Search

A microscopic derivation of the Bekenstein-Hawking entropy for the Schwarzschild black hole was presented earlier by using a non-trivial phase space. It was argued that the Schwarzschild black hole behaves like a 1D quantum mechanical system. In this paper, we show that if we assume the phase space to obey the holographic principle and take the microscopic particles inside the quantum gravitational system to be ideal bosonic gas, we can derive the Bekenstein-Hawking entropy. The assumption of the phase space to follow the holographic principle such that the Schwarzschild black hole behaves as a 2D system is very much in the spirit of our understanding of black holes than their behavior as a 1D system. However, the argument suggests that the black hole be treated as a system with the equation of state $P=\rho$., Comment: 6 pages, published in MPLA

With recent rapid growth in online shopping, AI-powered Engagement Surfaces (ES) have become ubiquitous across retail services. These engagement surfaces perform an increasing range of functions, including recommending new products for purchase, reminding customers of their orders and providing delivery notifications. Understanding the causal effect of engagement surfaces on value driven for customers and businesses remains an open scientific question. In this paper, we develop a dynamic causal model at scale to disentangle value attributable to an ES, and to assess its effectiveness. We demonstrate the application of this model to inform business decision-making by understanding returns on investment in the ES, and identifying product lines and features where the ES adds the most value., Comment: 10 pages, 5 figures. Accepted at Applied Data Science track of KDD 2024, Barcelona, Spain

Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge. Traditional supervised pre-training on static datasets falls short in enabling autonomous agent capabilities needed to perform complex decision-making in dynamic settings like web navigation. Previous attempts to bridge this ga-through supervised fine-tuning on curated expert demonstrations-often suffer from compounding errors and limited exploration data, resulting in sub-optimal policy outcomes. To overcome these challenges, we propose a framework that combines guided Monte Carlo Tree Search (MCTS) search with a self-critique mechanism and iterative fine-tuning on agent interactions using an off-policy variant of the Direct Preference Optimization (DPO) algorithm. Our method allows LLM agents to learn effectively from both successful and unsuccessful trajectories, thereby improving their generalization in complex, multi-step reasoning tasks. We validate our approach in the WebShop environment-a simulated e-commerce platform where it consistently outperforms behavior cloning and reinforced fine-tuning baseline, and beats average human performance when equipped with the capability to do online search. In real-world booking scenarios, our methodology boosts Llama-3 70B model's zero-shot performance from 18.6% to 81.7% success rate (a 340% relative increase) after a single day of data collection and further to 95.4% with online search. We believe this represents a substantial leap forward in the capabilities of autonomous agents, paving the way for more sophisticated and reliable decision-making in real-world settings.

Land Use Land Cover (LULC) mapping is a vital tool for urban and resource planning, playing a key role in the development of innovative and sustainable cities. This study introduces a semi-supervised segmentation model for LULC prediction using high-resolution satellite images with a vast diversity of data distributions in different areas of India. Our approach ensures a robust generalization across different types of buildings, roads, trees, and water bodies within these distinct areas. We propose a modified Cross Pseudo Supervision framework to train image segmentation models on sparsely labelled data. The proposed framework addresses the limitations of the famous 'Cross Pseudo Supervision' technique for semi-supervised learning, specifically tackling the challenges of training segmentation models on noisy satellite image data with sparse and inaccurate labels. This comprehensive approach significantly enhances the accuracy and utility of LULC mapping, providing valuable insights for urban and resource planning applications.

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Time series forecasting in the air cargo industry presents unique challenges due to volatile market dynamics and the significant impact of accurate forecasts on generated revenue. This paper explores a comprehensive approach to demand forecasting at the origin-destination (O\&D) level, focusing on the development and implementation of machine learning models in decision-making for the air cargo industry. We leverage a mixture of experts framework, combining statistical and advanced deep learning models to provide reliable forecasts for cargo demand over a six-month horizon. The results demonstrate that our approach outperforms industry benchmarks, offering actionable insights for cargo capacity allocation and strategic decision-making in the air cargo industry. While this work is applied in the airline industry, the methodology is broadly applicable to any field where forecast-based decision-making in a volatile environment is crucial., Comment: The 10th Mining and Learning from Time Series Workshop: From Classical Methods to LLMs. SIGKDD, Barcelona, Spain, 6 page

A central piece in enabling intelligent agentic behavior in foundation models is to make them capable of introspecting upon their behavior, reasoning, and correcting their mistakes as more computation or interaction is available. Even the strongest proprietary large language models (LLMs) do not quite exhibit the ability of continually improving their responses sequentially, even in scenarios where they are explicitly told that they are making a mistake. In this paper, we develop RISE: Recursive IntroSpEction, an approach for fine-tuning LLMs to introduce this capability, despite prior work hypothesizing that this capability may not be possible to attain. Our approach prescribes an iterative fine-tuning procedure, which attempts to teach the model how to alter its response after having executed previously unsuccessful attempts to solve a hard test-time problem, with optionally additional environment feedback. RISE poses fine-tuning for a single-turn prompt as solving a multi-turn Markov decision process (MDP), where the initial state is the prompt. Inspired by principles in online imitation learning and reinforcement learning, we propose strategies for multi-turn data collection and training so as to imbue an LLM with the capability to recursively detect and correct its previous mistakes in subsequent iterations. Our experiments show that RISE enables Llama2, Llama3, and Mistral models to improve themselves with more turns on math reasoning tasks, outperforming several single-turn strategies given an equal amount of inference-time computation. We also find that RISE scales well, often attaining larger benefits with more capable models. Our analysis shows that RISE makes meaningful improvements to responses to arrive at the correct solution for challenging prompts, without disrupting one-turn abilities as a result of expressing more complex distributions.

