Search

Speech Emotion Recognition (SER) has been traditionally formulated as a classification task. However, emotions are generally a spectrum whose distribution varies from situation to situation leading to poor Out-of-Domain (OOD) performance. We take inspiration from statistical formulation of Automatic Speech Recognition (ASR) and formulate the SER task as generating the most likely sequence of text tokens to infer emotion. The formulation breaks SER into predicting acoustic model features weighted by language model prediction. As an instance of this approach, we present SELM, an audio-conditioned language model for SER that predicts different emotion views. We train SELM on curated speech emotion corpus and test it on three OOD datasets (RAVDESS, CREMAD, IEMOCAP) not used in training. SELM achieves significant improvements over the state-of-the-art baselines, with 17% and 7% relative accuracy gains for RAVDESS and CREMA-D, respectively. Moreover, SELM can further boost its performance by Few-Shot Learning using a few annotated examples. The results highlight the effectiveness of our SER formulation, especially to improve performance in OOD scenarios., Comment: Accepted at INTERSPEECH 2024

Large neural models are often compressed before deployment. Model compression is necessary for many practical reasons, such as inference latency, memory footprint, and energy consumption. Compressed models are assumed to be miniature versions of corresponding large neural models. However, we question this belief in our work. We compare compressed models with corresponding large neural models using four model characteristics: prediction errors, data representation, data distribution, and vulnerability to adversarial attack. We perform experiments using the BERT-large model and its five compressed versions. For all four model characteristics, compressed models significantly differ from the BERT-large model. Even among compressed models, they differ from each other on all four model characteristics. Apart from the expected loss in model performance, there are major side effects of using compressed models to replace large neural models., Comment: Accepted at the 33rd ACM International Conference on Information and Knowledge Management (CIKM 2024) for the Short Research Paper track, 5 pages

Embeddings from Large Language Models (LLMs) have emerged as critical components in various applications, particularly for information retrieval. While high-dimensional embeddings generally demonstrate superior performance as they contain more salient information, their practical application is frequently hindered by elevated computational latency and the associated higher cost. To address these challenges, we propose Matryoshka-Adaptor, a novel tuning framework designed for the customization of LLM embeddings. Matryoshka-Adaptor facilitates substantial dimensionality reduction while maintaining comparable performance levels, thereby achieving a significant enhancement in computational efficiency and cost-effectiveness. Our framework directly modifies the embeddings from pre-trained LLMs which is designed to be seamlessly integrated with any LLM architecture, encompassing those accessible exclusively through black-box APIs. Also, it exhibits efficacy in both unsupervised and supervised learning settings. A rigorous evaluation conducted across a diverse corpus of English, multilingual, and multimodal datasets consistently reveals substantial gains with Matryoshka-Adaptor. Notably, with Google and OpenAI Embedding APIs, Matryoshka-Adaptor achieves a reduction in dimensionality ranging from two- to twelve-fold without compromising performance across multiple BEIR datasets.

Several studies have investigated human interaction using modern tracking techniques for face-to-face encounters across various settings and age groups. However, little attention has been given to understanding how individual characteristics relate to social behavior. This is particularly important in younger age groups due to its potential effects on early childhood development. In this study, conducted during the Complexity 72h Workshop, we analyze human social interactions in a French preschool, where children's face-to-face interactions were monitored using proximity sensors over an academic year. We use metadata from parent surveys and preschool linguistic tests, covering demographic information and home habits, to examine the interplay between individual characteristics and contact patterns. Using a mixture of approaches, from random forest classifiers to network-based metrics at both dyadic and higher-order (group) levels, we identify sex, age, language scores, and number of siblings as the variables displaying the most significant associations with interaction patterns. We explore these variables' relationships to interactions within and outside classrooms and across mixed and single-grade classes. At the group level, we investigate how group affinity affects group persistence. We also find that higher-order network centrality (hypercoreness) is higher among children with siblings, indicating different group embedding despite similar total contact duration. This study aligns with existing literature on early social development and highlights the importance of integrating individual traits into the study of human interactions. Focusing on 2-5-year-olds offers insights into emerging social preferences during critical phases of cognitive development. Future research could use these findings to enhance mechanistic models of complex social systems by incorporating individual traits., Comment: This work is the output of the Complexity72h workshop, held at the Universidad Carlos III de Madrid in Legan\'es, Spain, 24-28 June 2024

The formation and evolution of supermassive black holes (SMBHs) in the Universe remains an open question in cosmology. We show for the first time that the evolution of SMBHs with redshift leads to a unique signature on the angular cross-correlation power spectrum between the multi-frequency nano-hertz (nHz) stochastic gravitational wave (SGWB) and the galaxy density in the Universe. By using galaxy catalogs from the upcoming Rubin LSST Observatory in synergy with the nHz SGWB signal accessible from the Square Kilometer Array, we can measure this signal with a signal-to-noise ratio above five, thereby opening a new observational window to the cosmic evolution of SMBHs across redshift. This discovery space that can be opened by the cross-correlation of the nHz SGWB will not be possible by any other currently known techniques., Comment: 10 pages, 6 figures

We conduct a comprehensive investigation into the flavour phenomenology and collider signatures of flavon of $\mathcal{Z}_{\rm N} \times \mathcal{Z}_{\rm M}$ flavour symmetries for the soft symmetry-breaking scenario and a new symmetry-conserving mechanism at the high-luminosity LHC, high energy LHC, and a 100 TeV hadron collider. The flavour physics of quark and leptonic observables places different bounds on the parameter space of flavons of $\mathcal{Z}_{\rm N} \times \mathcal{Z}_{\rm M}$ flavour symmetries. On the collider side, the decay $t \rightarrow c a$ can be probed by the high-luminosity LHC, high energy LHC, and a 100 TeV hadron collider for the $\mathcal{Z}_{\rm 8} \times \mathcal{Z}_{\rm 22}$ flavour symmetry. The inclusive production signatures can be used to probe the flavon of all the $\mathcal{Z}_{\rm N} \times \mathcal{Z}_{\rm M} $ flavour symmetries for the soft symmetry-breaking scenario for a heavy flavon at a 100 TeV collider. Flavons of all the $\mathcal{Z}_{\rm N} \times \mathcal{Z}_{\rm M} $ flavour symmetries can be probed at high energy LHC and a 100 TeV collider for a low mass in the case of soft symmetry-breaking. The di-flavon production is within reach of the high-luminosity LHC, high energy LHC, and a 100 TeV collider only for a light flavon. The 14 TeV high-luminosity LHC can probe only the $\mathcal{Z}_{\rm 2} \times \mathcal{Z}_{\rm 5}$ and $\mathcal{Z}_{\rm 8} \times \mathcal{Z}_{\rm 22}$ flavour symmetries for a few specific inclusive signatures. The symmetry-conserving scenario remains beyond the detection capabilities of any collider., Comment: 66 pages, 31 figures, title slightly changed, accepted version in Phys. Rev. D

