Authors: Marco Esposito, Toni Mancini, Enrico Tronci
The increasing spreading of small commercial Unmanned Aerial Vehicles (UAVs, aka drones) presents serious threats for critical areas such as airports, power plants, governmental and military facilities. In fact, such UAVs can easily disturb or jam radio communications, collide with other flying objects, perform espionage activity, and carry offensive payloads, e.g., weapons or explosives. A central problem when designing surveillance solutions for the localization of unauthorized UAVs in critical areas is to decide how many triangulating sensors to use, and where to deploy them to optimise both coverage and cost effectiveness.
In this article, we compute deployments of triangulating sensors for UAV localization, optimizing a given blend of metrics, namely: coverage under multiple sensing quality levels, cost-effectiveness, fault-tolerance. We focus on large, complex 3D regions, which exhibit obstacles (e.g., buildings), varying terrain elevation, different coverage priorities, constraints on possible sensors placement. Our novel approach relies on computational geometry and statistical model checking, and enables the effective use of off-the-shelf AI-based black-box optimizers. Moreover, our method allows us to compute a closed-form, analytical representation of the region uncovered by a sensor deployment, which provides the means for rigorous, formal certification of the quality of the latter.
We show the practical feasibility of our approach by computing optimal sensor deployments for UAV localization in two large, complex 3D critical regions, the Rome Leonardo Da Vinci International Airport (FCO) and the Vienna International Center (VIC), using NOMAD as our state-of-the-art underlying optimization engine. Results show that we can compute optimal sensor deployments within a few hours on a standard workstation and within minutes on a small parallel infrastructure.
Authors: Ardi Tampuu, Ilmar Uduste, Kristjan Roosild
In the behavioral cloning approach to end-to-end driving, a dataset of expert driving is collected and the model learns to guess what the expert would do in different situations. Situations are summarized in observations and the outputs are low or mid-level commands (e.g. brake, throttle, and steering; or trajectories). The models learn to match observations at time T to actions recorded at T or as simultaneously as possible. However, when deploying the models to the real world (or to an asynchronous simulation), the action predicted based on observations at time T gets applied at T + $\Delta$ T. In a variety of cases, $\Delta$ T can be considerable and significantly influence performance.
We first demonstrate that driving at two different speeds is effectively two different tasks. Delays partially cause this difference and linearly amplify it. Even without computational delays, actuator delays and slipping due to inertia result in the need to perform actions preemptively when driving fast. The function mapping observations to commands becomes different compared to slow driving. We experimentally show that models trained to drive fast cannot perform the seemingly easier task of driving slow and vice-versa. Good driving models may be judged to be poor due to testing them at "a safe low speed", a task they cannot perform.
Secondly, we show how to counteract the effect of delays in end-to-end networks by changing the target labels. This is in contrast to the approaches attempting to minimize the delays, i.e. the cause, not the effect. To exemplify the problems and solutions in the real world, we use 1:10 scale minicars with limited computing power, using behavioral cloning for end-to-end driving. Some of the ideas discussed here may be transferable to the wider context of self-driving, to vehicles with more compute power and end-to-mid or modular approaches.
Authors: Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Michael Tontchev, Qing Hu, Brian Fuller, Davide Testuggine, Madian Khabsa
We introduce Llama Guard, an LLM-based input-output safeguard model geared towards Human-AI conversation use cases. Our model incorporates a safety risk taxonomy, a valuable tool for categorizing a specific set of safety risks found in LLM prompts (i.e., prompt classification). This taxonomy is also instrumental in classifying the responses generated by LLMs to these prompts, a process we refer to as response classification. For the purpose of both prompt and response classification, we have meticulously gathered a dataset of high quality. Llama Guard, a Llama2-7b model that is instruction-tuned on our collected dataset, albeit low in volume, demonstrates strong performance on existing benchmarks such as the OpenAI Moderation Evaluation dataset and ToxicChat, where its performance matches or exceeds that of currently available content moderation tools. Llama Guard functions as a language model, carrying out multi-class classification and generating binary decision scores. Furthermore, the instruction fine-tuning of Llama Guard allows for the customization of tasks and the adaptation of output formats. This feature enhances the model's capabilities, such as enabling the adjustment of taxonomy categories to align with specific use cases, and facilitating zero-shot or few-shot prompting with diverse taxonomies at the input. We are making Llama Guard model weights available and we encourage researchers to further develop and adapt them to meet the evolving needs of the community for AI safety.
Authors: Yanchu Guan, Dong Wang, Zhixuan Chu, Shiyu Wang, Feiyue Ni, Ruihua Song, Longfei Li, Jinjie Gu, Chenyi Zhuang
While intelligent virtual assistants like Siri, Alexa, and Google Assistant have become ubiquitous in modern life, they still face limitations in their ability to follow multi-step instructions and accomplish complex goals articulated in natural language. However, recent breakthroughs in large language models (LLMs) show promise for overcoming existing barriers by enhancing natural language processing and reasoning capabilities. Though promising, applying LLMs to create more advanced virtual assistants still faces challenges like ensuring robust performance and handling variability in real-world user commands. This paper proposes a novel LLM-based virtual assistant that can automatically perform multi-step operations within mobile apps based on high-level user requests. The system represents an advance in assistants by providing an end-to-end solution for parsing instructions, reasoning about goals, and executing actions. LLM-based Process Automation (LLMPA) has modules for decomposing instructions, generating descriptions, detecting interface elements, predicting next actions, and error checking. Experiments demonstrate the system completing complex mobile operation tasks in Alipay based on natural language instructions. This showcases how large language models can enable automated assistants to accomplish real-world tasks. The main contributions are the novel LLMPA architecture optimized for app process automation, the methodology for applying LLMs to mobile apps, and demonstrations of multi-step task completion in a real-world environment. Notably, this work represents the first real-world deployment and extensive evaluation of a large language model-based virtual assistant in a widely used mobile application with an enormous user base numbering in the hundreds of millions.
Authors: Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Matt Turner
We introduce Contrastive Activation Addition (CAA), an innovative method for steering language models by modifying activations during their forward passes. CAA computes ``steering vectors'' by averaging the difference in residual stream activations between pairs of positive and negative examples of a particular behavior such as factual versus hallucinatory responses. During inference, these steering vectors are added at all token positions after the user's prompt with either a positive or negative coefficient, allowing precise control over the degree of the targeted behavior. We evaluate CAA's effectiveness on Llama 2 Chat using both multiple-choice behavioral question datasets and open-ended generation tasks. We demonstrate that CAA significantly alters model behavior, outperforms traditional methods like finetuning and few-shot prompting, and minimally reduces capabilities. Moreover, by employing various activation space interpretation methods, we gain deeper insights into CAA's mechanisms. CAA both accurately steers model outputs and also sheds light on how high-level concepts are represented in Large Language Models (LLMs).
Authors: Tengfei Ma, Yujie Chen, Wen Tao, Dashun Zheng, Xuan Lin, Patrick Cheong-lao Pang, Yiping Liu, Yijun Wang, Bosheng Song, Xiangxiang Zeng
Link prediction in biomedical knowledge graphs (KGs) aims at predicting unknown interactions between entities, including drug-target interaction (DTI) and drug-drug interaction (DDI), which is critical for drug discovery and therapeutics. Previous methods prefer to utilize the rich semantic relations and topological structure of the KG to predict missing links, yielding promising outcomes. However, all these works only focus on improving the predictive performance without considering the inevitable noise and unreliable interactions existing in the KGs, which limits the development of KG-based computational methods. To address these limitations, we propose a Denoised Link Prediction framework, called DenoisedLP. DenoisedLP obtains reliable interactions based on the local subgraph by denoising noisy links in a learnable way, providing a universal module for mining underlying task-relevant relations. To collaborate with the smoothed semantic information, DenoisedLP introduces the semantic subgraph by blurring conflict relations around the predicted link. By maximizing the mutual information between the reliable structure and smoothed semantic relations, DenoisedLP emphasizes the informative interactions for predicting relation-specific links. Experimental results on real-world datasets demonstrate that DenoisedLP outperforms state-of-the-art methods on DTI and DDI prediction tasks, and verify the effectiveness and robustness of denoising unreliable interactions on the contaminated KGs.
Authors: Jianghong Zhou, Weizhi Du, Md Omar Faruk Rokon, Zhaodong Wang, Jiaxuan Xu, Isha Shah, Kuang-chih Lee, Musen Wen
The rapid proliferation of e-commerce platforms accentuates the need for advanced search and retrieval systems to foster a superior user experience. Central to this endeavor is the precise extraction of product attributes from customer queries, enabling refined search, comparison, and other crucial e-commerce functionalities. Unlike traditional Named Entity Recognition (NER) tasks, e-commerce queries present a unique challenge owing to the intrinsic decorative relationship between product types and attributes. In this study, we propose a pioneering framework that integrates BERT for classification, a Conditional Random Fields (CRFs) layer for attribute value extraction, and Large Language Models (LLMs) for data annotation, significantly advancing attribute recognition from customer inquiries. Our approach capitalizes on the robust representation learning of BERT, synergized with the sequence decoding prowess of CRFs, to adeptly identify and extract attribute values. We introduce a novel decorative relation correction mechanism to further refine the extraction process based on the nuanced relationships between product types and attributes inherent in e-commerce data. Employing LLMs, we annotate additional data to expand the model's grasp and coverage of diverse attributes. Our methodology is rigorously validated on various datasets, including Walmart, BestBuy's e-commerce NER dataset, and the CoNLL dataset, demonstrating substantial improvements in attribute recognition performance. Particularly, the model showcased promising results during a two-month deployment in Walmart's Sponsor Product Search, underscoring its practical utility and effectiveness.
Authors: Shitian Zhao, Zhuowan Li, Yadong Lu, Alan Yuille, Yan Wang
While Multi-modal Language Models (MLMs) demonstrate impressive multimodal ability, they still struggle on providing factual and precise responses for tasks like visual question answering (VQA). In this paper, we address this challenge from the perspective of contextual information. We propose Causal Context Generation, Causal-CoG, which is a prompting strategy that engages contextual information to enhance precise VQA during inference. Specifically, we prompt MLMs to generate contexts, i.e, text description of an image, and engage the generated contexts for question answering. Moreover, we investigate the advantage of contexts on VQA from a causality perspective, introducing causality filtering to select samples for which contextual information is helpful. To show the effectiveness of Causal-CoG, we run extensive experiments on 10 multimodal benchmarks and show consistent improvements, e.g., +6.30% on POPE, +13.69% on Vizwiz and +6.43% on VQAv2 compared to direct decoding, surpassing existing methods. We hope Casual-CoG inspires explorations of context knowledge in multimodal models, and serves as a plug-and-play strategy for MLM decoding.
Authors: Corentin Léger, Gautier Hamon, Eleni Nisioti, Xavier Hinaut, Clément Moulin-Frier
Animals often demonstrate a remarkable ability to adapt to their environments during their lifetime. They do so partly due to the evolution of morphological and neural structures. These structures capture features of environments shared between generations to bias and speed up lifetime learning. In this work, we propose a computational model for studying a mechanism that can enable such a process. We adopt a computational framework based on meta reinforcement learning as a model of the interplay between evolution and development. At the evolutionary scale, we evolve reservoirs, a family of recurrent neural networks that differ from conventional networks in that one optimizes not the weight values but hyperparameters of the architecture: the later control macro-level properties, such as memory and dynamics. At the developmental scale, we employ these evolved reservoirs to facilitate the learning of a behavioral policy through Reinforcement Learning (RL). Within an RL agent, a reservoir encodes the environment state before providing it to an action policy. We evaluate our approach on several 2D and 3D simulated environments. Our results show that the evolution of reservoirs can improve the learning of diverse challenging tasks. We study in particular three hypotheses: the use of an architecture combining reservoirs and reinforcement learning could enable (1) solving tasks with partial observability, (2) generating oscillatory dynamics that facilitate the learning of locomotion tasks, and (3) facilitating the generalization of learned behaviors to new tasks unknown during the evolution phase.
Authors: Zhipeng Bao, Yijun Li, Krishna Kumar Singh, Yu-Xiong Wang, Martial Hebert
Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object generation. This work illuminates the fundamental reasons for such misalignment, pinpointing issues related to low attention activation scores and mask overlaps. While previous research efforts have individually tackled these issues, we assert that a holistic approach is paramount. Thus, we propose two novel objectives, the Separate loss and the Enhance loss, that reduce object mask overlaps and maximize attention scores, respectively. Our method diverges from conventional test-time-adaptation techniques, focusing on finetuning critical parameters, which enhances scalability and generalizability. Comprehensive evaluations demonstrate the superior performance of our model in terms of image realism, text-image alignment, and adaptability, notably outperforming prominent baselines. Ultimately, this research paves the way for T2I diffusion models with enhanced compositional capacities and broader applicability. The project webpage is available at https://zpbao.github.io/projects/SepEn/.
Authors: Seth Neel, Peter Chang
This is the first survey of the active area of AI research that focuses on privacy issues in Large Language Models (LLMs). Specifically, we focus on work that red-teams models to highlight privacy risks, attempts to build privacy into the training or inference process, enables efficient data deletion from trained models to comply with existing privacy regulations, and tries to mitigate copyright issues. Our focus is on summarizing technical research that develops algorithms, proves theorems, and runs empirical evaluations. While there is an extensive body of legal and policy work addressing these challenges from a different angle, that is not the focus of our survey. Nevertheless, these works, along with recent legal developments do inform how these technical problems are formalized, and so we discuss them briefly in Section 1. While we have made our best effort to include all the relevant work, due to the fast moving nature of this research we may have missed some recent work. If we have missed some of your work please contact us, as we will attempt to keep this survey relatively up to date. We are maintaining a repository with the list of papers covered in this survey and any relevant code that was publicly available at https://github.com/safr-ml-lab/survey-llm.
Authors: Haotian Zhang, Semujju Stuart Dereck, Zhicheng Wang, Xianwei Lv, Kang Xu, Liang Wu, Ye Jia, Jing Wu, Zhuo Long, Wensheng Liang, X.G. Ma, Ruiyan Zhuang
Although the applications of artificial intelligence especially deep learning had greatly improved various aspects of intelligent manufacturing, they still face challenges for wide employment due to the poor generalization ability, difficulties to establish high-quality training datasets, and unsatisfactory performance of deep learning methods. The emergence of large scale foundational models(LSFMs) had triggered a wave in the field of artificial intelligence, shifting deep learning models from single-task, single-modal, limited data patterns to a paradigm encompassing diverse tasks, multimodal, and pre-training on massive datasets. Although LSFMs had demonstrated powerful generalization capabilities, automatic high-quality training dataset generation and superior performance across various domains, applications of LSFMs on intelligent manufacturing were still in their nascent stage. A systematic overview of this topic was lacking, especially regarding which challenges of deep learning can be addressed by LSFMs and how these challenges can be systematically tackled. To fill this gap, this paper systematically expounded current statue of LSFMs and their advantages in the context of intelligent manufacturing. and compared comprehensively with the challenges faced by current deep learning models in various intelligent manufacturing applications. We also outlined the roadmaps for utilizing LSFMs to address these challenges. Finally, case studies of applications of LSFMs in real-world intelligent manufacturing scenarios were presented to illustrate how LSFMs could help industries, improve their efficiency.
Authors: Alexey Yurtin
This article presents a method for recovering missing values in multidimensional time series. The method combines neural network technologies and an algorithm for searching snippets (behavioral patterns of a time series). It includes the stages of data preprocessing, recognition and reconstruction, using convolutional and recurrent neural networks. Experiments have shown high accuracy of recovery and the advantage of the method over SOTA methods.
