Authors: Muhammad Aurangzeb Ahmad, Ilker Yaramis, Taposh Dutta Roy
Large language models have proliferated across multiple domains in as short period of time. There is however hesitation in the medical and healthcare domain towards their adoption because of issues like factuality, coherence, and hallucinations. Give the high stakes nature of healthcare, many researchers have even cautioned against its usage until these issues are resolved. The key to the implementation and deployment of LLMs in healthcare is to make these models trustworthy, transparent (as much possible) and explainable. In this paper we describe the key elements in creating reliable, trustworthy, and unbiased models as a necessary condition for their adoption in healthcare. Specifically we focus on the quantification, validation, and mitigation of hallucinations in the context in healthcare. Lastly, we discuss how the future of LLMs in healthcare may look like.
Authors: Jaeff Hong, Duong Dung, Danielle Hutchinson, Zubair Akhtar, Rosalie Chen, Rebecca Dawson, Aditya Joshi, Samsung Lim, C Raina MacIntyre, Deepti Gurdasani
Relation Extraction from News Articles (RENA) is a browser-based tool designed to extract key entities and their semantic relationships in English language news articles related to infectious diseases. Constructed using the React framework, this system presents users with an elegant and user-friendly interface. It enables users to input a news article and select from a choice of two models to generate a comprehensive list of relations within the provided text. As a result, RENA allows real-time parsing of news articles to extract key information for epidemic surveillance, contributing to EPIWATCH, an open-source intelligence-based epidemic warning system.
Authors: Jiakai Wang, Donghua Wang, Jin Hu, Siyang Wu, Tingsong Jiang, Wen Yao, Aishan Liu, Xianglong Liu
Deep neural networks (DNNs) have demonstrated high vulnerability to adversarial examples. Besides the attacks in the digital world, the practical implications of adversarial examples in the physical world present significant challenges and safety concerns. However, current research on physical adversarial examples (PAEs) lacks a comprehensive understanding of their unique characteristics, leading to limited significance and understanding. In this paper, we address this gap by thoroughly examining the characteristics of PAEs within a practical workflow encompassing training, manufacturing, and re-sampling processes. By analyzing the links between physical adversarial attacks, we identify manufacturing and re-sampling as the primary sources of distinct attributes and particularities in PAEs. Leveraging this knowledge, we develop a comprehensive analysis and classification framework for PAEs based on their specific characteristics, covering over 100 studies on physical-world adversarial examples. Furthermore, we investigate defense strategies against PAEs and identify open challenges and opportunities for future research. We aim to provide a fresh, thorough, and systematic understanding of PAEs, thereby promoting the development of robust adversarial learning and its application in open-world scenarios.
Authors: Zheng Lin, Zhe Chen, Zihan Fang, Xianhao Chen, Xiong Wang, Yue Gao
Recently, a large number of Low Earth Orbit (LEO) satellites have been launched and deployed successfully in space by commercial companies, such as SpaceX. Due to multimodal sensors equipped by the LEO satellites, they serve not only for communication but also for various machine learning applications, such as space modulation recognition, remote sensing image classification, etc. However, the ground station (GS) may be incapable of downloading such a large volume of raw sensing data for centralized model training due to the limited contact time with LEO satellites (e.g. 5 minutes). Therefore, federated learning (FL) has emerged as the promising solution to address this problem via on-device training. Unfortunately, to enable FL on LEO satellites, we still face three critical challenges that are i) heterogeneous computing and memory capabilities, ii) limited uplink rate, and iii) model staleness. To this end, we propose FedSN as a general FL framework to tackle the above challenges, and fully explore data diversity on LEO satellites. Specifically, we first present a novel sub-structure scheme to enable heterogeneous local model training considering different computing, memory, and communication constraints on LEO satellites. Additionally, we propose a pseudo-synchronous model aggregation strategy to dynamically schedule model aggregation for compensating model staleness. To further demonstrate the effectiveness of the FedSN, we evaluate it using space modulation recognition and remote sensing image classification tasks by leveraging the data from real-world satellite networks. Extensive experimental results demonstrate that FedSN framework achieves higher accuracy, lower computing, and communication overhead than the state-of-the-art benchmarks and the effectiveness of each components in FedSN.
Authors: Priti Oli, Rabin Banjade, Jeevan Chapagain, Vasile Rus
This paper systematically explores how Large Language Models (LLMs) generate explanations of code examples of the type used in intro-to-programming courses. As we show, the nature of code explanations generated by LLMs varies considerably based on the wording of the prompt, the target code examples being explained, the programming language, the temperature parameter, and the version of the LLM. Nevertheless, they are consistent in two major respects for Java and Python: the readability level, which hovers around 7-8 grade, and lexical density, i.e., the relative size of the meaningful words with respect to the total explanation size. Furthermore, the explanations score very high in correctness but less on three other metrics: completeness, conciseness, and contextualization.
Authors: Shuo Cheng, Caelan Garrett, Ajay Mandlekar, Danfei Xu
Developing intelligent robots for complex manipulation tasks in household and factory settings remains challenging due to long-horizon tasks, contact-rich manipulation, and the need to generalize across a wide variety of object shapes and scene layouts. While Task and Motion Planning (TAMP) offers a promising solution, its assumptions such as kinodynamic models limit applicability in novel contexts. Neural object descriptors (NODs) have shown promise in object and scene generalization but face limitations in addressing broader tasks. Our proposed TAMP-based framework, NOD-TAMP, extracts short manipulation trajectories from a handful of human demonstrations, adapts these trajectories using NOD features, and composes them to solve broad long-horizon tasks. Validated in a simulation environment, NOD-TAMP effectively tackles varied challenges and outperforms existing methods, establishing a cohesive framework for manipulation planning. For videos and other supplemental material, see the project website: https://sites.google.com/view/nod-tamp/.
Authors: Daniel Garces, Sushmita Bhattacharya, Dimitri Bertsekas, Stephanie Gil
In this paper, we focus on the autonomous multiagent taxi routing problem for a large urban environment where the location and number of future ride requests are unknown a-priori, but follow an estimated empirical distribution. Recent theory has shown that if a base policy is stable then a rollout-based algorithm with such a base policy produces a near-optimal stable policy. Although, rollout-based approaches are well-suited for learning cooperative multiagent policies with considerations for future demand, applying such methods to a large urban environment can be computationally expensive. Large environments tend to have a large volume of requests, and hence require a large fleet of taxis to guarantee stability. In this paper, we aim to address the computational bottleneck of multiagent (one-at-a-time) rollout, where the computational complexity grows linearly in the number of agents. We propose an approximate one-at-a-time rollout-based two-phase algorithm that reduces the computational cost, while still achieving a stable near-optimal policy. Our approach partitions the graph into sectors based on the predicted demand and an user-defined maximum number of agents that can be planned for using the one-at-a-time rollout approach. The algorithm then applies instantaneous assignment (IA) for re-balancing taxis across sectors and a sector-wide one-at-a-time rollout algorithm that is executed in parallel for each sector. We characterize the number of taxis $m$ that is sufficient for IA base policy to be stable, and derive a necessary condition on $m$ as time goes to infinity. Our numerical results show that our approach achieves stability for an $m$ that satisfies the theoretical conditions. We also empirically demonstrate that our proposed two-phase algorithm has comparable performance to the one-at-a-time rollout over the entire map, but with significantly lower runtimes.
Authors: Pakorn Uttayopas, Xiaoxiao Cheng, Etienne Burdet
while most of the tactile robots are operated in close-set conditions, it is challenging for them to operate in open-set conditions where test objects are beyond the robots' knowledge. We proposed an open-set recognition framework using mechanical properties to recongise known objects and incrementally label novel objects. The main contribution is a clustering algorithm that exploits knowledge of known objects to estimate cluster centre and sizes, unlike a typical algorithm that randomly selects them. The framework is validated with the mechanical properties estimated from a real object during interaction. The results show that the framework could recognise objects better than alternative methods contributed by the novelty detector. Importantly, our clustering algorithm yields better clustering performance than other methods. Furthermore, the hyperparameters studies show that cluster size is important to clustering results and needed to be tuned properly.
Authors: Jai Vipra, Anton Korinek
We analyze the structure of the market for foundation models, i.e., large AI models such as those that power ChatGPT and that are adaptable to downstream uses, and we examine the implications for competition policy and regulation. We observe that the most capable models will have a tendency towards natural monopoly and may have potentially vast markets. This calls for a two-pronged regulatory response: (i) Antitrust authorities need to ensure the contestability of the market by tackling strategic behavior, in particular by ensuring that monopolies do not propagate vertically to downstream uses, and (ii) given the diminished potential for market discipline, there is a role for regulators to ensure that the most capable models meet sufficient quality standards (including safety, privacy, non-discrimination, reliability and interoperability standards) to maximally contribute to social welfare. Regulators should also ensure a level regulatory playing field between AI and non-AI applications in all sectors of the economy. For models that are behind the frontier, we expect competition to be quite intense, implying a more limited role for competition policy, although a role for regulation remains.
Authors: Mohammad Junayed Hasan, Suhra Noor, Mohammad Ashrafuzzaman Khan
Clinical texts, such as admission notes, discharge summaries, and progress notes, contain rich and valuable information that can be used for various clinical outcome prediction tasks. However, applying large language models, such as BERT-based models, to clinical texts poses two major challenges: the limitation of input length and the diversity of data sources. This paper proposes a novel method to preserve the knowledge of long clinical texts using aggregated ensembles of large language models. Unlike previous studies which use model ensembling or text aggregation methods separately, we combine ensemble learning with text aggregation and train multiple large language models on two clinical outcome tasks: mortality prediction and length of stay prediction. We show that our method can achieve better results than baselines, ensembling, and aggregation individually, and can improve the performance of large language models while handling long inputs and diverse datasets. We conduct extensive experiments on the admission notes from the MIMIC-III clinical database by combining multiple unstructured and high-dimensional datasets, demonstrating our method's effectiveness and superiority over existing approaches. We also provide a comprehensive analysis and discussion of our results, highlighting our method's applications and limitations for future research in the domain of clinical healthcare. The results and analysis of this study is supportive of our method assisting in clinical healthcare systems by enabling clinical decision-making with robust performance overcoming the challenges of long text inputs and varied datasets.
Authors: Moreno D'Incà, Christos Tzelepis, Ioannis Patras, Nicu Sebe
Fairness is crucial when training a deep-learning discriminative model, especially in the facial domain. Models tend to correlate specific characteristics (such as age and skin color) with unrelated attributes (downstream tasks), resulting in biases which do not correspond to reality. It is common knowledge that these correlations are present in the data and are then transferred to the models during training. This paper proposes a method to mitigate these correlations to improve fairness. To do so, we learn interpretable and meaningful paths lying in the semantic space of a pre-trained diffusion model (DiffAE) -- such paths being supervised by contrastive text dipoles. That is, we learn to edit protected characteristics (age and skin color). These paths are then applied to augment images to improve the fairness of a given dataset. We test the proposed method on CelebA-HQ and UTKFace on several downstream tasks with age and skin color as protected characteristics. As a proxy for fairness, we compute the difference in accuracy with respect to the protected characteristics. Quantitative results show how the augmented images help the model improve the overall accuracy, the aforementioned metric, and the disparity of equal opportunity. Code is available at: https://github.com/Moreno98/Vision-Language-Bias-Control.
Authors: Guangyue Xu, Parisa Kordjamshidi, Joyce Chai
Humans have the ability to learn novel compositional concepts by recalling and generalizing primitive concepts acquired from past experiences. Inspired by this observation, in this paper, we propose MetaReVision, a retrieval-enhanced meta-learning model to address the visually grounded compositional concept learning problem. The proposed MetaReVision consists of a retrieval module and a meta-learning module which are designed to incorporate retrieved primitive concepts as a supporting set to meta-train vision-anguage models for grounded compositional concept recognition. Through meta-learning from episodes constructed by the retriever, MetaReVision learns a generic compositional representation that can be fast updated to recognize novel compositional concepts. We create CompCOCO and CompFlickr to benchmark the grounded compositional concept learning. Our experimental results show that MetaReVision outperforms other competitive baselines and the retrieval module plays an important role in this compositional learning process.
Authors: Andrea Roncoli, Aleksandra Ćiprijanović, Maggie Voetberg, Francisco Villaescusa-Navarro, Brian Nord
Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross-dataset tasks (up to $28\%$ better relative error and up to almost an order of magnitude better $\chi^2$). Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.
Authors: Kunpeng Xu, Lifei Chen, Shengrui Wang
Machine learning techniques have outperformed numerous rule-based methods for decision-making in autonomous vehicles. Despite recent efforts, lane changing remains a major challenge, due to the complex driving scenarios and changeable social behaviors of surrounding vehicles. To help improve the state of the art, we propose to leveraging the emerging \underline{D}eep \underline{R}einforcement learning (DRL) approach for la\underline{NE} changing at the \underline{T}actical level. To this end, we present "DRNet", a novel and highly efficient DRL-based framework that enables a DRL agent to learn to drive by executing reasonable lane changing on simulated highways with an arbitrary number of lanes, and considering driving style of surrounding vehicles to make better decisions. Furthermore, to achieve a safe policy for decision-making, DRNet incorporates ideas from safety verification, the most important component of autonomous driving, to ensure that only safe actions are chosen at any time. The setting of our state representation and reward function enables the trained agent to take appropriate actions in a real-world-like simulator. Our DRL agent has the ability to learn the desired task without causing collisions and outperforms DDQN and other baseline models.
Authors: Niko A. Grupen
Responsible AI has risen to the forefront of the AI research community. As neural network-based learning algorithms continue to permeate real-world applications, the field of Responsible AI has played a large role in ensuring that such systems maintain a high-level of human-compatibility. Despite this progress, the state of the art in Responsible AI has ignored one crucial point: human problems are multi-agent problems. Predominant approaches largely consider the performance of a single AI system in isolation, but human problems are, by their very nature, multi-agent. From driving in traffic to negotiating economic policy, human problem-solving involves interaction and the interplay of the actions and motives of multiple individuals.
This dissertation develops the study of responsible emergent multi-agent behavior, illustrating how researchers and practitioners can better understand and shape multi-agent learning with respect to three pillars of Responsible AI: interpretability, fairness, and robustness. First, I investigate multi-agent interpretability, presenting novel techniques for understanding emergent multi-agent behavior at multiple levels of granularity. With respect to low-level interpretability, I examine the extent to which implicit communication emerges as an aid to coordination in multi-agent populations. I introduce a novel curriculum-driven method for learning high-performing policies in difficult, sparse reward environments and show through a measure of position-based social influence that multi-agent teams that learn sophisticated coordination strategies exchange significantly more information through implicit signals than lesser-coordinated agents. Then, at a high-level, I study concept-based interpretability in the context of multi-agent learning. I propose a novel method for learning intrinsically interpretable, concept-based policies and show that it enables...
