Search

In recent years, the development of the Lunar Gateway and Artemis missions has renewed interest in lunar exploration, including both manned and unmanned missions. This interest necessitates accurate initial orbit determination (IOD) and orbit prediction (OP) in this domain, which faces significant challenges such as severe nonlinearity, sensitivity to initial conditions, large state-space volume, and sparse, faint, and unreliable measurements. This paper explores the capability of data-driven Koopman operator-based approximations for OP in these scenarios. Three stable periodic trajectories from distinct cislunar families are analyzed. The analysis includes theoretical justification for using a linear time-invariant system as the data-driven surrogate. This theoretical framework is supported by experimental validation. Furthermore, the accuracy is assessed by comparing the spectral content captured to period estimates derived from the fast Fourier transform (FFT) and Poincare-like sections., Comment: arXiv admin note: text overlap with arXiv:2401.13784

Large Language Models (LLMs) are highly resource-intensive to fine-tune due to their enormous size. While low-rank adaptation is a prominent parameter-efficient fine-tuning approach, it suffers from sensitivity to hyperparameter choices, leading to instability in model performance on fine-tuning downstream tasks. This paper highlights the importance of effective parameterization in low-rank fine-tuning to reduce estimator variance and enhance the stability of final model outputs. We propose MonteCLoRA, an efficient fine-tuning technique, employing Monte Carlo estimation to learn an unbiased posterior estimation of low-rank parameters with low expected variance, which stabilizes fine-tuned LLMs with only O(1) additional parameters. MonteCLoRA shows significant improvements in accuracy and robustness, achieving up to 3.8% higher accuracy and 8.6% greater robustness than existing efficient fine-tuning methods on natural language understanding tasks with pre-trained RoBERTa-base. Furthermore, in generative tasks with pre-trained LLaMA-1-7B, MonteCLoRA demonstrates robust zero-shot performance with 50% lower variance than the contemporary efficient fine-tuning methods. The theoretical and empirical results presented in the paper underscore how parameterization and hyperpriors balance exploration-exploitation in the low-rank parametric space, therefore leading to more optimal and robust parameter estimation during efficient fine-tuning., Comment: 48 pages, 10 figures, 10 tables, Code: https://github.com/LCS2-IIITD/MonteCLoRA

Extended Reality (XR) technologies are gaining traction as effective tools for medical training and procedural guidance, particularly in complex cardiac interventions. This paper presents a novel system for real-time 3D tracking and visualization of intracardiac echocardiography (ICE) catheters, with precise measurement of the roll angle. A custom 3D-printed setup, featuring orthogonal cameras, captures biplane video of the catheter, while a specialized computer vision algorithm reconstructs its 3D trajectory, localizing the tip with sub-millimeter accuracy and tracking the roll angle in real-time. The system's data is integrated into an interactive Unity-based environment, rendered through the Meta Quest 3 XR headset, combining a dynamically tracked catheter with a patient-specific 3D heart model. This immersive environment allows the testing of the importance of 3D depth perception, in comparison to 2D projections, as a form of visualization in XR. Our experimental study, conducted using the ICE catheter with six participants, suggests that 3D visualization is not necessarily beneficial over 2D views offered by the XR system; although all cardiologists saw its utility for pre-operative training, planning, and intra-operative guidance. The proposed system qualitatively shows great promise in transforming catheter-based interventions, particularly ICE procedures, by improving visualization, interactivity, and skill development.

Topological effects manifest in a variety of lattice geometries. While square lattices, due to their simplicity, have been used for models supporting nontrivial topology, several exotic topological phenomena such as Dirac points, Weyl points and Haldane phases are most commonly supported by non-square lattices. Examples of prototypical non-square lattices include the honeycomb lattice of graphene and the Kagome lattice, both of which break fundamental symmetries and can exhibit quantized transport, especially when long-range hoppings and gauge fields are incorporated. The challenge of controllably realizing long-range hoppings and gauge fields has motivated a large body of research focused on harnessing lattices encoded in "synthetic" dimensions. Photons in particular have many internal degrees of freedom and hence show promise for implementing these synthetic dimensions; however, most photonic synthetic dimensions has hitherto created 1D or 2D square lattices. Here we show that non-square lattice Hamiltonians can be implemented using Floquet synthetic dimensions. Our construction uses dynamically modulated ring resonators and provides the capacity for direct $k$-space engineering of lattice Hamiltonians. Such a construction lifts constraints on the orthogonality of lattice vectors that make square geometries simpler to implement, and instead transfers the complexity to the engineering of complex Floquet drive signals. We simulate topological signatures of the Haldane and the brick-wall Haldane model and observe them to be robust in the presence of external optical drive and photon loss, and discuss unique characteristics of their topological transport when implemented on these Floquet lattices. Our proposal demonstrates the potential of driven-dissipative Floquet synthetic dimensions as a new architecture for $k$-space Hamiltonian simulation of high-dimensional lattice geometries.

In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a sense of safety that is carried over from task to task. We model this as a meta-learning process where each task is synchronized with a safeguard that monitors safety and provides a reward signal to the agent. The safeguard is implemented as a finite-state machine based on a safety specification; the reward signal is formally shaped around this specification. The safety specification and its corresponding safeguard can be arbitrarily complex and non-Markovian, which adds flexibility to the training process and explainability to the learned policy. The design of the safeguard is manual but it is high-level and model-agnostic, which gives rise to an end-to-end safe learning approach with wide applicability, from pixel-level game control to language model fine-tuning. Starting from a given set of safety specifications (tasks), we train a model such that it can adapt to new specifications using only a small number of training samples. This is made possible by our method for efficiently transferring safety bias between tasks, which effectively minimizes the number of safety violations. We evaluate our framework in a Minecraft-inspired Gridworld, a VizDoom game environment, and an LLM fine-tuning application. Agents trained with our approach achieve near-minimal safety violations, while baselines are shown to underperform.