Authors: Henry Hengyuan Zhao, Pan Zhou, Mike Zheng Shou
Large Language Models (LLMs) excel in understanding human instructions, driving the development of Multimodal LLMs (MLLMs) with instruction tuning. However, acquiring high-quality multimodal instruction tuning data poses a significant challenge. Previous approaches relying on GPT-4 for data generation proved expensive and exhibited unsatisfactory performance for certain tasks. To solve this, we present Genixer, an innovative data generation pipeline producing high-quality multimodal instruction tuning data for various tasks. Genixer collects datasets for ten prevalent multimodal tasks and designs instruction templates to transform these datasets into instruction-tuning data. It then trains pretrained MLLMs to generate task-specific instruction data and proposes an effective data filtering strategy to ensure high quality. To evaluate Genixer, a base MLLM model, Kakapo, is built and achieves SoTA performance in image captioning and visual question answering (VQA) tasks across multiple datasets. Experimental results show that filtered data from Genixer continually improves Kakapo for image captioning and VQA tasks. For the SoTA Shikra MLLM model on the image-region-related tasks, e.g., region caption and detection, Genixer also successfully generates corresponding data and improves its performance. Genixer opens avenues for generating high-quality multimodal instruction data for diverse tasks, enabling innovative applications across domains. The code and models will be released soon.
Authors: Junbum Cha, Wooyoung Kang, Jonghwan Mun, Byungseok Roh
In Multimodal Large Language Models (MLLMs), a visual projector plays a crucial role in bridging pre-trained vision encoders with LLMs, enabling profound visual understanding while harnessing the LLMs' robust capabilities. Despite the importance of the visual projector, it has been relatively less explored. In this study, we first identify two essential projector properties: (i) flexibility in managing the number of visual tokens, crucial for MLLMs' overall efficiency, and (ii) preservation of local context from visual features, vital for spatial understanding. Based on these findings, we propose a novel projector design that is both flexible and locality-enhanced, effectively satisfying the two desirable properties. Additionally, we present comprehensive strategies to effectively utilize multiple and multifaceted instruction datasets. Through extensive experiments, we examine the impact of individual design choices. Finally, our proposed MLLM, Honeybee, remarkably outperforms previous state-of-the-art methods across various benchmarks, including MME, MMBench, SEED-Bench, and LLaVA-Bench, achieving significantly higher efficiency. Code and models are available at https://github.com/kakaobrain/honeybee.
Authors: Ronghao Ni, Zinan Lin, Shuaiqi Wang, Giulia Fanti
Long-term time series forecasting (LTSF) aims to predict future values of a time series given the past values. The current state-of-the-art (SOTA) on this problem is attained in some cases by linear-centric models, which primarily feature a linear mapping layer. However, due to their inherent simplicity, they are not able to adapt their prediction rules to periodic changes in time series patterns. To address this challenge, we propose a Mixture-of-Experts-style augmentation for linear-centric models and propose Mixture-of-Linear-Experts (MoLE). Instead of training a single model, MoLE trains multiple linear-centric models (i.e., experts) and a router model that weighs and mixes their outputs. While the entire framework is trained end-to-end, each expert learns to specialize in a specific temporal pattern, and the router model learns to compose the experts adaptively. Experiments show that MoLE reduces forecasting error of linear-centric models, including DLinear, RLinear, and RMLP, in over 78% of the datasets and settings we evaluated. By using MoLE existing linear-centric models can achieve SOTA LTSF results in 68% of the experiments that PatchTST reports and we compare to, whereas existing single-head linear-centric models achieve SOTA results in only 25% of cases. Additionally, MoLE models achieve SOTA in all settings for the newly released Weather2K datasets.
Authors: Manas Gaur, Amit Sheth
Explainability and Safety engender Trust. These require a model to exhibit consistency and reliability. To achieve these, it is necessary to use and analyze data and knowledge with statistical and symbolic AI methods relevant to the AI application - neither alone will do. Consequently, we argue and seek to demonstrate that the NeuroSymbolic AI approach is better suited for making AI a trusted AI system. We present the CREST framework that shows how Consistency, Reliability, user-level Explainability, and Safety are built on NeuroSymbolic methods that use data and knowledge to support requirements for critical applications such as health and well-being. This article focuses on Large Language Models (LLMs) as the chosen AI system within the CREST framework. LLMs have garnered substantial attention from researchers due to their versatility in handling a broad array of natural language processing (NLP) scenarios. For example, ChatGPT and Google's MedPaLM have emerged as highly promising platforms for providing information in general and health-related queries, respectively. Nevertheless, these models remain black boxes despite incorporating human feedback and instruction-guided tuning. For instance, ChatGPT can generate unsafe responses despite instituting safety guardrails. CREST presents a plausible approach harnessing procedural and graph-based knowledge within a NeuroSymbolic framework to shed light on the challenges associated with LLMs.
Authors: Sara Abdali, Anjali Parikh, Steve Lim, Emre Kiciman
Microsoft Windows Feedback Hub is designed to receive customer feedback on a wide variety of subjects including critical topics such as power and battery. Feedback is one of the most effective ways to have a grasp of users' experience with Windows and its ecosystem. However, the sheer volume of feedback received by Feedback Hub makes it immensely challenging to diagnose the actual cause of reported issues. To better understand and triage issues, we leverage Double Machine Learning (DML) to associate users' feedback with telemetry signals. One of the main challenges we face in the DML pipeline is the necessity of domain knowledge for model design (e.g., causal graph), which sometimes is either not available or hard to obtain. In this work, we take advantage of reasoning capabilities in Large Language Models (LLMs) to generate a prior model that which to some extent compensates for the lack of domain knowledge and could be used as a heuristic for measuring feedback informativeness. Our LLM-based approach is able to extract previously known issues, uncover new bugs, and identify sequences of events that lead to a bug, while minimizing out-of-domain outputs.
Authors: Son The Nguyen, Theja Tulabandhula, Mary Beth Watson-Manheim
While there is significant interest in using generative AI tools as general-purpose models for specific ML applications, discriminative models are much more widely deployed currently. One of the key shortcomings of these discriminative AI tools that have been already deployed is that they are not adaptable and user-friendly compared to generative AI tools (e.g., GPT4, Stable Diffusion, Bard, etc.), where a non-expert user can iteratively refine model inputs and give real-time feedback that can be accounted for immediately, allowing users to build trust from the start. Inspired by this emerging collaborative workflow, we develop a new system architecture that enables users to work with discriminative models (such as for object detection, sentiment classification, etc.) in a fashion similar to generative AI tools, where they can easily provide immediate feedback as well as adapt the deployed models as desired. Our approach has implications on improving trust, user-friendliness, and adaptability of these versatile but traditional prediction models.
Authors: Moyosolu Akinloye
Despite the widespread testing protocols for COVID-19, there are still significant challenges in early detection of the disease, which is crucial for preventing its spread and optimizing patient outcomes. Owing to the limited testing capacity in resource-strapped settings and the limitations of the available traditional methods of testing, it has been established that a fast and efficient strategy is important to fully stop the virus. Machine learning models can analyze large datasets, incorporating patient-reported symptoms, clinical data, and medical imaging. Symptom-based detection methods have been developed to predict COVID-19, and they have shown promising results. In this paper, we provide an overview of the landscape of symptoms-only machine learning models for predicting COVID-19, including their performance and limitations. The review will also examine the performance of symptom-based models when compared to image-based models. Because different studies used varying datasets, methodologies, and performance metrics. Selecting the model that performs best relies on the context and objectives of the research. However, based on the results, we observed that ensemble classifier performed exceptionally well in predicting the occurrence of COVID-19 based on patient symptoms with the highest overall accuracy of 97.88%. Gradient Boosting Algorithm achieved an AUC (Area Under the Curve) of 0.90 and identified key features contributing to the decision-making process. Image-based models, as observed in the analyzed studies, have consistently demonstrated higher accuracy than symptom-based models, often reaching impressive levels ranging from 96.09% to as high as 99%.
Authors: Joel Shor, Hiro-o Yamano, Daisuke Tsurumaru, Yotami Intrator, Hiroki Kayama, Joe Ledsam, Atsushi Hamabe, Koji Ando, Mitsuhiko Ota, Haruei Ogino, Hiroshi Nakase, Kaho Kobayashi, Eiji Oki, Roman Goldenberg, Ehud Rivlin, Ichiro Takemasa
$\textbf{Background and aims}$: Artificial Intelligence (AI) Computer-Aided Detection (CADe) is commonly used for polyp detection, but data seen in clinical settings can differ from model training. Few studies evaluate how well CADe detectors perform on colonoscopies from countries not seen during training, and none are able to evaluate performance without collecting expensive and time-intensive labels.
$\textbf{Methods}$: We trained a CADe polyp detector on Israeli colonoscopy videos (5004 videos, 1106 hours) and evaluated on Japanese videos (354 videos, 128 hours) by measuring the True Positive Rate (TPR) versus false alarms per minute (FAPM). We introduce a colonoscopy dissimilarity measure called "MAsked mediCal Embedding Distance" (MACE) to quantify differences between colonoscopies, without labels. We evaluated CADe on all Japan videos and on those with the highest MACE.
$\textbf{Results}$: MACE correctly quantifies that narrow-band imaging (NBI) and chromoendoscopy (CE) frames are less similar to Israel data than Japan whitelight (bootstrapped z-test, |z| > 690, p < $10^{-8}$ for both). Despite differences in the data, CADe performance on Japan colonoscopies was non-inferior to Israel ones without additional training (TPR at 0.5 FAPM: 0.957 and 0.972 for Israel and Japan; TPR at 1.0 FAPM: 0.972 and 0.989 for Israel and Japan; superiority test t > 45.2, p < $10^{-8}$). Despite not being trained on NBI or CE, TPR on those subsets were non-inferior to Japan overall (non-inferiority test t > 47.3, p < $10^{-8}$, $\delta$ = 1.5% for both).
$\textbf{Conclusion}$: Differences that prevent CADe detectors from performing well in non-medical settings do not degrade the performance of our AI CADe polyp detector when applied to data from a new country. MACE can help medical AI models internationalize by identifying the most "dissimilar" data on which to evaluate models.
Authors: Ching-An Cheng, Andrey Kolobov, Dipendra Misra, Allen Nie, Adith Swaminathan
We introduce a new benchmark, LLF-Bench (Learning from Language Feedback Benchmark; pronounced as "elf-bench"), to evaluate the ability of AI agents to interactively learn from natural language feedback and instructions. Learning from language feedback (LLF) is essential for people, largely because the rich information this feedback provides can help a learner avoid much of trial and error and thereby speed up the learning process. Large Language Models (LLMs) have recently enabled AI agents to comprehend natural language -- and hence AI agents can potentially benefit from language feedback during learning like humans do. But existing interactive benchmarks do not assess this crucial capability: they either use numeric reward feedback or require no learning at all (only planning or information retrieval). LLF-Bench is designed to fill this omission. LLF-Bench is a diverse collection of sequential decision-making tasks that includes user recommendation, poem writing, navigation, and robot control. The objective of an agent is to interactively solve these tasks based on their natural-language instructions and the feedback received after taking actions. Crucially, to ensure that the agent actually "learns" from the feedback, LLF-Bench implements several randomization techniques (such as paraphrasing and environment randomization) to ensure that the task isn't familiar to the agent and that the agent is robust to various verbalizations. In addition, LLF-Bench provides a unified OpenAI Gym interface for all its tasks and allows the users to easily configure the information the feedback conveys (among suggestion, explanation, and instantaneous performance) to study how agents respond to different types of feedback. Together, these features make LLF-Bench a unique research platform for developing and testing LLF agents.
Authors: Ahmed Abdelrahman, Omar M. Shehata, Yarah Basyoni, Elsayed I. Morgan
Cooperative autonomous driving plays a pivotal role in improving road capacity and safety within intelligent transportation systems, particularly through the deployment of autonomous vehicles on urban streets. By enabling vehicle-to-vehicle communication, these systems expand the vehicles environmental awareness, allowing them to detect hidden obstacles and thereby enhancing safety and reducing crash rates compared to human drivers who rely solely on visual perception. A key application of this technology is vehicle platooning, where connected vehicles drive in a coordinated formation. This paper introduces a vehicle platooning approach designed to enhance traffic flow and safety. Developed using deep reinforcement learning in the Unity 3D game engine, known for its advanced physics, this approach aims for a high-fidelity physical simulation that closely mirrors real-world conditions. The proposed platooning model focuses on scalability, decentralization, and fostering positive cooperation through the introduced predecessor-follower "sharing and caring" communication framework. The study demonstrates how these elements collectively enhance autonomous driving performance and robustness, both for individual vehicles and for the platoon as a whole, in an urban setting. This results in improved road safety and reduced traffic congestion.
Authors: Eric Yeats, Cameron Darwin, Frank Liu, Hai Li
Quantification of the number of variables needed to locally explain complex data is often the first step to better understanding it. Existing techniques from intrinsic dimension estimation leverage statistical models to glean this information from samples within a neighborhood. However, existing methods often rely on well-picked hyperparameters and ample data as manifold dimension and curvature increases. Leveraging insight into the fixed point of the score matching objective as the score map is regularized by its Dirichlet energy, we show that it is possible to retrieve the topological dimension of the manifold learned by the score map. We then introduce a novel method to measure the learned manifold's topological dimension (i.e., local intrinsic dimension) using adversarial attacks, thereby generating useful interpretations of the learned manifold.
Authors: John Kos, Kenneth Eaton, Sareen Zhang, Rahul Dass, Stephen Buckley, Sungeun An, Ashok Goel
Conceptual and simulation models can function as useful pedagogical tools, however it is important to categorize different outcomes when evaluating them in order to more meaningfully interpret results. VERA is a ecology-based conceptual modeling software that enables users to simulate interactions between biotics and abiotics in an ecosystem, allowing users to form and then verify hypothesis through observing a time series of the species populations. In this paper, we classify this time series into common patterns found in the domain of ecological modeling through two methods, hierarchical clustering and curve fitting, illustrating a general methodology for showing content validity when combining different pedagogical tools. When applied to a diverse sample of 263 models containing 971 time series collected from three different VERA user categories: a Georgia Tech (GATECH), North Georgia Technical College (NGTC), and ``Self Directed Learners'', results showed agreement between both classification methods on 89.38\% of the sample curves in the test set. This serves as a good indication that our methodology for determining content validity was successful.
Authors: Lingfeng Sun, Devesh K. Jha, Chiori Hori, Siddarth Jain, Radu Corcodel, Xinghao Zhu, Masayoshi Tomizuka, Diego Romeres
Designing robotic agents to perform open vocabulary tasks has been the long-standing goal in robotics and AI. Recently, Large Language Models (LLMs) have achieved impressive results in creating robotic agents for performing open vocabulary tasks. However, planning for these tasks in the presence of uncertainties is challenging as it requires \enquote{chain-of-thought} reasoning, aggregating information from the environment, updating state estimates, and generating actions based on the updated state estimates. In this paper, we present an interactive planning technique for partially observable tasks using LLMs. In the proposed method, an LLM is used to collect missing information from the environment using a robot and infer the state of the underlying problem from collected observations while guiding the robot to perform the required actions. We also use a fine-tuned Llama 2 model via self-instruct and compare its performance against a pre-trained LLM like GPT-4. Results are demonstrated on several tasks in simulation as well as real-world environments. A video describing our work along with some results could be found here.
