deep overview of areas marked for substantial advancement while simultaneously pin-point those warranting future prioritization. We also hope that this work would serve as a conduit between finance and other domains, thus fostering the cross-pollination of innovative concepts and practices.

Vision-Language Models (VLMs) often generate plausible but incorrect responses to visual queries. However, reliably quantifying the effect of such hallucinations in free-form responses to open-ended queries is challenging as it requires visually verifying each claim within the response. We propose Programmatic VLM Evaluation (PROVE), a new benchmarking paradigm for evaluating VLM responses to open-ended queries. To construct PROVE, we provide a large language model (LLM) with a high-fidelity scene-graph representation constructed from a hyper-detailed image caption, and prompt it to generate diverse question-answer (QA) pairs, as well as programs that can be executed over the scene graph object to verify each QA pair. We thus construct a benchmark of 10.5k challenging but visually grounded QA pairs. Next, to evaluate free-form model responses to queries in PROVE, we propose a programmatic evaluation strategy that measures both the helpfulness and truthfulness of a response within a unified scene graph-based framework. We benchmark the helpfulness-truthfulness trade-offs of a range of VLMs on PROVE, finding that very few are in-fact able to achieve a good balance between the two. Project page: \url{https://prove-explorer.netlify.app/}.

Intercalation is a robust method for tuning the physical properties of a vast number of van der Waals (vdW) materials. However, the prospects of using intercalation to modify magnetism in vdWs systems and the associated mechanisms have not been investigated adequately. In this work, we modulate magnetic order in an XY antiferromagnet NiPS3 single crystals by introducing pyridine molecules into the vdWs gap under different thermal conditions. X-ray diffraction measurements indicated pronounced changes in the lattice parameter beta, while magnetization measurements at in-plane and out-of-plane configurations exposed reversal trends in the crystals Neel temperatures through intercalation-de-intercalation processes. The changes in magnetic ordering were also supported by three-dimensional thermal diffusivity experiments. The preferred orientation of the pyridine dipoles within vdW gaps was deciphered via polarized Raman spectroscopy. The results highlight the relation between the preferential alignment of the intercalants, thermal transport, and crystallographic disorder along with the modulation of anisotropy in the magnetic order. The theoretical concept of double-exchange interaction in NiPS3 was employed to explain the intercalation-induced magnetic ordering. The study uncovers the merit of intercalation as a foundation for spin switches and spin transistors in advanced quantum devices.

The increasing reliance on diffusion models for generating synthetic images has amplified concerns about the unauthorized use of personal data, particularly facial images, in model training. In this paper, we introduce a novel identity inference framework to hold model owners accountable for including individuals' identities in their training data. Our approach moves beyond traditional membership inference attacks by focusing on identity-level inference, providing a new perspective on data privacy violations. Through comprehensive evaluations on two facial image datasets, Labeled Faces in the Wild (LFW) and CelebA, our experiments demonstrate that the proposed membership inference attack surpasses baseline methods, achieving an attack success rate of up to 89% and an AUC-ROC of 0.91, while the identity inference attack attains 92% on LDM models trained on LFW, and the data extraction attack achieves 91.6% accuracy on DDPMs, validating the effectiveness of our approach across diffusion models., Comment: 5 figures, 3 tables,12 pages main body content

Understanding protein motion within the cell is crucial for predicting reaction rates and macromolecular transport in the cytoplasm. A key question is how crowded environments affect protein dynamics through hydrodynamic and direct interactions at molecular length scales. Using megahertz X-ray Photon Correlation Spectroscopy (MHz-XPCS) at the European X-ray Free Electron Laser (EuXFEL), we investigate ferritin diffusion at microsecond time scales. Our results reveal anomalous diffusion, indicated by the non-exponential decay of the intensity autocorrelation function $g_2(q,t)$ at high concentrations. This behavior is consistent with the presence of cage-trapping in between the short- and long-time protein diffusion regimes. Modeling with the $\delta\gamma$-theory of hydrodynamically interacting colloidal spheres successfully reproduces the experimental data by including a scaling factor linked to the protein direct interactions. These findings offer new insights into the complex molecular motion in crowded protein solutions, with potential applications for optimizing ferritin-based drug delivery, where protein diffusion is the rate-limiting step.