Deep neural networks (DNNS) excel at learning from static datasets but struggle with continual learning, where data arrives sequentially. Catastrophic forgetting, the phenomenon of forgetting previously learned knowledge, is a primary challenge. This paper introduces EXponentially Averaged Class-wise Feature Significance (EXACFS) to mitigate this issue in the class incremental learning (CIL) setting. By estimating the significance of model features for each learned class using loss gradients, gradually aging the significance through the incremental tasks and preserving the significant features through a distillation loss, EXACFS effectively balances remembering old knowledge (stability) and learning new knowledge (plasticity). Extensive experiments on CIFAR-100 and ImageNet-100 demonstrate EXACFS's superior performance in preserving stability while acquiring plasticity.

Material discovery is a critical area of research with the potential to revolutionize various fields, including carbon capture, renewable energy, and electronics. However, the immense scale of the chemical space makes it challenging to explore all possible materials experimentally. In this paper, we introduce FlowLLM, a novel generative model that combines large language models (LLMs) and Riemannian flow matching (RFM) to design novel crystalline materials. FlowLLM first fine-tunes an LLM to learn an effective base distribution of meta-stable crystals in a text representation. After converting to a graph representation, the RFM model takes samples from the LLM and iteratively refines the coordinates and lattice parameters. Our approach significantly outperforms state-of-the-art methods, increasing the generation rate of stable materials by over three times and increasing the rate for stable, unique, and novel crystals by $\sim50\%$ - a huge improvement on a difficult problem. Additionally, the crystals generated by FlowLLM are much closer to their relaxed state when compared with another leading model, significantly reducing post-hoc computational cost.

Large language models have drastically changed the prospects of AI by introducing technologies for more complex natural language processing. However, current methodologies to train such LLMs require extensive resources including but not limited to large amounts of data, expensive machinery, and lengthy training. To solve this problem, this paper proposes a new tokenization method inspired by universal Lempel-Ziv-Welch data compression that compresses repetitive phrases into multi-word tokens. With MultiTok as a new tokenizing tool, we show that language models are able to be trained notably more efficiently while offering a similar accuracy on more succinct and compressed training data. In fact, our results demonstrate that MultiTok achieves a comparable performance to the BERT standard as a tokenizer while also providing close to 2.5x faster training with more than 30% less training data.

Stablecoins are a class of cryptocurrencies which aim at providing consistency and predictability, typically by pegging the token's value to that of a real world asset. Designing resilient decentralized stablecoins is a challenge, and prominent stablecoins today either (i) give up on decentralization, or (ii) rely on user-owned cryptocurrencies as collateral, exposing the token to exogenous price fluctuations. In this latter category, it is increasingly common to employ algorithmic mechanisms to automate risk management, helping maintain the peg. One example of this is Reflexer's RAI, which adapts its system-internal exchange rate (redemption price) to secondary market conditions according to a proportional control law. In this paper, we take this idea of active management a step further, and introduce a new kind of control scheme based on a Stackelberg game model between the token protocol and its users. By doing so, we show that (i) we can mitigate adverse depeg events that inevitably arise in a fixed-redemption scheme such as MakerDao's DAI and (ii) generally outperform a simpler, adaptive-redemption scheme such as RAI in the task of targeting a desired market price. We demonstrate these results through extensive simulations over a range of market conditions.

This study proposes an advanced Federated Learning (FL) framework designed to enhance data privacy and security in IoT environments by integrating Decentralized Attribute-Based Encryption (DABE), Homomorphic Encryption (HE), Secure Multi-Party Computation (SMPC), and Blockchain technology. Unlike traditional FL, our framework enables secure, decentralized authentication and encryption directly on IoT devices using DABE, allowing sensitive data to remain locally encrypted. Homomorphic Encryption permits computations on encrypted data, and SMPC ensures privacy in collaborative computations, while Blockchain technology provides transparent, immutable record-keeping for all transactions and model updates. Local model weights are encrypted and transmitted to fog layers for aggregation using HE and SMPC, then iteratively refined by the central server using differential privacy to safeguard against data leakage. This secure, privacy-preserving FL framework delivers a robust solution for efficient model training and real-time analytics across distributed IoT devices, offering significant advancements in secure decentralized learning for IoT applications.

We introduce Controller-Embedded Language Model Interactions (CELI), a framework that integrates control logic directly within language model (LM) prompts, facilitating complex, multi-stage task execution. CELI addresses limitations of existing prompt engineering and workflow optimization techniques by embedding control logic directly within the operational context of language models, enabling dynamic adaptation to evolving task requirements. Our framework transfers control from the traditional programming execution environment to the LMs, allowing them to autonomously manage computational workflows while maintaining seamless interaction with external systems and functions. CELI supports arbitrary function calls with variable arguments, bridging the gap between LMs' adaptive reasoning capabilities and conventional software paradigms' structured control mechanisms. To evaluate CELI's versatility and effectiveness, we conducted case studies in two distinct domains: code generation (HumanEval benchmark) and multi-stage content generation (Wikipedia-style articles). The results demonstrate notable performance improvements across a range of domains. CELI achieved a 4.9 percentage point improvement over the best reported score of the baseline GPT-4 model on the HumanEval code generation benchmark. In multi-stage content generation, 94.4% of CELI-produced Wikipedia-style articles met or exceeded first draft quality when optimally configured, with 44.4% achieving high quality. These outcomes underscore CELI's potential for optimizing AI-driven workflows across diverse computational domains., Comment: 26 pages, 2 figures