Authors: Rouzbeh Meshkinnejad, Jie Mei, Daniel Lizotte, Yalda Mohsenzadeh
Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in continual learning has addressed forgetting by using previous task data and trained models. Inspired by event models created and updated in the brain, we propose a new mechanism that takes place during task boundaries, i.e., when one task finishes and another starts. By observing the redundancy-inducing ability of contrastive loss on the output of a neural network, our method leverages the first few samples of the new task to identify and retain parameters contributing most to the transfer ability of the neural network, freeing up the remaining parts of the network to learn new features. We evaluate the proposed methods on benchmark computer vision datasets including CIFAR10 and TinyImagenet and demonstrate state-of-the-art performance in the task-incremental, class-incremental, and domain-incremental continual learning scenarios.
Authors: Shan Yu, Zhenting Zhu, Yu Chen, Hanchen Xu, Pengzhan Zhao, Yang Wang, Arthi Padmanabhan, Hugo Latapie, Harry Xu
Video analytics is widely used in contemporary systems and services. At the forefront of video analytics are video queries that users develop to find objects of particular interest. Building upon the insight that video objects (e.g., human, animals, cars, etc.), the center of video analytics, are similar in spirit to objects modeled by traditional object-oriented languages, we propose to develop an object-oriented approach to video analytics. This approach, named VQPy, consists of a frontend$\unicode{x2015}$a Python variant with constructs that make it easy for users to express video objects and their interactions$\unicode{x2015}$as well as an extensible backend that can automatically construct and optimize pipelines based on video objects. We have implemented and open-sourced VQPy, which has been productized in Cisco as part of its DeepVision framework.
Authors: Cory Dal Ponte, Sathana Dushyanthen, Kayley Lyons
Delivering personalised, formative feedback to multiple problem-based learning groups in a short time period can be almost impossible. We employed ChatGPT to provide personalised formative feedback in a one-hour Zoom break-out room activity that taught practicing health professionals how to formulate evaluation plans for digital health initiatives. Learners completed an evaluation survey that included Likert scales and open-ended questions that were analysed. Half of the 44 survey respondents had never used ChatGPT before. Overall, respondents found the feedback favourable, described a wide range of group dynamics, and had adaptive responses to the feedback, yet only three groups used the feedback loop to improve their evaluation plans. Future educators can learn from our experience including engineering prompts, providing instructions on how to use ChatGPT, and scaffolding optimal group interactions with ChatGPT. Future researchers should explore the influence of ChatGPT on group dynamics and derive design principles for the use of ChatGPT in collaborative learning.
Authors: Cheng Luo, Tianle Zhong, Geoffrey Fox
In the evolving landscape of neural network models, one prominent challenge stand out: the significant memory overheads associated with training expansive models. Addressing this challenge, this study delves deep into the Rotated Tensor Parallelism (RTP). RTP is an innovative approach that strategically focuses on memory deduplication in distributed training environments. It boasts of unique features like a customized communication primitive and the Flyweight Pattern initialization. Furthermore, RTP ensures a seamless overlap between partition computation and partition weight communication, optimizing the training process. Our empirical evaluations underscore RTP's efficiency, revealing that its memory consumption during distributed system training is remarkably close to the optimal - distributing the memory overhead of a single machine equitably among multiple machines. The experimental results demonstrate that RTP is capable of achieving comparable performance to Distributed Data Parallel while providing support for significantly larger models with near-linear scalability in terms of memory. Code of RTP is available at https://github.com/wdlctc/rtp.
Authors: Halim Cagri Ates, Shruti Bhargava, Site Li, Jiarui Lu, Siddhardha Maddula, Joel Ruben Antony Moniz, Anil Kumar Nalamalapu, Roman Hoang Nguyen, Melis Ozyildirim, Alkesh Patel, Dhivya Piraviperumal, Vincent Renkens, Ankit Samal, Thy Tran, Bo-Hsiang Tseng, Hong Yu, Yuan Zhang, Rong Zou
Successfully handling context is essential for any dialog understanding task. This context maybe be conversational (relying on previous user queries or system responses), visual (relying on what the user sees, for example, on their screen), or background (based on signals such as a ringing alarm or playing music). In this work, we present an overview of MARRS, or Multimodal Reference Resolution System, an on-device framework within a Natural Language Understanding system, responsible for handling conversational, visual and background context. In particular, we present different machine learning models to enable handing contextual queries; specifically, one to enable reference resolution, and one to handle context via query rewriting. We also describe how these models complement each other to form a unified, coherent, lightweight system that can understand context while preserving user privacy.
Authors: Kai Yin, Ali Mostafavi
Community resilience is a complex and muti-faceted phenomenon that emerges from complex and nonlinear interactions among different socio-technical systems and their resilience properties. However, present studies on community resilience focus primarily on vulnerability assessment and utilize index-based approaches, with limited ability to capture heterogeneous features within community socio-technical systems and their nonlinear interactions in shaping robustness, redundancy, and resourcefulness components of resilience. To address this gap, this paper presents an integrated three-layer deep learning model for community resilience rating (called Resili-Net). Twelve measurable resilience features are specified and computed within community socio-technical systems (i.e., facilities, infrastructures, and society) related to three resilience components of robustness, redundancy, and resourcefulness. Using publicly accessible data from multiple metropolitan statistical areas in the United States, Resili-Net characterizes the resilience levels of spatial areas into five distinct levels. The interpretability of the model outcomes enables feature analysis for specifying the determinants of resilience in areas within each resilience level, allowing for the identification of specific resilience enhancement strategies. Changes in community resilience profiles under urban development patterns are further examined by changing the value of related socio-technical systems features. Accordingly, the outcomes provide novel perspectives for community resilience assessment by harnessing machine intelligence and heterogeneous urban big data.
Authors: Ezra MacDonald, Derek Jacoby, Yvonne Coady
Assessing the environmental impact of the mineral extraction industry plays a critical role in understanding and mitigating the ecological consequences of extractive activities. This paper presents MineSegSAT, a model that presents a novel approach to predicting environmentally impacted areas of mineral extraction sites using the SegFormer deep learning segmentation architecture trained on Sentinel-2 data. The data was collected from non-overlapping regions over Western Canada in 2021 containing areas of land that have been environmentally impacted by mining activities that were identified from high-resolution satellite imagery in 2021. The SegFormer architecture, a state-of-the-art semantic segmentation framework, is employed to leverage its advanced spatial understanding capabilities for accurate land cover classification. We investigate the efficacy of loss functions including Dice, Tversky, and Lovasz loss respectively. The trained model was utilized for inference over the test region in the ensuing year to identify potential areas of expansion or contraction over these same periods. The Sentinel-2 data is made available on Amazon Web Services through a collaboration with Earth Daily Analytics which provides corrected and tiled analytics-ready data on the AWS platform. The model and ongoing API to access the data on AWS allow the creation of an automated tool to monitor the extent of disturbed areas surrounding known mining sites to ensure compliance with their environmental impact goals.
Authors: Jiao Ou, Junda Lu, Che Liu, Yihong Tang, Fuzheng Zhang, Di Zhang, Zhongyuan Wang, Kun Gai
Large language models (LLMs) have achieved remarkable breakthroughs in new dialogue capabilities, refreshing human's impressions on dialogue systems. The long-standing goal of dialogue systems is to be human-like enough to establish long-term connections with users by satisfying the need for communication, affection and social belonging. Therefore, there has been an urgent need to evaluate LLMs as human-like dialogue systems. In this paper, we propose DialogBench, a dialogue evaluation benchmark that currently contains $12$ dialogue tasks to assess the capabilities of LLMs as human-like dialogue systems should have. Specifically, we prompt GPT-4 to generate evaluation instances for each task. We first design the basic prompt based on widely-used design principles and further mitigate the existing biases to generate higher-quality evaluation instances. Our extensive test over $28$ LLMs (including pre-trained and supervised instruction-tuning) shows that instruction fine-tuning benefits improve the human likeness of LLMs to a certain extent, but there is still much room to improve those capabilities for most LLMs as human-like dialogue systems. In addition, experimental results also indicate that LLMs perform differently in various abilities that human-like dialogue systems should have. We will publicly release DialogBench, along with the associated evaluation code for the broader research community.
Authors: Dimitris Bertsimas, Angelos G. Koulouras, Georgios Antonios Margonis
We propose a prognostic stratum matching framework that addresses the deficiencies of Randomized trial data subgroup analysis and transforms ObservAtional Data to be used as if they were randomized, thus paving the road for precision medicine. Our approach counters the effects of unobserved confounding in observational data by correcting the estimated probabilities of the outcome under a treatment through a novel two-step process. These probabilities are then used to train Optimal Policy Trees (OPTs), which are decision trees that optimally assign treatments to subgroups of patients based on their characteristics. This facilitates the creation of clinically intuitive treatment recommendations. We applied our framework to observational data of patients with gastrointestinal stromal tumors (GIST) and validated the OPTs in an external cohort using the sensitivity and specificity metrics. We show that these recommendations outperformed those of experts in GIST. We further applied the same framework to randomized clinical trial (RCT) data of patients with extremity sarcomas. Remarkably, despite the initial trial results suggesting that all patients should receive treatment, our framework, after addressing imbalances in patient distribution due to the trial's small sample size, identified through the OPTs a subset of patients with unique characteristics who may not require treatment. Again, we successfully validated our recommendations in an external cohort.
Authors: Zheyuan Bai, Xinduo Liu, Hailin Hu, Tianyu Guo, Qinghua Zhang, Yunhe Wang
Data-Free Knowledge Distillation (DFKD) plays a vital role in compressing the model when original training data is unavailable. Previous works for DFKD in NLP mainly focus on distilling encoder-only structures like BERT on classification tasks, which overlook the notable progress of generative language modeling. In this work, we propose a novel DFKD framework, namely DFKD-T$^{3}$, where the pretrained generative language model can also serve as a controllable data generator for model compression. This novel framework DFKD-T$^{3}$ leads to an end-to-end learnable text-to-text framework to transform the general domain corpus to compression-friendly task data, targeting to improve both the \textit{specificity} and \textit{diversity}. Extensive experiments show that our method can boost the distillation performance in various downstream tasks such as sentiment analysis, linguistic acceptability, and information extraction. Furthermore, we show that the generated texts can be directly used for distilling other language models and outperform the SOTA methods, making our method more appealing in a general DFKD setting. Our code is available at https://gitee.com/mindspore/models/tree/master/research/nlp/DFKD\_T3.
Authors: Junxian Zhou, Haiqin Yang, Ye Junpeng, Yuxuan He, Hao Mou
Aspect sentiment quad prediction (ASQP) is a critical subtask of aspect-level sentiment analysis. Current ASQP datasets are characterized by their small size and low quadruple density, which hinders technical development. To expand capacity, we construct two large Chinese ASQP datasets crawled from multiple online platforms. The datasets hold several significant characteristics: larger size (each with 10,000+ samples) and rich aspect categories, more words per sentence, and higher density than existing ASQP datasets. Moreover, we are the first to evaluate the performance of Generative Pre-trained Transformer (GPT) series models on ASQP and exhibit potential issues. The experiments with state-of-the-art ASQP baselines underscore the need to explore additional techniques to address ASQP, as well as the importance of further investigation into methods to improve the performance of GPTs.
Authors: Changdae Oh, Mijoo Kim, Hyesu Lim, Junhyeok Park, Euiseog Jeong, Zhi-Qi Cheng, Kyungwoo Song
While fine-tuning unleashes the potential of a pre-trained model to a specific task, it trades off the model's generalization capability on out-of-distribution (OOD) datasets. To mitigate this, robust fine-tuning aims to ensure performance on OOD datasets as well as an in-distribution (ID) dataset for which the model is being tuned. However, another criterion for reliable machine learning (ML), confidence calibration, has been overlooked despite its increasing demand for real-world high-stakes ML applications (e.g., autonomous driving and medical diagnosis). For the first time, we raise concerns about the calibration of fine-tuned vision-language models (VLMs) under distribution shift by showing that naive fine-tuning and even state-of-the-art robust fine-tuning methods hurt the calibration of pre-trained VLMs, especially on OOD datasets. To address this, we provide a simple approach, called a calibrated robust fine-tuning (CaRot) that incentivizes the calibration and robustness on both ID and OOD datasets. Empirical results on ImageNet-1K distribution shift evaluation verify the effectiveness of our method.
Authors: Manwen Liao, Yan Zhu, Giulio Chiribella, Yuxiang Yang
Neural networks have shown their effectiveness in various tasks in the realm of quantum computing. However, their application in quantum error mitigation, a crucial step towards realizing practical quantum advancements, has been restricted by reliance on noise-free statistics. To tackle this critical challenge, we propose a data augmentation empowered neural model for error mitigation (DAEM). Our model does not require any prior knowledge about the specific noise type and measurement settings and can estimate noise-free statistics solely from the noisy measurement results of the target quantum process, rendering it highly suitable for practical implementation. In numerical experiments, we show the model's superior performance in mitigating various types of noise, including Markovian noise and Non-Markovian noise, compared with previous error mitigation methods. We further demonstrate its versatility by employing the model to mitigate errors in diverse types of quantum processes, including those involving large-scale quantum systems and continuous-variable quantum states. This powerful data augmentation-empowered neural model for error mitigation establishes a solid foundation for realizing more reliable and robust quantum technologies in practical applications.
Authors: Kaiqiang Lin, Muhammad Asad Ullah, Hirley Alves, Konstantin Mikhaylov, Tong Hao
The integration of subterranean LoRaWAN and non-terrestrial networks (NTN) delivers substantial economic and societal benefits in remote agriculture and disaster rescue operations. The LoRa modulation leverages quasi-orthogonal spreading factors (SFs) to optimize data rates, airtime, coverage and energy consumption. However, it is still challenging to effectively assign SFs to end devices for minimizing co-SF interference in massive subterranean LoRaWAN NTN. To address this, we investigate a reinforcement learning (RL)-based SFs allocation scheme to optimize the system's energy efficiency (EE). To efficiently capture the device-to-environment interactions in dense networks, we proposed an SFs allocation technique using the multi-agent dueling double deep Q-network (MAD3QN) and the multi-agent advantage actor-critic (MAA2C) algorithms based on an analytical reward mechanism. Our proposed RL-based SFs allocation approach evinces better performance compared to four benchmarks in the extreme underground direct-to-satellite scenario. Remarkably, MAD3QN shows promising potentials in surpassing MAA2C in terms of convergence rate and EE.