Authors: Johannes Schneider, Mohit Prabhushanka
The learning dynamics of deep neural networks are not well understood. The information bottleneck (IB) theory proclaimed separate fitting and compression phases. But they have since been heavily debated. We comprehensively analyze the learning dynamics by investigating a layer's reconstruction ability of the input and prediction performance based on the evolution of parameters during training. We empirically show the existence of three phases using common datasets and architectures such as ResNet and VGG: (i) near constant reconstruction loss, (ii) decrease, and (iii) increase. We also derive an empirically grounded data model and prove the existence of phases for single-layer networks. Technically, our approach leverages classical complexity analysis. It differs from IB by relying on measuring reconstruction loss rather than information theoretic measures to relate information of intermediate layers and inputs. Our work implies a new best practice for transfer learning: We show empirically that the pre-training of a classifier should stop well before its performance is optimal.
Authors: Renlong Jie, Xiaojun Meng, Xin Jiang, Qun Liu
Unsupervised extractive summarization is an important technique in information extraction and retrieval. Compared with supervised method, it does not require high-quality human-labelled summaries for training and thus can be easily applied for documents with different types, domains or languages. Most of existing unsupervised methods including TextRank and PACSUM rely on graph-based ranking on sentence centrality. However, this scorer can not be directly applied in end-to-end training, and the positional-related prior assumption is often needed for achieving good summaries. In addition, less attention is paid to length-controllable extractor, where users can decide to summarize texts under particular length constraint. This paper introduces an unsupervised extractive summarization model based on a siamese network, for which we develop a trainable bidirectional prediction objective between the selected summary and the original document. Different from the centrality-based ranking methods, our extractive scorer can be trained in an end-to-end manner, with no other requirement of positional assumption. In addition, we introduce a differentiable length control module by approximating 0-1 knapsack solver for end-to-end length-controllable extracting. Experiments show that our unsupervised method largely outperforms the centrality-based baseline using a same sentence encoder. In terms of length control ability, via our trainable knapsack module, the performance consistently outperforms the strong baseline without utilizing end-to-end training. Human evaluation further evidences that our method performs the best among baselines in terms of relevance and consistency.
Authors: Jinqiang Yu, Graham Farr, Alexey Ignatiev, Peter J. Stuckey
Widespread use of artificial intelligence (AI) algorithms and machine learning (ML) models on the one hand and a number of crucial issues pertaining to them warrant the need for explainable artificial intelligence (XAI). A key explainability question is: given this decision was made, what are the input features which contributed to the decision? Although a range of XAI approaches exist to tackle this problem, most of them have significant limitations. Heuristic XAI approaches suffer from the lack of quality guarantees, and often try to approximate Shapley values, which is not the same as explaining which features contribute to a decision. A recent alternative is so-called formal feature attribution (FFA), which defines feature importance as the fraction of formal abductive explanations (AXp's) containing the given feature. This measures feature importance from the view of formally reasoning about the model's behavior. It is challenging to compute FFA using its definition because that involves counting AXp's, although one can approximate it. Based on these results, this paper makes several contributions. First, it gives compelling evidence that computing FFA is intractable, even if the set of contrastive formal explanations (CXp's) is provided, by proving that the problem is #P-hard. Second, by using the duality between AXp's and CXp's, it proposes an efficient heuristic to switch from CXp enumeration to AXp enumeration on-the-fly resulting in an adaptive explanation enumeration algorithm effectively approximating FFA in an anytime fashion. Finally, experimental results obtained on a range of widely used datasets demonstrate the effectiveness of the proposed FFA approximation approach in terms of the error of FFA approximation as well as the number of explanations computed and their diversity given a fixed time limit.
Authors: Anubhav Bhatti, Surajsinh Parmar, San Lee
We are introducing SM70, a 70 billion-parameter Large Language Model that is specifically designed for SpassMed's medical devices under the brand name 'JEE1' (pronounced as G1 and means 'Life'). This large language model provides more accurate and safe responses to medical-domain questions. To fine-tune SM70, we used around 800K data entries from the publicly available dataset MedAlpaca. The Llama2 70B open-sourced model served as the foundation for SM70, and we employed the QLoRA technique for fine-tuning. The evaluation is conducted across three benchmark datasets - MEDQA - USMLE, PUBMEDQA, and USMLE - each representing a unique aspect of medical knowledge and reasoning. The performance of SM70 is contrasted with other notable LLMs, including Llama2 70B, Clinical Camel 70 (CC70), GPT 3.5, GPT 4, and Med-Palm, to provide a comparative understanding of its capabilities within the medical domain. Our results indicate that SM70 outperforms several established models in these datasets, showcasing its proficiency in handling a range of medical queries, from fact-based questions derived from PubMed abstracts to complex clinical decision-making scenarios. The robust performance of SM70, particularly in the USMLE and PUBMEDQA datasets, suggests its potential as an effective tool in clinical decision support and medical information retrieval. Despite its promising results, the paper also acknowledges the areas where SM70 lags behind the most advanced model, GPT 4, thereby highlighting the need for further development, especially in tasks demanding extensive medical knowledge and intricate reasoning.
Authors: Prisha Shroff
Wildfires pose a serious threat to the environment of the world. The global wildfire season length has increased by 19% and severe wildfires have besieged nations around the world. Every year, forests are burned by wildfires, causing vast amounts of carbon dioxide to be released into the atmosphere, contributing to climate change. There is a need for a system which prevents, detects, and suppresses wildfires. The AI based Wildfire Prevention, Detection and Suppression System (WPDSS) is a novel, fully automated, end to end, AI based solution to effectively predict hotspots and detect wildfires, deploy drones to spray fire retardant, preventing and suppressing wildfires. WPDSS consists of four steps. 1. Preprocessing: WPDSS loads real time satellite data from NASA and meteorological data from NOAA of vegetation, temperature, precipitation, wind, soil moisture, and land cover for prevention. For detection, it loads the real time data of Land Cover, Humidity, Temperature, Vegetation, Burned Area Index, Ozone, and CO2. It uses the process of masking to eliminate not hotspots and not wildfires such as water bodies, and rainfall. 2. Learning: The AI model consists of a random forest classifier, which is trained using a labeled dataset of hotspots and wildfires and not hotspots and not wildfires. 3. Identification of hotspots and wildfires: WPDSS runs the real time data through the model to automatically identify hotspots and wildfires. 4. Drone deployment: The drone flies to the identified hotspot or wildfire location. WPDSS attained a 98.6% accuracy in identifying hotspots and a 98.7% accuracy in detecting wildfires. WPDSS will reduce the impacts of climate change, protect ecosystems and biodiversity, avert huge economic losses, and save human lives. The power of WPDSS developed can be applied to any location globally to prevent and suppress wildfires, reducing climate change.
Authors: Yuqing Yang, Ethan Chern, Xipeng Qiu, Graham Neubig, Pengfei Liu
Recent research has made significant strides in applying alignment techniques to enhance the helpfulness and harmlessness of large language models (LLMs) in accordance with human intentions. In this paper, we argue for the importance of alignment for honesty, ensuring that LLMs proactively refuse to answer questions when they lack knowledge, while still not being overly conservative. However, a pivotal aspect of alignment for honesty involves discerning the limits of an LLM's knowledge, which is far from straightforward. This challenge demands comprehensive solutions in terms of metric development, benchmark creation, and training methodologies. In this paper, we address these challenges by first establishing a precise problem definition and defining ``honesty'' inspired by the Analects of Confucius. This serves as a cornerstone for developing metrics that effectively measure an LLM's honesty by quantifying its progress post-alignment. Furthermore, we introduce a flexible training framework which is further instantiated by several efficient fine-tuning techniques that emphasize honesty without sacrificing performance on other tasks. Our extensive experiments reveal that these aligned models show a marked increase in honesty, as indicated by our proposed metrics. We open-source a wealth of resources to facilitate future research at https://github.com/GAIR-NLP/alignment-for-honesty, including honesty-aligned models, training and evaluation datasets for honesty alignment, concept glossary, as well as all relevant source code.
Authors: Tianyi Li, Alexander Halatsis, Raphael Stern
This paper introduces RACER, the Rational Artificial Intelligence Car-following model Enhanced by Reality, a cutting-edge deep learning car-following model, that satisfies partial derivative constraints, designed to predict Adaptive Cruise Control (ACC) driving behavior while staying theoretically feasible. Unlike conventional models, RACER effectively integrates Rational Driving Constraints (RDCs), crucial tenets of actual driving, resulting in strikingly accurate and realistic predictions. Against established models like the Optimal Velocity Relative Velocity (OVRV), a car-following Neural Network (NN), and a car-following Physics-Informed Neural Network (PINN), RACER excels across key metrics, such as acceleration, velocity, and spacing. Notably, it displays a perfect adherence to the RDCs, registering zero violations, in stark contrast to other models. This study highlights the immense value of incorporating physical constraints within AI models, especially for augmenting safety measures in transportation. It also paves the way for future research to test these models against human driving data, with the potential to guide safer and more rational driving behavior. The versatility of the proposed model, including its potential to incorporate additional derivative constraints and broader architectural applications, enhances its appeal and broadens its impact within the scientific community.
Authors: Zeming Chen, Wenwei Zhang, Xinjiang Wang, Kai Chen, Zhi Wang
While the pseudo-label method has demonstrated considerable success in semi-supervised object detection tasks, this paper uncovers notable limitations within this approach. Specifically, the pseudo-label method tends to amplify the inherent strengths of the detector while accentuating its weaknesses, which is manifested in the missed detection of pseudo-labels, particularly for small and tail category objects. To overcome these challenges, this paper proposes Mixed Pseudo Labels (MixPL), consisting of Mixup and Mosaic for pseudo-labeled data, to mitigate the negative impact of missed detections and balance the model's learning across different object scales. Additionally, the model's detection performance on tail categories is improved by resampling labeled data with relevant instances. Notably, MixPL consistently improves the performance of various detectors and obtains new state-of-the-art results with Faster R-CNN, FCOS, and DINO on COCO-Standard and COCO-Full benchmarks. Furthermore, MixPL also exhibits good scalability on large models, improving DINO Swin-L by 2.5% mAP and achieving nontrivial new records (60.2% mAP) on the COCO val2017 benchmark without extra annotations.
Authors: Yuwei Guo, Wenhao Zhang, Licheng Jiao, Shuang Wang, Shuo Wang, Fang Liu
Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality variation. However, these methods often lead to a higher computational overhead and may introduce interfering information when generating the corresponding images or features. To address this issue, it is critical to leverage pedestrian-attentive features and learn modality-complete and -consistent representation. In this paper, a novel Transferring Modality-Aware Pedestrian Attentive Learning (TMPA) model is proposed, focusing on the pedestrian regions to efficiently compensate for missing modality-specific features. Specifically, we propose a region-based data augmentation module PedMix to enhance pedestrian region coherence by mixing the corresponding regions from different modalities. A lightweight hybrid compensation module, i.e., the Modality Feature Transfer (MFT), is devised to integrate cross attention and convolution networks to fully explore the discriminative modality-complete features with minimal computational overhead. Extensive experiments conducted on the benchmark SYSU-MM01 and RegDB datasets demonstrated the effectiveness of our proposed TMPA model.
Authors: Wei Geng, Baidi Xiao, Rongpeng Li, Ning Wei, Dong Wang, Zhifeng Zhao
Generally, Reinforcement Learning (RL) agent updates its policy by repetitively interacting with the environment, contingent on the received rewards to observed states and undertaken actions. However, the environmental disturbance, commonly leading to noisy observations (e.g., rewards and states), could significantly shape the performance of agent. Furthermore, the learning performance of Multi-Agent Reinforcement Learning (MARL) is more susceptible to noise due to the interference among intelligent agents. Therefore, it becomes imperative to revolutionize the design of MARL, so as to capably ameliorate the annoying impact of noisy rewards. In this paper, we propose a novel decomposition-based multi-agent distributional RL method by approximating the globally shared noisy reward by a Gaussian mixture model (GMM) and decomposing it into the combination of individual distributional local rewards, with which each agent can be updated locally through distributional RL. Moreover, a diffusion model (DM) is leveraged for reward generation in order to mitigate the issue of costly interaction expenditure for learning distributions. Furthermore, the optimality of the distribution decomposition is theoretically validated, while the design of loss function is carefully calibrated to avoid the decomposition ambiguity. We also verify the effectiveness of the proposed method through extensive simulation experiments with noisy rewards. Besides, different risk-sensitive policies are evaluated in order to demonstrate the superiority of distributional RL in different MARL tasks.
Authors: Ibtihel Amara, Vinija Jain, Aman Chadha
We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in performance on the subsequent task. Inspired by the adaptive boosting method in traditional machine learning, we present an effective dynamic corrective self-distillation (DCS) approach to improve the fine-tuning of the PLMs. Our technique involves performing a self-distillation mechanism where, at each iteration, the student model actively adapts and corrects itself by dynamically adjusting the weights assigned to individual data points. This iterative self-correcting process significantly enhances the overall fine-tuning capability of PLMs, leading to improved performance and robustness. We conducted comprehensive evaluations using the GLUE benchmark demonstrating the efficacy of our method in enhancing the fine-tuning process for various PLMs across diverse downstream tasks.
Authors: Giang Do, Khiem Le, Quang Pham, TrungTin Nguyen, Thanh-Nam Doan, Bint T. Nguyen, Chenghao Liu, Savitha Ramasamy, Xiaoli Li, Steven Hoi
By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the routers can achieve competitive performance by alleviating the collapsing problem, where all experts eventually learn similar representations. However, this strategy has two key limitations: (i) the policy derived from random routers might be sub-optimal, and (ii) it requires extensive resources during training and evaluation, leading to limited efficiency gains. This work introduces \HyperRout, which dynamically generates the router's parameters through a fixed hypernetwork and trainable embeddings to achieve a balance between training the routers and freezing them to learn an improved routing policy. Extensive experiments across a wide range of tasks demonstrate the superior performance and efficiency gains of \HyperRouter compared to existing routing methods. Our implementation is publicly available at {\url{{https://github.com/giangdip2410/HyperRouter}}}.
Authors: Jonggyu Jang, Hyeonsu Lyu, Hyun Jong Yang
Model inversion (MI) attacks aim to reveal sensitive information in training datasets by solely accessing model weights. Generative MI attacks, a prominent strand in this field, utilize auxiliary datasets to recreate target data attributes, restricting the images to remain photo-realistic, but their success often depends on the similarity between auxiliary and target datasets. If the distributions are dissimilar, existing MI attack attempts frequently fail, yielding unrealistic or target-unrelated results. In response to these challenges, we introduce a groundbreaking approach named Patch-MI, inspired by jigsaw puzzle assembly. To this end, we build upon a new probabilistic interpretation of MI attacks, employing a generative adversarial network (GAN)-like framework with a patch-based discriminator. This approach allows the synthesis of images that are similar to the target dataset distribution, even in cases of dissimilar auxiliary dataset distribution. Moreover, we artfully employ a random transformation block, a sophisticated maneuver that crafts generalized images, thus enhancing the efficacy of the target classifier. Our numerical and graphical findings demonstrate that Patch-MI surpasses existing generative MI methods in terms of accuracy, marking significant advancements while preserving comparable statistical dataset quality. For reproducibility of our results, we make our source code publicly available in https://github.com/jonggyujang0123/Patch-Attack.