Multimodal AI has demonstrated superior performance over unimodal approaches by leveraging diverse data sources for more comprehensive analysis. However, applying this effectiveness in healthcare is challenging due to the limited availability of public datasets. Federated learning presents an exciting solution, allowing the use of extensive databases from hospitals and health centers without centralizing sensitive data, thus maintaining privacy and security. Yet, research in multimodal federated learning, particularly in scenarios with missing modalities a common issue in healthcare datasets remains scarce, highlighting a critical area for future exploration. Toward this, we propose a novel method for multimodal federated learning with missing modalities. Our contribution lies in a novel cross-modal data augmentation by retrieval, leveraging the small publicly available dataset to fill the missing modalities in the clients. Our method learns the parameters in a federated manner, ensuring privacy protection and improving performance in multiple challenging multimodal benchmarks in the medical domain, surpassing several competitive baselines. Code Available: https://github.com/bhattarailab/CAR-MFL, Comment: Accepted at MICCAI 2024

Enterprise chatbots, powered by generative AI, are emerging as key applications to enhance employee productivity. Retrieval Augmented Generation (RAG), Large Language Models (LLMs), and orchestration frameworks like Langchain and Llamaindex are crucial for building these chatbots. However, creating effective enterprise chatbots is challenging and requires meticulous RAG pipeline engineering. This includes fine-tuning embeddings and LLMs, extracting documents from vector databases, rephrasing queries, reranking results, designing prompts, honoring document access controls, providing concise responses, including references, safeguarding personal information, and building orchestration agents. We present a framework for building RAG-based chatbots based on our experience with three NVIDIA chatbots: for IT/HR benefits, financial earnings, and general content. Our contributions are three-fold: introducing the FACTS framework (Freshness, Architectures, Cost, Testing, Security), presenting fifteen RAG pipeline control points, and providing empirical results on accuracy-latency tradeoffs between large and small LLMs. To the best of our knowledge, this is the first paper of its kind that provides a holistic view of the factors as well as solutions for building secure enterprise-grade chatbots.", Comment: 8 pages, 6 figures, 2 tables, Preprint submission to ACM CIKM 2024

A sufficiently precise measurement of black hole spin is required to carry out quantitative tests of the Kerr metric and to understand several phenomena related to astrophysical black holes. After 24 years, XTE J2012+381 again underwent an outburst in December 2022. In this work, we focused on the measurement of spin and mass of black hole candidate XTE J2012+381 using broadband spectral analysis of X-ray data from \emph{Swift/XRT} and \emph{NuSTAR}. By using the relxillCp model, the spin and inclination of the source were found to be $0.883_{-0.061}^{+0.033}$ and $46.2_{-2.0}^{+3.7}$ degrees, respectively for high disk density ($i.e.\;10^{20}\;\mathrm{cm}^{-3}$). We further test our results for lamp post geometry using the relxilllpCp model. The spin and inclination of the source were found to be $0.892_{-0.044}^{+0.020}$ and $43.1_{-1.2}^{+1.4}$ degrees, respectively. Then "continuum-fitting" method was used for the soft state to estimate the mass of BH and found to be $7.95_{-3.25}^{+7.65}\;\mathrm{M}_{\odot}$ and $7.48_{-2.75}^{+5.80}\;\mathrm{M}_{\odot}$ for the spin and inclination estimated from the relxillCp and relxilllpCp model respectively. We used a distance of 5.4 kpc as measured by Gaia using the parallax method. This study also addresses the issue of supersolar iron abundance in XTE J2012+381 by using \texttt{reflionx} based reflection model and found high disk density for the source., Comment: Accepted for publication in MNRAS; 9 pages

Language Models (LMs) excel in natural language processing tasks for English but show reduced performance in most other languages. This problem is commonly tackled by continually pre-training and fine-tuning these models for said languages. A significant issue in this process is the limited vocabulary coverage in the original model's tokenizer, leading to inadequate representation of new languages and necessitating an expansion of the tokenizer. The initialization of the embeddings corresponding to new vocabulary items presents a further challenge. Current strategies require cross-lingual embeddings and lack a solid theoretical foundation as well as comparisons with strong baselines. In this paper, we first establish theoretically that initializing within the convex hull of existing embeddings is a good initialization, followed by a novel but simple approach, Constrained Word2Vec (CW2V), which does not require cross-lingual embeddings. Our study evaluates different initialization methods for expanding RoBERTa and LLaMA 2 across four languages and five tasks. The results show that CW2V performs equally well or even better than more advanced techniques. Additionally, simpler approaches like multivariate initialization perform on par with these advanced methods indicating that efficient large-scale multilingual continued pretraining can be achieved even with simpler initialization methods. We release our code publicly (https://github.com/AI4Bharat/VocabAdaptation_LLM/tree/CW2V)., Comment: CONLL 2024 (EMNLP 2024)

Affine formation control is a subset of formation control methods, which has gained increasing popularity for its flexibility and maneuverability in diverse applications. Affine formation control is inherently distributed in nature, where the local controllers onboard each agent are linearly dependent on the relative position measurements of the neighboring agents. The unavailability of these measurements in practice, due to node failure or missing links, leads to a change in the underlying graph topology, and subsequently causes instability and sub-optimal performance. In this paper, we propose an estimation framework to enhance the robustness of distributed affine formation control systems against these topology changes. Our estimation framework features an adaptive fusion of both temporal information from the dynamics of agents and spatial information which is derived from the geometry of the affine formations. We propose a suite of algorithms under this framework to tackle various practical scenarios, and numerically verify our proposed estimator on stability, convergence rate, and optimality criterion. Simulations show the performance of our proposed algorithms as compared to the state-of-the-art methods, and we summarize them with future research directions.

We contribute an unsupervised method that effectively learns from raw observation and disentangles its latent space into content and style representations. Unlike most disentanglement algorithms that rely on domain-specific labels and knowledge, our method is based on the insight of domain-general statistical differences between content and style -- content varies more among different fragments within a sample but maintains an invariant vocabulary across data samples, whereas style remains relatively invariant within a sample but exhibits more significant variation across different samples. We integrate such inductive bias into an encoder-decoder architecture and name our method after V3 (variance-versus-invariance). Experimental results show that V3 generalizes across two distinct domains in different modalities, music audio and images of written digits, successfully learning pitch-timbre and digit-color disentanglements, respectively. Also, the disentanglement robustness significantly outperforms baseline unsupervised methods and is even comparable to supervised counterparts. Furthermore, symbolic-level interpretability emerges in the learned codebook of content, forging a near one-to-one alignment between machine representation and human knowledge.