Pedestrian dynamics simulates the fine-scaled trajectories of individuals in a crowd. It has been used to suggest public health interventions to reduce infection risk in important components of air travel, such as during boarding and in airport security lines. Due to inherent variability in human behavior, it is difficult to generalize simulation results to new geographic, cultural, or temporal contexts. A digital twin, relying on real-time data, such as video feeds, can resolve this limitation. This paper addresses the following critical gaps in knowledge required for a digital twin. (1) Pedestrian dynamics models currently lack accurate representations of collision avoidance behavior when two moving pedestrians try to avoid collisions. (2) It is not known whether data assimilation techniques designed for physical systems are effective for pedestrian dynamics. We address the first limitation by training a model with data from offline video feeds of collision avoidance to simulate these trajectories realistically, using symbolic regression to identify unknown functional forms. We address the second limitation by showing that pedestrian dynamics with data assimilation can predict pedestrian trajectories with sufficient accuracy. These results promise to enable the development of a digital twin for pedestrian movement in airports that can help with real-time crowd management to reduce health risks., Comment: Submitted to IEEE

Quantum scars are nonthermal eigenstates that prevent thermalization of initial states with weight on the scars. When the scar states are equally spaced in energy, superpositions of scars show oscillating local observables that can be detected in experiments. However, we note that scarred models in the literature show fundamentally different scar entanglement dynamics: some show entanglement oscillations while others are completely frozen. We explain this freezing through a no-go theorem which we apply to more than a dozen scarred models in the literature. We also discuss a method for evading the no-go theorem by deforming the scarred models with frozen scar entanglement dynamics., Comment: Emailed comments and reference requests are welcome

Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data. To address this, Retrieval-Augmented Generation (RAG) uses external knowledge bases (KBs), but these can also suffer from inaccuracies. We introduce STACKFEED, a novel Structured Textual Actor-Critic Knowledge base editing with FEEDback approach that iteratively refines the KB based on expert feedback using a multi-actor, centralized critic reinforcement learning framework. Each document is assigned to an actor, modeled as a ReACT agent, which performs structured edits based on document-specific targeted instructions from a centralized critic. Experimental results show that STACKFEED significantly improves KB quality and RAG system performance, enhancing accuracy by up to 8% over baselines.

Recent work on fact-checking addresses a realistic setting where models incorporate evidence retrieved from the web to decide the veracity of claims. A bottleneck in this pipeline is in retrieving relevant evidence: traditional methods may surface documents directly related to a claim, but fact-checking complex claims requires more inferences. For instance, a document about how a vaccine was developed is relevant to addressing claims about what it might contain, even if it does not address them directly. We present Contrastive Fact-Checking Reranker (CFR), an improved retriever for this setting. By leveraging the AVeriTeC dataset, which annotates subquestions for claims with human written answers from evidence documents, we fine-tune Contriever with a contrastive objective based on multiple training signals, including distillation from GPT-4, evaluating subquestion answers, and gold labels in the dataset. We evaluate our model on both retrieval and end-to-end veracity judgments about claims. On the AVeriTeC dataset, we find a 6\% improvement in veracity classification accuracy. We also show our gains can be transferred to FEVER, ClaimDecomp, HotpotQA, and a synthetic dataset requiring retrievers to make inferences., Comment: EMNLP 2024 FEVER Workshop

In this work, we show that the edge dynamics of the Laughlin state in the weakly nonlinear regime is governed by the Korteweg-de Vries (KdV) equation. Our starting point is the Chern-Simons-Ginzburg-Landau theory in the lower half-plane, where the effective edge dynamics are encoded in anomaly-compatible boundary conditions. The saddle point bulk dynamics and the corresponding boundary conditions of this action can be reformulated as two-dimensional compressible fluid dynamic equations, subject to a quantum Hall constraint that links the superfluid vorticity to its density fluctuations. The boundary conditions in this hydrodynamic framework consist of no-penetration and no-stress conditions. We then apply the method of multiple scales to this hydrodynamic system and derive the KdV equation for the edge dynamics in the weakly nonlinear regime. By employing the Hamiltonian framework for the KdV equation, we show that we can recover the chiral Luttinger liquid theory in the linearized regime and provide a pathway for canonically quantizing the edge dynamics in the weakly non-linear limit., Comment: 33 pages, 1 figure

We conducted a high-throughput density functional theory calculation and comprehensive analysis of the momentum matrix elements between the band edges across a wide range of nonmagnetic two-dimensional monolayer materials with direct band gaps. The primary objectives of our study were twofold: (i) to identify and rank the materials as potential optical emitters and (ii) to enhance our understanding of the physical and chemical factors that determine the strength of the optical coupling. The momentum matrix elements range from nearly 0 to 1.13 at.u., depending on the specific structure and composition of the materials. By comparison, the most prominent group III-V bulk semiconductors have momentum matrix elements on the order of 1 at.u., indicating the high potential of two-dimensional monolayer materials as optical emitters. We applied a criterion derived from the atomic orbital selection rules for electronic transitions. Finally, we examined the prominent family of monolayer transition metal dichalcogenides, which exhibited high optical coupling and low criterion values. We propose a connection between the significant contribution to the momentum matrix elements for interband optical transitions and the anomalous Born effective charge phenomena. The implications of this phenomenon are such that, unlike materials that exhibit conventional Born effective charges, in which increased ionicity leads to diminished optical coupling. If the anomalous situation is present, it arises from a distinctive charge transfer and bonding mechanism, resulting in a positive correlation between ionicity and the optical coupling., Comment: 32 pages, 4 figures, and supporting information