Authors: Argyrios Deligkas, Eduard Eiben, Robert Ganian, Thekla Hamm, Sebastian Ordyniak
We consider the problem of fairly dividing a set of heterogeneous divisible resources among agents with different preferences. We focus on the setting where the resources correspond to the edges of a connected graph, every agent must be assigned a connected piece of this graph, and the fairness notion considered is the classical envy freeness. The problem is NP-complete, and we analyze its complexity with respect to two natural complexity measures: the number of agents and the number of edges in the graph. While the problem remains NP-hard even for instances with 2 agents, we provide a dichotomy characterizing the complexity of the problem when the number of agents is constant based on structural properties of the graph. For the latter case, we design a polynomial-time algorithm when the graph has a constant number of edges.
Authors: Quentin Hillebrand, Vorapong Suppakitpaisarn, Tetsuo Shibuya
We suggest the use of hash functions to cut down the communication costs when counting subgraphs under edge local differential privacy. While various algorithms exist for computing graph statistics, including the count of subgraphs, under the edge local differential privacy, many suffer with high communication costs, making them less efficient for large graphs. Though data compression is a typical approach in differential privacy, its application in local differential privacy requires a form of compression that every node can reproduce. In our study, we introduce linear congruence hashing. With a sampling rate of $s$, our method can cut communication costs by a factor of $s^2$, albeit at the cost of increasing variance in the published graph statistic by a factor of $s$. The experimental results indicate that, when matched for communication costs, our method achieves a reduction in the $\ell_2$-error for triangle counts by up to 1000 times compared to the performance of leading algorithms.
Authors: Praveen Damacharla, Hamid Rajabalipanah, Mohammad Hosein Fakheri
There are multiple applications to automatically count people and specify their gender at work, exhibitions, malls, sales, and industrial usage. Although current speech detection methods are supposed to operate well, in most situations, in addition to genders, the number of current speakers is unknown and the classification methods are not suitable due to many possible classes. In this study, we focus on a long-short-term memory convolutional neural network (LSTM-CNN) to extract time and / or frequency-dependent features of the sound data to estimate the number / gender of simultaneous active speakers at each frame in noisy environments. Considering the maximum number of speakers as 10, we have utilized 19000 audio samples with diverse combinations of males, females, and background noise in public cities, industrial situations, malls, exhibitions, workplaces, and nature for learning purposes. This proof of concept shows promising performance with training/validation MSE values of about 0.019/0.017 in detecting count and gender.
Authors: Xiang Li, Haoran Tang, Siyu Chen, Ziwei Wang, Anurag Maravi, Marcin Abram
In this paper, we explore the challenges inherent to Large Language Models (LLMs) like GPT-4, particularly their propensity for hallucinations, logic mistakes, and incorrect conclusions when tasked with answering complex questions. The capacity of LLMs to present erroneous answers in a coherent and semantically rigorous manner further complicates the detection of factual inaccuracies. This issue is especially pronounced in fields that require specialized expertise. Our work delves into these challenges, aiming to enhance the understanding and mitigation of such errors, thereby contributing to the improvement of LLM accuracy and reliability in scientific and other specialized domains. Our findings reveal a non-linear relationship between the context's relevancy and the answers' measured quality. In addition, we demonstrate that with the correct calibration, it is possible to automate the grading procedure -- a finding suggesting that, at least to some degree, the LLMs can be used to self-examine the quality of their own performance. Finally, we describe an experimental platform that can be seen as a proof-of-concept of the techniques described in this work.
Authors: Mike Perkins (1), Leon Furze (2), Jasper Roe (3), Jason MacVaugh (1) ((1) British University Vietnam, (2) Deakin University, (3) James Cook University Singapore)
Recent developments in Generative Artificial Intelligence (GenAI) have created a paradigm shift in multiple areas of society, and the use of these technologies is likely to become a defining feature of education in coming decades. GenAI offers transformative pedagogical opportunities, while simultaneously posing ethical and academic challenges. Against this backdrop, we outline a practical, simple, and sufficiently comprehensive tool to allow for the integration of GenAI tools into educational assessment: the AI Assessment Scale (AIAS). The AIAS empowers educators to select the appropriate level of GenAI usage in assessments based on the learning outcomes they seek to address. The AIAS offers greater clarity and transparency for students and educators, provides a fair and equitable policy tool for institutions to work with, and offers a nuanced approach which embraces the opportunities of GenAI while recognising that there are instances where such tools may not be pedagogically appropriate or necessary. By adopting a practical, flexible approach that can be implemented quickly, the AIAS can form a much-needed starting point to address the current uncertainty and anxiety regarding GenAI in education. As a secondary objective, we engage with the current literature and advocate for a refocused discourse on GenAI tools in education, one which foregrounds how technologies can help support and enhance teaching and learning, which contrasts with the current focus on GenAI as a facilitator of academic misconduct.
Authors: Hwanjun Song, Minseok Kim, Jae-Gil Lee
Multi-label classification poses challenges due to imbalanced and noisy labels in training data. We propose a unified data augmentation method, named BalanceMix, to address these challenges. Our approach includes two samplers for imbalanced labels, generating minority-augmented instances with high diversity. It also refines multi-labels at the label-wise granularity, categorizing noisy labels as clean, re-labeled, or ambiguous for robust optimization. Extensive experiments on three benchmark datasets demonstrate that BalanceMix outperforms existing state-of-the-art methods. We release the code at https://github.com/DISL-Lab/BalanceMix.
Authors: Nantao Zheng, Siyu Long, Xinyu Dai
Canonical relation extraction aims to extract relational triples from sentences, where the triple elements (entity pairs and their relationship) are mapped to the knowledge base. Recently, methods based on the encoder-decoder architecture are proposed and achieve promising results. However, these methods cannot well utilize the entity information, which is merely used as augmented training data. Moreover, they are incapable of representing novel entities, since no embeddings have been learned for them. In this paper, we propose a novel framework, Bi-Encoder-Decoder (BED), to solve the above issues. Specifically, to fully utilize entity information, we employ an encoder to encode semantics of this information, leading to high-quality entity representations. For novel entities, given a trained entity encoder, their representations can be easily generated. Experimental results on two datasets show that, our method achieves a significant performance improvement over the previous state-of-the-art and handle novel entities well without retraining.
Authors: Madalina Olteanu (CEREMADE), Fabrice Rossi (CEREMADE), Florian Yger (MILES, LAMSADE)
The impact of outliers and anomalies on model estimation and data processing is of paramount importance, as evidenced by the extensive body of research spanning various fields over several decades: thousands of research papers have been published on the subject. As a consequence, numerous reviews, surveys, and textbooks have sought to summarize the existing literature, encompassing a wide range of methods from both the statistical and data mining communities. While these endeavors to organize and summarize the research are invaluable, they face inherent challenges due to the pervasive nature of outliers and anomalies in all data-intensive applications, irrespective of the specific application field or scientific discipline. As a result, the resulting collection of papers remains voluminous and somewhat heterogeneous. To address the need for knowledge organization in this domain, this paper implements the first systematic meta-survey of general surveys and reviews on outlier and anomaly detection. Employing a classical systematic survey approach, the study collects nearly 500 papers using two specialized scientific search engines. From this comprehensive collection, a subset of 56 papers that claim to be general surveys on outlier detection is selected using a snowball search technique to enhance field coverage. A meticulous quality assessment phase further refines the selection to a subset of 25 high-quality general surveys. Using this curated collection, the paper investigates the evolution of the outlier detection field over a 20-year period, revealing emerging themes and methods. Furthermore, an analysis of the surveys sheds light on the survey writing practices adopted by scholars from different communities who have contributed to this field. Finally, the paper delves into several topics where consensus has emerged from the literature. These include taxonomies of outlier types, challenges posed by high-dimensional data, the importance of anomaly scores, the impact of learning conditions, difficulties in benchmarking, and the significance of neural networks. Non-consensual aspects are also discussed, particularly the distinction between local and global outliers and the challenges in organizing detection methods into meaningful taxonomies.
Authors: Jiawei Sun, Bin Zhao, Dong Wang, Zhigang Wang, Jie Zhang, Nektarios Koukourakis, Juergen W. Czarske, Xuelong Li
Quantitative phase imaging (QPI) through multi-core fibers (MCFs) has been an emerging in vivo label-free endoscopic imaging modality with minimal invasiveness. However, the computational demands of conventional iterative phase retrieval algorithms have limited their real-time imaging potential. We demonstrate a learning-based MCF phase imaging method, that significantly reduced the phase reconstruction time to 5.5 ms, enabling video-rate imaging at 181 fps. Moreover, we introduce an innovative optical system that automatically generated the first open-source dataset tailored for MCF phase imaging, comprising 50,176 paired speckle and phase images. Our trained deep neural network (DNN) demonstrates robust phase reconstruction performance in experiments with a mean fidelity of up to 99.8\%. Such an efficient fiber phase imaging approach can broaden the applications of QPI in hard-to-reach areas.
Authors: Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Jeff Huang, Chuyue Sun, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, Ying Sheng
Large language models (LLMs) are increasingly used for complex tasks requiring multiple chained generation calls, advanced prompting techniques, control flow, and interaction with external environments. However, efficient systems for programming and executing these applications are lacking. To bridge this gap, we introduce SGLang, a Structured Generation Language for LLMs. SGLang is designed for the efficient programming of LLMs and incorporates primitives for common LLM programming patterns. We have implemented SGLang as a domain-specific language embedded in Python, and we developed an interpreter, a compiler, and a high-performance runtime for SGLang. These components work together to enable optimizations such as parallelism, batching, caching, sharing, and other compilation techniques. Additionally, we propose RadixAttention, a novel technique that maintains a Least Recently Used (LRU) cache of the Key-Value (KV) cache for all requests in a radix tree, enabling automatic KV cache reuse across multiple generation calls at runtime. SGLang simplifies the writing of LLM programs and boosts execution efficiency. Our experiments demonstrate that SGLang can speed up common LLM tasks by up to 5x, while reducing code complexity and enhancing control.
Authors: Junli Jiang, Pavel Naumov
In many real-world situations, there is often not enough information to know that a certain strategy will succeed in achieving the goal, but there is a good reason to believe that it will. The paper introduces the term ``doxastic'' for such strategies.
The main technical contribution is a sound and complete logical system that describes the interplay between doxastic strategy and belief modalities.
Authors: Naufal Shidqi, Chaeyoon Jeong, Sungwon Park, Elke Zeller, Arjun Babu Nellikkattil, Karandeep Singh
Climate downscaling is a crucial technique within climate research, serving to project low-resolution (LR) climate data to higher resolutions (HR). Previous research has demonstrated the effectiveness of deep learning for downscaling tasks. However, most deep learning models for climate downscaling may not perform optimally for high scaling factors (i.e., 4x, 8x) due to their limited ability to capture the intricate details required for generating HR climate data. Furthermore, climate data behaves differently from image data, necessitating a nuanced approach when employing deep generative models. In response to these challenges, this paper presents a deep generative model for downscaling climate data, specifically precipitation on a regional scale. We employ a denoising diffusion probabilistic model (DDPM) conditioned on multiple LR climate variables. The proposed model is evaluated using precipitation data from the Community Earth System Model (CESM) v1.2.2 simulation. Our results demonstrate significant improvements over existing baselines, underscoring the effectiveness of the conditional diffusion model in downscaling climate data.
Authors: Matteo Bortoletto, Lei Shi, Andreas Bulling
We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks - with up to 48.9% improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks.
Authors: Yimo Deng, Huangxun Chen
Text-to-image generative models offer many innovative services but also raise ethical concerns due to their potential to generate unethical images. Most publicly available text-to-image models employ safety filters to prevent unintended generation intents. In this work, we introduce the Divide-and-Conquer Attack to circumvent the safety filters of state-of-the-art text-to-image models. Our attack leverages LLMs as agents for text transformation, creating adversarial prompts from sensitive ones. We have developed effective helper prompts that enable LLMs to break down sensitive drawing prompts into multiple harmless descriptions, allowing them to bypass safety filters while still generating sensitive images. This means that the latent harmful meaning only becomes apparent when all individual elements are drawn together. Our evaluation demonstrates that our attack successfully circumvents the closed-box safety filter of SOTA DALLE-3 integrated natively into ChatGPT to generate unethical images. This approach, which essentially uses LLM-generated adversarial prompts against GPT-4-assisted DALLE-3, is akin to using one's own spear to breach their shield. It could have more severe security implications than previous manual crafting or iterative model querying methods, and we hope it stimulates more attention towards similar efforts. Our code and data are available at: https://github.com/researchcode001/Divide-and-Conquer-Attack
Authors: Eduard Eiben, Robert Ganian, Iyad Kanj
In Coordinated Motion Planning (CMP), we are given a rectangular-grid on which $k$ robots occupy $k$ distinct starting gridpoints and need to reach $k$ distinct destination gridpoints. In each time step, any robot may move to a neighboring gridpoint or stay in its current gridpoint, provided that it does not collide with other robots. The goal is to compute a schedule for moving the $k$ robots to their destinations which minimizes a certain objective target - prominently the number of time steps in the schedule, i.e., the makespan, or the total length traveled by the robots. We refer to the problem arising from minimizing the former objective target as CMP-M and the latter as CMP-L. Both CMP-M and CMP-L are fundamental problems that were posed as the computational geometry challenge of SoCG 2021, and CMP also embodies the famous $(n^2-1)$-puzzle as a special case.
In this paper, we settle the parameterized complexity of CMP-M and CMP-L with respect to their two most fundamental parameters: the number of robots, and the objective target. We develop a new approach to establish the fixed-parameter tractability of both problems under the former parameterization that relies on novel structural insights into optimal solutions to the problem. When parameterized by the objective target, we show that CMP-L remains fixed-parameter tractable while CMP-M becomes para-NP-hard. The latter result is noteworthy, not only because it improves the previously-known boundaries of intractability for the problem, but also because the underlying reduction allows us to establish - as a simpler case - the NP-hardness of the classical Vertex Disjoint and Edge Disjoint Paths problems with constant path-lengths on grids.
Authors: Yuwei Han, Yuni Lai, Yulin Zhu, Kai Zhou
Graph Neural Networks (GNNs) have become widely used in the field of graph mining. However, these networks are vulnerable to structural perturbations. While many research efforts have focused on analyzing vulnerability through poisoning attacks, we have identified an inefficiency in current attack losses. These losses steer the attack strategy towards modifying edges targeting misclassified nodes or resilient nodes, resulting in a waste of structural adversarial perturbation. To address this issue, we propose a novel attack loss framework called the Cost Aware Poisoning Attack (CA-attack) to improve the allocation of the attack budget by dynamically considering the classification margins of nodes. Specifically, it prioritizes nodes with smaller positive margins while postponing nodes with negative margins. Our experiments demonstrate that the proposed CA-attack significantly enhances existing attack strategies
Authors: I-Jieh Liu, Ci-Siang Lin, Fu-En Yang, Yu-Chiang Frank Wang
Federated Learning (FL) is an emerging paradigm that enables multiple users to collaboratively train a robust model in a privacy-preserving manner without sharing their private data. Most existing approaches of FL only consider traditional single-label image classification, ignoring the impact when transferring the task to multi-label image classification. Nevertheless, it is still challenging for FL to deal with user heterogeneity in their local data distribution in the real-world FL scenario, and this issue becomes even more severe in multi-label image classification. Inspired by the recent success of Transformers in centralized settings, we propose a novel FL framework for multi-label classification. Since partial label correlation may be observed by local clients during training, direct aggregation of locally updated models would not produce satisfactory performances. Thus, we propose a novel FL framework of Language-Guided Transformer (FedLGT) to tackle this challenging task, which aims to exploit and transfer knowledge across different clients for learning a robust global model. Through extensive experiments on various multi-label datasets (e.g., FLAIR, MS-COCO, etc.), we show that our FedLGT is able to achieve satisfactory performance and outperforms standard FL techniques under multi-label FL scenarios. Code is available at https://github.com/Jack24658735/FedLGT.