Our objectives are to map the filamentary network around the Fornax-Eridanus Complex and probe the influence of the local environment on galaxy morphology. We employ the novel machine-learning tool, 1-DREAM (1-Dimensional, Recovery, Extraction, and Analysis of Manifolds) to detect and model filaments around the Fornax cluster. We then use the morphology-density relation of galaxies to examine the variation in the galaxies' morphology with respect to their distance from the central axis of the detected filaments. We detect 27 filaments that vary in length and galaxy-number density around the Fornax-Eridanus Complex. These filaments showcase a variety of environments; some filaments encompass groups/clusters, while others are only inhabited by galaxies in pristine filamentary environments. We also reveal a well-known structure -- the Fornax Wall, that passes through the Dorado group, Fornax cluster, and Eridanus supergroup. Regarding the morphology of galaxies, we find that early-type galaxies (ETGs) populate high-density filaments and high-density regions of the Fornax Wall. Furthermore, the fraction of ETGs decreases as the distance to the filament spine increases. Of the total galaxy population in filaments, ~7% are ETGs and ~24% are late-type galaxies (LTGs) located in pristine environments of filaments, while ~27% are ETGs and ~42% are LTGs in groups/clusters within filaments. This study reveals the Cosmic Web around the Fornax Cluster and asserts that filamentary environments are heterogeneous in nature. When investigating the role of the environment on galaxy morphology, it is essential to consider both, the local number-density and a galaxy's proximity to the filament spine. Within this framework, we ascribe the observed morphological segregation in the Fornax Wall to pre-processing of galaxies within groups embedded in it., Comment: Accepted for publication in A&A. 21 pages with 15 figures

We theoretically study the nonlinear optical response of ABC trilayer graphene with inversion symmetry broken by the application of a displacement field perpendicular to the trilayer. We show that rhombohedral trilayer graphene exhibits a large bulk photovoltaic effect arising from a DC shift current response. The conductivity of the trilayer contains features similar to AB bilayer graphene as well as features distinct from AB bilayer graphene. The new features of ABC trilayer graphene relative to AB bilayer graphene arise from the quantum geometric features of the electronic band structure and can be tuned by varying the displacement field. We focus on a regime of displacement field where certain band gaps close and reopen away from the charge neutrality point leading to drastic changes in the quantum geometric structure in momentum space, a feature characteristic of the trilayer graphene band structure. These features manifest as a sign change in shift current conductivity in a certain frequency window and can thus serve as a probe of quantum geometry., Comment: 15 pages, 12 figures

Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender:profession or race:crime. This narrow scope often overlooks a vast range of unexamined implicit associations, restricting the identification and, hence, mitigation of such biases. We address this gap by probing VLMs to (1) uncover hidden, implicit associations across 9 bias dimensions. We systematically explore diverse input and output modalities and (2) demonstrate how biased associations vary in their negativity, toxicity, and extremity. Our work (3) identifies subtle and extreme biases that are typically not recognized by existing methodologies. We make the Dataset of retrieved associations, (Dora), publicly available here https://github.com/chahatraj/BiasDora., Comment: Accepted to EMNLP Findings 2024

Large Language Models (LLMs) perpetuate social biases, reflecting prejudices in their training data and reinforcing societal stereotypes and inequalities. Our work explores the potential of the Contact Hypothesis, a concept from social psychology for debiasing LLMs. We simulate various forms of social contact through LLM prompting to measure their influence on the model's biases, mirroring how intergroup interactions can reduce prejudices in social contexts. We create a dataset of 108,000 prompts following a principled approach replicating social contact to measure biases in three LLMs (LLaMA 2, Tulu, and NousHermes) across 13 social bias dimensions. We propose a unique debiasing technique, Social Contact Debiasing (SCD), that instruction-tunes these models with unbiased responses to prompts. Our research demonstrates that LLM responses exhibit social biases when subject to contact probing, but more importantly, these biases can be significantly reduced by up to 40% in 1 epoch of instruction tuning LLaMA 2 following our SCD strategy. Our code and data are available at https://github.com/chahatraj/breakingbias., Comment: Under Review

Clay, the major ingredient of natural soils, is often used as a rheological modifier while formulating paints and coatings. When subjected to desiccation, colloidal clay suspensions and clayey soils crack due to the accumulation of drying-induced stresses. Even when desiccation is suppressed, aqueous clay suspensions exhibit physical aging, with their elastic and viscous moduli increasing over time as their microscopic structures evolve due to time-dependent inter-particle screened electrostatic interactions. The rate at which aging progresses is estimated from the rate of evolution of the mechanical moduli and can be controlled by changing clay concentration or by incorporating additives. Since physical aging and evaporation should both contribute to the consolidation of drying clay suspensions, we attempt to manipulate the desiccation process \textit{via} alterations of clay and additive concentrations. For a desiccating sample with an accelerated rate of aging, we observe faster consolidation into a semi-solid state and earlier onset of cracks. We estimate the crack onset time, $t_c$, in direct visualization experiments and the elasticity of the drying sample layer, $E$, using microindentation in an atomic force microscope. We demonstrate that $t_c \propto \sqrt{\frac{G_c}{E}}$, where $G_c$, the fracture energy, is estimated by fitting our experimental data to a linear poroelastic model that incorporates the Griffith's criterion for crack formation. Our work demonstrates that early crack onset is associated with lower sample ductility. The correlation between crack onset in a sample and its mechanical properties as uncovered here is potentially useful in preparing crack-resistant coatings and diverse clay structures., Comment: 9 pages, 6 figures, Supplementary Information file and supplementary videos are provided

Malaysian English is a low resource creole language, where it carries the elements of Malay, Chinese, and Tamil languages, in addition to Standard English. Named Entity Recognition (NER) models underperform when capturing entities from Malaysian English text due to its distinctive morphosyntactic adaptations, semantic features and code-switching (mixing English and Malay). Considering these gaps, we introduce MENmBERT and MENBERT, a pre-trained language model with contextual understanding, specifically tailored for Malaysian English. We have fine-tuned MENmBERT and MENBERT using manually annotated entities and relations from the Malaysian English News Article (MEN) Dataset. This fine-tuning process allows the PLM to learn representations that capture the nuances of Malaysian English relevant for NER and RE tasks. MENmBERT achieved a 1.52\% and 26.27\% improvement on NER and RE tasks respectively compared to the bert-base-multilingual-cased model. Although the overall performance of NER does not have a significant improvement, our further analysis shows that there is a significant improvement when evaluated by the 12 entity labels. These findings suggest that pre-training language models on language-specific and geographically-focused corpora can be a promising approach for improving NER performance in low-resource settings. The dataset and code published in this paper provide valuable resources for NLP research work focusing on Malaysian English., Comment: Accepted in 9th Workshop on Representation Learning for NLP (Rep4NLP) at ACL 2024