Recently large vision-language models have shown potential when interpreting complex images and generating natural language descriptions using advanced reasoning. Medicine's inherently multimodal nature incorporating scans and text-based medical histories to write reports makes it conducive to benefit from these leaps in AI capabilities. We evaluate the publicly available, state of the art, foundational vision-language models for chest X-ray interpretation across several datasets and benchmarks. We use linear probes to evaluate the performance of various components including CheXagent's vision transformer and Q-former, which outperform the industry-standard Torch X-ray Vision models across many different datasets showing robust generalisation capabilities. Importantly, we find that vision-language models often hallucinate with confident language, which slows down clinical interpretation. Based on these findings, we develop an agent-based vision-language approach for report generation using CheXagent's linear probes and BioViL-T's phrase grounding tools to generate uncertainty-aware radiology reports with pathologies localised and described based on their likelihood. We thoroughly evaluate our vision-language agents using NLP metrics, chest X-ray benchmarks and clinical evaluations by developing an evaluation platform to perform a user study with respiratory specialists. Our results show considerable improvements in accuracy, interpretability and safety of the AI-generated reports. We stress the importance of analysing results for normal and abnormal scans separately. Finally, we emphasise the need for larger paired (scan and report) datasets alongside data augmentation to tackle overfitting seen in these large vision-language models., Comment: Supervised by Professor Ben Glocker

Large-scale LiDAR mappings and localization leverage place recognition techniques to mitigate odometry drifts, ensuring accurate mapping. These techniques utilize scene representations from LiDAR point clouds to identify previously visited sites within a database. Local descriptors, assigned to each point within a point cloud, are aggregated to form a scene representation for the point cloud. These descriptors are also used to re-rank the retrieved point clouds based on geometric fitness scores. We propose SALSA, a novel, lightweight, and efficient framework for LiDAR place recognition. It consists of a Sphereformer backbone that uses radial window attention to enable information aggregation for sparse distant points, an adaptive self-attention layer to pool local descriptors into tokens, and a multi-layer-perceptron Mixer layer for aggregating the tokens to generate a scene descriptor. The proposed framework outperforms existing methods on various LiDAR place recognition datasets in terms of both retrieval and metric localization while operating in real-time.

This study introduces the Misclassification Likelihood Matrix (MLM) as a novel tool for quantifying the reliability of neural network predictions under distribution shifts. The MLM is obtained by leveraging softmax outputs and clustering techniques to measure the distances between the predictions of a trained neural network and class centroids. By analyzing these distances, the MLM provides a comprehensive view of the model's misclassification tendencies, enabling decision-makers to identify the most common and critical sources of errors. The MLM allows for the prioritization of model improvements and the establishment of decision thresholds based on acceptable risk levels. The approach is evaluated on the MNIST dataset using a Convolutional Neural Network (CNN) and a perturbed version of the dataset to simulate distribution shifts. The results demonstrate the effectiveness of the MLM in assessing the reliability of predictions and highlight its potential in enhancing the interpretability and risk mitigation capabilities of neural networks. The implications of this work extend beyond image classification, with ongoing applications in autonomous systems, such as self-driving cars, to improve the safety and reliability of decision-making in complex, real-world environments., Comment: 9 pages, 7 figures, 1 table

Understanding how light modifies long-range order is key to improve our ability to control material functionality on an ultrafast timescale. Transient spatial heterogeneity has been proposed in many materials, but isolating the dynamics of different regions experimentally has been challenging. Here we address this issue and measure the dynamics of orbital order melting in the layered manganite, La0.5Sr1.5MnO4, and isolate the surface dynamics from the bulk for the first time. Bulk measurements show orbital order is rapidly suppressed, but the correlation length surprisingly increases. However, the surface dynamics, show a stronger suppression and a significant decrease in correlation length. By isolating the surface changes, we find that light preferentially melts a less ordered surface and the loss of long-range order is likely driven by the formation of local and disordered polarons. Melting the disordered surface effectively increases the average correlation of the bulk probed volume, resolving the contradictory response. These results show that surface scattering methods are necessary to understand both surface and bulk dynamics in heterogeneous materials., Comment: 22 pages, 8 figures

This paper presents price prediction models using Machine Learning algorithms augmented with Superforecasters predictions, aimed at enhancing investment decisions. Five Machine Learning models are built, including Bidirectional LSTM, ARIMA, a combination of CNN and LSTM, GRU, and a model built using LSTM and GRU algorithms. The models are evaluated using the Mean Absolute Error to determine their predictive accuracy. Additionally, the paper suggests incorporating human intelligence by identifying Superforecasters and tracking their predictions to anticipate unpredictable shifts or changes in stock prices . The predictions made by these users can further enhance the accuracy of stock price predictions when combined with Machine Learning and Natural Language Processing techniques. Predicting the price of any commodity can be a significant task but predicting the price of a stock in the stock market deals with much more uncertainty. Recognising the limited knowledge and exposure to stocks among certain investors, this paper proposes price prediction models using Machine Learning algorithms. In this work, five Machine learning models are built using Bidirectional LSTM, ARIMA, a combination of CNN and LSTM, GRU and the last one is built using LSTM and GRU algorithms. Later these models are assessed using MAE scores to find which model is predicting with the highest accuracy. In addition to this, this paper also suggests the use of human intelligence to closely predict the shift in price patterns in the stock market The main goal is to identify Superforecasters and track their predictions to anticipate unpredictable shifts or changes in stock prices. By leveraging the combined power of Machine Learning and the Human Intelligence, predictive accuracy can be significantly increased., Comment: Keywords: Machine Learning, Artificial Intelligence, LSTM, GRU, ARMA, CNN, NLP, ANN, SVM, BSE, NIFTY, MAE, MSE, BiLSTM . Published in SSRN Journal