Authors: Yuxuan Song, Jingjing Gong, Minkai Xu, Ziyao Cao, Yanyan Lan, Stefano Ermon, Hao Zhou, Wei-Ying Ma
The generation of 3D molecules requires simultaneously deciding the categorical features~(atom types) and continuous features~(atom coordinates). Deep generative models, especially Diffusion Models (DMs), have demonstrated effectiveness in generating feature-rich geometries. However, existing DMs typically suffer from unstable probability dynamics with inefficient sampling speed. In this paper, we introduce geometric flow matching, which enjoys the advantages of both equivariant modeling and stabilized probability dynamics. More specifically, we propose a hybrid probability path where the coordinates probability path is regularized by an equivariant optimal transport, and the information between different modalities is aligned. Experimentally, the proposed method could consistently achieve better performance on multiple molecule generation benchmarks with 4.75$\times$ speed up of sampling on average.
Authors: Debo Cheng, Ziqi Xu, Jiuyong Li, Lin Liu, Jixue Liu, Wentao Gao, Thuc Duy Le (UniSA STEM, University of South Australia, Adelaide, SA, Australia)
Causal inference from longitudinal observational data is a challenging problem due to the difficulty in correctly identifying the time-dependent confounders, especially in the presence of latent time-dependent confounders. Instrumental variable (IV) is a powerful tool for addressing the latent confounders issue, but the traditional IV technique cannot deal with latent time-dependent confounders in longitudinal studies. In this work, we propose a novel Time-dependent Instrumental Factor Model (TIFM) for time-varying causal effect estimation from data with latent time-dependent confounders. At each time-step, the proposed TIFM method employs the Recurrent Neural Network (RNN) architecture to infer latent IV, and then uses the inferred latent IV factor for addressing the confounding bias caused by the latent time-dependent confounders. We provide a theoretical analysis for the proposed TIFM method regarding causal effect estimation in longitudinal data. Extensive evaluation with synthetic datasets demonstrates the effectiveness of TIFM in addressing causal effect estimation over time. We further apply TIFM to a climate dataset to showcase the potential of the proposed method in tackling real-world problems.
Authors: Manon Flageat, Bryan Lim, Antoine Cully
Many applications in Reinforcement Learning (RL) usually have noise or stochasticity present in the environment. Beyond their impact on learning, these uncertainties lead the exact same policy to perform differently, i.e. yield different return, from one roll-out to another. Common evaluation procedures in RL summarise the consequent return distributions using solely the expected return, which does not account for the spread of the distribution. Our work defines this spread as the policy reproducibility: the ability of a policy to obtain similar performance when rolled out many times, a crucial property in some real-world applications. We highlight that existing procedures that only use the expected return are limited on two fronts: first an infinite number of return distributions with a wide range of performance-reproducibility trade-offs can have the same expected return, limiting its effectiveness when used for comparing policies; second, the expected return metric does not leave any room for practitioners to choose the best trade-off value for considered applications. In this work, we address these limitations by recommending the use of Lower Confidence Bound, a metric taken from Bayesian optimisation that provides the user with a preference parameter to choose a desired performance-reproducibility trade-off. We also formalise and quantify policy reproducibility, and demonstrate the benefit of our metrics using extensive experiments of popular RL algorithms on common uncertain RL tasks.
Authors: Peiwen Sun, Yifan Zhang, Zishan Liu, Donghao Chen, Honggang Zhang
The vanilla fusion methods still dominate a large percentage of mainstream audio-visual tasks. However, the effectiveness of vanilla fusion from a theoretical perspective is still worth discussing. Thus, this paper reconsiders the signal fused in the multimodal case from a bionics perspective and proposes a simple, plug-and-play, attention module for vanilla fusion based on fundamental signal theory and uncertainty theory. In addition, previous work on multimodal dynamic gradient modulation still relies on decoupling the modalities. So, a decoupling-free gradient modulation scheme has been designed in conjunction with the aforementioned attention module, which has various advantages over the decoupled one. Experiment results show that just a few lines of code can achieve up to 2.0% performance improvements to several multimodal classification methods. Finally, quantitative evaluation of other fusion tasks reveals the potential for additional application scenarios.
Authors: Bihui Yu, Sibo Zhang
The continuous development of artificial intelligence has a profound impact on biomedical research and other fields.Brain-inspired computing is an important intersection of multimodal technology and biomedical field. This paper provides a comprehensive review of machine learning (ML) and deep learning (DL) models in brain-inspired computing, tracking their evolution, application value, challenges, and potential research trajectories. First, the basic concepts and development history are reviewed, and their evolution is divided into two stages: recent machine learning and current deep learning, emphasizing the importance of each stage in the research state of brain-inspired computing. In addition, the latest progress and key techniques of deep learning in different tasks of brain-inspired computing are introduced from six perspectives. Despite significant progress, challenges remain in making full use of its capabilities. This paper aims to provide a comprehensive review of brain-inspired computing models based on machine learning and deep learning, highlighting their potential in various applications and providing a valuable reference for future academic research. It can be accessed through the following url: https://github.com/ultracoolHub/brain-inspired-computing
Authors: Younes Lakhnati, Max Pascher, Jens Gerken
In a rapidly evolving digital landscape autonomous tools and robots are becoming commonplace. Recognizing the significance of this development, this paper explores the integration of Large Language Models (LLMs) like Generative pre-trained transformer (GPT) into human-robot teaming environments to facilitate variable autonomy through the means of verbal human-robot communication. In this paper, we introduce a novel framework for such a GPT-powered multi-robot testbed environment, based on a Unity Virtual Reality (VR) setting. This system allows users to interact with robot agents through natural language, each powered by individual GPT cores. By means of OpenAI's function calling, we bridge the gap between unstructured natural language input and structure robot actions. A user study with 12 participants explores the effectiveness of GPT-4 and, more importantly, user strategies when being given the opportunity to converse in natural language within a multi-robot environment. Our findings suggest that users may have preconceived expectations on how to converse with robots and seldom try to explore the actual language and cognitive capabilities of their robot collaborators. Still, those users who did explore where able to benefit from a much more natural flow of communication and human-like back-and-forth. We provide a set of lessons learned for future research and technical implementations of similar systems.
Authors: Yuanbin Wang, Shaofei Huang, Yulu Gao, Zhen Wang, Rui Wang, Kehua Sheng, Bo Zhang, Si Liu
Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-scale visual-language pre-trained models, such as CLIP, have shown their generalization ability in the zero-shot 2D vision tasks, but are still unable to be applied to 3D semantic segmentation directly. In this work, we focus on zero-shot point cloud semantic segmentation and propose a simple yet effective baseline to transfer the visual-linguistic knowledge implied in CLIP to point cloud encoder at both feature and output levels. Both feature-level and output-level alignments are conducted between 2D and 3D encoders for effective knowledge transfer. Concretely, a Multi-granularity Cross-modal Feature Alignment (MCFA) module is proposed to align 2D and 3D features from global semantic and local position perspectives for feature-level alignment. For the output level, per-pixel pseudo labels of unseen classes are extracted using the pre-trained CLIP model as supervision for the 3D segmentation model to mimic the behavior of the CLIP image encoder. Extensive experiments are conducted on two popular benchmarks of point cloud segmentation. Our method outperforms significantly previous state-of-the-art methods under zero-shot setting (+29.2% mIoU on SemanticKITTI and 31.8% mIoU on nuScenes), and further achieves promising results in the annotation-free point cloud semantic segmentation setting, showing its great potential for label-efficient learning.
Authors: Shentong Mo, Enze Xie, Yue Wu, Junsong Chen, Matthias Nießner, Zhenguo Li
Diffusion Transformers have recently shown remarkable effectiveness in generating high-quality 3D point clouds. However, training voxel-based diffusion models for high-resolution 3D voxels remains prohibitively expensive due to the cubic complexity of attention operators, which arises from the additional dimension of voxels. Motivated by the inherent redundancy of 3D compared to 2D, we propose FastDiT-3D, a novel masked diffusion transformer tailored for efficient 3D point cloud generation, which greatly reduces training costs. Specifically, we draw inspiration from masked autoencoders to dynamically operate the denoising process on masked voxelized point clouds. We also propose a novel voxel-aware masking strategy to adaptively aggregate background/foreground information from voxelized point clouds. Our method achieves state-of-the-art performance with an extreme masking ratio of nearly 99%. Moreover, to improve multi-category 3D generation, we introduce Mixture-of-Expert (MoE) in 3D diffusion model. Each category can learn a distinct diffusion path with different experts, relieving gradient conflict. Experimental results on the ShapeNet dataset demonstrate that our method achieves state-of-the-art high-fidelity and diverse 3D point cloud generation performance. Our FastDiT-3D improves 1-Nearest Neighbor Accuracy and Coverage metrics when generating 128-resolution voxel point clouds, using only 6.5% of the original training cost.
Authors: Enshu Liu, Xuefei Ning, Huazhong Yang, Yu Wang
Recent years have witnessed the rapid progress and broad application of diffusion probabilistic models (DPMs). Sampling from DPMs can be viewed as solving an ordinary differential equation (ODE). Despite the promising performance, the generation of DPMs usually consumes much time due to the large number of function evaluations (NFE). Though recent works have accelerated the sampling to around 20 steps with high-order solvers, the sample quality with less than 10 NFE can still be improved. In this paper, we propose a unified sampling framework (USF) to study the optional strategies for solver. Under this framework, we further reveal that taking different solving strategies at different timesteps may help further decrease the truncation error, and a carefully designed \emph{solver schedule} has the potential to improve the sample quality by a large margin. Therefore, we propose a new sampling framework based on the exponential integral formulation that allows free choices of solver strategy at each step and design specific decisions for the framework. Moreover, we propose $S^3$, a predictor-based search method that automatically optimizes the solver schedule to get a better time-quality trade-off of sampling. We demonstrate that $S^3$ can find outstanding solver schedules which outperform the state-of-the-art sampling methods on CIFAR-10, CelebA, ImageNet, and LSUN-Bedroom datasets. Specifically, we achieve 2.69 FID with 10 NFE and 6.86 FID with 5 NFE on CIFAR-10 dataset, outperforming the SOTA method significantly. We further apply $S^3$ to Stable-Diffusion model and get an acceleration ratio of 2$\times$, showing the feasibility of sampling in very few steps without retraining the neural network.
Authors: Chengyang Ye, Qiang Ma
Representation learning plays a critical role in the analysis of time series data and has high practical value across a wide range of applications. including trend analysis, time series data retrieval and forecasting. In practice, data confusion is a significant issue as it can considerably impact the effectiveness and accuracy of data analysis, machine learning models and decision-making processes. In general, previous studies did not consider the variability at various levels of granularity, thus resulting in inadequate information utilization, which further exacerbated the issue of data confusion. This paper proposes an unsupervised framework to realize multi-granularity representation learning for time series. Specifically, we employed a cross-granularity transformer to develop an association between fine- and coarse-grained representations. In addition, we introduced a retrieval task as an unsupervised training task to learn the multi-granularity representation of time series. Moreover, a novel loss function was designed to obtain the comprehensive multi-granularity representation of the time series via unsupervised learning. The experimental results revealed that the proposed framework demonstrates significant advantages over alternative representation learning models.
Authors: Lifeng Han, Serge Gladkoff, Gleb Erofeev, Irina Sorokina, Betty Galiano, Goran Nenadic
We conduct investigations on clinical text machine translation by examining multilingual neural network models using deep learning such as Transformer based structures. Furthermore, to address the language resource imbalance issue, we also carry out experiments using a transfer learning methodology based on massive multilingual pre-trained language models (MMPLMs). The experimental results on three subtasks including 1) clinical case (CC), 2) clinical terminology (CT), and 3) ontological concept (OC) show that our models achieved top-level performances in the ClinSpEn-2022 shared task on English-Spanish clinical domain data. Furthermore, our expert-based human evaluations demonstrate that the small-sized pre-trained language model (PLM) won over the other two extra-large language models by a large margin, in the clinical domain fine-tuning, which finding was never reported in the field. Finally, the transfer learning method works well in our experimental setting using the WMT21fb model to accommodate a new language space Spanish that was not seen at the pre-training stage within WMT21fb itself, which deserves more exploitation for clinical knowledge transformation, e.g. to investigate into more languages. These research findings can shed some light on domain-specific machine translation development, especially in clinical and healthcare fields. Further research projects can be carried out based on our work to improve healthcare text analytics and knowledge transformation.
Authors: Cheng Zeng, Yixuan Xu, Jiaqi Tian
This study explores the robustness of label noise classifiers, aiming to enhance model resilience against noisy data in complex real-world scenarios. Label noise in supervised learning, characterized by erroneous or imprecise labels, significantly impairs model performance. This research focuses on the increasingly pertinent issue of label noise's impact on practical applications. Addressing the prevalent challenge of inaccurate training data labels, we integrate adversarial machine learning (AML) and importance reweighting techniques. Our approach involves employing convolutional neural networks (CNN) as the foundational model, with an emphasis on parameter adjustment for individual training samples. This strategy is designed to heighten the model's focus on samples critically influencing performance.
Authors: Fausto Giunchiglia, Mayukh Bagchi
Knowledge Representation (KR) and facet-analytical Knowledge Organization (KO) have been the two most prominent methodologies of data and knowledge modelling in the Artificial Intelligence community and the Information Science community, respectively. KR boasts of a robust and scalable ecosystem of technologies to support knowledge modelling while, often, underemphasizing the quality of its models (and model-based data). KO, on the other hand, is less technology-driven but has developed a robust framework of guiding principles (canons) for ensuring modelling (and model-based data) quality. This paper elucidates both the KR and facet-analytical KO methodologies in detail and provides a functional mapping between them. Out of the mapping, the paper proposes an integrated KO-enriched KR methodology with all the standard components of a KR methodology plus the guiding canons of modelling quality provided by KO. The practical benefits of the methodological integration has been exemplified through a prominent case study of KR-based image annotation exercise.
Authors: Yuxiang Guo
Sparse attention as a efficient method can significantly decrease the computation cost, but current sparse attention tend to rely on window self attention which block the global information flow. For this problem, we present Shifted Cross Chunk Attention (SCCA), using different KV shifting strategy to extend respective field in each attention layer. Except, we combine Dilated Attention(DA) and Dilated Neighborhood Attention(DNA) to present Shifted Dilated Attention(SDA). Both SCCA and SDA can accumulate attention results in multi head attention to obtain approximate respective field in full attention. In this paper, we conduct language modeling experiments using different pattern of SCCA and combination of SCCA and SDA. The proposed shifted cross chunk attention (SCCA) can effectively extend large language models (LLMs) to longer context combined with Positional interpolation(PI) and LoRA than current sparse attention. Notably, SCCA adopts LLaMA2 7B from 4k context to 8k in single V100. This attention pattern can provide a Plug-and-play fine-tuning method to extend model context while retaining their original architectures, and is compatible with most existing techniques.