Recent work on distilling Whisper's knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50\%. This results in small, efficient, and dedicated models. However, a critical step of distillation from pseudo-labels involves filtering high-quality predictions and using only those during training. This step requires ground truth labels to compare and filter low-quality examples making the whole process supervised. In addition to that, the distillation process requires a large amount of data thereby limiting the ability to distill models in low-resource settings. To address this challenge, we propose a distillation framework that does not require any labeled data. Through experimentation, we show that our best distilled models outperform the teacher model by 5-7 points in terms of WER compared to those without filtering and are on par with or perform better than similar supervised data filtering setups. When we scale the data, our models significantly outperform all zero-shot and supervised models. We demonstrate that it is possible to distill large Whisper models into relatively small ones without using any labeled data. Our distilled models are also 25-50\% more compute- and memory-efficient while maintaining performance equal to or better than that of the teacher model., Comment: Work in progress

Recent studies show evidence for emergent cognitive abilities in Large Pre-trained Language Models (PLMs). The increasing cognitive alignment of these models has made them candidates for cognitive science theories. Prior research into the emergent cognitive abilities of PLMs has largely been path-independent to model training, i.e., has focused on the final model weights and not the intermediate steps. However, building plausible models of human cognition using PLMs would benefit from considering the developmental alignment of their performance during training to the trajectories of children's thinking. Guided by psychometric tests of human intelligence, we choose four sets of tasks to investigate the alignment of ten popular families of PLMs and evaluate their available intermediate and final training steps. These tasks are Numerical ability, Linguistic abilities, Conceptual understanding, and Fluid reasoning. We find a striking regularity: regardless of model size, the developmental trajectories of PLMs consistently exhibit a window of maximal alignment to human cognitive development. Before that window, training appears to endow "blank slate" models with the requisite structure to be poised to rapidly learn from experience. After that window, training appears to serve the engineering goal of reducing loss but not the scientific goal of increasing alignment with human cognition.

Finding a simple path of even length between two designated vertices in a directed graph is a fundamental NP-complete problem known as the EvenPath problem. Nedev proved in 1999, that for directed planar graphs, the problem can be solved in polynomial time. More than two decades since then, we make the first progress in extending the tractable classes of graphs for this problem. We give a polynomial time algorithm to solve the EvenPath problem for classes of H-minor-free directed graphs,1 where H is a single-crossing graph. We make two new technical contributions along the way, that might be of independent interest. The first, and perhaps our main, contribution is the construction of small, planar, parity-mimicking networks. These are graphs that mimic parities of all possible paths between a designated set of terminals of the original graph. Finding vertex disjoint paths between given source-destination pairs of vertices is another fundamental problem, known to be NP-complete in directed graphs, though known to be tractable in planar directed graphs. We encounter a natural variant of this problem, that of finding disjoint paths between given pairs of vertices, but with constraints on parity of the total length of paths. The other significant contribution of our paper is to give a polynomial time algorithm for the 3-disjoint paths with total parity problem, in directed planar graphs with some restrictions (and also in directed graphs of bounded treewidth).

This paper introduces a robust zero-trust architecture (ZTA) tailored for the decentralized system that empowers efficient remote work and collaboration within IoT networks. Using blockchain-based federated learning principles, our proposed framework includes a robust aggregation mechanism designed to counteract malicious updates from compromised clients, enhancing the security of the global learning process. Moreover, secure and reliable trust computation is essential for remote work and collaboration. The robust ZTA framework integrates anomaly detection and trust computation, ensuring secure and reliable device collaboration in a decentralized fashion. We introduce an adaptive algorithm that dynamically adjusts to varying user contexts, using unsupervised clustering to detect novel anomalies, like zero-day attacks. To ensure a reliable and scalable trust computation, we develop an algorithm that dynamically adapts to varying user contexts by employing incremental anomaly detection and clustering techniques to identify and share local and global anomalies between nodes. Future directions include scalability improvements, Dirichlet process for advanced anomaly detection, privacy-preserving techniques, and the integration of post-quantum cryptographic methods to safeguard against emerging quantum threats.

We identify the maximum cross sections probed by single-scatter ``WIMP" searches in dark matter direct detection. Due to Poisson fluctuations in scatter multiplicity, these ceilings scale logarithmically with mass for heavy dark matter and often lie in regions probed by multiscatter searches. Using a generalized formula for single-scatter event rates we recast WIMP searches by the quintal-to-tonne scale detectors XENON1T, XENONnT, LZ, PANDAX-II, PANDAX-4T, DarkSide-50 and DEAP-3600 to obtain ceilings and floors up to a few $10^{17}$ GeV mass and $10^{-22}$ cm$^2$ per-nucleus cross section. We do this for coherent, geometric, isospin-violating xenophobic and argophobic spin-independent scattering, and neutron-only and proton-only spin-dependent scattering. Future large-exposure detectors would register an almost irreducible background of atmospheric neutrinos that would determine a dark matter sensitivity ceiling that we call the ``neutrino roof", in analogy with the well-studied ``neutrino floor". Accounting for this background, we estimate the reaches of the 10$-$100 tonne scale DarkSide-20k, DARWIN/XLZD, PANDAX-xT, and Argo, which would probe many decades of unconstrained parameter space up to the Planck mass, as well as of $10^3-10^4$ tonne scale noble liquid detectors that have been proposed in synergy with neutrino experiments., Comment: 11 pages revtex4 + references, 3 figures, 1 table

Embodied agents require robust navigation systems to operate in unstructured environments, making the robustness of Simultaneous Localization and Mapping (SLAM) models critical to embodied agent autonomy. While real-world datasets are invaluable, simulation-based benchmarks offer a scalable approach for robustness evaluations. However, the creation of a challenging and controllable noisy world with diverse perturbations remains under-explored. To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations. The pipeline comprises a comprehensive taxonomy of sensor and motion perturbations for embodied multi-modal (specifically RGB-D) sensing, categorized by their sources and propagation order, allowing for procedural composition. We also provide a toolbox for synthesizing these perturbations, enabling the transformation of clean environments into challenging noisy simulations. Utilizing the pipeline, we instantiate the large-scale Noisy-Replica benchmark, which includes diverse perturbation types, to evaluate the risk tolerance of existing advanced RGB-D SLAM models. Our extensive analysis uncovers the susceptibilities of both neural (NeRF and Gaussian Splatting -based) and non-neural SLAM models to disturbances, despite their demonstrated accuracy in standard benchmarks. Our code is publicly available at https://github.com/Xiaohao-Xu/SLAM-under-Perturbation., Comment: 50 pages. arXiv admin note: substantial text overlap with arXiv:2402.08125