Automated software engineering has been greatly empowered by the recent advances in Large Language Models (LLMs) for programming. While current benchmarks have shown that LLMs can perform various software engineering tasks like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks. Solving challenging and practical programming tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions. Fulfilling both of these characteristics can pose a great challenge for LLMs. To assess how well LLMs can solve challenging and practical programming tasks, we introduce Bench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained programming tasks. To evaluate LLMs rigorously, each programming task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of Bench, Benchi, that automatically transforms the original docstrings into short instructions only with essential information. Our extensive evaluation of 60 LLMs shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. The results underscore the need for further advancements in this area., Comment: 44 pages, 14 figures, 7 tables, built with love by the BigCode community :)

The transition to online examinations and assignments raises significant concerns about academic integrity. Traditional plagiarism detection systems often struggle to identify instances of intelligent cheating, particularly when students utilize advanced generative AI tools to craft their responses. This study proposes a keystroke dynamics-based method to differentiate between bona fide and assisted writing within academic contexts. To facilitate this, a dataset was developed to capture the keystroke patterns of individuals engaged in writing tasks, both with and without the assistance of generative AI. The detector, trained using a modified TypeNet architecture, achieved accuracies ranging from 74.98% to 85.72% in condition-specific scenarios and from 52.24% to 80.54% in condition-agnostic scenarios. The findings highlight significant differences in keystroke dynamics between genuine and assisted writing. The outcomes of this study enhance our understanding of how users interact with generative AI and have implications for improving the reliability of digital educational platforms., Comment: Accepted for publication at The IEEE International Joint Conference on Biometrics (IJCB2024), contains 9 pages, 3 figures, 3 tables

Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question for math reasoning via an empirical study, followed by building a conceptual understanding of our observations. First, we find that while the typical approach of finetuning a model on synthetic correct or positive problem-solution pairs generated by capable models offers modest performance gains, sampling more correct solutions from the finetuned learner itself followed by subsequent fine-tuning on this self-generated data $\textbf{doubles}$ the efficiency of the same synthetic problems. At the same time, training on model-generated positives can amplify various spurious correlations, resulting in flat or even inverse scaling trends as the amount of data increases. Surprisingly, we find that several of these issues can be addressed if we also utilize negative responses, i.e., model-generated responses that are deemed incorrect by a final answer verifier. Crucially, these negatives must be constructed such that the training can appropriately recover the utility or advantage of each intermediate step in the negative response. With this per-step scheme, we are able to attain consistent gains over only positive data, attaining performance similar to amplifying the amount of synthetic data by $\mathbf{8 \times}$. We show that training on per-step negatives can help to unlearn spurious correlations in the positive data, and is equivalent to advantage-weighted reinforcement learning (RL), implying that it inherits robustness benefits of RL over imitating positive data alone.

There is a growing body of work on learning from human feedback to align various aspects of machine learning systems with human values and preferences. We consider the setting of fairness in content moderation, in which human feedback is used to determine how two comments -- referencing different sensitive attribute groups -- should be treated in comparison to one another. With a novel dataset collected from Prolific and MTurk, we find significant gaps in fairness preferences depending on the race, age, political stance, educational level, and LGBTQ+ identity of annotators. We also demonstrate that demographics mentioned in text have a strong influence on how users perceive individual fairness in moderation. Further, we find that differences also exist in downstream classifiers trained to predict human preferences. Finally, we observe that an ensemble, giving equal weight to classifiers trained on annotations from different demographics, performs better for different demographic intersections; compared to a single classifier that gives equal weight to each annotation., Comment: To appear in the Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

If we look at from a quantum perspective, the most natural way in which the universe can be created is in entangled pairs whose time flow is oppositely related. This suggests the idea of the creation of a universe-antiuniverse pair. Assuming the validity of this hypothesis, in this paper, we show that the universe expands in an accelerated manner. The same reasoning holds for the anti-universe as well. This idea does not require any form of dark energy as used in the standard cosmological model of ${\Lambda}$CDM or in the modified theories of gravity., Comment: published version, comments are welcome, covered in phys.org: https://phys.org/news/2024-06-partner-anti-universe-expansion-dark.html

Variational approaches to disparity estimation typically use a linearised brightness constancy constraint, which only applies in smooth regions and over small distances. Accordingly, current variational approaches rely on a schedule to progressively include image data. This paper proposes the use of Gradient Consistency information to assess the validity of the linearisation; this information is used to determine the weights applied to the data term as part of an analytically inspired Gradient Consistency Model. The Gradient Consistency Model penalises the data term for view pairs that have a mismatch between the spatial gradients in the source view and the spatial gradients in the target view. Instead of relying on a tuned or learned schedule, the Gradient Consistency Model is self-scheduling, since the weights evolve as the algorithm progresses. We show that the Gradient Consistency Model outperforms standard coarse-to-fine schemes and the recently proposed progressive inclusion of views approach in both rate of convergence and accuracy., Comment: 11 pages, 11 figures. Submitted to Transactions on Image Processing

Detection of out-of-distribution (OOD) samples is crucial for safe real-world deployment of machine learning models. Recent advances in vision language foundation models have made them capable of detecting OOD samples without requiring in-distribution (ID) images. However, these zero-shot methods often underperform as they do not adequately consider ID class likelihoods in their detection confidence scoring. Hence, we introduce CLIPScope, a zero-shot OOD detection approach that normalizes the confidence score of a sample by class likelihoods, akin to a Bayesian posterior update. Furthermore, CLIPScope incorporates a novel strategy to mine OOD classes from a large lexical database. It selects class labels that are farthest and nearest to ID classes in terms of CLIP embedding distance to maximize coverage of OOD samples. We conduct extensive ablation studies and empirical evaluations, demonstrating state of the art performance of CLIPScope across various OOD detection benchmarks.