Authors: Wenjie Yin, Yi Yu, Hang Yin, Danica Kragic, Mårten Björkman
Current training of motion style transfer systems relies on consistency losses across style domains to preserve contents, hindering its scalable application to a large number of domains and private data. Recent image transfer works show the potential of independent training on each domain by leveraging implicit bridging between diffusion models, with the content preservation, however, limited to simple data patterns. We address this by imposing biased sampling in backward diffusion while maintaining the domain independence in the training stage. We construct the bias from the source domain keyframes and apply them as the gradient of content constraints, yielding a framework with keyframe manifold constraint gradients (KMCGs). Our validation demonstrates the success of training separate models to transfer between as many as ten dance motion styles. Comprehensive experiments find a significant improvement in preserving motion contents in comparison to baseline and ablative diffusion-based style transfer models. In addition, we perform a human study for a subjective assessment of the quality of generated dance motions. The results validate the competitiveness of KMCGs.
Authors: Pavel Petracek, Kostas Alexis, Martin Saska
The typical point cloud sampling methods used in state estimation for mobile robots preserve a high level of point redundancy. The point redundancy slows down the estimation pipeline and can make real-time estimation drift in geometrically symmetrical and structureless environments. We propose a novel point cloud sampling method that is capable of lowering the effects of geometrical degeneracies by minimizing redundancy within the cloud. The proposed method is an alternative to the commonly used sparsification methods that normalize the density of points to comply with the constraints on the real-time capabilities of a robot. In contrast to density normalization, our method builds on the fact that linear and planar surfaces contain a high level of redundancy propagated into iterative estimation pipelines. We define the concept of gradient flow quantifying the surface underlying a point. We also show that maximizing the entropy of the gradient flow minimizes point redundancy for robot ego-motion estimation. We integrate the proposed method into the point-based KISS-ICP and feature-based LOAM odometry pipelines and evaluate it experimentally on KITTI, Hilti-Oxford, and custom datasets from multirotor UAVs. The experiments show that the proposed sampling technique outperforms state-of-the-art methods in well-conditioned as well as in geometrically-degenerated settings, in both accuracy and speed.
Authors: Anishka, Atharva Mehta, Nipun Gupta, Dhruv Kumar, Pankaj Jalote
The emergence of Large language models (LLMs) is expected to have a major impact on education. This paper explores the potential of using ChatGPT, an LLM, as a virtual Teaching Assistant (TA) in an Introductory Programming Course. We evaluate ChatGPT's capabilities by comparing its performance with that of human TAs in some TA functions. The TA functions which we focus on include (1) solving programming assignments, (2) grading student code submissions, and (3) providing feedback to undergraduate students in an introductory programming course. Firstly, we investigate how closely ChatGPT's solutions align with those submitted by students. This analysis goes beyond code correctness and also considers code quality. Secondly, we assess ChatGPT's proficiency in grading student code submissions using a given grading rubric and compare its performance with the grades assigned by human TAs. Thirdly, we analyze the quality and relevance of the feedback provided by ChatGPT. This evaluation considers how well ChatGPT addresses mistakes and offers suggestions for improvement in student solutions from both code correctness and code quality perspectives. We conclude with a discussion on the implications of integrating ChatGPT into computing education for automated grading, personalized learning experiences, and instructional support.
Authors: Chinedu Innocent Nwoye, Kareem Elgohary, Anvita Srinivas, Fauzan Zaid, Joël L. Lavanchy, Nicolas Padoy
Tool tracking in surgical videos is vital in computer-assisted intervention for tasks like surgeon skill assessment, safety zone estimation, and human-machine collaboration during minimally invasive procedures. The lack of large-scale datasets hampers Artificial Intelligence implementation in this domain. Current datasets exhibit overly generic tracking formalization, often lacking surgical context: a deficiency that becomes evident when tools move out of the camera's scope, resulting in rigid trajectories that hinder realistic surgical representation. This paper addresses the need for a more precise and adaptable tracking formalization tailored to the intricacies of endoscopic procedures by introducing CholecTrack20, an extensive dataset meticulously annotated for multi-class multi-tool tracking across three perspectives representing the various ways of considering the temporal duration of a tool trajectory: (1) intraoperative, (2) intracorporeal, and (3) visibility within the camera's scope. The dataset comprises 20 laparoscopic videos with over 35,000 frames and 65,000 annotated tool instances with details on spatial location, category, identity, operator, phase, and surgical visual conditions. This detailed dataset caters to the evolving assistive requirements within a procedure.
Authors: Swarna Kamal Paul
Sequential planning in large state space and action space quickly becomes intractable due to combinatorial explosion of the search space. Heuristic methods, like monte-carlo tree search, though effective for large state space, but struggle if action space is large. Pure reinforcement learning methods, relying only on reward signals, needs prohibitively large interactions with the environment to device a viable plan. If the state space, observations and actions can be represented in natural language then Large Language models (LLM) can be used to generate action plans. Recently several such goal-directed agents like Reflexion, CLIN, SayCan were able to surpass the performance of other state-of-the-art methods with minimum or no task specific training. But they still struggle with exploration and get stuck in local optima. Their planning capabilities are limited by the limited reasoning capability of the foundational LLMs on text data. We propose a hybrid agent "neoplanner", that synergizes both state space search with queries to foundational LLM to get the best action plan. The reward signals are quantitatively used to drive the search. A balance of exploration and exploitation is maintained by maximizing upper confidence bounds of values of states. In places where random exploration is needed, the LLM is queried to generate an action plan. Learnings from each trial are stored as entity relationships in text format. Those are used in future queries to the LLM for continual improvement. Experiments in the Scienceworld environment reveals a 124% improvement from the current best method in terms of average reward gained across multiple tasks.
Authors: Sen Yan, Hongyuan Fang, Ji Li, Tomas Ward, Noel O'Connor, Mingming Liu
Battery Electric Vehicles (BEVs) are increasingly significant in modern cities due to their potential to reduce air pollution. Precise and real-time estimation of energy consumption for them is imperative for effective itinerary planning and optimizing vehicle systems, which can reduce driving range anxiety and decrease energy costs. As public awareness of data privacy increases, adopting approaches that safeguard data privacy in the context of BEV energy consumption modeling is crucial. Federated Learning (FL) is a promising solution mitigating the risk of exposing sensitive information to third parties by allowing local data to remain on devices and only sharing model updates with a central server. Our work investigates the potential of using FL methods, such as FedAvg, and FedPer, to improve BEV energy consumption prediction while maintaining user privacy. We conducted experiments using data from 10 BEVs under simulated real-world driving conditions. Our results demonstrate that the FedAvg-LSTM model achieved a reduction of up to 67.84\% in the MAE value of the prediction results. Furthermore, we explored various real-world scenarios and discussed how FL methods can be employed in those cases. Our findings show that FL methods can effectively improve the performance of BEV energy consumption prediction while maintaining user privacy.
Authors: Haoyu Tang, Han Jiang, Mingzhu Xu, Yupeng Hu, Jihua Zhu, Liqiang Nie
Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and action categories, which is labor-intensive and time-consuming. Although some unsupervised methods have utilized the ``iteratively clustering and localization'' paradigm for TAL, they still suffer from two pivotal impediments: 1) unsatisfactory video clustering confidence, and 2) unreliable video pseudolabels for model training. To address these limitations, we present a novel self-paced incremental learning model to enhance clustering and localization training simultaneously, thereby facilitating more effective unsupervised TAL. Concretely, we improve the clustering confidence through exploring the contextual feature-robust visual information. Thereafter, we design two (constant- and variable- speed) incremental instance learning strategies for easy-to-hard model training, thus ensuring the reliability of these video pseudolabels and further improving overall localization performance. Extensive experiments on two public datasets have substantiated the superiority of our model over several state-of-the-art competitors.
Authors: Xiangyu Yin, Sihao Wu, Jiaxu Liu, Meng Fang, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan
While Goal-Conditioned Reinforcement Learning (GCRL) has gained attention, its algorithmic robustness, particularly against adversarial perturbations, remains unexplored. Unfortunately, the attacks and robust representation training methods specifically designed for traditional RL are not so effective when applied to GCRL. To address this challenge, we propose the \textit{Semi-Contrastive Representation} attack, a novel approach inspired by the adversarial contrastive attack. Unlike existing attacks in RL, it only necessitates information from the policy function and can be seamlessly implemented during deployment. Furthermore, to mitigate the vulnerability of existing GCRL algorithms, we introduce \textit{Adversarial Representation Tactics}. This strategy combines \textit{Semi-Contrastive Adversarial Augmentation} with \textit{Sensitivity-Aware Regularizer}. It improves the adversarial robustness of the underlying agent against various types of perturbations. Extensive experiments validate the superior performance of our attack and defence mechanism across multiple state-of-the-art GCRL algorithms. Our tool {\bf ReRoGCRL} is available at \url{https://github.com/TrustAI/ReRoGCRL}.
Authors: Yue Zhang, Ming Zhang, Haipeng Yuan, Shichun Liu, Yongyao Shi, Tao Gui, Qi Zhang, Xuanjing Huang
Recently, the evaluation of Large Language Models has emerged as a popular area of research. The three crucial questions for LLM evaluation are ``what, where, and how to evaluate''. However, the existing research mainly focuses on the first two questions, which are basically what tasks to give the LLM during testing and what kind of knowledge it should deal with. As for the third question, which is about what standards to use, the types of evaluators, how to score, and how to rank, there hasn't been much discussion. In this paper, we analyze evaluation methods by comparing various criteria with both manual and automatic evaluation, utilizing onsite, crowd-sourcing, public annotators and GPT-4, with different scoring methods and ranking systems. We propose a new dataset, LLMEval and conduct evaluations on 20 LLMs. A total of 2,186 individuals participated, leading to the generation of 243,337 manual annotations and 57,511 automatic evaluation results. We perform comparisons and analyses of different settings and conduct 10 conclusions that can provide some insights for evaluating LLM in the future. The dataset and the results are publicly available at https://github.com/llmeval .
Authors: Taeyoon Kwon, Kai Tzu-iunn Ong, Dongjin Kang, Seungjun Moon, Jeong Ryong Lee, Dosik Hwang, Yongsik Sim, Beomseok Sohn, Dongha Lee, Jinyoung Yeo
Machine reasoning has made great progress in recent years owing to large language models (LLMs). In the clinical domain, however, most NLP-driven projects mainly focus on clinical classification or reading comprehension, and under-explore clinical reasoning for disease diagnosis due to the expensive rationale annotation with clinicians. In this work, we present a ``reasoning-aware'' diagnosis framework that rationalizes the diagnostic process via prompt-based learning in a time- and labor-efficient manner, and learns to reason over the prompt-generated rationales. Specifically, we address the clinical reasoning for disease diagnosis, where the LLM generates diagnostic rationales providing its insight on presented patient data and the reasoning path towards the diagnosis, namely Clinical Chain-of-Thought (Clinical CoT). We empirically demonstrate LLMs/LMs' ability of clinical reasoning via extensive experiments and analyses on both rationale generation and disease diagnosis in various settings. We further propose a novel set of criteria for evaluating machine-generated rationales' potential for real-world clinical settings, facilitating and benefiting future research in this area.
Authors: Dun Zeng, Yong Dai, Pengyu Cheng, Tianhao Hu, Wanshun Chen, Nan Du, Zenglin Xu
The alignment of large language models (LLMs) with human values is crucial for the development of artificial general intelligence (AGI). One promising approach to achieve this alignment is reinforcement learning from human feedback, which employs a reward model (RM) learned from human preference datasets to guide LLMs in generating text that aligns with human preferences. Through intensive experiments and analysis of reward distribution, this paper finds that preference datasets are diverse from each other, even though they are all proposed to align human preference. Hence, mixing diverse human preference datasets to increase data size for enhancing reward modeling could fail. To address the issue and capture the shared human values from diverse preferences, a new training policy called MORE is introduced, which minimizes preference bias by adaptively adjusting the preference objective across diverse preferences. Experiments with the Pythia-1.4B model and five mixed preference datasets show that MORE achieves superior reward accuracy and lower calibration error, highlighting its ability to leverage diverse human preference data.
Authors: Tom Davidson, Jean-Stanislas Denain, Pablo Villalobos, Guillem Bas
State-of-the-art AI systems can be significantly improved without expensive retraining via "post-training enhancements"-techniques applied after initial training like fine-tuning the system to use a web browser. We review recent post-training enhancements, categorizing them into five types: tool-use, prompting methods, scaffolding, solution selection, and data generation. Different enhancements improve performance on different tasks, making it hard to compare their significance. So we translate improvements from different enhancements into a common currency, the compute-equivalent gain: how much additional training compute would be needed to improve performance by the same amount as the enhancement. Our non-experimental work shows that post-training enhancements have significant benefits: most surveyed enhancements improve benchmark performance by more than a 5x increase in training compute, some by more than 20x. Post-training enhancements are relatively cheap to develop: fine-tuning costs are typically <1% of the original training cost. Governing the development of capable post-training enhancements may be challenging because frontier models could be enhanced by a wide range of actors.
Authors: Zhongyi Han, Guanglin Zhou, Rundong He, Jindong Wang, Xing Xie, Tailin Wu, Yilong Yin, Salman Khan, Lina Yao, Tongliang Liu, Kun Zhang
In machine learning, generalization against distribution shifts -- where deployment conditions diverge from the training scenarios -- is crucial, particularly in fields like climate modeling, biomedicine, and autonomous driving. The emergence of foundation models, distinguished by their extensive pretraining and task versatility, has led to an increased interest in their adaptability to distribution shifts. GPT-4V(ision) acts as the most advanced publicly accessible multimodal foundation model, with extensive applications across various domains, including anomaly detection, video understanding, image generation, and medical diagnosis. However, its robustness against data distributions remains largely underexplored. Addressing this gap, this study rigorously evaluates GPT-4V's adaptability and generalization capabilities in dynamic environments, benchmarking against prominent models like CLIP and LLaVA. We delve into GPT-4V's zero-shot generalization across 13 diverse datasets spanning natural, medical, and molecular domains. We further investigate its adaptability to controlled data perturbations and examine the efficacy of in-context learning as a tool to enhance its adaptation. Our findings delineate GPT-4V's capability boundaries in distribution shifts, shedding light on its strengths and limitations across various scenarios. Importantly, this investigation contributes to our understanding of how AI foundation models generalize to distribution shifts, offering pivotal insights into their adaptability and robustness. Code is publicly available at https://github.com/jameszhou-gl/gpt-4v-distribution-shift.
Authors: Alhassan Mabrouk, Rebeca P. Díaz Redondo, Mohamed Abd Elaziz, Mohammed Kayed
Federated learning is a very convenient approach for scenarios where (i) the exchange of data implies privacy concerns and/or (ii) a quick reaction is needed. In smart healthcare systems, both aspects are usually required. In this paper, we work on the first scenario, where preserving privacy is key and, consequently, building a unique and massive medical image data set by fusing different data sets from different medical institutions or research centers (computation nodes) is not an option. We propose an ensemble federated learning (EFL) approach that is based on the following characteristics: First, each computation node works with a different data set (but of the same type). They work locally and apply an ensemble approach combining eight well-known CNN models (densenet169, mobilenetv2, xception, inceptionv3, vgg16, resnet50, densenet121, and resnet152v2) on Chest X-ray images. Second, the best two local models are used to create a local ensemble model that is shared with a central node. Third, the ensemble models are aggregated to obtain a global model, which is shared with the computation nodes to continue with a new iteration. This procedure continues until there are no changes in the best local models. We have performed different experiments to compare our approach with centralized ones (with or without an ensemble approach)\color{black}. The results conclude that our proposal outperforms these ones in Chest X-ray images (achieving an accuracy of 96.63\%) and offers very competitive results compared to other proposals in the literature.