The metric dimension of a graph measures how uniquely vertices may be identified using a set of landmark vertices. This concept is frequently used in the study of network architecture, location-based problems and communication. Given a graph $G$, the metric dimension, denoted as $\dim(G)$, is the minimum size of a resolving set, a subset of vertices such that for every pair of vertices in $G$, there exists a vertex in the resolving set whose shortest path distance to the two vertices is different. This subset of vertices helps to uniquely determine the location of other vertices in the graph. A basis is a resolving set with a least cardinality. Finding a basis is a problem with practical applications in network design, where it is important to efficiently locate and identify nodes based on a limited set of reference points. The Cartesian product of $P_m$ and $P_n$ is the grid network in network science. In this paper, we investigate two novel types of grids in network science: the Villarceau grid Type I and Type II. For each of these grid types, we find the precise metric dimension.

Automated persistent and fine-grained monitoring of orchards at the individual tree or fruit level helps maximize crop yield and optimize resources such as water, fertilizers, and pesticides while preventing agricultural waste. Towards this goal, we present a 4D spatio-temporal metric-semantic mapping method that fuses data from multiple sensors, including LiDAR, RGB camera, and IMU, to monitor the fruits in an orchard across their growth season. A LiDAR-RGB fusion module is designed for 3D fruit tracking and localization, which first segments fruits using a deep neural network and then tracks them using the Hungarian Assignment algorithm. Additionally, the 4D data association module aligns data from different growth stages into a common reference frame and tracks fruits spatio-temporally, providing information such as fruit counts, sizes, and positions. We demonstrate our method's accuracy in 4D metric-semantic mapping using data collected from a real orchard under natural, uncontrolled conditions with seasonal variations. We achieve a 3.1 percent error in total fruit count estimation for over 1790 fruits across 60 apple trees, along with accurate size estimation results with a mean error of 1.1 cm. The datasets, consisting of LiDAR, RGB, and IMU data of five fruit species captured across their growth seasons, along with corresponding ground truth data, will be made publicly available at: https://4d-metric-semantic-mapping.org/

A search for proton decay into $e^+/\mu^+$ and a $\eta$ meson has been performed using data from a 0.373 Mton$\cdot$year exposure (6050.3 live days) of Super-Kamiokande. Compared to previous searches this work introduces an improved model of the intranuclear $\eta$ interaction cross section, resulting in a factor of two reduction in uncertainties from this source and $\sim$10\% increase in signal efficiency. No significant data excess was found above the expected number of atmospheric neutrino background events resulting in no indication of proton decay into either mode. Lower limits on the proton partial lifetime of $1.4\times\mathrm{10^{34}~years}$ for $p\rightarrow e^+\eta$ and $7.3\times\mathrm{10^{33}~years}$ for $p\rightarrow \mu^+\eta$ at the 90$\%$ C.L. were set. These limits are around 1.5 times longer than our previous study and are the most stringent to date.

Recent works have shown that neural radiance fields (NeRFs) on top of parametric models have reached SOTA quality to build photorealistic head avatars from a monocular video. However, one major limitation of the NeRF-based avatars is the slow rendering speed due to the dense point sampling of NeRF, preventing them from broader utility on resource-constrained devices. We introduce LightAvatar, the first head avatar model based on neural light fields (NeLFs). LightAvatar renders an image from 3DMM parameters and a camera pose via a single network forward pass, without using mesh or volume rendering. The proposed approach, while being conceptually appealing, poses a significant challenge towards real-time efficiency and training stability. To resolve them, we introduce dedicated network designs to obtain proper representations for the NeLF model and maintain a low FLOPs budget. Meanwhile, we tap into a distillation-based training strategy that uses a pretrained avatar model as teacher to synthesize abundant pseudo data for training. A warping field network is introduced to correct the fitting error in the real data so that the model can learn better. Extensive experiments suggest that our method can achieve new SOTA image quality quantitatively or qualitatively, while being significantly faster than the counterparts, reporting 174.1 FPS (512x512 resolution) on a consumer-grade GPU (RTX3090) with no customized optimization., Comment: ECCV'24 CADL Workshop. Code: https://github.com/MingSun-Tse/LightAvatar-TensorFlow. V2: Corrected speed benchmark with GaussianAvatar