The COVID-19 Forecast Hub, a repository of COVID-19 forecasts from over 50 independent research groups, is used by the Centers for Disease Control and Prevention (CDC) for their official COVID-19 communications. As such, the Forecast Hub is a critical centralized resource to promote transparent decision making. Nevertheless, by focusing exclusively on prediction accuracy, the Forecast Hub fails to evaluate whether the proposed models have similar performance across social determinants that have been known to play a role in the COVID-19 pandemic including race, ethnicity and urbanization level. In this paper, we carry out a comprehensive fairness analysis of the Forecast Hub model predictions and we show statistically significant diverse predictive performance across social determinants, with minority racial and ethnic groups as well as less urbanized areas often associated with higher prediction errors. We hope this work will encourage COVID-19 modelers and the CDC to report fairness metrics together with accuracy, and to reflect on the potential harms of the models on specific social groups and contexts.

Early in the pandemic, counties and states implemented a variety of non-pharmacological interventions (NPIs) focused on mobility, such as national lockdowns or work-from-home strategies, as it became clear that restricting movement was essential to containing the epidemic. Due to these restrictions, businesses were severely affected and in particular, small, urban restaurant businesses. In addition to that, COVID-19 has also amplified many of the socioeconomic disparities and systemic racial inequities that exist in our society. The overarching objective of this study was to examine the changes in small urban restaurant visitation patterns following the COVID-19 pandemic and associated mobility restrictions, as well as to uncover potential disparities across different racial/ethnic groups in order to understand inequities in the impact and recovery. Specifically, the two key objectives were: 1) to analyze the overall changes in restaurant visitation patterns in US metropolitan areas during the pandemic compared to a pre-pandemic baseline, and 2) to investigate differences in visitation pattern changes across Census Block Groups with majority Asian, Black, Hispanic, White, and American Indian populations, identifying any disproportionate effects. Using aggregated geolocated cell phone data from SafeGraph, we document the overall changes in small urban restaurant businesses' visitation patterns with respect to racial composition at a granularity of Census Block Groups. Our results show clear indications of reduced visitation patterns after the pandemic, with slow recoveries. Via visualizations and statistical analyses, we show that reductions in visitation patterns were the highest for small urban restaurant businesses in majority Asian neighborhoods.

One of the central difficulties of addressing the COVID-19 pandemic has been accurately measuring and predicting the spread of infections. In particular, official COVID-19 case counts in the United States are under counts of actual caseloads due to the absence of universal testing policies. Researchers have proposed a variety of methods for recovering true caseloads, often through the estimation of statistical models on more reliable measures, such as death and hospitalization counts, positivity rates, and demographics. However, given the disproportionate impact of COVID-19 on marginalized racial, ethnic, and socioeconomic groups, it is important to consider potential unintended effects of case correction methods on these groups. Thus, we investigate two of these correction methods for their impact on a downstream COVID-19 case prediction task. For that purpose, we tailor an auditing approach and evaluation protocol to analyze the fairness of the COVID-19 prediction task by measuring the difference in model performance between majority-White counties and majority-minority counties. We find that one of the correction methods improves fairness, decreasing differences in performance between majority-White and majority-minority counties, while the other method increases differences, introducing bias. While these results are mixed, it is evident that correction methods have the potential to exacerbate existing biases in COVID-19 case data and in downstream prediction tasks. Researchers planning to develop or use case correction methods must be careful to consider negative effects on marginalized groups.

COVID-19 forecasting models have been used to inform decision making around resource allocation and intervention decisions e.g., hospital beds or stay-at-home orders. State of the art deep learning models often use multimodal data such as mobility or socio-demographic data to enhance COVID-19 case prediction models. Nevertheless, related work has revealed under-reporting bias in COVID-19 cases as well as sampling bias in mobility data for certain minority racial and ethnic groups, which could in turn affect the fairness of the COVID-19 predictions along race labels. In this paper, we show that state of the art deep learning models output mean prediction errors that are significantly different across racial and ethnic groups; and which could, in turn, support unfair policy decisions. We also propose a novel de-biasing method, DemOpts, to increase the fairness of deep learning based forecasting models trained on potentially biased datasets. Our results show that DemOpts can achieve better error parity that other state of the art de-biasing approaches, thus effectively reducing the differences in the mean error distributions across more racial and ethnic groups.

Human mobility data has been extensively used in covid-19 case prediction models. Nevertheless, related work has questioned whether mobility data really helps that much. We present a systematic analysis across mobility datasets and prediction lookaheads and reveal that adding mobility data to predictive models improves model performance only for about two months at the onset of the testing period, and that performance improvements -- measured as predicted vs. actual correlation improvement over non-mobility baselines -- are at most 0.3., Comment: Presented as a poster in ACM COMPASS 2023

Quantum Federated Learning (QFL) is an emerging concept that aims to unfold federated learning (FL) over quantum networks, enabling collaborative quantum model training along with local data privacy. We explore the challenges of deploying QFL on cloud platforms, emphasizing quantum intricacies and platform limitations. The proposed data-encoding-driven QFL, with a proof of concept (GitHub Open Source) using genomic data sets on quantum simulators, shows promising results., Comment: SIGCOMM 2024, Quantum Computing, Federated Learning, Qiskit

In this letter, we show that in a particular braneworld scenario with variable brane tension, we obtain matter acting as dark energy while the gravitational constant $G$ promoted to a scalar field on the brane plays the role of matter (both in the sense they have an 'effective' Equation of State equivalent to that of dark energy and matter respectively). This result is interpreted from the Friedmann equation obtained from our model that exactly matches the standard Friedmann equation of General Relativity with a cosmological constant $\Lambda$ in terms of the aforementioned quantities. The universe is assumed to consist of only matter and dark energy in this model which is a good approximation for our universe.