This work reports the fabrication and characterization of a NiOx/\b{eta}-Ga2O3 heterojunction diode (HJD) that uses a metallic nickel (Ni) target to deposit NiOx layers via reactive RF magnetron sputtering and lift-off processing with >3 kV breakdown voltage, record-low reverse current leakage under high reverse bias, and high junction electric fields (>3.34 MV/cm). The heterojunction diodes are fabricated via bilayer NiOx sputtering followed by self-aligned mesa-etching for field-termination on both large (1-mm2) and small area (100-{\mu}m diameter) devices. The HJD exhibits a ~135 A/cm2 forward current density at 5 V with a rectifying ratio of ~1010. The minimum differential specific on-resistance is measured to be 17.26 m{\Omega} cm2. The breakdown voltage on 100-{\mu}m diameter pads was measured to be greater than 3 kV with a noise floor-level reverse leakage current density (10-8~10-6 A/cm2) until 3 kV, accomplishing a parallel-plane junction electric field to be at least 3.34 MV/cm at 3 kV with a power figure of merit (PFOM) >0.52 GW/cm2. Temperature-dependent forward current density-voltage (J-V) measurements are performed from room temperature (25 C) to 200 C which showed a temperature coefficient of resistance ({\alpha}) equaling 1.56, higher than that of \b{eta}-Ga2O3 Schottky barrier diodes (SBDs), indicating potential conductivity degradation within NiOx at elevated temperatures., Comment: 6 pages, 5 figures, APL Journal

We present an approach for systematically anticipating the actions and policies employed by \emph{oblivious} environments in concurrent stochastic games, while maximizing a reward function. Our main contribution lies in the synthesis of a finite \emph{information state machine} whose alphabet ranges over the actions of the environment. Each state of the automaton is mapped to a belief state about the policy used by the environment. We introduce a notion of consistency that guarantees that the belief states tracked by our automaton stays within a fixed distance of the precise belief state obtained by knowledge of the full history. We provide methods for checking consistency of an automaton and a synthesis approach which upon successful termination yields such a machine. We show how the information state machine yields an MDP that serves as the starting point for computing optimal policies for maximizing a reward function defined over plays. We present an experimental evaluation over benchmark examples including human activity data for tasks such as cataract surgery and furniture assembly, wherein our approach successfully anticipates the policies and actions of the environment in order to maximize the reward.

The recent advancements in artificial intelligence (AI), with the release of several large models having only query access, make a strong case for explainability of deep models in a post-hoc gradient free manner. In this paper, we propose a framework, named distillation aided explainability (DAX), that attempts to generate a saliency-based explanation in a model agnostic gradient free application. The DAX approach poses the problem of explanation in a learnable setting with a mask generation network and a distillation network. The mask generation network learns to generate the multiplier mask that finds the salient regions of the input, while the student distillation network aims to approximate the local behavior of the black-box model. We propose a joint optimization of the two networks in the DAX framework using the locally perturbed input samples, with the targets derived from input-output access to the black-box model. We extensively evaluate DAX across different modalities (image and audio), in a classification setting, using a diverse set of evaluations (intersection over union with ground truth, deletion based and subjective human evaluation based measures) and benchmark it with respect to $9$ different methods. In these evaluations, the DAX significantly outperforms the existing approaches on all modalities and evaluation metrics., Comment: 12 pages, 10 figures, Accepted in IEEE Journal of Selected Topics in Signal Processing (JSTSP), 2024

Inverse Constrained Reinforcement Learning (ICRL) is the task of inferring the implicit constraints followed by expert agents from their demonstration data. As an emerging research topic, ICRL has received considerable attention in recent years. This article presents a categorical survey of the latest advances in ICRL. It serves as a comprehensive reference for machine learning researchers and practitioners, as well as starters seeking to comprehend the definitions, advancements, and important challenges in ICRL. We begin by formally defining the problem and outlining the algorithmic framework that facilitates constraint inference across various scenarios. These include deterministic or stochastic environments, environments with limited demonstrations, and multiple agents. For each context, we illustrate the critical challenges and introduce a series of fundamental methods to tackle these issues. This survey encompasses discrete, virtual, and realistic environments for evaluating ICRL agents. We also delve into the most pertinent applications of ICRL, such as autonomous driving, robot control, and sports analytics. To stimulate continuing research, we conclude the survey with a discussion of key unresolved questions in ICRL that can effectively foster a bridge between theoretical understanding and practical industrial applications., Comment: 29 pages

Ni-Mo superalloys have emerged as materials of choice for a diverse array of applications owing to their superior mechanical properties, exceptional corrosion and oxidation resistance, electrocatalytic behavior, and surface stability. Understanding and optimizing the surface composition of Ni-Mo alloys is critical for enhancing their performance in practical applications. Traditional experimental surface analysis techniques, while informative, are often prohibitive in terms of cost and time. Likewise, theoretical approaches such as first-principle calculations demand substantial computational resources and it is difficult to simulate large structures. This study introduces an alternative approach utilizing hybrid Monte-Carlo / Molecular Dynamics (MC/MD) simulations to investigate the surface composition of Ni-Mo alloys. We report the development of an optimized Embedded-Atom Method (EAM) potential specifically for Ni-Mo alloys, carefully parameterized using empirical lattice constants and formation energies of elemental and face-centered cubic (FCC) Ni-Mo solid solution alloys. The reliability of the EAM potential is corroborated via the evaluation of equations of state, with a particular focus on reproducing structural properties. Utilizing this validated potential, MC/MD simulations were performed to understand the depth-wise variations in the compositions of Ni-Mo alloy nanoparticles and extended surfaces. These simulations reveal a preferential segregation of nickel on surface, and molybdenum in sub-surface layer. Due to this preferential segregation, it is imperative to consider surface segregation while tailoring the surface properties for targeted applications.