Authors: Love Panta, Prashant Shrestha, Brabeem Sapkota, Amrita Bhattarai, Suresh Manandhar, Anand Kumar Sah
Video moment retrieval is a challenging task requiring fine-grained interactions between video and text modalities. Recent work in image-text pretraining has demonstrated that most existing pretrained models suffer from information asymmetry due to the difference in length between visual and textual sequences. We question whether the same problem also exists in the video-text domain with an auxiliary need to preserve both spatial and temporal information. Thus, we evaluate a recently proposed solution involving the addition of an asymmetric co-attention network for video grounding tasks. Additionally, we incorporate momentum contrastive loss for robust, discriminative representation learning in both modalities. We note that the integration of these supplementary modules yields better performance compared to state-of-the-art models on the TACoS dataset and comparable results on ActivityNet Captions, all while utilizing significantly fewer parameters with respect to baseline.
Authors: Alhassan Mabrouk, Abdelghani Dahou, Mohamed Abd Elaziz, Rebeca P. Díaz Redondo, Mohammed Kayed
The Internet of Medical Things (IoMT) has dramatically benefited medical professionals that patients and physicians can access from all regions. Although the automatic detection and prediction of diseases such as melanoma and leukemia is still being researched and studied in IoMT, existing approaches are not able to achieve a high degree of efficiency. Thus, with a new approach that provides better results, patients would access the adequate treatments earlier and the death rate would be reduced. Therefore, this paper introduces an IoMT proposal for medical images classification that may be used anywhere, i.e. it is an ubiquitous approach. It was design in two stages: first, we employ a Transfer Learning (TL)-based method for feature extraction, which is carried out using MobileNetV3; second, we use the Chaos Game Optimization (CGO) for feature selection, with the aim of excluding unnecessary features and improving the performance, which is key in IoMT. Our methodology was evaluated using ISIC-2016, PH2, and Blood-Cell datasets. The experimental results indicated that the proposed approach obtained an accuracy of 88.39% on ISIC-2016, 97.52% on PH2, and 88.79% on Blood-cell. Moreover, our approach had successful performances for the metrics employed compared to other existing methods.
Authors: Daniel Ordoñez-Apraez, Vladimir Kostic, Giulio Turrisi, Pietro Novelli, Carlos Mastalli, Claudio Semini, Massimiliano Pontil
We introduce the use of harmonic analysis to decompose the state space of symmetric robotic systems into orthogonal isotypic subspaces. These are lower-dimensional spaces that capture distinct, symmetric, and synergistic motions. For linear dynamics, we characterize how this decomposition leads to a subdivision of the dynamics into independent linear systems on each subspace, a property we term dynamics harmonic analysis (DHA). To exploit this property, we use Koopman operator theory to propose an equivariant deep-learning architecture that leverages the properties of DHA to learn a global linear model of system dynamics. Our architecture, validated on synthetic systems and the dynamics of locomotion of a quadrupedal robot, demonstrates enhanced generalization, sample efficiency, and interpretability, with less trainable parameters and computational costs.
Authors: Aitor Martinez Seras, Javier Del Ser, Pablo Garcia-Bringas
Besides performance, efficiency is a key design driver of technologies supporting vehicular perception. Indeed, a well-balanced trade-off between performance and energy consumption is crucial for the sustainability of autonomous vehicles. In this context, the diversity of real-world contexts in which autonomous vehicles can operate motivates the need for empowering perception models with the capability to detect, characterize and identify newly appearing objects by themselves. In this manuscript we elaborate on this threefold conundrum (performance, efficiency and open-world learning) for object detection modeling tasks over image data collected from vehicular scenarios. Specifically, we show that well-performing and efficient models can be realized by virtue of Spiking Neural Networks (SNNs), reaching competitive levels of detection performance when compared to their non-spiking counterparts at dramatic energy consumption savings (up to 85%) and a slightly improved robustness against image noise. Our experiments herein offered also expose qualitatively the complexity of detecting new objects based on the preliminary results of a simple approach to discriminate potential object proposals in the captured image.
Authors: Caoyun Fan, Jidong Tian, Yitian Li, Hao He, Yaohui Jin
In-Context Learning (ICL) is an important paradigm for adapting Large Language Models (LLMs) to downstream tasks through a few demonstrations. Despite the great success of ICL, the limitation of the demonstration number may lead to demonstration bias, i.e. the input-label mapping induced by LLMs misunderstands the task's essence. Inspired by human experience, we attempt to mitigate such bias through the perspective of the inter-demonstration relationship. Specifically, we construct Comparable Demonstrations (CDs) by minimally editing the texts to flip the corresponding labels, in order to highlight the task's essence and eliminate potential spurious correlations through the inter-demonstration comparison. Through a series of experiments on CDs, we find that (1) demonstration bias does exist in LLMs, and CDs can significantly reduce such bias; (2) CDs exhibit good performance in ICL, especially in out-of-distribution scenarios. In summary, this study explores the ICL mechanisms from a novel perspective, providing a deeper insight into the demonstration selection strategy for ICL.
Authors: Manar Mohamed Hafez, Rebeca P. Díaz Redondo, Ana Fernández-Vilas, Héctor Olivera Pazó
Food retailing is now on an accelerated path to a success penetration into the digital market by new ways of value creation at all stages of the consumer decision process. One of the most important imperatives in this path is the availability of quality data to feed all the process in digital transformation. But the quality of data is not so obvious if we consider the variety of products and suppliers in the grocery market. Within this context of digital transformation of grocery industry, \textit{Midiadia} is Spanish data provider company that works on converting data from the retailers' products into knowledge with attributes and insights from the product labels, that is, maintaining quality data in a dynamic market with a high dispersion of products. Currently, they manually categorize products (groceries) according to the information extracted directly (text processing) from the product labelling and packaging. This paper introduces a solution to automatically categorize the constantly changing product catalogue into a 3-level food taxonomy. Our proposal studies three different approaches: a score-based ranking method, traditional machine learning algorithms, and deep neural networks. Thus, we provide four different classifiers that support a more efficient and less error-prone maintenance of groceries catalogues, the main asset of the company. Finally, we have compared the performance of these three alternatives, concluding that traditional machine learning algorithms perform better, but closely followed by the score-based approach.
Authors: Hao Shao, Yuxuan Hu, Letian Wang, Steven L. Waslander, Yu Liu, Hongsheng Li
Despite significant recent progress in the field of autonomous driving, modern methods still struggle and can incur serious accidents when encountering long-tail unforeseen events and challenging urban scenarios. On the one hand, large language models (LLM) have shown impressive reasoning capabilities that approach "Artificial General Intelligence". On the other hand, previous autonomous driving methods tend to rely on limited-format inputs (e.g. sensor data and navigation waypoints), restricting the vehicle's ability to understand language information and interact with humans. To this end, this paper introduces LMDrive, a novel language-guided, end-to-end, closed-loop autonomous driving framework. LMDrive uniquely processes and integrates multi-modal sensor data with natural language instructions, enabling interaction with humans and navigation software in realistic instructional settings. To facilitate further research in language-based closed-loop autonomous driving, we also publicly release the corresponding dataset which includes approximately 64K instruction-following data clips, and the LangAuto benchmark that tests the system's ability to handle complex instructions and challenging driving scenarios. Extensive closed-loop experiments are conducted to demonstrate LMDrive's effectiveness. To the best of our knowledge, we're the very first work to leverage LLMs for closed-loop end-to-end autonomous driving. Codes can be found at https://github.com/opendilab/LMDrive
Authors: Manish Nagireddy, Lamogha Chiazor, Moninder Singh, Ioana Baldini
Current datasets for unwanted social bias auditing are limited to studying protected demographic features such as race and gender. In this work, we introduce a comprehensive benchmark that is meant to capture the amplification of social bias, via stigmas, in generative language models. We start with a comprehensive list of 93 stigmas documented in social science literature and curate a question-answering (QA) dataset which involves simple social situations. Our benchmark, SocialStigmaQA, contains roughly 10K prompts, with a variety of prompt styles, carefully constructed to systematically test for both social bias and model robustness. We present results for SocialStigmaQA with two widely used open source generative language models and we demonstrate that the output generated by these models considerably amplifies existing social bias against stigmatized groups. Specifically, we find that the proportion of socially biased output ranges from 45% to 59% across a variety of decoding strategies and prompting styles. We discover that the deliberate design of the templates in our benchmark (e.g., by adding biasing text to the prompt or varying the answer that indicates bias) impact the model tendencies to generate socially biased output. Additionally, we report on patterns in the generated chain-of-thought output, finding a variety of problems from subtle bias to evidence of a lack of reasoning.
Warning: This paper contains examples of text which is toxic, biased, and harmful.
Authors: Bencheng Yan, Pengjie Wang, Kai Zhang, Feng Li, Hongbo Deng, Jian Xu, Bo Zheng
In many web applications, deep learning-based CTR prediction models (deep CTR models for short) are widely adopted. Traditional deep CTR models learn patterns in a static manner, i.e., the network parameters are the same across all the instances. However, such a manner can hardly characterize each of the instances which may have different underlying distributions. It actually limits the representation power of deep CTR models, leading to sub-optimal results. In this paper, we propose an efficient, effective, and universal module, named as Adaptive Parameter Generation network (APG), which can dynamically generate parameters for deep CTR models on-the-fly based on different instances. Extensive experimental evaluation results show that APG can be applied to a variety of deep CTR models and significantly improve their performance. Meanwhile, APG can reduce the time cost by 38.7\% and memory usage by 96.6\% compared to a regular deep CTR model. We have deployed APG in the industrial sponsored search system and achieved 3\% CTR gain and 1\% RPM gain respectively.
Authors: Andreas Haupt, Aroon Narayanan
Agents' learning from feedback shapes economic outcomes, and many economic decision-makers today employ learning algorithms to make consequential choices. This note shows that a widely used learning algorithm, $\varepsilon$-Greedy, exhibits emergent risk aversion: it prefers actions with lower variance. When presented with actions of the same expectation, under a wide range of conditions, $\varepsilon$-Greedy chooses the lower-variance action with probability approaching one. This emergent preference can have wide-ranging consequences, ranging from concerns about fairness to homogenization, and holds transiently even when the riskier action has a strictly higher expected payoff. We discuss two methods to correct this bias. The first method requires the algorithm to reweight data as a function of how likely the actions were to be chosen. The second requires the algorithm to have optimistic estimates of actions for which it has not collected much data. We show that risk-neutrality is restored with these corrections.
Authors: Julien Grand-Clément, Jean Pauphilet
Many high-stake decisions follow an expert-in-loop structure in that a human operator receives recommendations from an algorithm but is the ultimate decision maker. Hence, the algorithm's recommendation may differ from the actual decision implemented in practice. However, most algorithmic recommendations are obtained by solving an optimization problem that assumes recommendations will be perfectly implemented. We propose an adherence-aware optimization framework to capture the dichotomy between the recommended and the implemented policy and analyze the impact of partial adherence on the optimal recommendation. We show that overlooking the partial adherence phenomenon, as is currently being done by most recommendation engines, can lead to arbitrarily severe performance deterioration, compared with both the current human baseline performance and what is expected by the recommendation algorithm. Our framework also provides useful tools to analyze the structure and to compute optimal recommendation policies that are naturally immune against such human deviations, and are guaranteed to improve upon the baseline policy.
Authors: Han Wu, Syed Yunas, Sareh Rowlands, Wenjie Ruan, Johan Wahlstrom
Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. Therefore, it is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. This paper bridges this gap by presenting the first real-time online attack against object detection models. We devise three attacks that fabricate bounding boxes for nonexistent objects at desired locations. The attacks achieve a success rate of about 90% within about 20 iterations. The demo video is available at https://youtu.be/zJZ1aNlXsMU.
Authors: Tavish McDonald, Brian Tsan, Amar Saini, Juanita Ordonez, Luis Gutierrez, Phan Nguyen, Blake Mason, Brenda Ng
Researchers produce thousands of scholarly documents containing valuable technical knowledge. The community faces the laborious task of reading these documents to identify, extract, and synthesize information. To automate information gathering, document-level question answering (QA) offers a flexible framework where human-posed questions can be adapted to extract diverse knowledge. Finetuning QA systems requires access to labeled data (tuples of context, question and answer). However, data curation for document QA is uniquely challenging because the context (i.e. answer evidence passage) needs to be retrieved from potentially long, ill-formatted documents. Existing QA datasets sidestep this challenge by providing short, well-defined contexts that are unrealistic in real-world applications. We present a three-stage document QA approach: (1) text extraction from PDF; (2) evidence retrieval from extracted texts to form well-posed contexts; (3) QA to extract knowledge from contexts to return high-quality answers -- extractive, abstractive, or Boolean. Using QASPER for evaluation, our detect-retrieve-comprehend (DRC) system achieves a +7.19 improvement in Answer-F1 over existing baselines while delivering superior context selection. Our results demonstrate that DRC holds tremendous promise as a flexible framework for practical scientific document QA.
Authors: Jinwoo Bae, Kyumin Hwang, Sunghoon Im
Monocular depth estimation has been widely studied, and significant improvements in performance have been recently reported. However, most previous works are evaluated on a few benchmark datasets, such as KITTI datasets, and none of the works provide an in-depth analysis of the generalization performance of monocular depth estimation. In this paper, we deeply investigate the various backbone networks (e.g.CNN and Transformer models) toward the generalization of monocular depth estimation. First, we evaluate state-of-the-art models on both in-distribution and out-of-distribution datasets, which have never been seen during network training. Then, we investigate the internal properties of the representations from the intermediate layers of CNN-/Transformer-based models using synthetic texture-shifted datasets. Through extensive experiments, we observe that the Transformers exhibit a strong shape-bias rather than CNNs, which have a strong texture-bias. We also discover that texture-biased models exhibit worse generalization performance for monocular depth estimation than shape-biased models. We demonstrate that similar aspects are observed in real-world driving datasets captured under diverse environments. Lastly, we conduct a dense ablation study with various backbone networks which are utilized in modern strategies. The experiments demonstrate that the intrinsic locality of the CNNs and the self-attention of the Transformers induce texture-bias and shape-bias, respectively.
Authors: Christian Antić
This research note provides algebraic characterizations of the least model, subsumption, and uniform equivalence of propositional Krom logic programs.
Authors: Christian Antić
Detecting and exploiting similarities between seemingly distant objects is without doubt an important human ability. This paper develops \textit{from the ground up} an abstract algebraic and qualitative justification-based notion of similarity based on the observation that sets of generalizations encode important properties of elements. We show that similarity defined in this way has appealing mathematical properties. As we construct our notion of similarity from first principles using only elementary concepts of universal algebra, to convince the reader of its plausibility, we show that it can be naturally embedded into first-order logic via model-theoretic types.
Temporal Knowledge Graph (TKG) representation learning embeds entities and event types into a continuous low-dimensional vector space by integrating the temporal information, which is essential for downstream tasks, e.g., event prediction and question answering. Existing methods stack multiple graph convolution layers to model the influence of distant entities, leading to the over-smoothing problem. To alleviate the problem, recent studies infuse reinforcement learning to obtain paths that contribute to modeling the influence of distant entities. However, due to the limited number of hops, these studies fail to capture the correlation between entities that are far apart and even unreachable. To this end, we propose GTRL, an entity Group-aware Temporal knowledge graph Representation Learning method. GTRL is the first work that incorporates the entity group modeling to capture the correlation between entities by stacking only a finite number of layers. Specifically, the entity group mapper is proposed to generate entity groups from entities in a learning way. Based on entity groups, the implicit correlation encoder is introduced to capture implicit correlations between any pairwise entity groups. In addition, the hierarchical GCNs are exploited to accomplish the message aggregation and representation updating on the entity group graph and the entity graph. Finally, GRUs are employed to capture the temporal dependency in TKGs. Extensive experiments on three real-world datasets demonstrate that GTRL achieves the state-of-the-art performances on the event prediction task, outperforming the best baseline by an average of 13.44%, 9.65%, 12.15%, and 15.12% in MRR, Hits@1, Hits@3, and Hits@10, respectively.