This work is motivated by two key trends. On one hand, large language models (LLMs) have shown remarkable versatility in various generative tasks such as writing, drawing, and question answering, significantly reducing the time required for many routine tasks. On the other hand, researchers, whose work is not only time-consuming but also highly expertise-demanding, face increasing challenges as they have to spend more time reading, writing, and reviewing papers. This raises the question: how can LLMs potentially assist researchers in alleviating their heavy workload? This study focuses on the topic of LLMs assist NLP Researchers, particularly examining the effectiveness of LLM in assisting paper (meta-)reviewing and its recognizability. To address this, we constructed the ReviewCritique dataset, which includes two types of information: (i) NLP papers (initial submissions rather than camera-ready) with both human-written and LLM-generated reviews, and (ii) each review comes with "deficiency" labels and corresponding explanations for individual segments, annotated by experts. Using ReviewCritique, this study explores two threads of research questions: (i) "LLMs as Reviewers", how do reviews generated by LLMs compare with those written by humans in terms of quality and distinguishability? (ii) "LLMs as Metareviewers", how effectively can LLMs identify potential issues, such as Deficient or unprofessional review segments, within individual paper reviews? To our knowledge, this is the first work to provide such a comprehensive analysis., Comment: Accepted by EMNLP 2024 main conference

The Semiempirical Pseudopotential Method (SEPM) has emerged as a valuable tool for accurately determining band structures, especially in the realm of low-dimensional materials. SEPM operates by utilizing atomic pseudopotentials, which are derived from DFT calculations. SEPM calculations offer a unique advantage compared to DFT as they eliminate the requirement for iterative self-consistent solutions in solving the Schr\"odinger equation, leading to a substantial reduction in computational complexity. The incorporation of both non-local and local Semiempirical Pseudopotentials in our current approach yields band structures and wavefunctions with enhanced precision compared to traditional empirical methods. When applied to monolayer TMDCs, adjusting the parameters to align with pertinent values obtained from DFT computations enables us to faithfully replicate the band structure, opening avenues for investigating the optoelectronic properties of TMDCs and exploring their potential applications in nanodevices., Comment: 13 page

Machine Translation (MT) between linguistically dissimilar languages is challenging, especially due to the scarcity of parallel corpora. Prior works suggest that pivoting through a high-resource language can help translation into a related low-resource language. However, existing works tend to discard the source sentence when pivoting. Taking the case of English to Indian language MT, this paper explores the 'multi-source translation' approach with pivoting, using both source and pivot sentences to improve translation. We conducted extensive experiments with various multi-source techniques for translating English to Konkani, Manipuri, Sanskrit, and Bodo, using Hindi, Marathi, and Bengali as pivot languages. We find that multi-source pivoting yields marginal improvements over the state-of-the-art, contrary to previous claims, but these improvements can be enhanced with synthetic target language data. We believe multi-source pivoting is a promising direction for Low-resource translation.

Large Language Models (LLMs), originally shown to ace various text comprehension tasks have also remarkably been shown to tackle table comprehension tasks without specific training. While previous research has explored LLM capabilities with tabular dataset tasks, our study assesses the influence of $\textit{in-context learning}$,$ \textit{model scale}$, $\textit{instruction tuning}$, and $\textit{domain biases}$ on Tabular Question Answering (TQA). We evaluate the robustness of LLMs on Wikipedia-based $\textbf{WTQ}$ and financial report-based $\textbf{TAT-QA}$ TQA datasets, focusing on their ability to robustly interpret tabular data under various augmentations and perturbations. Our findings indicate that instructions significantly enhance performance, with recent models like Llama3 exhibiting greater robustness over earlier versions. However, data contamination and practical reliability issues persist, especially with WTQ. We highlight the need for improved methodologies, including structure-aware self-attention mechanisms and better handling of domain-specific tabular data, to develop more reliable LLMs for table comprehension.

Supply chain data management faces challenges in traceability, transparency, and trust. These issues stem from data silos and communication barriers. This research introduces DIDChain, a framework leveraging blockchain technology, Decentralized Identifiers, and the InterPlanetary File System. DIDChain improves supply chain data management. To address privacy concerns, DIDChain employs a hybrid blockchain architecture that combines public blockchain transparency with the control of private systems. Our hybrid approach preserves the authenticity and reliability of supply chain events. It also respects the data privacy requirements of the participants in the supply chain. Central to DIDChain is the cheqd infrastructure. The cheqd infrastructure enables digital tracing of asset events, such as an asset moving from the milk-producing dairy farm to the cheese manufacturer. In this research, assets are raw materials and products. The cheqd infrastructure ensures the traceability and reliability of assets in the management of supply chain data. Our contribution to blockchain-enabled supply chain systems demonstrates the robustness of DIDChain. Integrating blockchain technology through DIDChain offers a solution to data silos and communication barriers. With DIDChain, we propose a framework to transform the supply chain infrastructure across industries., Comment: Accepted to be published at the 18th IEEE International Conference on Service-Oriented System Engineering 2024

The Universal Rotation Curve (URC) of disk galaxies was originally proposed to predict the shape and amplitude of any rotation curve (RC) based solely on photometric data. Here, the URC is investigated with an extensive set of spatially-resolved rotation curves drawn from the PROBES-I, PROBES-II, and MaNGA data bases with matching multi-band surface brightness profiles from the DESI-LIS and WISE surveys for 3,846 disk galaxies. Common URC formulations fail to achieve an adequate level of accuracy to qualify as truly universal over fully sampled RCs. We develop neural network (NN) equivalents for the proposed URCs which predict RCs with higher accuracy, showing that URC inaccuracies are not due to insufficient data but rather non-optimal formulations or sampling effects. This conclusion remains even if the total RC sample is pruned for symmetry. The latest URC prescriptions and their NN equivalents trained on our sub-sample of 579 disk galaxies with symmetric RCs perform similarly to the URC/NN trained on the complete data sample. We conclude that a URC with an acceptable level of accuracy ($\Delta V_{\rm circ} \lesssim15$ per cent) at all radii would require a detailed modelling of a galaxy's central regions and outskirts (e.g., for baryonic effects leading to contraction or expansion of any dark-matter-only halo)., Comment: 36 full pages, 13 figures, 2 appendices. Accepted for publication in the Astrophysical Journal

With the rapid growth of Large Language Models (LLMs), safeguarding textual content against unauthorized use is crucial. Text watermarking offers a vital solution, protecting both - LLM-generated and plain text sources. This paper presents a unified overview of different perspectives behind designing watermarking techniques, through a comprehensive survey of the research literature. Our work has two key advantages, (1) we analyze research based on the specific intentions behind different watermarking techniques, evaluation datasets used, watermarking addition, and removal methods to construct a cohesive taxonomy. (2) We highlight the gaps and open challenges in text watermarking to promote research in protecting text authorship. This extensive coverage and detailed analysis sets our work apart, offering valuable insights into the evolving landscape of text watermarking in language models.