In this letter, we show that the Semiclassical Einstein's Field Equation can be recovered using the generalized entropy $S_{gen}$. This approach is reminiscent of non-equilibrium thermodynamics. Furthermore, contrary to the entanglement equilibrium approach of deriving the semiclassical Einstein's equation, this approach does not require any such assumptions and still recovers its correct form. Therefore, in a sense, we also show the validity of the semiclassical approximation, a crucial approach for establishing a number of important ideas such as the Hawking effect.

In this paper, we study the relativistic correction to Bekenstein-Hawking entropy in the canonical ensemble and isothermal-isobaric ensemble and apply it to the cases of non-rotating BTZ and AdS-Schwarzschild black holes. This is realized by generalizing the equations obtained using Boltzmann-Gibbs(BG) statistics with its relativistic generalization, Kaniadakis statistics, or $\kappa$-statistics. The relativistic corrections are found to be logarithmic in nature and it is observed that their effect becomes appreciable in the high-temperature limit suggesting that the entropy corrections must include these relativistically corrected terms while taking the aforementioned limit. The non-relativistic corrections are recovered in the $\kappa\rightarrow 0$ limit.

Citation text plays a pivotal role in elucidating the connection between scientific documents, demanding an in-depth comprehension of the cited paper. Constructing citations is often time-consuming, requiring researchers to delve into extensive literature and grapple with articulating relevant content. To address this challenge, the field of citation text generation (CTG) has emerged. However, while earlier methods have primarily centered on creating single-sentence citations, practical scenarios frequently necessitate citing multiple papers within a single paragraph. To bridge this gap, we propose a method that leverages Large Language Models (LLMs) to generate multi-citation sentences. Our approach involves a single source paper and a collection of target papers, culminating in a coherent paragraph containing multi-sentence citation text. Furthermore, we introduce a curated dataset named MCG-S2ORC, composed of English-language academic research papers in Computer Science, showcasing multiple citation instances. In our experiments, we evaluate three LLMs LLaMA, Alpaca, and Vicuna to ascertain the most effective model for this endeavor. Additionally, we exhibit enhanced performance by integrating knowledge graphs from target papers into the prompts for generating citation text. This research underscores the potential of harnessing LLMs for citation generation, opening a compelling avenue for exploring the intricate connections between scientific documents., Comment: 14 pages, 7 figures, 11th International Conference, BDA 2023, Delhi, India

Recent advancements in LLMs have shown their significant potential in tasks like text summarization and generation. Yet, they often encounter difficulty while solving complex physics problems that require arithmetic calculation and a good understanding of concepts. Moreover, many physics problems include images that contain important details required to understand the problem's context. We propose an LMM-based chatbot to answer multimodal physics MCQs. For domain adaptation, we utilize the MM-PhyQA dataset comprising Indian high school-level multimodal physics problems. To improve the LMM's performance, we experiment with two techniques, RLHF (Reinforcement Learning from Human Feedback) and Image Captioning. In image captioning, we add a detailed explanation of the diagram in each image, minimizing hallucinations and image processing errors. We further explore the integration of Reinforcement Learning from Human Feedback (RLHF) methodology inspired by the ranking approach in RLHF to enhance the human-like problem-solving abilities of the models. The RLHF approach incorporates human feedback into the learning process of LLMs, improving the model's problem-solving skills, truthfulness, and reasoning capabilities, minimizing the hallucinations in the answers, and improving the quality instead of using vanilla-supervised fine-tuned models. We employ the LLaVA open-source model to answer multimodal physics MCQs and compare the performance with and without using RLHF.

Citation Text Generation (CTG) is a task in natural language processing (NLP) that aims to produce text that accurately cites or references a cited document within a source document. In CTG, the generated text draws upon contextual cues from both the source document and the cited paper, ensuring accurate and relevant citation information is provided. Previous work in the field of citation generation is mainly based on the text summarization of documents. Following this, this paper presents a framework, and a comparative study to demonstrate the use of Large Language Models (LLMs) for the task of citation generation. Also, we have shown the improvement in the results of citation generation by incorporating the knowledge graph relations of the papers in the prompt for the LLM to better learn the relationship between the papers. To assess how well our model is performing, we have used a subset of standard S2ORC dataset, which only consists of computer science academic research papers in the English Language. Vicuna performs best for this task with 14.15 Meteor, 12.88 Rouge-1, 1.52 Rouge-2, and 10.94 Rouge-L. Also, Alpaca performs best, and improves the performance by 36.98% in Rouge-1, and 33.14% in Meteor by including knowledge graphs.

Large ground-truth datasets and recent advances in deep learning techniques have been useful for layout detection. However, because of the restricted layout diversity of these datasets, training on them requires a sizable number of annotated instances, which is both expensive and time-consuming. As a result, differences between the source and target domains may significantly impact how well these models function. To solve this problem, domain adaptation approaches have been developed that use a small quantity of labeled data to adjust the model to the target domain. In this research, we introduced a synthetic document dataset called RanLayNet, enriched with automatically assigned labels denoting spatial positions, ranges, and types of layout elements. The primary aim of this endeavor is to develop a versatile dataset capable of training models with robustness and adaptability to diverse document formats. Through empirical experimentation, we demonstrate that a deep layout identification model trained on our dataset exhibits enhanced performance compared to a model trained solely on actual documents. Moreover, we conduct a comparative analysis by fine-tuning inference models using both PubLayNet and IIIT-AR-13K datasets on the Doclaynet dataset. Our findings emphasize that models enriched with our dataset are optimal for tasks such as achieving 0.398 and 0.588 mAP95 score in the scientific document domain for the TABLE class., Comment: 8 pages, 6 figures, MMAsia 2023 Proceedings of the 5th ACM International Conference on Multimedia in Asia