Alzheimer's Disease is an incurable cognitive condition that affects thousands of people globally. While some diagnostic methods exist for Alzheimer's Disease, many of these methods cannot detect Alzheimer's in its earlier stages. Recently, researchers have explored the use of Electroencephalogram (EEG) technology for diagnosing Alzheimer's. EEG is a noninvasive method of recording the brain's electrical signals, and EEG data has shown distinct differences between patients with and without Alzheimer's. In the past, Artificial Neural Networks (ANNs) have been used to predict Alzheimer's from EEG data, but these models sometimes produce false positive diagnoses. This study aims to compare losses between ANNs and Kolmogorov-Arnold Networks (KANs) across multiple types of epochs, learning rates, and nodes. The results show that across these different parameters, ANNs are more accurate in predicting Alzheimer's Disease from EEG signals.

Speech emotion recognition (SER), the task of identifying the expression of emotion from spoken content, is challenging due to the difficulty in extracting representations that capture emotional attributes from speech. The scarcity of large labeled datasets further complicates the challenge where large models are prone to over-fitting. In this paper, we propose CARE (Content and Acoustic Representations of Emotions), where we design a dual encoding scheme which emphasizes semantic and acoustic factors of speech. While the semantic encoder is trained with the distillation of utterance-level text representation model, the acoustic encoder is trained to predict low-level frame-wise features of the speech signal. The proposed dual encoding scheme is a base-sized model trained only on unsupervised raw speech. With a simple light-weight classification model trained on the downstream task, we show that the CARE embeddings provide effective emotion recognition on a variety of tasks. We compare the proposal with several other self-supervised models as well as recent large-language model based approaches. In these evaluations, the proposed CARE model is shown to be the best performing model based on average performance across 8 diverse datasets. We also conduct several ablation studies to analyze the importance of various design choices., Comment: 10 pages, 4 figures, 7 tables

Large Language Models (LLMs) have shown versatility in various Natural Language Processing (NLP) tasks, including their potential as effective question-answering systems. However, to provide precise and relevant information in response to specific customer queries in industry settings, LLMs require access to a comprehensive knowledge base to avoid hallucinations. Retrieval Augmented Generation (RAG) emerges as a promising technique to address this challenge. Yet, developing an accurate question-answering framework for real-world applications using RAG entails several challenges: 1) data availability issues, 2) evaluating the quality of generated content, and 3) the costly nature of human evaluation. In this paper, we introduce an end-to-end framework that employs LLMs with RAG capabilities for industry use cases. Given a customer query, the proposed system retrieves relevant knowledge documents and leverages them, along with previous chat history, to generate response suggestions for customer service agents in the contact centers of a major retail company. Through comprehensive automated and human evaluations, we show that this solution outperforms the current BERT-based algorithms in accuracy and relevance. Our findings suggest that RAG-based LLMs can be an excellent support to human customer service representatives by lightening their workload., Comment: Accepted at the 1st Workshop on GenAI and RAG Systems for Enterprise, CIKM'24. 6 pages

The performance of quantum error correcting (QEC) codes are often studied under the assumption of spatio-temporally uniform error rates. On the other hand, experimental implementations almost always produce heterogeneous error rates, in either space or time, as a result of effects such as imperfect fabrication and/or cosmic rays. It is therefore important to understand if and how their presence can affect the performance of QEC in qualitative ways. In this work, we study effects of non-uniform error rates in the representative examples of the 1D repetition code and the 2D toric code, focusing on when they have extended spatio-temporal correlations; these may arise, for instance, from rare events (such as cosmic rays) that temporarily elevate error rates over the entire code patch. These effects can be described in the corresponding statistical mechanics models for decoding, where long-range correlations in the error rates lead to extended rare regions of weaker coupling. For the 1D repetition code where the rare regions are linear, we find two distinct decodable phases: a conventional ordered phase in which logical failure rates decay exponentially with the code distance, and a rare-region dominated Griffiths phase in which failure rates are parametrically larger and decay as a stretched exponential. In particular, the latter phase is present when the error rates in the rare regions are above the bulk threshold. For the 2D toric code where the rare regions are planar, we find no decodable Griffiths phase: rare events which boost error rates above the bulk threshold lead to an asymptotic loss of threshold and failure to decode. Unpacking the failure mechanism implies that techniques for suppressing extended sequences of repeated rare events (which, without intervention, will be statistically present with high probability) will be crucial for QEC with the toric code., Comment: 22 pages, 17 figures

Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text, thus enabling the use of speech as an input to the widely successful large language models (LLMs). Currently, while several speech tokenizers have been proposed, there is ambiguity regarding the properties that are desired from a tokenizer for specific downstream tasks and its overall generalizability. Evaluating the performance of tokenizers across different downstream tasks is a computationally intensive effort that poses challenges for scalability. To circumvent this requirement, we present STAB (Speech Tokenizer Assessment Benchmark), a systematic evaluation framework designed to assess speech tokenizers comprehensively and shed light on their inherent characteristics. This framework provides a deeper understanding of the underlying mechanisms of speech tokenization, thereby offering a valuable resource for expediting the advancement of future tokenizer models and enabling comparative analysis using a standardized benchmark. We evaluate the STAB metrics and correlate this with downstream task performance across a range of speech tasks and tokenizer choices., Comment: 5 pages