Authors: Siqi Shen, Chennan Ma, Chao Li, Weiquan Liu, Yongquan Fu, Songzhu Mei, Xinwang Liu, Cheng Wang
Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks. In the context of Multi-Agent Reinforcement Learning (MARL), learning coordinated and decentralized policies that are sensitive to risk is challenging. To formulate the coordination requirements in risk-sensitive MARL, we introduce the Risk-sensitive Individual-Global-Max (RIGM) principle as a generalization of the Individual-Global-Max (IGM) and Distributional IGM (DIGM) principles. This principle requires that the collection of risk-sensitive action selections of each agent should be equivalent to the risk-sensitive action selection of the central policy. Current MARL value factorization methods do not satisfy the RIGM principle for common risk metrics such as the Value at Risk (VaR) metric or distorted risk measurements. Therefore, we propose RiskQ to address this limitation, which models the joint return distribution by modeling quantiles of it as weighted quantile mixtures of per-agent return distribution utilities. RiskQ satisfies the RIGM principle for the VaR and distorted risk metrics. We show that RiskQ can obtain promising performance through extensive experiments. The source code of RiskQ is available in https://github.com/xmu-rl-3dv/RiskQ.
Authors: Randy Zakya Suchrady, Ayu Purwarianti
Aspect-based sentiment analysis is a method in natural language processing aimed at identifying and understanding sentiments related to specific aspects of an entity. Aspects are words or phrases that represent an aspect or attribute of a particular entity. Previous research has utilized generative pre-trained language models to perform aspect-based sentiment analysis. LEGO-ABSA is one framework that has successfully employed generative pre-trained language models in aspect-based sentiment analysis, particularly in English. LEGO-ABSA uses a multitask learning and prompting approach to enhance model performance. However, the application of this approach has not been done in the context of Bahasa Indonesia. Therefore, this research aims to implement the multitask learning and prompting approach in aspect-based sentiment analysis for Bahasa Indonesia using generative pre-trained language models. In this study, the Indo LEGO-ABSA model is developed, which is an aspect-based sentiment analysis model utilizing generative pre-trained language models and trained with multitask learning and prompting. Indo LEGO-ABSA is trained with a hotel domain dataset in the Indonesian language. The obtained results include an f1-score of 79.55% for the Aspect Sentiment Triplet Extraction task, 86.09% for Unified Aspect-based Sentiment Analysis, 79.85% for Aspect Opinion Pair Extraction, 87.45% for Aspect Term Extraction, and 88.09% for Opinion Term Extraction. Indo LEGO-ABSA adopts the LEGO-ABSA framework that employs the T5 model, specifically mT5, by applying multitask learning to train all tasks within aspect-based sentiment analysis.
Authors: Jiaqi Wu, Junbiao Pang, Qingming Huang
Semi-supervised pose estimation is a practically challenging task for computer vision. Although numerous excellent semi-supervised classification methods have emerged, these methods typically use confidence to evaluate the quality of pseudo-labels, which is difficult to achieve in pose estimation tasks. For example, in pose estimation, confidence represents only the possibility that a position of the heatmap is a keypoint, not the quality of that prediction. In this paper, we propose a simple yet efficient framework to estimate the quality of pseudo-labels in semi-supervised pose estimation tasks from the perspective of modeling the uncertainty of the pseudo-labels. Concretely, under the dual mean-teacher framework, we construct the two maximum discrepant students (MDSs) to effectively push two teachers to generate different decision boundaries for the same sample. Moreover, we create multiple uncertainties to assess the quality of the pseudo-labels. Experimental results demonstrate that our method improves the performance of semi-supervised pose estimation on three datasets.
Authors: Guoxing Yang, Jianyu Shi, Zan Wang, Xiaohong Liu, Guangyu Wang
Pre-training and fine-tuning have emerged as a promising paradigm across various natural language processing (NLP) tasks. The effectiveness of pretrained large language models (LLM) has witnessed further enhancement, holding potential for applications in the field of medicine, particularly in the context of Traditional Chinese Medicine (TCM). However, the application of these general models to specific domains often yields suboptimal results, primarily due to challenges like lack of domain knowledge, unique objectives, and computational efficiency. Furthermore, their effectiveness in specialized domains, such as Traditional Chinese Medicine, requires comprehensive evaluation. To address the above issues, we propose a novel domain specific TCMDA (TCM Domain Adaptation) approach, efficient pre-training with domain-specific corpus. Specifically, we first construct a large TCM-specific corpus, TCM-Corpus-1B, by identifying domain keywords and retreving from general corpus. Then, our TCMDA leverages the LoRA which freezes the pretrained model's weights and uses rank decomposition matrices to efficiently train specific dense layers for pre-training and fine-tuning, efficiently aligning the model with TCM-related tasks, namely TCM-GPT-7B. We further conducted extensive experiments on two TCM tasks, including TCM examination and TCM diagnosis. TCM-GPT-7B archived the best performance across both datasets, outperforming other models by relative increments of 17% and 12% in accuracy, respectively. To the best of our knowledge, our study represents the pioneering validation of domain adaptation of a large language model with 7 billion parameters in TCM domain. We will release both TCMCorpus-1B and TCM-GPT-7B model once accepted to facilitate interdisciplinary development in TCM and NLP, serving as the foundation for further study.
Authors: Yijia Zhang, Sicheng Zhang, Shijie Cao, Dayou Du, Jianyu Wei, Ting Cao, Ningyi Xu
Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Although floating-point (FP) formats show good performance in LLM quantization, they tend to perform poorly with small group sizes or sub-4 bits. We find the reason is that the absence of asymmetry in previous FP quantization makes it unsuitable for handling asymmetric value distribution of LLM weight tensors. In this work, we propose asymmetric FP quantization (AFPQ), which sets separate scales for positive and negative values. Our method leads to large accuracy improvements and can be easily plugged into other quantization methods, including GPTQ and AWQ, for better performance. Besides, no additional storage is needed compared with asymmetric integer (INT) quantization. The code is available at https://github.com/zhangsichengsjtu/AFPQ.
Authors: Tao Liu, Chenpeng Du, Shuai Fan, Feilong Chen, Kai Yu
Generating high-quality and person-generic visual dubbing remains a challenge. Recent innovation has seen the advent of a two-stage paradigm, decoupling the rendering and lip synchronization process facilitated by intermediate representation as a conduit. Still, previous methodologies rely on rough landmarks or are confined to a single speaker, thus limiting their performance. In this paper, we propose DiffDub: Diffusion-based dubbing. We first craft the Diffusion auto-encoder by an inpainting renderer incorporating a mask to delineate editable zones and unaltered regions. This allows for seamless filling of the lower-face region while preserving the remaining parts. Throughout our experiments, we encountered several challenges. Primarily, the semantic encoder lacks robustness, constricting its ability to capture high-level features. Besides, the modeling ignored facial positioning, causing mouth or nose jitters across frames. To tackle these issues, we employ versatile strategies, including data augmentation and supplementary eye guidance. Moreover, we encapsulated a conformer-based reference encoder and motion generator fortified by a cross-attention mechanism. This enables our model to learn person-specific textures with varying references and reduces reliance on paired audio-visual data. Our rigorous experiments comprehensively highlight that our ground-breaking approach outpaces existing methods with considerable margins and delivers seamless, intelligible videos in person-generic and multilingual scenarios.
Authors: D. Dhinakaran, S. M. Udhaya Sankar, G. Elumalai, N. Jagadish kumar
A mobile ad hoc network is made up of a number of wireless portable nodes that spontaneously come together en route for establish a transitory network with no need for any central management. A mobile ad hoc network (MANET) is made up of a sizable and reasonably dense community of mobile nodes that travel across any terrain and rely solely on wireless interfaces for communication, not on any well before centralized management. Furthermore, routing be supposed to offer a method for instantly delivering data across a network between any two nodes. Finding the best packet routing from across infrastructure is the major issue, though. The proposed protocol's major goal is to identify the least-expensive nominal capacity acquisition that assures the transportation of realistic transport that ensures its durability in the event of any node failure. This study suggests the Optimized Route Selection via Red Imported Fire Ants (RIFA) Strategy as a way to improve on-demand source routing systems. Predicting Route Failure and energy Utilization is used to pick the path during the routing phase. Proposed work assess the results of the comparisons based on performance parameters like as energy usage, packet delivery rate (PDR), and end-to-end (E2E) delay. The outcome demonstrates that the proposed strategy is preferable and increases network lifetime while lowering node energy consumption and typical E2E delay under the majority of network performance measures and factors.
Authors: Shahar Jacob, Chen Shani, Dafna Shahaf
Analogy is one of the core capacities of human cognition; when faced with new situations, we often transfer prior experience from other domains. Most work on computational analogy relies heavily on complex, manually crafted input. In this work, we relax the input requirements, requiring only names of entities to be mapped. We automatically extract commonsense representations and use them to identify a mapping between the entities. Unlike previous works, our framework can handle partial analogies and suggest new entities to be added. Moreover, our method's output is easily interpretable, allowing for users to understand why a specific mapping was chosen.
Experiments show that our model correctly maps 81.2% of classical 2x2 analogy problems (guess level=50%). On larger problems, it achieves 77.8% accuracy (mean guess level=13.1%). In another experiment, we show our algorithm outperforms human performance, and the automatic suggestions of new entities resemble those suggested by humans. We hope this work will advance computational analogy by paving the way to more flexible, realistic input requirements, with broader applicability.
Authors: Leonardo Rigutini, Tiziano Papini, Marco Maggini, Franco Scarselli
The problem of relevance ranking consists of sorting a set of objects with respect to a given criterion. Since users may prefer different relevance criteria, the ranking algorithms should be adaptable to the user needs. Two main approaches exist in literature for the task of learning to rank: 1) a score function, learned by examples, which evaluates the properties of each object yielding an absolute relevance value that can be used to order the objects or 2) a pairwise approach, where a "preference function" is learned using pairs of objects to define which one has to be ranked first. In this paper, we present SortNet, an adaptive ranking algorithm which orders objects using a neural network as a comparator. The neural network training set provides examples of the desired ordering between pairs of items and it is constructed by an iterative procedure which, at each iteration, adds the most informative training examples. Moreover, the comparator adopts a connectionist architecture that is particularly suited for implementing a preference function. We also prove that such an architecture has the universal approximation property and can implement a wide class of functions. Finally, the proposed algorithm is evaluated on the LETOR dataset showing promising performances in comparison with other state of the art algorithms.
Authors: Chen Shani, Jilles Vreeken, Dafna Shahaf
Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular, state-of-the-art large language models (LLMs) work at the level of tokens, not concepts.
In this work, we analyze how well contemporary LLMs capture human concepts and their structure. We then discuss ways to develop concept-aware LLMs, taking place at different stages of the pipeline. We sketch a method for pretraining LLMs using concepts, and also explore the simpler approach that uses the output of existing LLMs. Despite its simplicity, our proof-of-concept is shown to better match human intuition, as well as improve the robustness of predictions. These preliminary results underscore the promise of concept-aware LLMs.
Authors: Jinrui Yang, Timothy Baldwin, Trevor Cohn
We present Multi-EuP, a new multilingual benchmark dataset, comprising 22K multi-lingual documents collected from the European Parliament, spanning 24 languages. This dataset is designed to investigate fairness in a multilingual information retrieval (IR) context to analyze both language and demographic bias in a ranking context. It boasts an authentic multilingual corpus, featuring topics translated into all 24 languages, as well as cross-lingual relevance judgments. Furthermore, it offers rich demographic information associated with its documents, facilitating the study of demographic bias. We report the effectiveness of Multi-EuP for benchmarking both monolingual and multilingual IR. We also conduct a preliminary experiment on language bias caused by the choice of tokenization strategy.
Authors: J. Zhao, J. Li, M. Chen, S. Jadhav
Functional Data Analysis (FDA) is a statistical domain developed to handle functional data characterized by high dimensionality and complex data structures. Sequential Neural Networks (SNNs) are specialized neural networks capable of processing sequence data, a fundamental aspect of functional data. Despite their great flexibility in modeling functional data, SNNs have been inadequately employed in the FDA community. One notable advantage of SNNs is the ease of implementation, making them accessible to a broad audience beyond academia. Conversely, FDA-based methodologies present challenges, particularly for practitioners outside the field, due to their intricate complexity. In light of this, we propose utilizing SNNs in FDA applications and demonstrate their effectiveness through comparative analyses against popular FDA regression models based on numerical experiments and real-world data analysis. SNN architectures allow us to surpass the limitations of traditional FDA methods, offering scalability, flexibility, and improved analytical performance. Our findings highlight the potential of SNN-based methodologies as powerful tools for data applications involving functional data.
Authors: Mingze Yuan, Peng Bao, Jiajia Yuan, Yunhao Shen, Zifan Chen, Yi Xie, Jie Zhao, Yang Chen, Li Zhang, Lin Shen, Bin Dong
With the rapid development of artificial intelligence, large language models (LLMs) have shown promising capabilities in mimicking human-level language comprehension and reasoning. This has sparked significant interest in applying LLMs to enhance various aspects of healthcare, ranging from medical education to clinical decision support. However, medicine involves multifaceted data modalities and nuanced reasoning skills, presenting challenges for integrating LLMs. This paper provides a comprehensive review on the applications and implications of LLMs in medicine. It begins by examining the fundamental applications of general-purpose and specialized LLMs, demonstrating their utilities in knowledge retrieval, research support, clinical workflow automation, and diagnostic assistance. Recognizing the inherent multimodality of medicine, the review then focuses on multimodal LLMs, investigating their ability to process diverse data types like medical imaging and EHRs to augment diagnostic accuracy. To address LLMs' limitations regarding personalization and complex clinical reasoning, the paper explores the emerging development of LLM-powered autonomous agents for healthcare. Furthermore, it summarizes the evaluation methodologies for assessing LLMs' reliability and safety in medical contexts. Overall, this review offers an extensive analysis on the transformative potential of LLMs in modern medicine. It also highlights the pivotal need for continuous optimizations and ethical oversight before these models can be effectively integrated into clinical practice. Visit https://github.com/mingze-yuan/Awesome-LLM-Healthcare for an accompanying GitHub repository containing latest papers.
Authors: Tobias Katsch
Linear Recurrence has proven to be a powerful tool for modeling long sequences efficiently. In this work, we show that existing models fail to take full advantage of its potential. Motivated by this finding, we develop GateLoop, a foundational sequence model that generalizes linear recurrent models such as S4, S5, LRU and RetNet, by employing data-controlled state transitions. Utilizing this theoretical advance, GateLoop empirically outperforms existing models for auto-regressive language modeling. Our method comes with a low-cost $O(l)$ recurrent mode and an efficient $O(l \log_{2} l)$ parallel mode making use of highly optimized associative scan implementations. Furthermore, we derive an $O(l^2)$ surrogate attention mode, revealing remarkable implications for Transformer and recently proposed architectures. Specifically, we prove that our approach can be interpreted as providing data-controlled relative-positional information to Attention. While many existing models solely rely on data-controlled cumulative sums for context aggregation, our findings suggest that incorporating data-controlled complex cumulative products may be a crucial step towards more powerful sequence models.