While Large Language Models (LLMs) can achieve human-level performance in various tasks, they continue to face challenges when it comes to effectively tackling multi-step physics reasoning tasks. To identify the shortcomings of existing models and facilitate further research in this area, we curated a novel dataset, MM-PhyQA, which comprises well-constructed, high schoollevel multimodal physics problems. By evaluating the performance of contemporary LLMs that are publicly available, both with and without the incorporation of multimodal elements in these problems, we aim to shed light on their capabilities. For generating answers for questions consisting of multimodal input (in this case, images and text) we employed Zero-shot prediction using GPT-4 and utilized LLaVA (LLaVA and LLaVA-1.5), the latter of which were fine-tuned on our dataset. For evaluating the performance of LLMs consisting solely of textual input, we tested the performance of the base and fine-tuned versions of the Mistral-7B and LLaMA2-7b models. We also showcased the performance of the novel Multi-Image Chain-of-Thought (MI-CoT) Prompting technique, which when used to train LLaVA-1.5 13b yielded the best results when tested on our dataset, with superior scores in most metrics and the highest accuracy of 71.65% on the test set.

Understanding how robots plan and execute tasks is crucial in today's world, where they are becoming more prevalent in our daily lives. However, teaching non-experts the complexities of robot planning can be challenging. This work presents an open-source platform that simplifies the process using a visual interface that completely abstracts the complex internals of hierarchical planning that robots use for performing task and motion planning. Using the principles developed in the field of explainable AI, this intuitive platform enables users to create plans for robots to complete tasks, and provides helpful hints and natural language explanations for errors. The platform also has a built-in simulator to demonstrate how robots execute submitted plans. This platform's efficacy was tested in a user study on university students with little to no computer science background. Our results show that this platform is highly effective in teaching novice users the intuitions of robot task planning.

The paper presents Maximal Covariance Backward Reachable Trees (MAXCOVAR BRT), which is a multi-query algorithm for planning of dynamic systems under stochastic motion uncertainty and constraints on the control input with explicit coverage guarantees. In contrast to existing roadmap-based probabilistic planning methods that sample belief nodes randomly and draw edges between them \cite{csbrm_tro2024}, under control constraints, the reachability of belief nodes needs to be explicitly established and is determined by checking the feasibility of a non-convex program. Moreover, there is no explicit consideration of coverage of the roadmap while adding nodes and edges during the construction procedure for the existing methods. Our contribution is a novel optimization formulation to add nodes and construct the corresponding edge controllers such that the generated roadmap results in provably maximal coverage under control constraints as compared to any other method of adding nodes and edges. We characterize formally the notion of coverage of a roadmap in this stochastic domain via introduction of the h-$\operatorname{BRS}$ (Backward Reachable Set of Distributions) of a tree of distributions under control constraints, and also support our method with extensive simulations on a 6 DoF model.

We present SocialGenPod, a decentralised and privacy-friendly way of deploying generative AI Web applications. Unlike centralised Web and data architectures that keep user data tied to application and service providers, we show how one can use Solid -- a decentralised Web specification -- to decouple user data from generative AI applications. We demonstrate SocialGenPod using a prototype that allows users to converse with different Large Language Models, optionally leveraging Retrieval Augmented Generation to generate answers grounded in private documents stored in any Solid Pod that the user is allowed to access, directly or indirectly. SocialGenPod makes use of Solid access control mechanisms to give users full control of determining who has access to data stored in their Pods. SocialGenPod keeps all user data (chat history, app configuration, personal documents, etc) securely in the user's personal Pod; separate from specific model or application providers. Besides better privacy controls, this approach also enables portability across different services and applications. Finally, we discuss challenges, posed by the large compute requirements of state-of-the-art models, that future research in this area should address. Our prototype is open-source and available at: https://github.com/Vidminas/socialgenpod/., Comment: Demo paper accepted in Companion Proceedings of the ACM Web Conference 2024

Pretraining Large Language Models (LLMs) on large corpora of textual data is now a standard paradigm. When using these LLMs for many downstream applications, it is common to additionally bake in new knowledge (e.g., time-critical news, or private domain knowledge) into the pretrained model either through RAG-based-prompting, or fine-tuning. However, the optimal methodology for the model to gain such new knowledge remains an open question. In this paper, we present Retrieval Augmented FineTuning (RAFT), a training recipe that improves the model's ability to answer questions in a "open-book" in-domain settings. In RAFT, given a question, and a set of retrieved documents, we train the model to ignore those documents that don't help in answering the question, which we call, distractor documents. RAFT accomplishes this by citing verbatim the right sequence from the relevant document that would help answer the question. This coupled with RAFT's chain-of-thought-style response helps improve the model's ability to reason. In domain-specific RAG, RAFT consistently improves the model's performance across PubMed, HotpotQA, and Gorilla datasets, presenting a post-training recipe to improve pre-trained LLMs to in-domain RAG. RAFT's code and demo are open-sourced at github.com/ShishirPatil/gorilla.

[Ne II] 12.81 $\mu\mathrm{m}$ emission is a well-used tracer of protoplanetary disk winds due to its blueshifted line profile. MIRI-MRS recently observed T Cha, detecting this line along with lines of [Ne III], [Ar II] and [Ar III], with the [Ne II] and [Ne III] lines found to be extended while the [Ar II] was not. In this complementary work, we use these lines to address long-debated questions about protoplanetary disk winds regarding their mass-loss rate, the origin of their ionization, and the role of magnetically-driven winds as opposed to photoevaporation. To this end, we perform photoionization radiative transfer on simple hydrodynamic wind models to map the line emission. We compare the integrated model luminosities to those observed with MIRI-MRS to identify which models most closely reproduce the data and produce synthetic images from these to understand what information is captured by measurements of the line extents. Along with the low degree of ionization implied by the line ratios, the relative compactness of [Ar II] compared to [Ne II] is particularly constraining. This requires Ne II production by hard X-rays and Ar II production by soft X-rays (and/or EUV) in an extended ($\gtrsim 10$ au) wind that is shielded from soft X-rays - necessitating a dense wind with material launched on scales down to ~1 au. Such conditions could be produced by photoevaporation, whereas an extended MHD wind producing equal shielding would likely underpredict the line fluxes. However, a tenuous inner MHD wind may still contribute to shielding the extended wind. This picture is consistent with constraints from spectrally-resolved line profiles., Comment: 32 pages, 16 figures, Accepted 14/03/24 to the Astronomical Journal. Complementary modeling to Bajaj et al. 2024 (arXiv:2403.01060)