We consider codimension-one defects in the theory of $d$ compact scalars on a two-dimensional worldsheet, acting linearly by mixing the scalars and their duals. By requiring that the defects are topological, we find that they correspond to a non-Abelian zero-form symmetry acting on the fields as elements of $\text{O}(d;\mathbb{R}) \times \text{O}(d;\mathbb{R})$, and on momentum and winding charges as elements of $\text{O}(d,d;\mathbb{R})$. When the latter action is rational, we prove that it can be realized by combining gauging of non-anomalous discrete subgroups of the momentum and winding $\text{U}(1)$ symmetries, and elements of the $\text{O}(d,d;\mathbb{Z})$ duality group, such that the couplings of the theory are left invariant. Generically, these defects map local operators into non-genuine operators attached to lines, thus corresponding to a non-invertible symmetry. We confirm our results within a Lagrangian description of the non-invertible topological defects associated to the $\text{O}(d,d;\mathbb{Q})$ action on charges, giving a natural explanation of the rationality conditions. Finally, we apply our findings to toroidal compactifications of bosonic string theory. In the simplest non-trivial case, we discuss the selection rules of these non-invertible symmetries, verifying explicitly that they are satisfied on a worldsheet of higher genus., Comment: 38 pages, 5 figures

In this article, we investigate the in-situ growth of Al$_2$O$_3$ on $\beta$-Ga$_2$O$_3$ using metal-organic chemical vapor deposition (MOCVD) at a high temperature of 800{\deg}C. The Al$_2$O$_3$ is grown within the same reactor as the $\beta$-Ga$_2$O$_3$, employing trimethylaluminum (TMAl) and O$_2$ as precursors without breaking the vacuum. We characterize the shallow and deep-level traps through stressed capacitance-voltage (C-V) and photo-assisted C-V methods. The high-temperature deposited dielectric demonstrates an impressive breakdown field of approximately 10 MV/cm. Furthermore, we evaluate the reliability and lifetime of the dielectrics using time-dependent dielectric breakdown (TDDB) measurements. By modifying the dielectric deposition process to include a high-temperature (800{\deg}C) thin interfacial layer and a low-temperature (600{\deg}C) bulk layer, we report a 10-year lifetime under a stress field of 3.5 MV/cm along a breakdown field of 7.8 MV/cm.

Most of the work on learning action models focus on learning the actions' dynamics from input plans. This allows us to specify the valid plans of a planning task. However, very little work focuses on learning action costs, which in turn allows us to rank the different plans. In this paper we introduce a new problem: that of learning the costs of a set of actions such that a set of input plans are optimal under the resulting planning model. To solve this problem we present $LACFIP^k$, an algorithm to learn action's costs from unlabeled input plans. We provide theoretical and empirical results showing how $LACFIP^k$ can successfully solve this task.

A fundamental question about the nature of quantum materials such as High-T$_c$ systems remain open to date -- it is unclear whether they are (some variety of) Fermi liquids, or (some variety of) non Fermi liquids. A direct avenue to determine their nature is to study the (imaginary part of the) self-energy at low energies. Here we present a novel method to extract this low $\omega$ self-energy from experimentally derived spectral functions. The method seems suited for implementation with high quality angle resolved photoemission data. It is based on a helpful Theorem proposed here, which assures us that the method has minimal (or vanishing) error at the lowest energies. We provide numerical examples showing that a few popular model systems yield distinguishably different low energy self-energies., Comment: 25 pages, 12 Figures

We introduce a new version of symplectic annular Khovanov homology and establish spectral sequences from (i) the symplectic annular Khovanov homology of a knot to the link Floer homology of the lift of the annular axis in the double branched cover; (ii) the symplectic Khovanov homology of a two-periodic knot to the symplectic annular Khovanov homology of its quotient; and (iii) the symplectic Khovanov homology of a strongly invertible knot to the cone of the axis-moving map between the symplectic annular Khovanov homology of the two resolutions of its quotient., Comment: 63 pages; 28 figures. Comments welcome!

In a Fermi system near or at half-filling, a specific superconducting pairing channel, if not explicitly included in the Hamiltonian, can be boosted by suppressing a competing pairing channel; this is exemplified by the enhancement of extended $s$-wave correlations upon suppressing $s$-wave Cooper pairing. This phenomenon, originally found by the use of generalized uncertainty relations is referred to as \emph{order by projection}. The case of zero on-site Coulomb interaction in the thermodynamic limit, confirms this mechanism through the analytical solution. In this study, we go further and systematically investigate this mechanism for a strongly correlated fermionic Hubbard model, now with finite on-site interaction, on a square lattice with an extended set of hopping parameters. We explore the behaviors of different pairing channels when one of them is suppressed, utilizing density matrix renormalization group calculations. Our findings provide numerical evidence supporting the existence of \emph{order by projection} in the strongly correlated system we studied. We also investigate the effect of the strength of Hubbard $U$, next-nearest neighbor $t'$, hole-doping, as well as finite-size scaling approaching the thermodynamic limit.