Authors: Steven R. Rick, Gianni Giacomelli, Haoran Wen, Robert J. Laubacher, Nancy Taubenslag, Jennifer L. Heyman, Max Sina Knicker, Younes Jeddi, Hendrik Maier, Stephen Dwyer, Pranav Ragupathy, Thomas W. Malone
Previous efforts to support creative problem-solving have included (a) techniques (such as brainstorming and design thinking) to stimulate creative ideas, and (b) software tools to record and share these ideas. Now, generative AI technologies can suggest new ideas that might never have occurred to the users, and users can then select from these ideas or use them to stimulate even more ideas. Here, we describe such a system, Supermind Ideator. The system uses a large language model (GPT 3.5) and adds prompting, fine tuning, and a user interface specifically designed to help people use creative problem-solving techniques. Some of these techniques can be applied to any problem; others are specifically intended to help generate innovative ideas about how to design groups of people and/or computers ("superminds"). We also describe our early experiences with using this system and suggest ways it could be extended to support additional techniques for other specific problem-solving domains.
Authors: Nasser Gyagenda (1), Hubert Roth (1) ((1) University of Siegen)
Although autonomous functioning facilitates deployment of robotic systems in domains that admit limited human oversight on our planet and beyond, finding correspondence between task requirements and autonomous capability is still an open challenge. Consequently, a number of methods for quantifying autonomy have been proposed over the last three decades, but to our knowledge all these have no discernment of sub-mode features of variation of autonomy and some are based on metrics that violet the Goodhart's law. This paper focuses on the full autonomous mode and proposes a task-requirements based autonomy assessment framework. The framework starts by establishing robot task characteristics from which three autonomy metrics, namely requisite capability, reliability and responsiveness, and functions for determining autonomy as a two-part measure, namely of level of autonomy and degree of autonomy are derived. These characteristics are founded on the realization that robots ultimately replace human skilled workers, to find a mapping between human job and robot task characteristics. The distinction between level and degree of autonomy stemmed from the acknowledgment that autonomy is not just a question of existence, but also one of performance of requisite capability. When continuously monitored, the proposed metrics provide a means of monitoring the integrity of a system. The framework has been demonstrated on two case studies, namely autonomous vehicle at an on-road dynamic driving task and the DARPA subT challenge rules analysis. The framework provides not only a tool for quantifying autonomy, but also a regulatory interface and common language for autonomous systems developers and users.
Authors: Stefan Kambiz Behfar, Jon Crowcroft
This study addresses the security challenges associated with the current internet transformations, specifically focusing on emerging technologies such as blockchain and decentralized storage. It also investigates the role of Web3 applications in shaping the future of the internet. The primary objective is to propose a novel design for 'smart certificates,' which are digital certificates that can be programmatically enforced. Utilizing such certificates, an enterprise can better protect itself from cyberattacks and ensure the security of its data and systems. Web3 recent security solutions by companies and projects like Certik, Forta, Slither, and Securify are the equivalent of code scanning tool that were originally developed for Web1 and Web2 applications, and definitely not like certificates to help enterprises feel safe against cyberthreats. We aim to improve the resilience of enterprises' digital infrastructure by building on top of Web3 application and put methodologies in place for vulnerability analysis and attack correlation, focusing on architecture of different layers, Wallet/Client, Application and Smart Contract, where specific components are provided to identify and predict threats and risks. Furthermore, Certificate Transparency is used for enhancing the security, trustworthiness and decentralized management of the certificates, and detecting misuses, compromises, and malfeasances.
Authors: M. Miró-Nicolau, A. Jaume-i-Capó, G. Moyà-Alcover
The evaluation of the fidelity of eXplainable Artificial Intelligence (XAI) methods to their underlying models is a challenging task, primarily due to the absence of a ground truth for explanations. However, assessing fidelity is a necessary step for ensuring a correct XAI methodology. In this study, we conduct a fair and objective comparison of the current state-of-the-art XAI methods by introducing three novel image datasets with reliable ground truth for explanations. The primary objective of this comparison is to identify methods with low fidelity and eliminate them from further research, thereby promoting the development of more trustworthy and effective XAI techniques. Our results demonstrate that XAI methods based on the backpropagation of output information to input yield higher accuracy and reliability compared to methods relying on sensitivity analysis or Class Activation Maps (CAM). However, the backpropagation method tends to generate more noisy saliency maps. These findings have significant implications for the advancement of XAI methods, enabling the elimination of erroneous explanations and fostering the development of more robust and reliable XAI.
Authors: Kun Zhou, Yutao Zhu, Zhipeng Chen, Wentong Chen, Wayne Xin Zhao, Xu Chen, Yankai Lin, Ji-Rong Wen, Jiawei Han
Large language models~(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for measuring the ability level of LLMs in different aspects. Despite that a number of high-quality benchmarks have been released, the concerns about the appropriate use of these benchmarks and the fair comparison of different models are increasingly growing. Considering these concerns, in this paper, we discuss the potential risk and impact of inappropriately using evaluation benchmarks and misleadingly interpreting the evaluation results. Specially, we focus on a special issue that would lead to inappropriate evaluation, \ie \emph{benchmark leakage}, referring that the data related to evaluation sets is occasionally used for model training. This phenomenon now becomes more common since pre-training data is often prepared ahead of model test. We conduct extensive experiments to study the effect of benchmark leverage, and find that it can dramatically boost the evaluation results, which would finally lead to an unreliable assessment of model performance. To improve the use of existing evaluation benchmarks, we finally present several guidelines for both LLM developers and benchmark maintainers. We hope this work can draw attention to appropriate training and evaluation of LLMs.
Authors: Alina Leidinger, Robert van Rooij, Ekaterina Shutova
The latest generation of LLMs can be prompted to achieve impressive zero-shot or few-shot performance in many NLP tasks. However, since performance is highly sensitive to the choice of prompts, considerable effort has been devoted to crowd-sourcing prompts or designing methods for prompt optimisation. Yet, we still lack a systematic understanding of how linguistic properties of prompts correlate with task performance. In this work, we investigate how LLMs of different sizes, pre-trained and instruction-tuned, perform on prompts that are semantically equivalent, but vary in linguistic structure. We investigate both grammatical properties such as mood, tense, aspect and modality, as well as lexico-semantic variation through the use of synonyms. Our findings contradict the common assumption that LLMs achieve optimal performance on lower perplexity prompts that reflect language use in pretraining or instruction-tuning data. Prompts transfer poorly between datasets or models, and performance cannot generally be explained by perplexity, word frequency, ambiguity or prompt length. Based on our results, we put forward a proposal for a more robust and comprehensive evaluation standard for prompting research.
Authors: Jiayuan Gu, Sean Kirmani, Paul Wohlhart, Yao Lu, Montserrat Gonzalez Arenas, Kanishka Rao, Wenhao Yu, Chuyuan Fu, Keerthana Gopalakrishnan, Zhuo Xu, Priya Sundaresan, Peng Xu, Hao Su, Karol Hausman, Chelsea Finn, Quan Vuong, Ted Xiao
Generalization remains one of the most important desiderata for robust robot learning systems. While recently proposed approaches show promise in generalization to novel objects, semantic concepts, or visual distribution shifts, generalization to new tasks remains challenging. For example, a language-conditioned policy trained on pick-and-place tasks will not be able to generalize to a folding task, even if the arm trajectory of folding is similar to pick-and-place. Our key insight is that this kind of generalization becomes feasible if we represent the task through rough trajectory sketches. We propose a policy conditioning method using such rough trajectory sketches, which we call RT-Trajectory, that is practical, easy to specify, and allows the policy to effectively perform new tasks that would otherwise be challenging to perform. We find that trajectory sketches strike a balance between being detailed enough to express low-level motion-centric guidance while being coarse enough to allow the learned policy to interpret the trajectory sketch in the context of situational visual observations. In addition, we show how trajectory sketches can provide a useful interface to communicate with robotic policies: they can be specified through simple human inputs like drawings or videos, or through automated methods such as modern image-generating or waypoint-generating methods. We evaluate RT-Trajectory at scale on a variety of real-world robotic tasks, and find that RT-Trajectory is able to perform a wider range of tasks compared to language-conditioned and goal-conditioned policies, when provided the same training data.
Authors: Sanjeeb Dash, Soumyadip Ghosh, Joao Goncalves, Mark S. Squillante
Model explainability is crucial for human users to be able to interpret how a proposed classifier assigns labels to data based on its feature values. We study generalized linear models constructed using sets of feature value rules, which can capture nonlinear dependencies and interactions. An inherent trade-off exists between rule set sparsity and its prediction accuracy. It is computationally expensive to find the right choice of sparsity -- e.g., via cross-validation -- with existing methods. We propose a new formulation to learn an ensemble of rule sets that simultaneously addresses these competing factors. Good generalization is ensured while keeping computational costs low by utilizing distributionally robust optimization. The formulation utilizes column generation to efficiently search the space of rule sets and constructs a sparse ensemble of rule sets, in contrast with techniques like random forests or boosting and their variants. We present theoretical results that motivate and justify the use of our distributionally robust formulation. Extensive numerical experiments establish that our method improves over competing methods -- on a large set of publicly available binary classification problem instances -- with respect to one or more of the following metrics: generalization quality, computational cost, and explainability.
Authors: Harshit Sikchi, Rohan Chitnis, Ahmed Touati, Alborz Geramifard, Amy Zhang, Scott Niekum
Offline Goal-Conditioned Reinforcement Learning (GCRL) is tasked with learning to achieve multiple goals in an environment purely from offline datasets using sparse reward functions. Offline GCRL is pivotal for developing generalist agents capable of leveraging pre-existing datasets to learn diverse and reusable skills without hand-engineering reward functions. However, contemporary approaches to GCRL based on supervised learning and contrastive learning are often suboptimal in the offline setting. An alternative perspective on GCRL optimizes for occupancy matching, but necessitates learning a discriminator, which subsequently serves as a pseudo-reward for downstream RL. Inaccuracies in the learned discriminator can cascade, negatively influencing the resulting policy. We present a novel approach to GCRL under a new lens of mixture-distribution matching, leading to our discriminator-free method: SMORe. The key insight is combining the occupancy matching perspective of GCRL with a convex dual formulation to derive a learning objective that can better leverage suboptimal offline data. SMORe learns scores or unnormalized densities representing the importance of taking an action at a state for reaching a particular goal. SMORe is principled and our extensive experiments on the fully offline GCRL benchmark composed of robot manipulation and locomotion tasks, including high-dimensional observations, show that SMORe can outperform state-of-the-art baselines by a significant margin.
Authors: Ashman Mehra, Snehanshu Saha, Vaskar Raychoudhury, Archana Mathur
Delivery of items from the producer to the consumer has experienced significant growth over the past decade and has been greatly fueled by the recent pandemic. Amazon Fresh, Shopify, UberEats, InstaCart, and DoorDash are rapidly growing and are sharing the same business model of consumer items or food delivery. Existing food delivery methods are sub-optimal because each delivery is individually optimized to go directly from the producer to the consumer via the shortest time path. We observe a significant scope for reducing the costs associated with completing deliveries under the current model. We model our food delivery problem as a multi-objective optimization, where consumer satisfaction and delivery costs, both, need to be optimized. Taking inspiration from the success of ride-sharing in the taxi industry, we propose DeliverAI - a reinforcement learning-based path-sharing algorithm. Unlike previous attempts for path-sharing, DeliverAI can provide real-time, time-efficient decision-making using a Reinforcement learning-enabled agent system. Our novel agent interaction scheme leverages path-sharing among deliveries to reduce the total distance traveled while keeping the delivery completion time under check. We generate and test our methodology vigorously on a simulation setup using real data from the city of Chicago. Our results show that DeliverAI can reduce the delivery fleet size by 12\%, the distance traveled by 13%, and achieve 50% higher fleet utilization compared to the baselines.
Authors: Manjie Xu, Guangyuan Jiang, Wei Liang, Chi Zhang, Yixin Zhu
Recent advances in vision-language learning have achieved notable success on complete-information question-answering datasets through the integration of extensive world knowledge. Yet, most models operate passively, responding to questions based on pre-stored knowledge. In stark contrast, humans possess the ability to actively explore, accumulate, and reason using both newfound and existing information to tackle incomplete-information questions. In response to this gap, we introduce $Conan$, an interactive open-world environment devised for the assessment of active reasoning. $Conan$ facilitates active exploration and promotes multi-round abductive inference, reminiscent of rich, open-world settings like Minecraft. Diverging from previous works that lean primarily on single-round deduction via instruction following, $Conan$ compels agents to actively interact with their surroundings, amalgamating new evidence with prior knowledge to elucidate events from incomplete observations. Our analysis on $Conan$ underscores the shortcomings of contemporary state-of-the-art models in active exploration and understanding complex scenarios. Additionally, we explore Abduction from Deduction, where agents harness Bayesian rules to recast the challenge of abduction as a deductive process. Through $Conan$, we aim to galvanize advancements in active reasoning and set the stage for the next generation of artificial intelligence agents adept at dynamically engaging in environments.
Authors: Miguel Contreras, Brandon Silva, Benjamin Shickel, Tezcan Ozrazgat Baslanti, Yuanfang Ren, Ziyuan Guan, Sabyasachi Bandyopadhyay, Kia Khezeli, Azra Bihorac, Parisa Rashidi
The acuity state of patients in the intensive care unit (ICU) can quickly change from stable to unstable, sometimes leading to life-threatening conditions. Early detection of deteriorating conditions can result in providing more timely interventions and improved survival rates. Current approaches rely on manual daily assessments. Some data-driven approaches have been developed, that use mortality as a proxy of acuity in the ICU. However, these methods do not integrate acuity states to determine the stability of a patient or the need for life-sustaining therapies. In this study, we propose APRICOT (Acuity Prediction in Intensive Care Unit), a Transformer-based neural network to predict acuity state in real-time in ICU patients. We develop and extensively validate externally, temporally, and prospectively the APRICOT model on three large datasets: University of Florida Health (UFH), eICU Collaborative Research Database (eICU), and Medical Information Mart for Intensive Care (MIMIC)-IV. The performance of APRICOT shows comparable results to state-of-the-art mortality prediction models (external AUROC 0.93-0.93, temporal AUROC 0.96-0.98, and prospective AUROC 0.98) as well as acuity prediction models (external AUROC 0.80-0.81, temporal AUROC 0.77-0.78, and prospective AUROC 0.87). Furthermore, APRICOT can make predictions for the need for life-sustaining therapies, showing comparable results to state-of-the-art ventilation prediction models (external AUROC 0.80-0.81, temporal AUROC 0.87-0.88, and prospective AUROC 0.85), and vasopressor prediction models (external AUROC 0.82-0.83, temporal AUROC 0.73-0.75, prospective AUROC 0.87). This tool allows for real-time acuity monitoring of a patient and can provide helpful information to clinicians to make timely interventions. Furthermore, the model can suggest life-sustaining therapies that the patient might need in the next hours in the ICU.