Large Language Models (LLMs) applied to code-related applications have emerged as a prominent field, attracting significant interest from both academia and industry. However, as new and improved LLMs are developed, existing evaluation benchmarks (e.g., HumanEval, MBPP) are no longer sufficient for assessing their capabilities. In this work, we propose LiveCodeBench, a comprehensive and contamination-free evaluation of LLMs for code, which continuously collects new problems over time from contests across three competition platforms, namely LeetCode, AtCoder, and CodeForces. Notably, our benchmark also focuses on a broader range of code related capabilities, such as self-repair, code execution, and test output prediction, beyond just code generation. Currently, LiveCodeBench hosts four hundred high-quality coding problems that were published between May 2023 and May 2024. We have evaluated 18 base LLMs and 34 instruction-tuned LLMs on LiveCodeBench. We present empirical findings on contamination, holistic performance comparisons, potential overfitting in existing benchmarks as well as individual model comparisons. We will release all prompts and model completions for further community analysis, along with a general toolkit for adding new scenarios and model, Comment: Website - https://livecodebench.github.io/

Machine learning requires defining one's target variable for predictions or decisions, a process that can have profound implications on fairness: biases are often encoded in target variable definition itself, before any data collection or training. We present an interactive simulator, FairTargetSim (FTS), that illustrates how target variable definition impacts fairness. FTS is a valuable tool for algorithm developers, researchers, and non-technical stakeholders. FTS uses a case study of algorithmic hiring, using real-world data and user-defined target variables. FTS is open-source and available at: http://tinyurl.com/ftsinterface. The video accompanying this paper is here: http://tinyurl.com/ijcaifts.

Stacking, a heuristic technique for training deep residual networks by progressively increasing the number of layers and initializing new layers by copying parameters from older layers, has proven quite successful in improving the efficiency of training deep neural networks. In this paper, we propose a theoretical explanation for the efficacy of stacking: viz., stacking implements a form of Nesterov's accelerated gradient descent. The theory also covers simpler models such as the additive ensembles constructed in boosting methods, and provides an explanation for a similar widely-used practical heuristic for initializing the new classifier in each round of boosting. We also prove that for certain deep linear residual networks, stacking does provide accelerated training, via a new potential function analysis of the Nesterov's accelerated gradient method which allows errors in updates. We conduct proof-of-concept experiments to validate our theory as well.

Understanding the environmental impact of professional activities is becoming paramount in current times, especially within sectors that historically have had significant resource utilisation, such as High Energy Physics (HEP) and related fields. The young High Energy Physicists (yHEP) association launched the Know your footprint (Kyf) campaign to evaluate the CO$_\text{2}$-equivalent emissions generated by HEP-related research. This study delves into the carbon footprints associated with four distinct categories: Experiments, tied to extensive collaborations with substantial infrastructure; Institutional, representing the resource consumption of research institutes and universities; Computing, focusing on simulations and data analysis; and Travel, covering professional trips such as to conferences, meetings, and workshops. The findings in this assessment are integrated into a tool for self-evaluation, the Know-your-footprint (Kyf) calculator, which allows colleagues to assess their personal and professional footprint, and optionally share their data with the yHEP association. The aim of the Kyf campaign is to heighten awareness, foster sustainability, and inspire the community to adopt more environmentally-responsible research methodologies., Comment: 16 pages, 5 figures

This work proposes to augment the lifting steps of the conventional wavelet transform with additional neural network assisted lifting steps. These additional steps reduce residual redundancy (notably aliasing information) amongst the wavelet subbands, and also improve the visual quality of reconstructed images at reduced resolutions. The proposed approach involves two steps, a high-to-low step followed by a low-to-high step. The high-to-low step suppresses aliasing in the low-pass band by using the detail bands at the same resolution, while the low-to-high step aims to further remove redundancy from detail bands, so as to achieve higher energy compaction. The proposed two lifting steps are trained in an end-to-end fashion; we employ a backward annealing approach to overcome the non-differentiability of the quantization and cost functions during back-propagation. Importantly, the networks employed in this paper are compact and with limited non-linearities, allowing a fully scalable system; one pair of trained network parameters are applied for all levels of decomposition and for all bit-rates of interest. By employing the proposed approach within the JPEG 2000 image coding standard, our method can achieve up to 17.4% average BD bit-rate saving over a wide range of bit-rates, while retaining quality and resolution scalability features of JPEG 2000., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Understanding when and how circumstellar disks disperse is crucial to constrain planet formation and migration. Thermal winds powered by high-energy stellar photons have long been theorized to drive disk dispersal. However, evidence for these winds is currently based only on small (~3-6 km/s) blue-shifts in [Ne II] 12.81 um lines, which does not exclude MHD winds. We report JWST MIRI MRS spectro-imaging of T Cha, a disk with a large dust gap (~30 au in radius) and blue-shifted [Ne II] emission. We detect four forbidden noble gas lines, [Ar II], [Ar III], [Ne II], and [Ne III], of which [Ar III] is the first detection in any protoplanetary disk. We use line flux ratios to constrain the energy of the ionizing photons and find that Argon is ionized by EUV whereas Neon is most likely ionized by X-rays. After performing continuum and Point Spread Function (PSF) subtraction on the IFU cube, we discover a spatial extension in the [Ne II] emission off the disk continuum emission. This is the first spatially resolved [Ne II] disk wind emission. The mostly ionic spectrum of T Cha, in combination with the extended [Ne II] emission, points to an evolved stage for any inner MHD wind and is consistent with the existence of an outer thermal wind ionized and driven by high-energy stellar photons. This work acts as a pathfinder for future observations aiming at investigating disk dispersal using JWST., Comment: 20 pages, 8 figures, Accepted for publication in AJ