Earth Observation (EO) systems are crucial for cartography, disaster surveillance, and resource administration. Nonetheless, they encounter considerable obstacles in the processing and transmission of extensive data, especially in specialized domains such as precision agriculture and real-time disaster response. Earth observation satellites, outfitted with remote sensing technology, gather data from onboard sensors and IoT-enabled terrestrial objects, delivering important information remotely. Domain-adapted Large Language Models (LLMs) provide a solution by enabling the integration of raw and processed EO data. Through domain adaptation, LLMs improve the assimilation and analysis of many data sources, tackling the intricacies of specialized datasets in agriculture and disaster response. This data synthesis, directed by LLMs, enhances the precision and pertinence of conveyed information. This study provides a thorough examination of using semantic inference and deep learning for sophisticated EO systems. It presents an innovative architecture for semantic communication in EO satellite networks, designed to improve data transmission efficiency using semantic processing methodologies. Recent advancements in onboard processing technologies enable dependable, adaptable, and energy-efficient data management in orbit. These improvements guarantee reliable performance in adverse space circumstances using radiation-hardened and reconfigurable technology. Collectively, these advancements enable next-generation satellite missions with improved processing capabilities, crucial for operational flexibility and real-time decision-making in 6G satellite communication., Comment: 17 pages, 7 figures, Journal

Denoising diffusion models have emerged as state-of-the-art in generative tasks across image, audio, and video domains, producing high-quality, diverse, and contextually relevant data. However, their broader adoption is limited by high computational costs and large memory footprints. Post-training quantization (PTQ) offers a promising approach to mitigate these challenges by reducing model complexity through low-bandwidth parameters. Yet, direct application of PTQ to diffusion models can degrade synthesis quality due to accumulated quantization noise across multiple denoising steps, particularly in conditional tasks like text-to-audio synthesis. This work introduces PTQ4ADM, a novel framework for quantizing audio diffusion models(ADMs). Our key contributions include (1) a coverage-driven prompt augmentation method and (2) an activation-aware calibration set generation algorithm for text-conditional ADMs. These techniques ensure comprehensive coverage of audio aspects and modalities while preserving synthesis fidelity. We validate our approach on TANGO, Make-An-Audio, and AudioLDM models for text-conditional audio generation. Extensive experiments demonstrate PTQ4ADM's capability to reduce the model size by up to 70\% while achieving synthesis quality metrics comparable to full-precision models($<$5\% increase in FD scores). We show that specific layers in the backbone network can be quantized to 4-bit weights and 8-bit activations without significant quality loss. This work paves the way for more efficient deployment of ADMs in resource-constrained environments.

We employed sodium mesitylene sulfonate crystals to investigate angle-dependent phonon resonance and thickness-dependent splitting in THz time-domain polarimetry. This crystal possesses a C2 space group, leading to a repetition pattern after 180deg rotations. Our experimental observations revealed intriguing behaviour: We observed a non-linear response when varying the angle from 10deg to 360deg in both 0.182mm and 1.266mm thick crystals. specifically, at 90deg and 270deg, dip resonance occurred, while at 180deg and 360deg, no phonon resonance was observed. For thick crystals, we observed the splitting of phonon modes. Our findings offer valuable insights into the phononic properties of this crystal as the angle varies., Comment: 9 pages, 9 figures

Differential Dynamic Programming (DDP) is one of the indirect methods for solving an optimal control problem. Several extensions to DDP have been proposed to add stagewise state and control constraints, which can mainly be classified as augmented lagrangian methods, active set methods, and barrier methods. In this paper, we use an interior point method, which is a type of barrier method, to incorporate arbitrary stagewise equality and inequality state and control constraints. We also provide explicit update formulas for all the involved variables. Finally, we apply this algorithm to example systems such as the inverted pendulum, a continuously stirred tank reactor, car parking, and obstacle avoidance.

Collaborating in a group, whether face-to-face or virtually, involves continuously expressing emotions and interpreting those of other group members. Therefore, understanding group affect is essential to comprehending how groups interact and succeed in collaborative efforts. In this study, we move beyond individual-level affect and investigate group-level affect -- a collective phenomenon that reflects the shared mood or emotions among group members at a particular moment. As the first in literature, we gather annotations for group-level affective expressions using a fine-grained temporal approach (15 second windows) that also captures the inherent dynamics of the collective construct. To this end, we use trained annotators and an annotation procedure specifically tuned to capture the entire scope of the group interaction. In addition, we model group affect dynamics over time. One way to study the ebb and flow of group affect in group interactions is to model the underlying convergence (driven by emotional contagion) and divergence (resulting from emotional reactivity) of affective expressions amongst group members. To capture these interpersonal dynamics, we extract synchrony based features from both audio and visual social signal cues. An analysis of these features reveals that interacting groups tend to diverge in terms of their social signals along neutral levels of group affect, and converge along extreme levels of affect expression. We further present results on the predictive modeling of dynamic group affect which underscores the importance of using synchrony-based features in the modeling process, as well as the multimodal nature of group affect. We anticipate that the presented models will serve as the baselines of future research on the automatic recognition of dynamic group affect., Comment: This work has been submitted to the IEEE for possible publication