Authors: Florian Fürrutter, Gorka Muñoz-Gil, Hans J. Briegel
Quantum computing has recently emerged as a transformative technology. Yet, its promised advantages rely on efficiently translating quantum operations into viable physical realizations. In this work, we use generative machine learning models, specifically denoising diffusion models (DMs), to facilitate this transformation. Leveraging text-conditioning, we steer the model to produce desired quantum operations within gate-based quantum circuits. Notably, DMs allow to sidestep during training the exponential overhead inherent in the classical simulation of quantum dynamics -- a consistent bottleneck in preceding ML techniques. We demonstrate the model's capabilities across two tasks: entanglement generation and unitary compilation. The model excels at generating new circuits and supports typical DM extensions such as masking and editing to, for instance, align the circuit generation to the constraints of the targeted quantum device. Given their flexibility and generalization abilities, we envision DMs as pivotal in quantum circuit synthesis, enhancing both practical applications but also insights into theoretical quantum computation.
Authors: Alexey Tikhonov, Ivan P. Yamshchikov
In the rapidly evolving landscape of Large Language Models (LLMs), introduction of well-defined and standardized evaluation methodologies remains a crucial challenge. This paper traces the historical trajectory of LLM evaluations, from the foundational questions posed by Alan Turing to the modern era of AI research. We categorize the evolution of LLMs into distinct periods, each characterized by its unique benchmarks and evaluation criteria. As LLMs increasingly mimic human-like behaviors, traditional evaluation proxies, such as the Turing test, have become less reliable. We emphasize the pressing need for a unified evaluation system, given the broader societal implications of these models. Through an analysis of common evaluation methodologies, we advocate for a qualitative shift in assessment approaches, underscoring the importance of standardization and objective criteria. This work serves as a call for the AI community to collaboratively address the challenges of LLM evaluation, ensuring their reliability, fairness, and societal benefit.
Authors: David Bertoin (ISAE-SUPAERO), Jérôme Bolte (TSE-R), Sébastien Gerchinovitz (IMT), Edouard Pauwels (IRIT-ADRIA)
In theory, the choice of ReLU(0) in [0, 1] for a neural network has a negligible influence both on backpropagation and training. Yet, in the real world, 32 bits default precision combined with the size of deep learning problems makes it a hyperparameter of training methods. We investigate the importance of the value of ReLU'(0) for several precision levels (16, 32, 64 bits), on various networks (fully connected, VGG, ResNet) and datasets (MNIST, CIFAR10, SVHN, ImageNet). We observe considerable variations of backpropagation outputs which occur around half of the time in 32 bits precision. The effect disappears with double precision, while it is systematic at 16 bits. For vanilla SGD training, the choice ReLU'(0) = 0 seems to be the most efficient. For our experiments on ImageNet the gain in test accuracy over ReLU'(0) = 1 was more than 10 points (two runs). We also evidence that reconditioning approaches as batch-norm or ADAM tend to buffer the influence of ReLU'(0)'s value. Overall, the message we convey is that algorithmic differentiation of nonsmooth problems potentially hides parameters that could be tuned advantageously.
Authors: Yun William Yu
Minimizers and convolutional neural networks (CNNs) are two quite distinct popular techniques that have both been employed to analyze categorical biological sequences. At face value, the methods seem entirely dissimilar. Minimizers use min-wise hashing on a rolling window to extract a single important k-mer feature per window. CNNs start with a wide array of randomly initialized convolutional filters, paired with a pooling operation, and then multiple additional neural layers to learn both the filters themselves and how they can be used to classify the sequence.
Here, our main result is a careful mathematical analysis of hash function properties showing that for sequences over a categorical alphabet, random Gaussian initialization of convolutional filters with max-pooling is equivalent to choosing a minimizer ordering such that selected k-mers are (in Hamming distance) far from the k-mers within the sequence but close to other minimizers. In empirical experiments, we find that this property manifests as decreased density in repetitive regions, both in simulation and on real human telomeres. We additionally train from scratch a CNN embedding of synthetic short-reads from the SARS-CoV-2 genome into 3D Euclidean space that locally recapitulates the linear sequence distance of the read origins, a modest step towards building a deep learning assembler, though it is at present too slow to be practical. In total, this manuscript provides a partial explanation for the effectiveness of CNNs in categorical sequence analysis.
Authors: Wilka Carvalho, Andrew Lampinen, Kyriacos Nikiforou, Felix Hill, Murray Shanahan
Many important tasks are defined in terms of object. To generalize across these tasks, a reinforcement learning (RL) agent needs to exploit the structure that the objects induce. Prior work has either hard-coded object-centric features, used complex object-centric generative models, or updated state using local spatial features. However, these approaches have had limited success in enabling general RL agents. Motivated by this, we introduce "Feature-Attending Recurrent Modules" (FARM), an architecture for learning state representations that relies on simple, broadly applicable inductive biases for capturing spatial and temporal regularities. FARM learns a state representation that is distributed across multiple modules that each attend to spatiotemporal features with an expressive feature attention mechanism. We show that this improves an RL agent's ability to generalize across object-centric tasks. We study task suites in both 2D and 3D environments and find that FARM better generalizes compared to competing architectures that leverage attention or multiple modules.
Authors: Wei Ye, Zexi Huang, Yunqi Hong, Ambuj Singh
Graph Convolutional Networks (GCN) is a pioneering model for graph-based semi-supervised learning. However, GCN does not perform well on sparsely-labeled graphs. Its two-layer version cannot effectively propagate the label information to the whole graph structure (i.e., the under-smoothing problem) while its deep version over-smoothens and is hard to train (i.e., the over-smoothing problem). To solve these two issues, we propose a new graph neural network called GND-Nets (for Graph Neural Diffusion Networks) that exploits the local and global neighborhood information of a vertex in a single layer. Exploiting the shallow network mitigates the over-smoothing problem while exploiting the local and global neighborhood information mitigates the under-smoothing problem. The utilization of the local and global neighborhood information of a vertex is achieved by a new graph diffusion method called neural diffusions, which integrate neural networks into the conventional linear and nonlinear graph diffusions. The adoption of neural networks makes neural diffusions adaptable to different datasets. Extensive experiments on various sparsely-labeled graphs verify the effectiveness and efficiency of GND-Nets compared to state-of-the-art approaches.
Authors: Luca Herranz-Celotti, Jean Rouat
Spiking Neuromorphic Computing uses binary activity to improve Artificial Intelligence energy efficiency. However, the non-smoothness of binary activity requires approximate gradients, known as Surrogate Gradients (SG), to close the performance gap with Deep Learning. Several SG have been proposed in the literature, but it remains unclear how to determine the best SG for a given task and network. Good performance can be achieved with most SG shapes, after a costly search of hyper-parameters. Thus, we aim at experimentally and theoretically define the best SG across different stress tests, to reduce future need of grid search. To understand the gap for this line of work, we show that more complex tasks and networks need more careful choice of SG, even if overall the derivative of the fast sigmoid outperforms other SG across tasks and networks, for a wide range of learning rates. We therefore design a stability based theoretical method to choose initialization and SG shape before training on the most common spiking architecture, the Leaky Integrate and Fire (LIF). Since our stability method suggests the use of high firing rates at initialization, which is non-standard in the neuromorphic literature, we show that high initial firing rates, combined with a sparsity encouraging loss term introduced gradually, can lead to better generalization, depending on the SG shape. Our stability based theoretical solution, finds a SG and initialization that experimentally result in improved accuracy. We show how it can be used to reduce the need of extensive grid-search of dampening, sharpness and tail-fatness of the SG.
Authors: Weijie Zheng, Benjamin Doerr
Estimation-of-distribution algorithms (EDAs) are optimization algorithms that learn a distribution on the search space from which good solutions can be sampled easily. A key parameter of most EDAs is the sample size (population size). If the population size is too small, the update of the probabilistic model builds on few samples, leading to the undesired effect of genetic drift. Too large population sizes avoid genetic drift, but slow down the process.
Building on a recent quantitative analysis of how the population size leads to genetic drift, we design a smart-restart mechanism for EDAs. By stopping runs when the risk for genetic drift is high, it automatically runs the EDA in good parameter regimes.
Via a mathematical runtime analysis, we prove a general performance guarantee for this smart-restart scheme. This in particular shows that in many situations where the optimal (problem-specific) parameter values are known, the restart scheme automatically finds these, leading to the asymptotically optimal performance.
We also conduct an extensive experimental analysis. On four classic benchmark problems, we clearly observe the critical influence of the population size on the performance, and we find that the smart-restart scheme leads to a performance close to the one obtainable with optimal parameter values. Our results also show that previous theory-based suggestions for the optimal population size can be far from the optimal ones, leading to a performance clearly inferior to the one obtained via the smart-restart scheme. We also conduct experiments with PBIL (cross-entropy algorithm) on two combinatorial optimization problems from the literature, the max-cut problem and the bipartition problem. Again, we observe that the smart-restart mechanism finds much better values for the population size than those suggested in the literature, leading to a much better performance.
Authors: Xinzhe Ni, Yong Liu, Hao Wen, Yatai Ji, Jing Xiao, Yujiu Yang
Current methods for few-shot action recognition mainly fall into the metric learning framework following ProtoNet, which demonstrates the importance of prototypes. Although they achieve relatively good performance, the effect of multimodal information is ignored, e.g. label texts. In this work, we propose a novel MultimOdal PRototype-ENhanced Network (MORN), which uses the semantic information of label texts as multimodal information to enhance prototypes. A CLIP visual encoder and a frozen CLIP text encoder are introduced to obtain features with good multimodal initialization. Then in the visual flow, visual prototypes are computed by a Temporal-Relational CrossTransformer (TRX) module for example. In the text flow, a semantic-enhanced (SE) module and an inflating operation are used to obtain text prototypes. The final multimodal prototypes are then computed by a multimodal prototype-enhanced (MPE) module. Besides, we define a PRototype SImilarity DiffErence (PRIDE) to evaluate the quality of prototypes, which is used to verify our improvement on the prototype level and effectiveness of MORN. We conduct extensive experiments on four popular datasets, and MORN achieves state-of-the-art results on HMDB51, UCF101, Kinetics and SSv2. When plugging PRIDE into the training stage, the performance can be further improved.
Authors: David Lindner, János Kramár, Sebastian Farquhar, Matthew Rahtz, Thomas McGrath, Vladimir Mikulik
We show how to "compile" human-readable programs into standard decoder-only transformer models. Our compiler, Tracr, generates models with known structure. This structure can be used to design experiments. For example, we use it to study "superposition" in transformers that execute multi-step algorithms. Additionally, the known structure of Tracr-compiled models can serve as ground-truth for evaluating interpretability methods. Commonly, because the "programs" learned by transformers are unknown it is unclear whether an interpretation succeeded. We demonstrate our approach by implementing and examining programs including computing token frequencies, sorting, and parenthesis checking. We provide an open-source implementation of Tracr at https://github.com/google-deepmind/tracr.
Authors: Manuel Brack, Felix Friedrich, Dominik Hintersdorf, Lukas Struppek, Patrick Schramowski, Kristian Kersting
Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. However, achieving one-shot generation that aligns with the user's intent is nearly impossible, yet small changes to the input prompt often result in very different images. This leaves the user with little semantic control. To put the user in control, we show how to interact with the diffusion process to flexibly steer it along semantic directions. This semantic guidance (SEGA) generalizes to any generative architecture using classifier-free guidance. More importantly, it allows for subtle and extensive edits, changes in composition and style, as well as optimizing the overall artistic conception. We demonstrate SEGA's effectiveness on both latent and pixel-based diffusion models such as Stable Diffusion, Paella, and DeepFloyd-IF using a variety of tasks, thus providing strong evidence for its versatility, flexibility, and improvements over existing methods.
Authors: Zhiwei Xu, Min Zhou, Xibin Zhao, Yang Chen, Xi Cheng, Hongyu Zhang
The application of deep learning techniques in software engineering becomes increasingly popular. One key problem is developing high-quality and easy-to-use source code representations for code-related tasks. The research community has acquired impressive results in recent years. However, due to the deployment difficulties and performance bottlenecks, seldom these approaches are applied to the industry. In this paper, we present xASTNN, an eXtreme Abstract Syntax Tree (AST)-based Neural Network for source code representation, aiming to push this technique to industrial practice. The proposed xASTNN has three advantages. First, xASTNN is completely based on widely-used ASTs and does not require complicated data pre-processing, making it applicable to various programming languages and practical scenarios. Second, three closely-related designs are proposed to guarantee the effectiveness of xASTNN, including statement subtree sequence for code naturalness, gated recursive unit for syntactical information, and gated recurrent unit for sequential information. Third, a dynamic batching algorithm is introduced to significantly reduce the time complexity of xASTNN. Two code comprehension downstream tasks, code classification and code clone detection, are adopted for evaluation. The results demonstrate that our xASTNN can improve the state-of-the-art while being faster than the baselines.
Authors: Mark Stefik
The vision of AI collaborators has long been a staple of stories and science fiction, where artificial agents understand nuances of collaboration and human communication. They assist their human partners and teams and have special talents. Government advisory groups and leaders in AI have advocated for years that AIs should be human compatible and effective collaborators. Nonetheless, robust AIs that collaborate like talented people remain out of reach. The simpler dream of effective information tools that augment human intelligence (IA) has its roots in the 1960s and helped to drive an information technology revolution. With the vast increase in hybrid and remote work since the COVID pandemic, the benefits and requirements for better coordination, collaboration, and communication are in focus for the workplace. Many factors (such as the costs of homes near work) are impeding a mass return to in-person work at the office. Are human-like AI teammates part of a solution? If we just need better tools for collaboration, how artificially intelligent (AI) could and should these tools be? This position paper reviews the arc of technology and calls by others for human-machine teaming. It draws on earlier research in psychology and the social sciences about what human-like collaboration actually requires. This paper argues that current mainstream AI cannot produce robust, intelligent, and human-compatible collaborators. It sets a context for a second paper that proposes exploring a radical shift in technology and methodology for creating resilient, intelligent, and human-compatible AIs (Stefik & Price, 2023). The aspirational goal is that such AIs would learn, share what they learn, and collaborate to achieve high standards.