Since most inverse problems arising in scientific and engineering applications are ill-posed, prior information about the solution space is incorporated, typically through regularization, to establish a well-posed problem with a unique solution. Often, this prior information is an assumed statistical distribution of the desired inverse problem solution. Recently, due to the unprecedented success of generative adversarial networks (GANs), the generative network from a GAN has been implemented as the prior information in imaging inverse problems. In this paper, we devise a novel iterative algorithm to solve inverse problems in imaging where a dual-structured prior is imposed by combining a GAN prior with the compound Gaussian (CG) class of distributions. A rigorous computational theory for the convergence of the proposed iterative algorithm, which is based upon the alternating direction method of multipliers, is established. Furthermore, elaborate empirical results for the proposed iterative algorithm are presented. By jointly exploiting the powerful CG and GAN classes of image priors, we find, in compressive sensing and tomographic imaging problems, our proposed algorithm outperforms and provides improved generalizability over competitive prior art approaches while avoiding performance saturation issues in previous GAN prior-based methods., Comment: Submitted to IEEE TSP for publication. 13 pages, 2 figures

In recent work, we demonstrated a double-copy relation between inclusive gluon radiation in shock wave collisions of ultrarelativistic nuclei and inclusive graviton radiation in trans-Planckian gravitational shock wave collisions. We compute here the corresponding gravitational shock wave propagators in general relativity and demonstrate that they too obey a double copy relation to gluon shock wave propagators computed previously. These results provide key input in a renormalization group approach towards computing the high frequency radiation spectrum in close black hole encounters., Comment: 16 pages, revised version to appear in Physical Review D

Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, high inference latency, and difficulties of integration with large language models (LLMs) have necessitated exploring alternatives to DMs. This paper introduces ControlVAR, a novel framework that explores pixel-level controls in visual autoregressive (VAR) modeling for flexible and efficient conditional generation. In contrast to traditional conditional models that learn the conditional distribution, ControlVAR jointly models the distribution of image and pixel-level conditions during training and imposes conditional controls during testing. To enhance the joint modeling, we adopt the next-scale AR prediction paradigm and unify control and image representations. A teacher-forcing guidance strategy is proposed to further facilitate controllable generation with joint modeling. Extensive experiments demonstrate the superior efficacy and flexibility of ControlVAR across various conditional generation tasks against popular conditional DMs, \eg, ControlNet and T2I-Adaptor. Code: \url{https://github.com/lxa9867/ControlVAR}., Comment: 25 pages, 19 figures, 4 tables

Recently many techniques have emerged to create high quality 3D assets and scenes. When it comes to editing of these objects, however, existing approaches are either slow, compromise on quality, or do not provide enough customization. We introduce a novel approach to quickly edit a 3D model from a single reference view. Our technique first segments the edit image, and then matches semantically corresponding regions across chosen segmented dataset views using DINO features. A color or texture change from a particular region of the edit image can then be applied to other views automatically in a semantically sensible manner. These edited views act as an updated dataset to further train and re-style the 3D scene. The end-result is therefore an edited 3D model. Our framework enables a wide variety of editing tasks such as manual local edits, correspondence based style transfer from any example image, and a combination of different styles from multiple example images. We use Gaussian Splats as our primary 3D representation due to their speed and ease of local editing, but our technique works for other methods such as NeRFs as well. We show through multiple examples that our method produces higher quality results while offering fine-grained control of editing. Project page: ice-gaussian.github.io, Comment: Accepted to CVPR AI4CC Workshop 2024. Project page: https://ice-gaussian.github.io

The major Sustainable Development Goals (SDG) 2030, set by the United Nations Development Program (UNDP), include sustainable cities and communities, no poverty, and reduced inequalities. However, millions of people live in slums or informal settlements with poor living conditions in many major cities around the world, especially in less developed countries. To emancipate these settlements and their inhabitants through government intervention, accurate data about slum location and extent is required. While ground survey data is the most reliable, such surveys are costly and time-consuming. An alternative is remotely sensed data obtained from very high-resolution (VHR) imagery. With the advancement of new technology, remote sensing based mapping of slums has emerged as a prominent research area. The parallel rise of Artificial Intelligence, especially Deep Learning has added a new dimension to this field as it allows automated analysis of satellite imagery to identify complex spatial patterns associated with slums. This article offers a detailed review and meta-analysis of research on slum mapping using remote sensing imagery from 2014 to 2024, with a special focus on deep learning approaches. Our analysis reveals a trend towards increasingly complex neural network architectures, with advancements in data preprocessing and model training techniques significantly enhancing slum identification accuracy. We have attempted to identify key methodologies that are effective across diverse geographic contexts. While acknowledging the transformative impact Convolutional Neural Networks (CNNs) in slum detection, our review underscores the absence of a universally optimal model, suggesting the need for context-specific adaptations. We also identify prevailing challenges in this field, such as data limitations and a lack of model explainability and suggest potential strategies for overcoming these.

The dynamic nature of indoor environments poses unique challenges for next-generation millimeter-wave (mmwave) connectivity. These challenges arise from blockages due to mobile obstacles, mm-wave signal scattering caused by indoor surfaces, and user phased antenna array imperfections. Traditional compressed sensing (CS) based beam alignment techniques enable swift mm-wave connectivity with a limited number of measurements. These techniques, however, rely on prior knowledge of the communication channel model and the user's array manifold to design the sensing matrix and minimize angle quantization errors. This limits their effectiveness in dynamic environments. This paper proposes a novel CS-based beam alignment technique for mm-wave systems operating in indoor environments. Unlike prior work that rely on knowledge of the user's antenna architecture, communication codebook, and channel, the proposed technique is agnostic to these factors. The proposed formulation eliminates angle quantization errors by mapping the recovered angular directions onto the user's specific codebook. This is achieved by exploiting the energy compaction property of the Discrete Cosine Transform (DCT) to compress and identify the strongest cluster locations in the transform domain for robust beamforming. Experimental results at 60 GHz demonstrate successful recovery of the mm-wave power distribution in the angular domain, facilitating accurate beam alignment with limited measurements compared to exhaustive search solutions.

In the absence of any new physics signals at the Large Hadron Collider (LHC), anomalous results at low energy experiments have become the subject of increased attention. We focus on three such results from the LSND, MiniBooNE (MB), and ATOMKI experiments. A 17 MeV pseudoscalar mediator ($a'$) can account for two ($^8$Be and $^4$He) out of the three cases in which excess events have been seen in pair creation transitions in ATOMKI. We incorporate this mediator in a gauge invariant extension of the Standard Model (SM) with a second Higgs doublet and three singlet (seesaw) neutrinos ($N_i, i=1,2,3$). $N_{1,2}$ participate in an interaction in MB and LSND which, with $a'$ as mediator, leads to the production of $e^+ e^-$ pairs. The $N_i$ also lead to mass-squared differences for SM neutrinos in agreement with global oscillation data. We first show that such a model offers a natural joint solution to the MB and LSND excesses, providing excellent fits to their data. Next, using the values of the couplings to the quarks and electrons which are required to explain pair creation nuclear transition data for $^8$Be and $^4$He in ATOMKI, we show that these values still lead to fits for MB and LSND data. However, once ATOMKI is incorporated, we find that strong constraints from the decays $K^+ \rightarrow \pi^+ a' \, (a'\rightarrow e^+e^-)$ and $\pi^+ \rightarrow $ $ e^+ ~\nu_e ~e^+ e^- $ come into play. While our solution is in conformity with the bounds on the former decay, it remains in tension with $90\%$ CL bounds on the latter. We also discuss other constraints from both collider and non-collider experiments and from electroweak precision data, stability and unitarity. We compute the contributions to the electron and muon $g-2$ up to two loops for our model. We discuss tests of the model in upcoming experiments., Comment: 40 pages, 6 figures and 3 tables, Replaced with the published version