While language models are increasingly more proficient at code generation, they still frequently generate incorrect programs. Many of these programs are obviously wrong, but others are more subtle and pass weaker correctness checks such as being able to compile. In this work, we focus on these counterfeit samples: programs sampled from a language model that 1) have a high enough log-probability to be generated at a moderate temperature and 2) pass weak correctness checks. Overall, we discover that most models have a very shallow understanding of counterfeits through three clear failure modes. First, models mistakenly classify them as correct. Second, models are worse at reasoning about the execution behaviour of counterfeits and often predict their execution results as if they were correct. Third, when asking models to fix counterfeits, the likelihood of a model successfully repairing a counterfeit is often even lower than that of sampling a correct program from scratch. Counterfeits also have very unexpected properties: first, counterfeit programs for problems that are easier for a model to solve are not necessarily easier to detect and only slightly easier to execute and repair. Second, counterfeits from a given model are just as confusing to the model itself as they are to other models. Finally, both strong and weak models are able to generate counterfeit samples that equally challenge all models. In light of our findings, we recommend that care and caution be taken when relying on models to understand their own samples, especially when no external feedback is incorporated., Comment: 54 pages, 25 figures

The BigCode project, an open-scientific collaboration focused on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In partnership with Software Heritage (SWH), we build The Stack v2 on top of the digital commons of their source code archive. Alongside the SWH repositories spanning 619 programming languages, we carefully select other high-quality data sources, such as GitHub pull requests, Kaggle notebooks, and code documentation. This results in a training set that is 4x larger than the first StarCoder dataset. We train StarCoder2 models with 3B, 7B, and 15B parameters on 3.3 to 4.3 trillion tokens and thoroughly evaluate them on a comprehensive set of Code LLM benchmarks. We find that our small model, StarCoder2-3B, outperforms other Code LLMs of similar size on most benchmarks, and also outperforms StarCoderBase-15B. Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size. In addition, it matches or outperforms CodeLlama-34B, a model more than twice its size. Although DeepSeekCoder- 33B is the best-performing model at code completion for high-resource languages, we find that StarCoder2-15B outperforms it on math and code reasoning benchmarks, as well as several low-resource languages. We make the model weights available under an OpenRAIL license and ensure full transparency regarding the training data by releasing the SoftWare Heritage persistent IDentifiers (SWHIDs) of the source code data.

This paper provides a comprehensive study on features and performance of different ways to incorporate neural networks into lifting-based wavelet-like transforms, within the context of fully scalable and accessible image compression. Specifically, we explore different arrangements of lifting steps, as well as various network architectures for learned lifting operators. Moreover, we examine the impact of the number of learned lifting steps, the number of channels, the number of layers and the support of kernels in each learned lifting operator. To facilitate the study, we investigate two generic training methodologies that are simultaneously appropriate to a wide variety of lifting structures considered. Experimental results ultimately suggest that retaining fixed lifting steps from the base wavelet transform is highly beneficial. Moreover, we demonstrate that employing more learned lifting steps and more layers in each learned lifting operator do not contribute strongly to the compression performance. However, benefits can be obtained by utilizing more channels in each learned lifting operator. Ultimately, the learned wavelet-like transform proposed in this paper achieves over 25% bit-rate savings compared to JPEG 2000 with compact spatial support., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Semantic Overlap Summarization (SOS) is a constrained multi-document summarization task, where the constraint is to capture the common/overlapping information between two alternative narratives. While recent advancements in Large Language Models (LLMs) have achieved superior performance in numerous summarization tasks, a benchmarking study of the SOS task using LLMs is yet to be performed. As LLMs' responses are sensitive to slight variations in prompt design, a major challenge in conducting such a benchmarking study is to systematically explore a variety of prompts before drawing a reliable conclusion. Fortunately, very recently, the TELeR taxonomy has been proposed which can be used to design and explore various prompts for LLMs. Using this TELeR taxonomy and 15 popular LLMs, this paper comprehensively evaluates LLMs on the SOS Task, assessing their ability to summarize overlapping information from multiple alternative narratives. For evaluation, we report well-established metrics like ROUGE, BERTscore, and SEM-F1$ on two different datasets of alternative narratives. We conclude the paper by analyzing the strengths and limitations of various LLMs in terms of their capabilities in capturing overlapping information The code and datasets used to conduct this study are available at https://anonymous.4open.science/r/llm_eval-E16D.

One of the most important yet onerous tasks in the academic peer-reviewing process is composing meta-reviews, which involves understanding the core contributions, strengths, and weaknesses of a scholarly manuscript based on peer-review narratives from multiple experts and then summarizing those multiple experts' perspectives into a concise holistic overview. Given the latest major developments in generative AI, especially Large Language Models (LLMs), it is very compelling to rigorously study the utility of LLMs in generating such meta-reviews in an academic peer-review setting. In this paper, we perform a case study with three popular LLMs, i.e., GPT-3.5, LLaMA2, and PaLM2, to automatically generate meta-reviews by prompting them with different types/levels of prompts based on the recently proposed TELeR taxonomy. Finally, we perform a detailed qualitative study of the meta-reviews generated by the LLMs and summarize our findings and recommendations for prompting LLMs for this complex task.