Most of the sophisticated AI models utilize huge amounts of annotated data and heavy training to achieve high-end performance. However, there are certain challenges that hinder the deployment of AI models "in-the-wild" scenarios, i.e., inefficient use of unlabeled data, lack of incorporation of human expertise, and lack of interpretation of the results. To mitigate these challenges, we propose a novel Explainable Active Learning (XAL) model, XAL-based semantic segmentation model "SegXAL", that can (i) effectively utilize the unlabeled data, (ii) facilitate the "Human-in-the-loop" paradigm, and (iii) augment the model decisions in an interpretable way. In particular, we investigate the application of the SegXAL model for semantic segmentation in driving scene scenarios. The SegXAL model proposes the image regions that require labeling assistance from Oracle by dint of explainable AI (XAI) and uncertainty measures in a weakly-supervised manner. Specifically, we propose a novel Proximity-aware Explainable-AI (PAE) module and Entropy-based Uncertainty (EBU) module to get an Explainable Error Mask, which enables the machine teachers/human experts to provide intuitive reasoning behind the results and to solicit feedback to the AI system via an active learning strategy. Such a mechanism bridges the semantic gap between man and machine through collaborative intelligence, where humans and AI actively enhance each other's complementary strengths. A novel high-confidence sample selection technique based on the DICE similarity coefficient is also presented within the SegXAL framework. Extensive quantitative and qualitative analyses are carried out in the benchmarking Cityscape dataset. Results show the outperformance of our proposed SegXAL against other state-of-the-art models., Comment: 17 pages, 7 figures. To appear in the proceedings of the 27th International Conference on Pattern Recognition (ICPR), 01-05 December, 2024, Kolkata, India

Since the recent discovery of polar topologies, a recurrent question has been in the way to remotely tune them. Many efforts have focused on the pumping of polar optical phonons from optical methods but with limited success, as only switching between specific phases has been achieved so far. Additionally, the correlation between optical pulse characteristics and the resulting phase remains poorly understood. Here, we propose an alternative approach and demonstrate the deterministic and dynamical tailoring of polar topologies using instead acoustic phonon pumping. Our second-principles simulations reveal that by pumping specific longitudinal and transverse acoustic phonons, various topological textures can be induced in materials like BaTiO$_\mathrm{3}$ or PbTiO$_\mathrm{3}$. This method leverages the strong coupling between polarization and strain in these materials, enabling predictable and dynamical control of polar patterns. Our findings open up an alternative possibility for the manipulation of polar textures, inaugurating a promising research direction.

Using "soft" targets to improve model performance has been shown to be effective in classification settings, but the usage of soft targets for regression is a much less studied topic in machine learning. The existing literature on the usage of soft targets for regression fails to properly assess the method's limitations, and empirical evaluation is quite limited. In this work, we assess the strengths and drawbacks of existing methods when applied to molecular property regression tasks. Our assessment outlines key biases present in existing methods and proposes methods to address them, evaluated through careful ablation studies. We leverage these insights to propose Distributional Mixture of Experts (DMoE): A model-independent, and data-independent method for regression which trains a model to predict probability distributions of its targets. Our proposed loss function combines the cross entropy between predicted and target distributions and the L1 distance between their expected values to produce a loss function that is robust to the outlined biases. We evaluate the performance of DMoE on different molecular property prediction datasets -- Open Catalyst (OC20), MD17, and QM9 -- across different backbone model architectures -- SchNet, GemNet, and Graphormer. Our results demonstrate that the proposed method is a promising alternative to classical regression for molecular property prediction tasks, showing improvements over baselines on all datasets and architectures.

We report on metalorganic chemical vapor deposition (MOCVD) growth of controllably Si-doped 4.5 $\mu$m thick $\beta$-Ga$_2$O$_3$ films with electron concentrations in the 10$^{15}$ cm$^{-3}$ range and record-high room temperature Hall electron mobilities of up to 200 cm$^2$/V.s, reaching the predicted theoretical maximum room temperature mobility value for $\beta$-Ga$_2$O$_3$. Growth of the homoepitaxial films was performed on Fe-doped (010) $\beta$-Ga$_2$O$_3$ substrates at a growth rate of 1.9 $\mu$m/hr using TEGa as the Gallium precursor. To probe the background electron concentration, an unintentionally doped film was grown with a Hall concentration of 3.43 x 10$^{15}$ cm$^{-3}$ and Hall mobility of 196 cm$^2$/V.s. Growth of intentionally Si-Doped films was accomplished by fixing all growth conditions and varying only the silane flow, with controllable Hall electron concentrations ranging from 4.38 x 10$^{15}$ cm$^{-3}$ to 8.30 x 10$^{15}$ cm$^{-3}$ and exceptional Hall mobilities ranging from 194 - 200 cm$^2$/V.s demonstrated. C-V measurements showed a flat charge profile with the N$_D^+$ - N$_A^-$ values correlating well with the Hall-measured electron concentration in the films. SIMS measurements showed the silicon atomic concentration matched the Hall electron concentration with Carbon and Hydrogen below detection limit in the films. The Hall, C-V, and SIMS data indicate the growth of high-quality 4.5 $\mu$m thick $\beta$-Ga$_2$O$_3$ films and controllable doping into the mid 10$^{15}$ cm$^{-3}$ range. These results demonstrate MOCVD growth of electronics grade record-high mobility, low carrier density, and thick $\beta$-Ga$_2$O$_3$ drift layers for next generation vertical $\beta$-Ga$_2$O$_3$ power devices., Comment: 16 Pages, 10 Figures, 2 Tables

We present a conceptual design for a fiber positioning system for multi-object high-resolution spectroscopy, designed to be compatible with the upcoming large telescopes with a wide field of view. The design incorporates multiple Atmospheric Dispersion Correctors (ADCs) and tip-tilt mirrors that receive non-telecentric input from individual targets and direct it to the ADCs. Here, we introduce a mechanical design for the fiber positioner that accommodates the optics and operates in a curved focal plane with a Radius of Curvature (R) of 3m. This mechanical design provides four degrees of freedom to access the focal volume, enhancing targeting efficiency. The proposed design and an efficient target allocation algorithm ensure a targeting efficiency of approximately 80-100% for a primary observation session. We also present a methodology for target assignment, positioning, and quantification based on sequential and Monte Carlo (MC) algorithms. This method has been tested on realistic fields with varying target densities to validate its performance.