Monolayer molybdenum disulfide ($\mathrm{MoS_2}$) under strain has many interesting properties and possible applications in technology. A recent experimental study examined the effect of strain on the bandgap of monolayer $\mathrm{MoS_2}$ on a mildly curved graphite surface, reporting that under biaxial strain with a Poisson's ratio of 0.44, the bandgap decreases at a rate of 400 meV/\% strain. In this work, we performed density functional theory (DFT) calculations for a free-standing $\mathrm{MoS_2}$ monolayer, using the generalized gradient approximation (GGA) PBE, the hybrid functional HSE06, and many-body perturbation theory with the GW approximation using PBE wavefunctions (G0W0@PBE). For the unstrained monolayer, we found a standard level of agreement for the bandgap between theory and experiment. For biaxial strain at the experimental Poisson's ratio, we found that the bandgap decreases at rates of 63 meV/\% strain (PBE), 73 meV/\% strain (HSE06), and 43 meV/\% strain (G0W0@PBE), which are significantly smaller than the experimental rate. We also found that PBE predicts a similarly smaller rate (90 meV/\% strain) for a different Poisson's ratio of 0.25. Spin-orbit correction (SOC) has little effect on the gap or its strain dependence. The strong disagreement between theory and experiment may reflect an unexpectedly strong effect of the substrate on the strain dependence of the gap. Additionally, we observed a transition from a direct to an indirect bandgap under strain, and (under an equal biaxial strain of 10\%) a semiconductor-to-metal transition, consistent with previous theoretical work.

Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with images that are typically Western-centric. While recent efforts have tried to increase the number of languages covered on VQA datasets, they still lack diversity in low-resource languages. More importantly, although these datasets often extend their linguistic range via translation or some other approaches, they usually keep images the same, resulting in narrow cultural representation. To address these limitations, we construct CVQA, a new Culturally-diverse multilingual Visual Question Answering benchmark, designed to cover a rich set of languages and cultures, where we engage native speakers and cultural experts in the data collection process. As a result, CVQA includes culturally-driven images and questions from across 30 countries on four continents, covering 31 languages with 13 scripts, providing a total of 10k questions. We then benchmark several Multimodal Large Language Models (MLLMs) on CVQA, and show that the dataset is challenging for the current state-of-the-art models. This benchmark can serve as a probing evaluation suite for assessing the cultural capability and bias of multimodal models and hopefully encourage more research efforts toward increasing cultural awareness and linguistic diversity in this field., Comment: 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks

Due to the unavailability of solar irradiance data for many potential sites of Nepal, the paper proposes predicting solar irradiance based on alternative meteorological parameters. The study focuses on five distinct regions in Nepal and utilizes a dataset spanning almost ten years, obtained from CERES SYN1deg and MERRA-2. Machine learning models such as Random Forest, XGBoost, K-Nearest Neighbors, and deep learning models like LSTM and ANN-MLP are employed and evaluated for their performance. The results indicate high accuracy in predicting solar irradiance, with R-squared(R2) scores close to unity for both train and test datasets. The impact of parameter integration on model performance is analyzed, revealing the significance of various parameters in enhancing predictive accuracy. Each model demonstrates strong performance across all parameters, consistently achieving MAE values below 6, RMSE values under 10, MBE within |2|, and nearly unity R2 values. Upon removal of various solar parameters such as "Solar_Irradiance_Clear_Sky", "UVA", etc. from the datasets, the model's performance is significantly affected. This exclusion leads to considerable increases in MAE, reaching up to 82, RMSE up to 135, and MBE up to |7|. Among the models, KNN displays the weakest performance, with an R2 of 0.7582546. Conversely, ANN exhibits the strongest performance, boasting an R2 value of 0.9245877. Hence, the study concludes that Artificial Neural Network (ANN) performs exceptionally well, showcasing its versatility even under sparse data parameter conditions., Comment: 20 pages, 12 figures, 5 tables

Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks. However, they have been shown to suffer from a critical limitation pertinent to 'hallucination' in their output. Recent research has focused on investigating and addressing this problem for a variety of tasks such as biography generation, question answering, abstractive summarization, and dialogue generation. However, the crucial aspect pertaining to 'negation' has remained considerably underexplored. Negation is important because it adds depth and nuance to the understanding of language and is also crucial for logical reasoning and inference. In this work, we address the above limitation and particularly focus on studying the impact of negation in LLM hallucinations. Specifically, we study four tasks with negation: 'false premise completion', 'constrained fact generation', 'multiple choice question answering', and 'fact generation'. We show that open-source state-of-the-art LLMs such as LLaMA-2-chat, Vicuna, and Orca-2 hallucinate considerably on all these tasks involving negation which underlines a critical shortcoming of these models. Addressing this problem, we further study numerous strategies to mitigate these hallucinations and demonstrate their impact.

This paper presents a simulation approach to enhance the power quality of a PV-micro hydro grid supplying both linear consumer load and non-linear industrial load by integrating Shunt Active Power Filter (SAPF), utilizing instantaneous PQ theory and hysteresis current control band logic. The non-linear load draws reactive power and harmonic current from the source thereby affecting the power quality. The integration of the SAPF at the point of common coupling (PCC) offers reactive power and harmonic current compensation, ensuring that the current supply to the grid remains nearly sinusoidal and proportional to the active power. By injecting equal and opposite harmonic components, the SAPF effectively reduces Total Harmonic Distortion (THD) from 7% to 2.96%, thereby enhancing the overall power quality of the PV-micro hydro grid system., Comment: 5 pages, 21 figures, submitted on IEEE powercon 2024 conference

We perform the numerical simulations of axisymmetric, relativistic, optically thin jets under the influence of the radiation field of an accretion disk. We show that starting from a very low injection velocity at the base, jets can be accelerated to relativistic terminal speeds when traveling through the radiation field. The jet gains momentum through the interaction with the radiation field. We use a relativistic equation of state for multi-species plasma, which self-consistently calculates the adiabatic index for the jet material. All the jet solutions obtained are transonic in nature. In addition to the acceleration of the jet to relativistic speeds, our results show that the radiation field also acts as a collimating agent. The jets remain well collimated under the effect of radiation pressure. We also show that if the jet starts with a rotational velocity, the radiation field will reduce the angular momentum of the jet beam., Comment: 19 pages, 11 figures, accepted for publication in ApJ

While machine translation evaluation has been studied primarily for high-resource languages, there has been a recent interest in evaluation for low-resource languages due to the increasing availability of data and models. In this paper, we focus on a zero-shot evaluation setting focusing on low-resource Indian languages, namely Assamese, Kannada, Maithili, and Punjabi. We collect sufficient Multi-Dimensional Quality Metrics (MQM) and Direct Assessment (DA) annotations to create test sets and meta-evaluate a plethora of automatic evaluation metrics. We observe that even for learned metrics, which are known to exhibit zero-shot performance, the Kendall Tau and Pearson correlations with human annotations are only as high as 0.32 and 0.45. Synthetic data approaches show mixed results and overall do not help close the gap by much for these languages. This indicates that there is still a long way to go for low-resource evaluation.