Authors: Ben Prystawski, Michael Y. Li, Noah D. Goodman
Humans have a powerful and mysterious capacity to reason. Working through a set of mental steps enables us to make inferences we would not be capable of making directly even though we get no additional data from the world. Similarly, when large language models generate intermediate steps (a chain of thought) before answering a question, they often produce better answers than they would directly. We investigate why and how chain-of-thought reasoning is useful in language models, testing the hypothesis that reasoning is effective when training data consists of overlapping local clusters of variables that influence each other strongly. These training conditions enable the chaining of accurate local inferences to estimate relationships between variables that were not seen together in training. We prove that there will exist a "reasoning gap", where reasoning through intermediate variables reduces bias, for the simple case of an autoregressive density estimator trained on local samples from a chain-structured probabilistic model. We then test our hypothesis experimentally in more complex models, training an autoregressive language model on samples from Bayes nets but only including a subset of variables in each sample. We test language models' ability to match conditional probabilities with and without intermediate reasoning steps, finding that intermediate steps are only helpful when the training data is locally structured with respect to dependencies between variables. The combination of locally structured observations and reasoning is much more data-efficient than training on all variables. Our results illustrate how the effectiveness of reasoning step by step is rooted in the local statistical structure of the training data.
Authors: Yingqiang Ge, Wenyue Hua, Kai Mei, Jianchao Ji, Juntao Tan, Shuyuan Xu, Zelong Li, Yongfeng Zhang
Human Intelligence (HI) excels at combining basic skills to solve complex tasks. This capability is vital for Artificial Intelligence (AI) and should be embedded in comprehensive AI Agents, enabling them to harness expert models for complex task-solving towards Artificial General Intelligence (AGI). Large Language Models (LLMs) show promising learning and reasoning abilities, and can effectively use external models, tools, plugins, or APIs to tackle complex problems. In this work, we introduce OpenAGI, an open-source AGI research and development platform designed for solving multi-step, real-world tasks. Specifically, OpenAGI uses a dual strategy, integrating standard benchmark tasks for benchmarking and evaluation, and open-ended tasks including more expandable models, tools, plugins, or APIs for creative problem-solving. Tasks are presented as natural language queries to the LLM, which then selects and executes appropriate models. We also propose a Reinforcement Learning from Task Feedback (RLTF) mechanism that uses task results to improve the LLM's task-solving ability, which creates a self-improving AI feedback loop. While we acknowledge that AGI is a broad and multifaceted research challenge with no singularly defined solution path, the integration of LLMs with domain-specific expert models, inspired by mirroring the blend of general and specialized intelligence in humans, offers a promising approach towards AGI. We are open-sourcing the OpenAGI project's code, dataset, benchmarks, evaluation methods, and the UI demo to foster community involvement in AGI advancement: https://github.com/agiresearch/OpenAGI.
Authors: Mohammadreza Pourreza, Davood Rafiei
There is currently a significant gap between the performance of fine-tuned models and prompting approaches using Large Language Models (LLMs) on the challenging task of text-to-SQL, as evaluated on datasets such as Spider. To improve the performance of LLMs in the reasoning process, we study how decomposing the task into smaller sub-tasks can be effective. In particular, we show that breaking down the generation problem into sub-problems and feeding the solutions of those sub-problems into LLMs can be an effective approach for significantly improving their performance. Our experiments with three LLMs show that this approach consistently improves their simple few-shot performance by roughly 10%, pushing the accuracy of LLMs towards SOTA or surpassing it. On the holdout test set of Spider, the SOTA, in terms of execution accuracy, was 79.9 and the new SOTA at the time of this writing using our approach is 85.3. Our approach with in-context learning beats many heavily fine-tuned models by at least 5%. Additionally, when evaluated on the BIRD benchmark, our approach achieved an execution accuracy of 55.9%, setting a new SOTA on its holdout test set.
Authors: Sascha Marton, Stefan Lüdtke, Christian Bartelt, Heiner Stuckenschmidt
Decision Trees (DTs) are commonly used for many machine learning tasks due to their high degree of interpretability. However, learning a DT from data is a difficult optimization problem, as it is non-convex and non-differentiable. Therefore, common approaches learn DTs using a greedy growth algorithm that minimizes the impurity locally at each internal node. Unfortunately, this greedy procedure can lead to inaccurate trees. In this paper, we present a novel approach for learning hard, axis-aligned DTs with gradient descent. The proposed method uses backpropagation with a straight-through operator on a dense DT representation, to jointly optimize all tree parameters. Our approach outperforms existing methods on binary classification benchmarks and achieves competitive results for multi-class tasks. The method is available under: https://github.com/s-marton/GradTree
Authors: Alessio Zanga, Alice Bernasconi, Peter J.F. Lucas, Hanny Pijnenborg, Casper Reijnen, Marco Scutari, Fabio Stella
Causal inference for testing clinical hypotheses from observational data presents many difficulties because the underlying data-generating model and the associated causal graph are not usually available. Furthermore, observational data may contain missing values, which impact the recovery of the causal graph by causal discovery algorithms: a crucial issue often ignored in clinical studies. In this work, we use data from a multi-centric study on endometrial cancer to analyze the impact of different missingness mechanisms on the recovered causal graph. This is achieved by extending state-of-the-art causal discovery algorithms to exploit expert knowledge without sacrificing theoretical soundness. We validate the recovered graph with expert physicians, showing that our approach finds clinically-relevant solutions. Finally, we discuss the goodness of fit of our graph and its consistency from a clinical decision-making perspective using graphical separation to validate causal pathways.
Authors: Jinghan Yao, Nawras Alnaasan, Tian Chen, Aamir Shafi, Hari Subramoni, Dhabaleswar K. (DK) Panda
Autoregressive models, despite their commendable performance in a myriad of generative tasks, face challenges stemming from their inherently sequential structure. Inference on these models, by design, harnesses a temporal dependency, where the current token's probability distribution is conditioned on preceding tokens. This inherent characteristic severely impedes computational efficiency during inference as a typical inference request can require more than thousands of tokens, where generating each token requires a load of entire model weights, making the inference more memory-bound. The large overhead becomes profound in real deployment where requests arrive randomly, necessitating various generation lengths. Existing solutions, such as dynamic batching and concurrent instances, introduce significant response delays and bandwidth contention, falling short of achieving optimal latency and throughput. To address these shortcomings, we propose Flover -- a temporal fusion framework for efficiently inferring multiple requests in parallel. We deconstruct the general generation pipeline into pre-processing and token generation, and equip the framework with a dedicated work scheduler for fusing the generation process temporally across all requests. By orchestrating the token-level parallelism, Flover exhibits optimal hardware efficiency and significantly spares the system resources. By further employing a fast buffer reordering algorithm that allows memory eviction of finished tasks, it brings over 11x inference speedup on GPT and 16x on LLAMA compared to the cutting-edge solutions provided by NVIDIA FasterTransformer. Crucially, by leveraging the advanced tensor parallel technique, Flover proves efficacious across diverse computational landscapes, from single-GPU setups to distributed scenarios, thereby offering robust performance optimization that adapts to variable use cases.
Authors: Shuo Zhang, Liangming Pan, Junzhou Zhao, William Yang Wang
Large language models often necessitate grounding on external knowledge to generate faithful and reliable answers. Yet even with the correct groundings in the reference, they can ignore them and rely on wrong groundings or their inherent biases to hallucinate when users, being largely unaware of the specifics of the stored information, pose questions that might not directly correlate with the retrieved groundings. In this work, we formulate this knowledge alignment problem and introduce MixAlign, a framework that interacts with both the human user and the knowledge base to obtain and integrate clarifications on how the user question relates to the stored information. MixAlign employs a language model to achieve automatic knowledge alignment and, if necessary, further enhances this alignment through human user clarifications. Experimental results highlight the crucial role of knowledge alignment in boosting model performance and mitigating hallucination, with improvements noted up to 22.2% and 27.1% respectively. We also demonstrate the effectiveness of MixAlign in improving knowledge alignment by producing high-quality, user-centered clarifications.
Authors: Benno Krojer, Elinor Poole-Dayan, Vikram Voleti, Christopher Pal, Siva Reddy
Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generative models to automatic fine-grained quantitative evaluation of high-level phenomena such as compositionality. Towards this goal, we perform two innovations. First, we transform diffusion-based models (in our case, Stable Diffusion) for any image-text matching (ITM) task using a novel method called DiffusionITM. Second, we introduce the Generative-Discriminative Evaluation Benchmark (GDBench) benchmark with 7 complex vision-and-language tasks, bias evaluation and detailed analysis. We find that Stable Diffusion + DiffusionITM is competitive on many tasks and outperforms CLIP on compositional tasks like like CLEVR and Winoground. We further boost its compositional performance with a transfer setup by fine-tuning on MS-COCO while retaining generative capabilities. We also measure the stereotypical bias in diffusion models, and find that Stable Diffusion 2.1 is, for the most part, less biased than Stable Diffusion 1.5. Overall, our results point in an exciting direction bringing discriminative and generative model evaluation closer. We will release code and benchmark setup soon.
Authors: Mohammad Pedramfar, Christopher John Quinn, Vaneet Aggarwal
This paper presents a unified approach for maximizing continuous DR-submodular functions that encompasses a range of settings and oracle access types. Our approach includes a Frank-Wolfe type offline algorithm for both monotone and non-monotone functions, with different restrictions on the general convex set. We consider settings where the oracle provides access to either the gradient of the function or only the function value, and where the oracle access is either deterministic or stochastic. We determine the number of required oracle accesses in all cases. Our approach gives new/improved results for nine out of the sixteen considered cases, avoids computationally expensive projections in two cases, with the proposed framework matching performance of state-of-the-art approaches in the remaining five cases. Notably, our approach for the stochastic function value-based oracle enables the first regret bounds with bandit feedback for stochastic DR-submodular functions.
Authors: Yue Xu, Yong-Lu Li, Kaitong Cui, Ziyu Wang, Cewu Lu, Yu-Wing Tai, Chi-Keung Tang
Data-efficient learning has drawn significant attention, especially given the current trend of large multi-modal models, where dataset distillation can be an effective solution. However, the dataset distillation process itself is still very inefficient. In this work, we model the distillation problem with reference to information transport. Observing that severe data redundancy exists in dataset distillation, we argue to put more emphasis on the utility of the training samples. We propose a family of methods to exploit the most valuable samples, which is validated by our comprehensive analysis of the optimal data selection. The new strategy significantly reduces the training cost and extends a variety of existing distillation algorithms to larger and more diversified datasets, e.g., in some cases only 0.04% training data is sufficient for comparable distillation performance. Moreover, our strategy consistently enhances the performance, which may open up new analyses on the dynamics of distillation and networks. Our method is able to extend the distillation algorithms to much larger-scale datasets and more heterogeneous datasets, e.g., ImageNet-1K and Kinetics-400. Our code is available on https://github.com/silicx/GoldFromOres.
Authors: Bailin Wang, Zi Wang, Xuezhi Wang, Yuan Cao, Rif A. Saurous, Yoon Kim
Large language models (LLMs) can learn to perform a wide range of natural language tasks from just a handful of in-context examples. However, for generating strings from highly structured languages (e.g., semantic parsing to complex domain-specific languages), it is challenging for the LLM to generalize from just a few exemplars. We propose \emph{grammar prompting}, a simple approach to enable LLMs to use external knowledge and domain-specific constraints, expressed through a grammar in Backus--Naur Form (BNF), during in-context learning. Grammar prompting augments each demonstration example with a specialized grammar that is minimally sufficient for generating the particular output example, where the specialized grammar is a subset of the full DSL grammar. For inference, the LLM first predicts a BNF grammar given a test input, and then generates the output according to the rules of the grammar. Experiments demonstrate that grammar prompting can enable LLMs to perform competitively on a diverse set of DSL generation tasks, including semantic parsing (SMCalFlow, Overnight, GeoQuery), PDDL planning, and SMILES-based molecule generation.
Authors: Banghua Zhu, Mingyu Ding, Philip Jacobson, Ming Wu, Wei Zhan, Michael Jordan, Jiantao Jiao
Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of self-training heavily relies on the accuracy of these pseudo-labels. In this paper, we introduce doubly robust self-training, a novel semi-supervised algorithm that provably balances between two extremes. When the pseudo-labels are entirely incorrect, our method reduces to a training process solely using labeled data. Conversely, when the pseudo-labels are completely accurate, our method transforms into a training process utilizing all pseudo-labeled data and labeled data, thus increasing the effective sample size. Through empirical evaluations on both the ImageNet dataset for image classification and the nuScenes autonomous driving dataset for 3D object detection, we demonstrate the superiority of the doubly robust loss over the standard self-training baseline.
Authors: Banghua Zhu, Hiteshi Sharma, Felipe Vieira Frujeri, Shi Dong, Chenguang Zhu, Michael I. Jordan, Jiantao Jiao
Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach to aligning large language models (LLMs) to human preferences. Among the plethora of RLHF techniques, proximal policy optimization (PPO) is of the most widely used methods. Despite its popularity, however, PPO may suffer from mode collapse, instability, and poor sample efficiency. We show that these issues can be alleviated by a novel algorithm that we refer to as Advantage-Induced Policy Alignment (APA), which leverages a squared error loss function based on the estimated advantages. We demonstrate empirically that APA consistently outperforms PPO in language tasks by a large margin, when a separate reward model is employed as the evaluator. In addition, compared with PPO, APA offers a more stable form of control over the deviation from the model's initial policy, ensuring that the model improves its performance without collapsing to deterministic output. In addition to empirical results, we also provide a theoretical justification supporting the design of our loss function.
Authors: Lakshya A Agrawal, Aditya Kanade, Navin Goyal, Shuvendu K. Lahiri, Sriram K. Rajamani
Language models of code (LMs) work well when the surrounding code provides sufficient context. This is not true when it becomes necessary to use types, functionality or APIs defined elsewhere in the repository or a linked library, especially those not seen during training. LMs suffer from limited awareness of such global context and end up hallucinating.
Integrated development environments (IDEs) assist developers in understanding repository context using static analysis. We extend this assistance, enjoyed by developers, to LMs. We propose monitor-guided decoding (MGD) where a monitor uses static analysis to guide the decoding. We construct a repository-level dataset PragmaticCode for method-completion in Java and evaluate MGD on it. On models of varying parameter scale, by monitoring for type-consistent object dereferences, MGD consistently improves compilation rates and agreement with ground truth. Further, LMs with fewer parameters, when augmented with MGD, can outperform larger LMs. With MGD, SantaCoder-1.1B achieves better compilation rate and next-identifier match than the much larger text-davinci-003 model.