Objective: This work explores use of a few-shot transfer learning method to train and implement a convolutional spiking neural network (CSNN) on a BrainChip Akida AKD1000 neuromorphic system-on-chip for developing individual-level, instead of traditionally used group-level, models using electroencephalographic data. Main Results: Efficacy of the above methodology to develop individual-specific braking intention predictive models by rapidly adapting the group-level model in as few as three training epochs while achieving at least 90% accuracy, true positive rate and true negative rate is presented. Further, results show the energy-efficiency of the neuromorphic hardware through a power reduction of over 97% with only a $1.3* increase in latency when using the Akida AKD1000 processor for network inference compared to an Intel Xeon central processing unit. Similar results were obtained in a subsequent ablation study using a subset of five out of 19 channels., Comment: Journal of NeuroEngineering Submission

In this paper, we consider a K-user interference channel where interference among the users is neither too strong nor too weak, a scenario that is relatively underexplored in the literature. We propose a novel deep learning-based approach to design the encoder and decoder functions that aim to maximize the sumrate of the interference channel for discrete constellations. We first consider the MaxSINR algorithm, a state-of-the-art linear scheme for Gaussian inputs, as the baseline and then propose a modified version of the algorithm for discrete inputs. We then propose a neural network-based approach that learns a constellation mapping with the objective of maximizing the sumrate. We provide numerical results to show that the constellations learned by the neural network-based approach provide enhanced alignments, not just in beamforming directions but also in terms of the effective constellation at the receiver, thereby leading to improved sum-rate performance.

In recent years, Large Language Models (LLM) have demonstrated impressive capabilities in the field of natural language processing (NLP). This paper explores the application of LLMs in negotiation transcript analysis by the Vanderbilt AI Negotiation Lab. Starting in September 2022, we applied multiple strategies using LLMs from zero shot learning to fine tuning models to in-context learning). The final strategy we developed is explained, along with how to access and use the model. This study provides a sense of both the opportunities and roadblocks for the implementation of LLMs in real life applications and offers a model for how LLMs can be applied to coding in other fields.

In order to develop robots that can effectively serve as versatile and capable home assistants, it is crucial for them to reliably perceive and interact with a wide variety of objects across diverse environments. To this end, we proposed Open Vocabulary Mobile Manipulation as a key benchmark task for robotics: finding any object in a novel environment and placing it on any receptacle surface within that environment. We organized a NeurIPS 2023 competition featuring both simulation and real-world components to evaluate solutions to this task. Our baselines on the most challenging version of this task, using real perception in simulation, achieved only an 0.8% success rate; by the end of the competition, the best participants achieved an 10.8\% success rate, a 13x improvement. We observed that the most successful teams employed a variety of methods, yet two common threads emerged among the best solutions: enhancing error detection and recovery, and improving the integration of perception with decision-making processes. In this paper, we detail the results and methodologies used, both in simulation and real-world settings. We discuss the lessons learned and their implications for future research. Additionally, we compare performance in real and simulated environments, emphasizing the necessity for robust generalization to novel settings.

We introduce a novel approach for safe control design based on the density function. A control density function (CDF) is introduced to synthesize a safe controller for a nonlinear dynamic system. The CDF can be viewed as a dual to the control barrier function (CBF), a popular approach used for safe control design. While the safety certificate using the barrier function is based on the notion of invariance, the dual certificate involving the density function has a physical interpretation of occupancy. This occupancy-based physical interpretation is instrumental in providing an analytical construction of density function used for safe control synthesis. The safe control design problem is formulated using the density function as a quadratic programming (QP) problem. In contrast to the QP proposed for control synthesis using CBF, the proposed CDF-based QP can combine both the safety and convergence conditions to target state into single constraints. Further, we consider robustness against uncertainty in system dynamics and the initial condition and provide theoretical results for robust navigation using the CDF. Finally, we present simulation results for safe navigation with single integrator and double-gyre fluid flow-field examples, followed by robust navigation using the bicycle model and autonomous lane-keeping examples.

Speech accents present a serious challenge to the performance of state-of-the-art end-to-end Automatic Speech Recognition (ASR) systems. Even with self-supervised learning and pre-training of ASR models, accent invariance is seldom achieved. In this work, we propose an accent-aware adaptation technique for self-supervised learning that introduces a trainable set of accent-specific codebooks to the self-supervised architecture. These learnable codebooks enable the model to capture accent specific information during pre-training, that is further refined during ASR finetuning. On the Mozilla Common Voice dataset, our proposed approach outperforms all other accent-adaptation approaches on both seen and unseen English accents, with up to 9% relative reduction in word error rate (WER)., Comment: Accepted to INTERSPEECH 2024

The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech recognition and related tasks, this has largely ignored factors of speech that are encoded at coarser level, like characteristics of the speaker or channel that remain consistent through-out a speech utterance. In this work, we propose a framework for Learning Disentangled Self Supervised (termed as Learn2Diss) representations of speech, which consists of frame-level and an utterance-level encoder modules. The two encoders are initially learned independently, where the frame-level model is largely inspired by existing self supervision techniques, thereby learning pseudo-phonemic representations, while the utterance-level encoder is inspired by constrastive learning of pooled embeddings, thereby learning pseudo-speaker representations. The joint learning of these two modules consists of disentangling the two encoders using a mutual information based criterion. With several downstream evaluation experiments, we show that the proposed Learn2Diss achieves state-of-the-art results on a variety of tasks, with the frame-level encoder representations improving semantic tasks, while the utterance-level representations improve non-semantic tasks.