This research combines MediaPipe and CNNs for the efficient and accurate interpretation of ASL dataset for the real-time detection of sign language. The system presented here captures and processes hands' gestures in real time. the intended purpose was to create a very easy, accurate, and fast way of entering commands without the necessity of touching something.MediaPipe supports one of the powerful frameworks in real-time hand tracking capabilities for the ability to capture and preprocess hand movements, which increases the accuracy of the gesture recognition system. Actually, the integration of CNN with the MediaPipe results in higher efficiency in using the model of real-time processing.The accuracy achieved by the model on ASL datasets is 99.12\%.The model was tested using American Sign Language (ASL) datasets. The results were then compared to those of existing methods to evaluate how well it performed, using established evaluation techniques. The system will have applications in the communication, education, and accessibility domains. Making systems such as described in this paper even better will assist people with hearing impairment and make things accessible to them. We tested the recognition and translation performance on an ASL dataset and achieved better accuracy over previous models.It is meant to the research is to identify the characters that American signs recognize using hand images taken from a web camera by based on mediapipe and CNNs, Comment: We have decided to withdraw our paper due to significant revisions and improvements that need to be made based on new findings. After further analysis, we believe these changes are necessary to ensure the accuracy and completeness of our work. We plan to resubmit the revised version in the future once the updates are complete

The Vision-Language Foundation Model has recently shown outstanding performance in various perception learning tasks. The outstanding performance of the vision-language model mainly relies on large-scale pre-training datasets and different data augmentation techniques. However, the domain generalization problem of the vision-language foundation model needs to be addressed. This problem has limited the generalizability of the vision-language foundation model to unknown data distributions. In this paper, we introduce a new simple but efficient Diffusion Sampling approach to Domain Generalization (ED-SAM) to improve the generalizability of the vision-language foundation model. Our theoretical analysis in this work reveals the critical role and relation of the diffusion model to domain generalization in the vision-language foundation model. Then, based on the insightful analysis, we introduce a new simple yet effective Transport Transformation to diffusion sampling method. It can effectively generate adversarial samples to improve the generalizability of the foundation model against unknown data distributions. The experimental results on different scales of vision-language pre-training datasets, including CC3M, CC12M, and LAION400M, have consistently shown State-of-the-Art performance and scalability of the proposed ED-SAM approach compared to the other recent methods.

Unsupervised Domain Adaptation has been an efficient approach to transferring the semantic segmentation model across data distributions. Meanwhile, the recent Open-vocabulary Semantic Scene understanding based on large-scale vision language models is effective in open-set settings because it can learn diverse concepts and categories. However, these prior methods fail to generalize across different camera views due to the lack of cross-view geometric modeling. At present, there are limited studies analyzing cross-view learning. To address this problem, we introduce a novel Unsupervised Cross-view Adaptation Learning approach to modeling the geometric structural change across views in Semantic Scene Understanding. First, we introduce a novel Cross-view Geometric Constraint on Unpaired Data to model structural changes in images and segmentation masks across cameras. Second, we present a new Geodesic Flow-based Correlation Metric to efficiently measure the geometric structural changes across camera views. Third, we introduce a novel view-condition prompting mechanism to enhance the view-information modeling of the open-vocabulary segmentation network in cross-view adaptation learning. The experiments on different cross-view adaptation benchmarks have shown the effectiveness of our approach in cross-view modeling, demonstrating that we achieve State-of-the-Art (SOTA) performance compared to prior unsupervised domain adaptation and open-vocabulary semantic segmentation methods., Comment: Accepted to NeurIPS'24

During epithelial-mesenchymal transition (EMT), epithelial cells change their morphology, disperse, and gain mesenchymal-like characteristics. Usually, cells are categorized into discrete cell types or states based on gene expression and other cellular features. Subsequently, EMT is investigated as a dynamical process where cells jump from one discrete state to another. In the current work, we moved away from this idea of discrete state transition and investigated EMT dynamics in a continuous phenotypic space. We used morphology to define the phenotype of a cell. We used the data from quantitative image analysis of MDA-MB-468 cells undergoing EGF-induced EMT. We defined the morphological state space or 'morphospace' using the morphological features extracted through image analysis. During EMT, as the morphology changed, the distribution of cells in the morphospace also changed. However, this morphospace had a very high dimension. We reduced it to a 2-dimensional "reduced morphospace" and investigated the temporal change in the spatial distribution of cells in this reduced space. We used proper orthogonal decomposition to find dominant dynamical features of this spatio-temporal data. The modal analysis detected key features of EMT in this experimental system - reversible transition, distinct paths of phenotypic transition during induction and reversal of EMT, and enhanced diversity of cells during reversal of EMT. We also provide some intuitive physical meaning of the spatial modes and connect them to the key molecular event during EMT., Comment: 33 pages, 8 figures

Large language models (LLMs) have shown remarkable performance across a wide range of applications, often outperforming human experts. However, deploying these parameter-heavy models efficiently for diverse inference use cases requires carefully designed hardware platforms with ample computing, memory, and network resources. With LLM deployment scenarios and models evolving at breakneck speed, the hardware requirements to meet SLOs remains an open research question. In this work, we present an analytical tool, GenZ, to study the relationship between LLM inference performance and various platform design parameters. Our analysis provides insights into configuring platforms for different LLM workloads and use cases. We quantify the platform requirements to support SOTA LLMs models like LLaMA and GPT-4 under diverse serving settings. Furthermore, we project the hardware capabilities needed to enable future LLMs potentially exceeding hundreds of trillions of parameters. The trends and insights derived from GenZ can guide AI engineers deploying LLMs as well as computer architects designing next-generation hardware accelerators and platforms. Ultimately, this work sheds light on the platform design considerations for unlocking the full potential of large language models across a spectrum of applications. The source code is available at https://github.com/abhibambhaniya/GenZ-LLM-Analyzer ., Comment: 12 Pages, https://github.com/abhibambhaniya/GenZ-LLM-Analyzer