In the Generalized Mastermind problem, there is an unknown subset $H$ of the hypercube $\{0,1\}^d$ containing $n$ points. The goal is to learn $H$ by making a few queries to an oracle, which, given a point $q$ in $\{0,1\}^d$, returns the point in $H$ nearest to $q$. We give a two-round adaptive algorithm for this problem that learns $H$ while making at most $\exp(\tilde{O}(\sqrt{d \log n}))$ queries. Furthermore, we show that any $r$-round adaptive randomized algorithm that learns $H$ with constant probability must make $\exp(\Omega(d^{3^{-(r-1)}}))$ queries even when the input has $\text{poly}(d)$ points; thus, any $\text{poly}(d)$ query algorithm must necessarily use $\Omega(\log \log d)$ rounds of adaptivity. We give optimal query complexity bounds for the variant of the problem where queries are allowed to be from $\{0,1,2\}^d$. We also study a continuous variant of the problem in which $H$ is a subset of unit vectors in $\mathbb{R}^d$, and one can query unit vectors in $\mathbb{R}^d$. For this setting, we give an $O(n^{d/2})$ query deterministic algorithm to learn the hidden set of points., Comment: This work appeared at ICML 2024

This study focuses on identifying the most effective pre-trained model for land use classification in onboard satellite processing, emphasizing achieving high accuracy, computational efficiency, and robustness against noisy data conditions commonly encountered during satellite-based inference. Through extensive experimentation, we compare the performance of traditional CNN-based, ResNet-based, and various pre-trained vision Transformer models. Our findings demonstrate that pre-trained Vision Transformer (ViT) models, particularly MobileViTV2 and EfficientViT-M2, outperform models trained from scratch in terms of accuracy and efficiency. These models achieve high performance with reduced computational requirements and exhibit greater resilience during inference under noisy conditions. While MobileViTV2 has excelled on clean validation data, EfficientViT-M2 has proved more robust when handling noise, making it the most suitable model for onboard satellite EO tasks. Our experimental results demonstrate that EfficientViT-M2 is the optimal choice for reliable and efficient RS-IC in satellite operations, achieving 98.76 % of accuracy, precision, and recall. Precisely, EfficientViT-M2 delivers the highest performance across all metrics, excels in training efficiency (1,000s) and inference time (10s), and demonstrates greater robustness (overall robustness score of 0.79). Consequently, EfficientViT-M2 consumes 63.93 % less power than MobileViTV2 (79.23 W) and 73.26 % less power than SwinTransformer (108.90 W). This highlights its significant advantage in energy efficiency.

Harnessing pre-trained LLMs to improve ASR systems, particularly for low-resource languages, is now an emerging area of research. Existing methods range from using LLMs for ASR error correction to tightly coupled systems that replace the ASR decoder with the LLM. These approaches either increase decoding time or require expensive training of the cross-attention layers. We propose SALSA, which couples the decoder layers of the ASR to the LLM decoder, while synchronously advancing both decoders. Such coupling is performed with a simple projection of the last decoder state, and is thus significantly more training efficient than earlier approaches. A challenge of our proposed coupling is handling the mismatch between the tokenizers of the LLM and ASR systems. We handle this mismatch using cascading tokenization with respect to the LLM and ASR vocabularies. We evaluate SALSA on 8 low-resource languages in the FLEURS benchmark, yielding substantial WER reductions of up to 38%., Comment: Accepted to INTERSPEECH 2024

Multimodal foundation models serve numerous applications at the intersection of vision and language. Still, despite being pretrained on extensive data, they become outdated over time. To keep models updated, research into continual pretraining mainly explores scenarios with either (1) infrequent, indiscriminate updates on large-scale new data, or (2) frequent, sample-level updates. However, practical model deployment often operates in the gap between these two limit cases, as real-world applications often demand adaptation to specific subdomains, tasks or concepts -- spread over the entire, varying life cycle of a model. In this work, we complement current perspectives on continual pretraining through a research test bed as well as provide comprehensive guidance for effective continual model updates in such scenarios. We first introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements, constructed over 63 datasets with diverse visual and semantic coverage. Using FoMo-in-Flux, we explore the complex landscape of practical continual pretraining through multiple perspectives: (1) A data-centric investigation of data mixtures and stream orderings that emulate real-world deployment situations, (2) a method-centric investigation ranging from simple fine-tuning and traditional continual learning strategies to parameter-efficient updates and model merging, (3) meta learning rate schedules and mechanistic design choices, and (4) the influence of model and compute scaling. Together, our insights provide a practitioner's guide to continual multimodal pretraining for real-world deployment. Our benchmark and code is here: https://github.com/ExplainableML/fomo_in_flux., Comment: Technical Report. 52 pages