We also conduct a generalizability study to evaluate the ability of MGD to generalize to multiple programming languages (Java, C# and Rust), coding scenarios (e.g., correct number of arguments to method calls), and to enforce richer semantic constraints (e.g., stateful API protocols). Our data and implementation are available at https://github.com/microsoft/monitors4codegen .
Authors: Phong Tran, Haoran Wu, Cunjun Yu, Panpan Cai, Sifa Zheng, David Hsu
Trajectory prediction plays a vital role in the performance of autonomous driving systems, and prediction accuracy, such as average displacement error (ADE) or final displacement error (FDE), is widely used as a performance metric. However, a significant disparity exists between the accuracy of predictors on fixed datasets and driving performance when the predictors are used downstream for vehicle control, because of a dynamics gap. In the real world, the prediction algorithm influences the behavior of the ego vehicle, which, in turn, influences the behaviors of other vehicles nearby. This interaction results in predictor-specific dynamics that directly impacts prediction results. In fixed datasets, since other vehicles' responses are predetermined, this interaction effect is lost, leading to a significant dynamics gap. This paper studies the overlooked significance of this dynamics gap. We also examine several other factors contributing to the disparity between prediction performance and driving performance. The findings highlight the trade-off between the predictor's computational efficiency and prediction accuracy in determining real-world driving performance. In summary, an interactive, task-driven evaluation protocol for trajectory prediction is crucial to capture its effectiveness for autonomous driving. Source code along with experimental settings is available online.
Authors: Outongyi Lv, Bingxin Zhou
Modern reinforcement learning (RL) can be categorized into online and offline variants. As a pivotal aspect of both online and offline RL, current research on the Bellman equation revolves primarily around optimization techniques and performance enhancement rather than exploring the inherent structural properties of the Bellman error, such as its distribution characteristics. This study investigates the distribution of the Bellman approximation error in both online and offline settings through iterative exploration of the Bellman equation. We observed that both in online RL and offline RL, the Bellman error conforms to a Logistic distribution. Building upon this discovery, this study employed the Logistics maximum likelihood function (LLoss) as an alternative to the commonly used MSE Loss, assuming that Bellman errors adhere to a normal distribution. We validated our hypotheses through extensive numerical experiments across diverse online and offline environments. In particular, we applied corrections to the loss function across various baseline algorithms and consistently observed that the loss function with Logistic corrections outperformed the MSE counterpart significantly. Additionally, we conducted Kolmogorov-Smirnov tests to confirm the reliability of the Logistic distribution. This study's theoretical and empirical insights provide valuable groundwork for future investigations and enhancements centered on the distribution of Bellman errors.
Authors: Yudong Luo, Guiliang Liu, Pascal Poupart, Yangchen Pan
Restricting the variance of a policy's return is a popular choice in risk-averse Reinforcement Learning (RL) due to its clear mathematical definition and easy interpretability. Traditional methods directly restrict the total return variance. Recent methods restrict the per-step reward variance as a proxy. We thoroughly examine the limitations of these variance-based methods, such as sensitivity to numerical scale and hindering of policy learning, and propose to use an alternative risk measure, Gini deviation, as a substitute. We study various properties of this new risk measure and derive a policy gradient algorithm to minimize it. Empirical evaluation in domains where risk-aversion can be clearly defined, shows that our algorithm can mitigate the limitations of variance-based risk measures and achieves high return with low risk in terms of variance and Gini deviation when others fail to learn a reasonable policy.
Authors: Arman Zharmagambetov, Brandon Amos, Aaron Ferber, Taoan Huang, Bistra Dilkina, Yuandong Tian
Recent works in learning-integrated optimization have shown promise in settings where the optimization problem is only partially observed or where general-purpose optimizers perform poorly without expert tuning. By learning an optimizer $\mathbf{g}$ to tackle these challenging problems with $f$ as the objective, the optimization process can be substantially accelerated by leveraging past experience. The optimizer can be trained with supervision from known optimal solutions or implicitly by optimizing the compound function $f\circ \mathbf{g}$. The implicit approach may not require optimal solutions as labels and is capable of handling problem uncertainty; however, it is slow to train and deploy due to frequent calls to optimizer $\mathbf{g}$ during both training and testing. The training is further challenged by sparse gradients of $\mathbf{g}$, especially for combinatorial solvers. To address these challenges, we propose using a smooth and learnable Landscape Surrogate $M$ as a replacement for $f\circ \mathbf{g}$. This surrogate, learnable by neural networks, can be computed faster than the solver $\mathbf{g}$, provides dense and smooth gradients during training, can generalize to unseen optimization problems, and is efficiently learned via alternating optimization. We test our approach on both synthetic problems, including shortest path and multidimensional knapsack, and real-world problems such as portfolio optimization, achieving comparable or superior objective values compared to state-of-the-art baselines while reducing the number of calls to $\mathbf{g}$. Notably, our approach outperforms existing methods for computationally expensive high-dimensional problems.
Authors: Isaac Triguero, Daniel Molina, Javier Poyatos, Javier Del Ser, Francisco Herrera
Most applications of Artificial Intelligence (AI) are designed for a confined and specific task. However, there are many scenarios that call for a more general AI, capable of solving a wide array of tasks without being specifically designed for them. The term General-Purpose Artificial Intelligence Systems (GPAIS) has been defined to refer to these AI systems. To date, the possibility of an Artificial General Intelligence, powerful enough to perform any intellectual task as if it were human, or even improve it, has remained an aspiration, fiction, and considered a risk for our society. Whilst we might still be far from achieving that, GPAIS is a reality and sitting at the forefront of AI research. This work discusses existing definitions for GPAIS and proposes a new definition that allows for a gradual differentiation among types of GPAIS according to their properties and limitations. We distinguish between closed-world and open-world GPAIS, characterising their degree of autonomy and ability based on several factors such as adaptation to new tasks, competence in domains not intentionally trained for, ability to learn from few data, or proactive acknowledgment of their own limitations. We propose a taxonomy of approaches to realise GPAIS, describing research trends such as the use of AI techniques to improve another AI (AI-powered AI) or (single) foundation models. As a prime example, we delve into GenAI, aligning them with the concepts presented in the taxonomy. We explore multi-modality, which involves fusing various types of data sources to expand the capabilities of GPAIS. Through the proposed definition and taxonomy, our aim is to facilitate research collaboration across different areas that are tackling general purpose tasks, as they share many common aspects. Finally, we discuss the state of GPAIS, prospects, societal implications, and the need for regulation and governance.
Authors: Zhenpeng Chen, Jie M. Zhang, Federica Sarro, Mark Harman
Existing research mostly improves the fairness of Machine Learning (ML) software regarding a single protected attribute at a time, but this is unrealistic given that many users have multiple protected attributes. This paper conducts an extensive study of fairness improvement regarding multiple protected attributes, covering 11 state-of-the-art fairness improvement methods. We analyze the effectiveness of these methods with different datasets, metrics, and ML models when considering multiple protected attributes. The results reveal that improving fairness for a single protected attribute can largely decrease fairness regarding unconsidered protected attributes. This decrease is observed in up to 88.3% of scenarios (57.5% on average). More surprisingly, we find little difference in accuracy loss when considering single and multiple protected attributes, indicating that accuracy can be maintained in the multiple-attribute paradigm. However, the effect on precision and recall when handling multiple protected attributes is about 5 times and 8 times that of a single attribute. This has important implications for future fairness research: reporting only accuracy as the ML performance metric, which is currently common in the literature, is inadequate.
Authors: Saipraneeth Devunuri, Shirin Qiam, Lewis Lehe
The General Transit Feed Specification (GTFS) standard for publishing transit data is ubiquitous. GTFS being tabular data, with information spread across different files, necessitates specialized tools or packages to retrieve information. Concurrently, the use of Large Language Models(LLMs) for text and information retrieval is growing. The idea of this research is to see if the current widely adopted LLMs (ChatGPT) are able to understand GTFS and retrieve information from GTFS using natural language instructions without explicitly providing information. In this research, we benchmark OpenAI's GPT-3.5-Turbo and GPT-4 LLMs which are the backbone of ChatGPT. ChatGPT demonstrates a reasonable understanding of GTFS by answering 59.7% (GPT-3.5-Turbo) and 73.3% (GPT-4) of our multiple-choice questions (MCQ) correctly. Furthermore, we evaluated the LLMs on information extraction tasks using a filtered GTFS feed containing four routes. We found that program synthesis techniques outperformed zero-shot approaches, achieving up to 93% (90%) accuracy for simple queries and 61% (41%) for complex ones using GPT-4 (GPT-3.5-Turbo).
Authors: Wei-Chao Cheng, Tan-Ha Mai, Hsuan-Tien Lin
Given imbalanced data, it is hard to train a good classifier using deep learning because of the poor generalization of minority classes. Traditionally, the well-known synthetic minority oversampling technique (SMOTE) for data augmentation, a data mining approach for imbalanced learning, has been used to improve this generalization. However, it is unclear whether SMOTE also benefits deep learning. In this work, we study why the original SMOTE is insufficient for deep learning, and enhance SMOTE using soft labels. Connecting the resulting soft SMOTE with Mixup, a modern data augmentation technique, leads to a unified framework that puts traditional and modern data augmentation techniques under the same umbrella. A careful study within this framework shows that Mixup improves generalization by implicitly achieving uneven margins between majority and minority classes. We then propose a novel margin-aware Mixup technique that more explicitly achieves uneven margins. Extensive experimental results demonstrate that our proposed technique yields state-of-the-art performance on deep imbalanced classification while achieving superior performance on extremely imbalanced data. The code is open-sourced in our developed package https://github.com/ntucllab/imbalanced-DL to foster future research in this direction.
Authors: Yu Liu, Gesine Muller, Nassir Navab, Carsten Marr, Jan Huisken, Tingying Peng
Light-sheet fluorescence microscopy (LSFM), a planar illumination technique that enables high-resolution imaging of samples, experiences defocused image quality caused by light scattering when photons propagate through thick tissues. To circumvent this issue, dualview imaging is helpful. It allows various sections of the specimen to be scanned ideally by viewing the sample from opposing orientations. Recent image fusion approaches can then be applied to determine in-focus pixels by comparing image qualities of two views locally and thus yield spatially inconsistent focus measures due to their limited field-of-view. Here, we propose BigFUSE, a global context-aware image fuser that stabilizes image fusion in LSFM by considering the global impact of photon propagation in the specimen while determining focus-defocus based on local image qualities. Inspired by the image formation prior in dual-view LSFM, image fusion is considered as estimating a focus-defocus boundary using Bayes Theorem, where (i) the effect of light scattering onto focus measures is included within Likelihood; and (ii) the spatial consistency regarding focus-defocus is imposed in Prior. The expectation-maximum algorithm is then adopted to estimate the focus-defocus boundary. Competitive experimental results show that BigFUSE is the first dual-view LSFM fuser that is able to exclude structured artifacts when fusing information, highlighting its abilities of automatic image fusion.
Authors: Javier Ferrando, Matthias Sperber, Hendra Setiawan, Dominic Telaar, Saša Hasan
Behavioral testing in NLP allows fine-grained evaluation of systems by examining their linguistic capabilities through the analysis of input-output behavior. Unfortunately, existing work on behavioral testing in Machine Translation (MT) is currently restricted to largely handcrafted tests covering a limited range of capabilities and languages. To address this limitation, we propose to use Large Language Models (LLMs) to generate a diverse set of source sentences tailored to test the behavior of MT models in a range of situations. We can then verify whether the MT model exhibits the expected behavior through matching candidate sets that are also generated using LLMs. Our approach aims to make behavioral testing of MT systems practical while requiring only minimal human effort. In our experiments, we apply our proposed evaluation framework to assess multiple available MT systems, revealing that while in general pass-rates follow the trends observable from traditional accuracy-based metrics, our method was able to uncover several important differences and potential bugs that go unnoticed when relying only on accuracy.
Authors: Xueyi Wang
Falls are significant and often fatal for vulnerable populations such as the elderly. Previous works have addressed the detection of falls by relying on data capture by a single sensor, images or accelerometers. In this work, we rely on multimodal descriptors extracted from videos captured by egocentric cameras. Our proposed method includes a late decision fusion layer that builds on top of the extracted descriptors. Furthermore, we collect a new dataset on which we assess our proposed approach. We believe this is the first public dataset of its kind. The dataset comprises 10,948 video samples by 14 subjects. We conducted ablation experiments to assess the performance of individual feature extractors, fusion of visual information, and fusion of both visual and audio information. Moreover, we experimented with internal and external cross-validation. Our results demonstrate that the fusion of audio and visual information through late decision fusion improves detection performance, making it a promising tool for fall prevention and mitigation.
Authors: Fabio Ferreira, Ivo Rapant, Frank Hutter
Many Contrastive Learning (CL) methods train their models to be invariant to different "views" of an image input for which a good data augmentation pipeline is crucial. While considerable efforts were directed towards improving pre-text tasks, architectures, or robustness (e.g., Siamese networks or teacher-softmax centering), the majority of these methods remain strongly reliant on the random sampling of operations within the image augmentation pipeline, such as the random resized crop or color distortion operation. In this paper, we argue that the role of the view generation and its effect on performance has so far received insufficient attention. To address this, we propose an easy, learning-free, yet powerful Hard View Selection (HVS) strategy designed to extend the random view generation to expose the pretrained model to harder samples during CL training. It encompasses the following iterative steps: 1) randomly sample multiple views and create pairs of two views, 2) run forward passes for each view pair on the currently trained model, 3) adversarially select the pair yielding the worst loss, and 4) run the backward pass with the selected pair. In our empirical analysis we show that under the hood, HVS increases task difficulty by controlling the Intersection over Union of views during pretraining. With only 300-epoch pretraining, HVS is able to closely rival the 800-epoch DINO baseline which remains very favorable even when factoring in the slowdown induced by the additional forwards of HVS. Additionally, HVS consistently achieves accuracy improvements on ImageNet between 0.4% and 1.9% on linear evaluation and similar improvements on transfer tasks across multiple CL methods, such as DINO, SimSiam, and SimCLR.