Lexicographic multi-objective problems, which impose a lexicographic importance order over the objectives, arise in many real-life scenarios. Existing Reinforcement Learning work directly addressing lexicographic tasks has been scarce. The few proposed approaches were all noted to be heuristics without theoretical guarantees as the Bellman equation is not applicable to them. Additionally, the practical applicability of these prior approaches also suffers from various issues such as not being able to reach the goal state. While some of these issues have been known before, in this work we investigate further shortcomings, and propose fixes for improving practical performance in many cases. We also present a policy optimization approach using our Lexicographic Projection Optimization (LPO) algorithm that has the potential to address these theoretical and practical concerns. Finally, we demonstrate our proposed algorithms on benchmark problems., Comment: Full version of ECAI 2024 paper

Extreme Classification (XC) aims to map a query to the most relevant documents from a very large document set. XC algorithms used in real-world applications learn this mapping from datasets curated from implicit feedback, such as user clicks. However, these datasets inevitably suffer from missing labels. In this work, we observe that systematic missing labels lead to missing knowledge, which is critical for accurately modelling relevance between queries and documents. We formally show that this absence of knowledge cannot be recovered using existing methods such as propensity weighting and data imputation strategies that solely rely on the training dataset. While LLMs provide an attractive solution to augment the missing knowledge, leveraging them in applications with low latency requirements and large document sets is challenging. To incorporate missing knowledge at scale, we propose SKIM (Scalable Knowledge Infusion for Missing Labels), an algorithm that leverages a combination of small LM and abundant unstructured meta-data to effectively mitigate the missing label problem. We show the efficacy of our method on large-scale public datasets through exhaustive unbiased evaluation ranging from human annotations to simulations inspired from industrial settings. SKIM outperforms existing methods on Recall@100 by more than 10 absolute points. Additionally, SKIM scales to proprietary query-ad retrieval datasets containing 10 million documents, outperforming contemporary methods by 12% in offline evaluation and increased ad click-yield by 1.23% in an online A/B test conducted on a popular search engine. We release our code, prompts, trained XC models and finetuned SLMs at: https://github.com/bicycleman15/skim, Comment: Preprint, 23 pages

This report introduces xGen-MM (also known as BLIP-3), a framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. xGen-MM, short for xGen-MultiModal, expands the Salesforce xGen initiative on foundation AI models. Our models undergo rigorous evaluation across a range of tasks, including both single and multi-image benchmarks. Our pre-trained base model exhibits strong in-context learning capabilities and the instruction-tuned model demonstrates competitive performance among open-source LMMs with similar model sizes. In addition, we introduce a safety-tuned model with DPO, aiming to mitigate harmful behaviors such as hallucinations and improve safety. We open-source our models, curated large-scale datasets, and our fine-tuning codebase to facilitate further advancements in LMM research. Associated resources will be available on our project page above.

Self-ensembling techniques with diverse reasoning paths such as Self-Consistency have demonstrated remarkable performance gains in text generation with Large Language Models (LLMs). However, such techniques depend on the availability of an accurate answer extraction process to aggregate across multiple outputs. Moreover, they acquire higher inference cost, in comparison to Greedy Decoding, due to generation of relatively higher number of output tokens. Research has shown that the free form text outputs from Self-Consistency can be aggregated reliably using LLMs to produce the final output. Additionally, recent advancements in LLM inference have demonstrated that usage of diverse exemplars in prompts have the ability to induce diversity in the LLM outputs. Such proven techniques can be easily extended to self-ensembling based approaches to achieve enhanced results in text generation. In this paper, we introduce PEDAL (Prompts based on Exemplar Diversity Aggregated using LLMs), a hybrid self-ensembling approach, that combines the strengths of diverse exemplar based prompts and LLM based aggregation to achieve improvement in overall performance. On the publicly available SVAMP and ARC datasets, our experiments reveal that PEDAL can achieve better accuracy than Greedy Decoding based strategies with lower inference cost compared to Self Consistency based approaches.