Authors: Songtao Luo, Shuang Yang, Shiguang Shan, Xilin Chen
In this paper, we propose a novel method for speaker adaptation in lip reading, motivated by two observations. Firstly, a speaker's own characteristics can always be portrayed well by his/her few facial images or even a single image with shallow networks, while the fine-grained dynamic features associated with speech content expressed by the talking face always need deep sequential networks to represent accurately. Therefore, we treat the shallow and deep layers differently for speaker adaptive lip reading. Secondly, we observe that a speaker's unique characteristics ( e.g. prominent oral cavity and mandible) have varied effects on lip reading performance for different words and pronunciations, necessitating adaptive enhancement or suppression of the features for robust lip reading. Based on these two observations, we propose to take advantage of the speaker's own characteristics to automatically learn separable hidden unit contributions with different targets for shallow layers and deep layers respectively. For shallow layers where features related to the speaker's characteristics are stronger than the speech content related features, we introduce speaker-adaptive features to learn for enhancing the speech content features. For deep layers where both the speaker's features and the speech content features are all expressed well, we introduce the speaker-adaptive features to learn for suppressing the speech content irrelevant noise for robust lip reading. Our approach consistently outperforms existing methods, as confirmed by comprehensive analysis and comparison across different settings. Besides the evaluation on the popular LRW-ID and GRID datasets, we also release a new dataset for evaluation, CAS-VSR-S68h, to further assess the performance in an extreme setting where just a few speakers are available but the speech content covers a large and diversified range.
Authors: Yixin Wan, Jieyu Zhao, Aman Chadha, Nanyun Peng, Kai-Wei Chang
Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as "an Asian person", whereas specific personas may take the form of specific popular Asian names like "Yumi". While the adoption of personas enriches user experiences by making dialogue systems more engaging and approachable, it also casts a shadow of potential risk by exacerbating social biases within model responses, thereby causing societal harm through interactions with users. In this paper, we systematically study "persona biases", which we define to be the sensitivity of dialogue models' harmful behaviors contingent upon the personas they adopt. We categorize persona biases into biases in harmful expression and harmful agreement, and establish a comprehensive evaluation framework to measure persona biases in five aspects: Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic Agreement. Additionally, we propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a systematically constructed persona dataset encompassing various types of both generic and specific model personas. Through benchmarking on four different models -- including Blender, ChatGPT, Alpaca, and Vicuna -- our study uncovers significant persona biases in dialogue systems. Our findings also underscore the pressing need to revisit the use of personas in dialogue agents to ensure safe application.
Authors: Jonathan Kamp, Lisa Beinborn, Antske Fokkens
Feature attribution scores are used for explaining the prediction of a text classifier to users by highlighting a k number of tokens. In this work, we propose a way to determine the number of optimal k tokens that should be displayed from sequential properties of the attribution scores. Our approach is dynamic across sentences, method-agnostic, and deals with sentence length bias. We compare agreement between multiple methods and humans on an NLI task, using fixed k and dynamic k. We find that perturbation-based methods and Vanilla Gradient exhibit highest agreement on most method--method and method--human agreement metrics with a static k. Their advantage over other methods disappears with dynamic ks which mainly improve Integrated Gradient and GradientXInput. To our knowledge, this is the first evidence that sequential properties of attribution scores are informative for consolidating attribution signals for human interpretation.
Authors: Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng
Large Language Models (LLMs) have recently emerged as an effective tool to assist individuals in writing various types of content, including professional documents such as recommendation letters. Though bringing convenience, this application also introduces unprecedented fairness concerns. Model-generated reference letters might be directly used by users in professional scenarios. If underlying biases exist in these model-constructed letters, using them without scrutinization could lead to direct societal harms, such as sabotaging application success rates for female applicants. In light of this pressing issue, it is imminent and necessary to comprehensively study fairness issues and associated harms in this real-world use case. In this paper, we critically examine gender biases in LLM-generated reference letters. Drawing inspiration from social science findings, we design evaluation methods to manifest biases through 2 dimensions: (1) biases in language style and (2) biases in lexical content. We further investigate the extent of bias propagation by analyzing the hallucination bias of models, a term that we define to be bias exacerbation in model-hallucinated contents. Through benchmarking evaluation on 2 popular LLMs- ChatGPT and Alpaca, we reveal significant gender biases in LLM-generated recommendation letters. Our findings not only warn against using LLMs for this application without scrutinization, but also illuminate the importance of thoroughly studying hidden biases and harms in LLM-generated professional documents.
Authors: Roger Creus Castanyer, Joshua Romoff, Glen Berseth
Exploration bonuses in reinforcement learning guide long-horizon exploration by defining custom intrinsic objectives. Count-based methods use the frequency of state visits to derive an exploration bonus. In this paper, we identify that any intrinsic reward function derived from count-based methods is non-stationary and hence induces a difficult objective to optimize for the agent. The key contribution of our work lies in transforming the original non-stationary rewards into stationary rewards through an augmented state representation. For this purpose, we introduce the Stationary Objectives For Exploration (SOFE) framework. SOFE requires identifying sufficient statistics for different exploration bonuses and finding an efficient encoding of these statistics to use as input to a deep network. SOFE is based on proposing state augmentations that expand the state space but hold the promise of simplifying the optimization of the agent's objective. Our experiments show that SOFE improves the agents' performance in challenging exploration problems, including sparse-reward tasks, pixel-based observations, 3D navigation, and procedurally generated environments.
Authors: Yao Yao, Peike Li, Boyu Chen, Alex Wang
With rapid advances in generative artificial intelligence, the text-to-music synthesis task has emerged as a promising direction for music generation from scratch. However, finer-grained control over multi-track generation remains an open challenge. Existing models exhibit strong raw generation capability but lack the flexibility to compose separate tracks and combine them in a controllable manner, differing from typical workflows of human composers. To address this issue, we propose JEN-1 Composer, a unified framework to efficiently model marginal, conditional, and joint distributions over multi-track music via a single model. JEN-1 Composer framework exhibits the capacity to seamlessly incorporate any diffusion-based music generation system, \textit{e.g.} Jen-1, enhancing its capacity for versatile multi-track music generation. We introduce a curriculum training strategy aimed at incrementally instructing the model in the transition from single-track generation to the flexible generation of multi-track combinations. During the inference, users have the ability to iteratively produce and choose music tracks that meet their preferences, subsequently creating an entire musical composition incrementally following the proposed Human-AI co-composition workflow. Quantitative and qualitative assessments demonstrate state-of-the-art performance in controllable and high-fidelity multi-track music synthesis. The proposed JEN-1 Composer represents a significant advance toward interactive AI-facilitated music creation and composition. Demos will be available at https://www.jenmusic.ai/audio-demos.
Authors: Prakamya Mishra, Zonghai Yao, Shuwei Chen, Beining Wang, Rohan Mittal, Hong Yu
Large Language Models (LLMs) like the GPT and LLaMA families have demonstrated exceptional capabilities in capturing and condensing critical contextual information and achieving state-of-the-art performance in the summarization task. However, community concerns about these models' hallucination issues continue to rise. LLMs sometimes generate factually hallucinated summaries, which can be extremely harmful in the clinical domain NLP tasks (e.g., clinical note summarization), where factually incorrect statements can lead to critically erroneous diagnoses. Fine-tuning LLMs using human feedback has shown the promise of aligning LLMs to be factually consistent during generation, but such training procedure requires high-quality human-annotated data, which can be extremely expensive to get in the clinical domain. In this work, we propose a new pipeline using ChatGPT instead of human experts to generate high-quality feedback data for improving factual consistency in the clinical note summarization task. We focus specifically on edit feedback because recent work discusses the shortcomings of human alignment via preference feedback in complex situations (such as clinical NLP tasks that require extensive expert knowledge), as well as some advantages of collecting edit feedback from domain experts. In addition, although GPT has reached the expert level in many clinical NLP tasks (e.g., USMLE QA), there is not much previous work discussing whether GPT can generate expert-level edit feedback for LMs in the clinical note summarization task. We hope to fill this gap. Finally, our evaluations demonstrate the potential use of GPT edits in human alignment, especially from a factuality perspective.
Authors: Yingshu Li, Yunyi Liu, Zhanyu Wang, Xinyu Liang, Lingqiao Liu, Lei Wang, Leyang Cui, Zhaopeng Tu, Longyue Wang, Luping Zhou
This paper presents a comprehensive evaluation of GPT-4V's capabilities across diverse medical imaging tasks, including Radiology Report Generation, Medical Visual Question Answering (VQA), and Visual Grounding. While prior efforts have explored GPT-4V's performance in medical image anaylsis, to the best of our knowledge, our study represents the first quantitative evaluation on publicly available benchmarks. Our findings highlight GPT-4V's potential in generating descriptive reports for chest X-ray images, particularly when guided by well-structured prompts. Meanwhile, its performance on the MIMIC-CXR dataset benchmark reveals areas for improvement in certain evaluation metrics, such as CIDEr. In the domain of Medical VQA, GPT-4V demonstrates proficiency in distinguishing between question types but falls short of the VQA-RAD benchmark in terms of accuracy. Furthermore, our analysis finds the limitations of conventional evaluation metrics like the BLEU score, advocating for the development of more semantically robust assessment methods. In the field of Visual Grounding, GPT-4V exhibits preliminary promise in recognizing bounding boxes, but its precision is lacking, especially in identifying specific medical organs and signs. Our evaluation underscores the significant potential of GPT-4V in the medical imaging domain, while also emphasizing the need for targeted refinements to fully unlock its capabilities.
Authors: Benji Alwis
This paper introduces a new approach for quickly adapting a multi-view visuomotor system for robots to varying camera configurations from the baseline setup. It utilises meta-learning to fine-tune the perceptual network while keeping the policy network fixed. Experimental results demonstrate a significant reduction in the number of new training episodes needed to attain baseline performance.
Authors: Qiying Yu, Quan Sun, Xiaosong Zhang, Yufeng Cui, Fan Zhang, Yue Cao, Xinlong Wang, Jingjing Liu
Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise. Recent studies use alternative captions synthesized by captioning models and have achieved notable benchmark performance. However, our experiments reveal significant Scalability Deficiency and World Knowledge Loss issues in models trained with synthetic captions, which have been largely obscured by their initial benchmark success. Upon closer examination, we identify the root cause as the overly-simplified language structure and lack of knowledge details in existing synthetic captions. To provide higher-quality and more scalable multimodal pretraining data, we propose CapsFusion, an advanced framework that leverages large language models to consolidate and refine information from both web-based image-text pairs and synthetic captions. Extensive experiments show that CapsFusion captions exhibit remarkable all-round superiority over existing captions in terms of model performance (e.g., 18.8 and 18.3 improvements in CIDEr score on COCO and NoCaps), sample efficiency (requiring 11-16 times less computation than baselines), world knowledge depth, and scalability. These effectiveness, efficiency and scalability advantages position CapsFusion as a promising candidate for future scaling of LMM training.
Authors: Ryan Liu, Howard Yen, Raja Marjieh, Thomas L. Griffiths, Ranjay Krishna
How do we communicate with others to achieve our goals? We use our prior experience or advice from others, or construct a candidate utterance by predicting how it will be received. However, our experiences are limited and biased, and reasoning about potential outcomes can be difficult and cognitively challenging. In this paper, we explore how we can leverage Large Language Model (LLM) simulations to help us communicate better. We propose the Explore-Generate-Simulate (EGS) framework, which takes as input any scenario where an individual is communicating to an audience with a goal they want to achieve. EGS (1) explores the solution space by producing a diverse set of advice relevant to the scenario, (2) generates communication candidates conditioned on subsets of the advice, and (3) simulates the reactions from various audiences to determine both the best candidate and advice to use. We evaluate the framework on eight scenarios spanning the ten fundamental processes of interpersonal communication. For each scenario, we collect a dataset of human evaluations across candidates and baselines, and showcase that our framework's chosen candidate is preferred over popular generation mechanisms including Chain-of-Thought. We also find that audience simulations achieve reasonably high agreement with human raters across 5 of the 8 scenarios. Finally, we demonstrate the generality of our framework by applying it to real-world scenarios described by users on web forums. Through evaluations and demonstrations, we show that EGS enhances the effectiveness and outcomes of goal-oriented communication across a variety of situations, thus opening up new possibilities for the application of large language models in revolutionizing communication and decision-making processes.
Authors: Julian Moosmann, Pietro Bonazzi, Yawei Li, Sizhen Bian, Philipp Mayer, Luca Benini, Michele Magno
Smart glasses are rapidly gaining advanced functionality thanks to cutting-edge computing technologies, accelerated hardware architectures, and tiny AI algorithms. Integrating AI into smart glasses featuring a small form factor and limited battery capacity is still challenging when targeting full-day usage for a satisfactory user experience. This paper illustrates the design and implementation of tiny machine-learning algorithms exploiting novel low-power processors to enable prolonged continuous operation in smart glasses. We explore the energy- and latency-efficient of smart glasses in the case of real-time object detection. To this goal, we designed a smart glasses prototype as a research platform featuring two microcontrollers, including a novel milliwatt-power RISC-V parallel processor with a hardware accelerator for visual AI, and a Bluetooth low-power module for communication. The smart glasses integrate power cycling mechanisms, including image and audio sensing interfaces. Furthermore, we developed a family of novel tiny deep-learning models based on YOLO with sub-million parameters customized for microcontroller-based inference dubbed TinyissimoYOLO v1.3, v5, and v8, aiming at benchmarking object detection with smart glasses for energy and latency. Evaluations on the prototype of the smart glasses demonstrate TinyissimoYOLO's 17ms inference latency and 1.59mJ energy consumption per inference while ensuring acceptable detection accuracy. Further evaluation reveals an end-to-end latency from image capturing to the algorithm's prediction of 56ms or equivalently 18 fps, with a total power consumption of 62.9mW, equivalent to a 9.3 hours of continuous run time on a 154mAh battery. These results outperform MCUNet (TinyNAS+TinyEngine), which runs a simpler task (image classification) at just 7.3 fps per second.
Authors: Yiangos Georgiou, Marios Loizou, Tom Kelly, Melinos Averkiou
We introduce FacadeNet, a deep learning approach for synthesizing building facade images from diverse viewpoints. Our method employs a conditional GAN, taking a single view of a facade along with the desired viewpoint information and generates an image of the facade from the distinct viewpoint. To precisely modify view-dependent elements like windows and doors while preserving the structure of view-independent components such as walls, we introduce a selective editing module. This module leverages image embeddings extracted from a pre-trained vision transformer. Our experiments demonstrated state-of-the-art performance on building facade generation, surpassing alternative methods.
Authors: Yoshua Bengio, Geoffrey Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atılım Güneş Baydin, Sheila McIlraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca Dragan, Philip Torr, Stuart Russell, Daniel Kahneman, Jan Brauner, Sören Mindermann
In this short consensus paper, we outline risks from upcoming, advanced AI systems. We examine large-scale social harms and malicious uses, as well as an irreversible loss of human control over autonomous AI systems. In light of rapid and continuing AI progress, we propose priorities for AI R&D and governance.