Authors: Wenlong Huang, Fei Xia, Dhruv Shah, Danny Driess, Andy Zeng, Yao Lu, Pete Florence, Igor Mordatch, Sergey Levine, Karol Hausman, Brian Ichter
Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models. Unfortunately, applying such models to settings with embodied agents, such as robots, is challenging due to their lack of experience with the physical world, inability to parse non-language observations, and ignorance of rewards or safety constraints that robots may require. On the other hand, language-conditioned robotic policies that learn from interaction data can provide the necessary grounding that allows the agent to be correctly situated in the real world, but such policies are limited by the lack of high-level semantic understanding due to the limited breadth of the interaction data available for training them. Thus, if we want to make use of the semantic knowledge in a language model while still situating it in an embodied setting, we must construct an action sequence that is both likely according to the language model and also realizable according to grounded models of the environment. We frame this as a problem similar to probabilistic filtering: decode a sequence that both has high probability under the language model and high probability under a set of grounded model objectives. We demonstrate how such grounded models can be obtained across three simulation and real-world domains, and that the proposed decoding strategy is able to solve complex, long-horizon embodiment tasks in a robotic setting by leveraging the knowledge of both models. The project's website can be found at grounded-decoding.github.io.
Authors: Xuyang Zhao, Tianqi Du, Yisen Wang, Jun Yao, Weiran Huang
Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and training distributions differ. However, the theoretical understanding of its transferability remains limited. In this paper, we develop a theoretical framework to analyze the transferability of self-supervised contrastive learning, by investigating the impact of data augmentation on it. Our results reveal that the downstream performance of contrastive learning depends largely on the choice of data augmentation. Moreover, we show that contrastive learning fails to learn domain-invariant features, which limits its transferability. Based on these theoretical insights, we propose a novel method called Augmentation-robust Contrastive Learning (ArCL), which guarantees to learn domain-invariant features and can be easily integrated with existing contrastive learning algorithms. We conduct experiments on several datasets and show that ArCL significantly improves the transferability of contrastive learning.
Authors: Xingyu Zhao, Simos Gerasimou, Radu Calinescu, Calum Imrie, Valentin Robu, David Flynn
Autonomous robots used in infrastructure inspection, space exploration and other critical missions operate in highly dynamic environments. As such, they must continually verify their ability to complete the tasks associated with these missions safely and effectively. Here we present a Bayesian learning framework that enables this runtime verification of autonomous robots. The framework uses prior knowledge and observations of the verified robot to learn expected ranges for the occurrence rates of regular and singular (e.g., catastrophic failure) events. Interval continuous-time Markov models defined using these ranges are then analysed to obtain expected intervals of variation for system properties such as mission duration and success probability. We apply the framework to an autonomous robotic mission for underwater infrastructure inspection and repair. The formal proofs and experiments presented in the paper show that our framework produces results that reflect the uncertainty intrinsic to many real-world systems, enabling the robust verification of their quantitative properties under parametric uncertainty.
Authors: Hongbo Tian, Yulong Li, Linzhi Huang, Xu Ling, Yue Yang, Jiani Hu
Structured reconstruction is a non-trivial dense prediction problem, which extracts structural information (\eg, building corners and edges) from a raster image, then reconstructs it to a 2D planar graph accordingly. Compared with common segmentation or detection problems, it significantly relays on the capability that leveraging holistic geometric information for structural reasoning. Current transformer-based approaches tackle this challenging problem in a two-stage manner, which detect corners in the first model and classify the proposed edges (corner-pairs) in the second model. However, they separate two-stage into different models and only share the backbone encoder. Unlike the existing modeling strategies, we present an enhanced corner representation method: 1) It fuses knowledge between the corner detection and edge prediction by sharing feature in different granularity; 2) Corner candidates are proposed in four heatmap channels w.r.t its direction. Both qualitative and quantitative evaluations demonstrate that our proposed method can better reconstruct fine-grained structures, such as adjacent corners and tiny edges. Consequently, it outperforms the state-of-the-art model by +1.9\%@F-1 on Corner and +3.0\%@F-1 on Edge.
Authors: Li-Hsiang Shen, An-Hung Hsiao, Fang-Yu Chu, Kai-Ten Feng
Device-free human presence detection is a crucial technology for various applications, including home automation, security, and healthcare. While camera-based systems have traditionally been used for this purpose, they raise privacy concerns. To address this issue, recent research has explored the use of wireless channel state information (CSI) extracted from commercial WiFi access points (APs) to provide detailed channel characteristics. In this paper, we propose a device-free human presence detection system for multi-room scenarios using a time-selective conditional dual feature extract recurrent network (TCD-FERN). Our system is designed to capture significant time features on current human features using a dynamic and static data preprocessing technique. We extract both moving and spatial features of people and differentiate between line-of-sight (LoS) and non-line-of-sight (NLoS) cases. Subcarrier fusion is carried out in order to provide more objective variation of each sample while reducing the computational complexity. A voting scheme is further adopted to mitigate the feature attenuation problem caused by room partitions, with around 3% improvement of human presence detection accuracy. Experimental results have revealed the significant improvement of leveraging subcarrier fusion, dual-feature recurrent network, time selection and condition mechanisms. Compared to the existing works in open literature, our proposed TCD-FERN system can achieve above 97% of human presence detection accuracy for multi-room scenarios with the adoption of fewer WiFi APs.
Authors: Yue Wu, Shrimai Prabhumoye, So Yeon Min, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Tom Mitchell, Yuanzhi Li
Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample complexity limits its effectiveness in complex open-world games like Crafter or Minecraft. We propose a novel approach, SPRING, to read the game's original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM). Prompted with the LaTeX source as game context and a description of the agent's current observation, our SPRING framework employs a directed acyclic graph (DAG) with game-related questions as nodes and dependencies as edges. We identify the optimal action to take in the environment by traversing the DAG and calculating LLM responses for each node in topological order, with the LLM's answer to final node directly translating to environment actions. In our experiments, we study the quality of in-context "reasoning" induced by different forms of prompts under the setting of the Crafter open-world environment. Our experiments suggest that LLMs, when prompted with consistent chain-of-thought, have great potential in completing sophisticated high-level trajectories. Quantitatively, SPRING with GPT-4 outperforms all state-of-the-art RL baselines, trained for 1M steps, without any training. Finally, we show the potential of games as a test bed for LLMs.
Authors: Shilin Yan, Renrui Zhang, Ziyu Guo, Wenchao Chen, Wei Zhang, Hongyang Li, Yu Qiao, Hao Dong, Zhongjiang He, Peng Gao
Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames. However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities. Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video. On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2% and +8.7% J&F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at https://github.com/OpenGVLab/MUTR.
Authors: Sunny Sanyal, Atula Neerkaje, Jean Kaddour, Abhishek Kumar, Sujay Sanghavi
Training Large Language Models (LLMs) incurs significant cost; hence, any strategy that accelerates model convergence is helpful. In this paper, we investigate the ability of a simple idea checkpoint averaging along the trajectory of a training run to improve both convergence and generalization quite early on during training. Here we show that models trained with high learning rates observe higher gains due to checkpoint averaging. Furthermore, these gains are amplified when checkpoints are sampled with considerable spacing in training steps. Our training recipe outperforms conventional training and popular checkpoint averaging baselines such as exponential moving average (EMA) and stochastic moving average (SWA). We evaluate our training recipe by pre-training LLMs, where high learning rates are inherently preferred due to extremely large batch sizes. Specifically, we pre-trained nanoGPT-2 models of varying sizes, small (125M), medium (335M), and large (770M)on the OpenWebText dataset, comprised of 9B tokens. Additionally, we present results for publicly available Pythia LLMs, ranging from 1B to 12B, which were trained on the PILE-deduped dataset containing 207B tokens.
Authors: Jonas Oppenlaender, Joonas Hämäläinen
Large language models (LLMs), such as ChatGPT and GPT-4, are gaining wide-spread real world use. Yet, these LLMs are closed source, and little is known about their performance in real-world use cases. In this paper, we apply and evaluate the combination of ChatGPT and GPT-4 for the real-world task of mining insights from a text corpus in order to identify research challenges in the field of HCI. We extract 4,392 research challenges in over 100 topics from the 2023 CHI conference proceedings and visualize the research challenges for interactive exploration. We critically evaluate the LLMs on this practical task and conclude that the combination of ChatGPT and GPT-4 makes an excellent cost-efficient means for analyzing a text corpus at scale. Cost-efficiency is key for flexibly prototyping research ideas and analyzing text corpora from different perspectives, with implications for applying LLMs for mining insights in academia and practice.
Authors: Kai Zhao, Yi Ma, Jianye Hao, Jinyi Liu, Yan Zheng, Zhaopeng Meng
Offline reinforcement learning (RL) is a learning paradigm where an agent learns from a fixed dataset of experience. However, learning solely from a static dataset can limit the performance due to the lack of exploration. To overcome it, offline-to-online RL combines offline pre-training with online fine-tuning, which enables the agent to further refine its policy by interacting with the environment in real-time. Despite its benefits, existing offline-to-online RL methods suffer from performance degradation and slow improvement during the online phase. To tackle these challenges, we propose a novel framework called Ensemble-based Offline-to-Online (E2O) RL. By increasing the number of Q-networks, we seamlessly bridge offline pre-training and online fine-tuning without degrading performance. Moreover, to expedite online performance enhancement, we appropriately loosen the pessimism of Q-value estimation and incorporate ensemble-based exploration mechanisms into our framework. Experimental results demonstrate that E2O can substantially improve the training stability, learning efficiency, and final performance of existing offline RL methods during online fine-tuning on a range of locomotion and navigation tasks, significantly outperforming existing offline-to-online RL methods.
Authors: Caixin Kang, Yinpeng Dong, Zhengyi Wang, Shouwei Ruan, Yubo Chen, Hang Su, Xingxing Wei
Adversarial attacks, particularly patch attacks, pose significant threats to the robustness and reliability of deep learning models. Developing reliable defenses against patch attacks is crucial for real-world applications, yet current research in this area is unsatisfactory. In this paper, we propose DIFFender, a novel defense method that leverages a text-guided diffusion model to defend against adversarial patches. DIFFender includes two main stages: patch localization and patch restoration. In the localization stage, we find and exploit an intriguing property of the diffusion model to precisely identify the locations of adversarial patches. In the restoration stage, we employ the diffusion model to reconstruct the adversarial regions in the images while preserving the integrity of the visual content. Thanks to the former finding, these two stages can be simultaneously guided by a unified diffusion model. Thus, we can utilize the close interaction between them to improve the whole defense performance. Moreover, we propose a few-shot prompt-tuning algorithm to fine-tune the diffusion model, enabling the pre-trained diffusion model to adapt to the defense task easily. We conduct extensive experiments on image classification, face recognition, and further in the physical world, demonstrating that our proposed method exhibits superior robustness under strong adaptive attacks and generalizes well across various scenarios, diverse classifiers, and multiple patch attack methods.
Authors: Max Pascher, Kirill Kronhardt, Jan Freienstein, Jens Gerken
Assistive technologies and in particular assistive robotic arms have the potential to enable people with motor impairments to live a self-determined life. More and more of these systems have become available for end users in recent years, such as the Kinova Jaco robotic arm. However, they mostly require complex manual control, which can overwhelm users. As a result, researchers have explored ways to let such robots act autonomously. However, at least for this specific group of users, such an approach has shown to be futile. Here, users want to stay in control to achieve a higher level of personal autonomy, to which an autonomous robot runs counter. In our research, we explore how Artifical Intelligence (AI) can be integrated into a shared control paradigm. In particular, we focus on the consequential requirements for the interface between human and robot and how we can keep humans in the loop while still significantly reducing the mental load and required motor skills.
Authors: Koustava Goswami, Srikrishna Karanam, Prateksha Udhayanan, K J Joseph, Balaji Vasan Srinivasan
Recent advances in multimodal learning has resulted in powerful vision-language models, whose representations are generalizable across a variety of downstream tasks. Recently, their generalization ability has been further extended by incorporating trainable prompts, borrowed from the natural language processing literature. While such prompt learning techniques have shown impressive results, we identify that these prompts are trained based on global image features which limits itself in two aspects: First, by using global features, these prompts could be focusing less on the discriminative foreground image, resulting in poor generalization to various out-of-distribution test cases. Second, existing work weights all prompts equally whereas intuitively, prompts should be reweighed according to the semantics of the image. We address these as part of our proposed Contextual Prompt Learning (CoPL) framework, capable of aligning the prompts to the localized features of the image. Our key innovations over earlier works include using local image features as part of the prompt learning process, and more crucially, learning to weight these prompts based on local features that are appropriate for the task at hand. This gives us dynamic prompts that are both aligned to local image features as well as aware of local contextual relationships. Our extensive set of experiments on a variety of standard and few-shot datasets show that our method produces substantially improved performance when compared to the current state of the art methods. We also demonstrate both few-shot and out-of-distribution performance to establish the utility of learning dynamic prompts that are aligned to local image features.
Authors: Elena Tiukhova, Emiliano Penaloza, María Óskarsdóttir, Bart Baesens, Monique Snoeck, Cristián Bravo
Leveraging network information for predictive modeling has become widespread in many domains. Within the realm of referral and targeted marketing, influencer detection stands out as an area that could greatly benefit from the incorporation of dynamic network representation due to the ongoing development of customer-brand relationships. To elaborate this idea, we introduce INFLECT-DGNN, a new framework for INFLuencer prEdiCTion with Dynamic Graph Neural Networks that combines Graph Neural Networks (GNN) and Recurrent Neural Networks (RNN) with weighted loss functions, the Synthetic Minority Oversampling TEchnique (SMOTE) adapted for graph data, and a carefully crafted rolling-window strategy. To evaluate predictive performance, we utilize a unique corporate data set with networks of three cities and derive a profit-driven evaluation methodology for influencer prediction. Our results show how using RNN to encode temporal attributes alongside GNNs significantly improves predictive performance. We compare the results of various models to demonstrate the importance of capturing graph representation, temporal dependencies, and using a profit-driven methodology for evaluation.
Authors: Bing Han, Junyu Dai, Weituo Hao, Xinyan He, Dong Guo, Jitong Chen, Yuxuan Wang, Yanmin Qian, Xuchen Song
Music editing primarily entails the modification of instrument tracks or remixing in the whole, which offers a novel reinterpretation of the original piece through a series of operations. These music processing methods hold immense potential across various applications but demand substantial expertise. Prior methodologies, although effective for image and audio modifications, falter when directly applied to music. This is attributed to music's distinctive data nature, where such methods can inadvertently compromise the intrinsic harmony and coherence of music. In this paper, we develop InstructME, an Instruction guided Music Editing and remixing framework based on latent diffusion models. Our framework fortifies the U-Net with multi-scale aggregation in order to maintain consistency before and after editing. In addition, we introduce chord progression matrix as condition information and incorporate it in the semantic space to improve melodic harmony while editing. For accommodating extended musical pieces, InstructME employs a chunk transformer, enabling it to discern long-term temporal dependencies within music sequences. We tested InstructME in instrument-editing, remixing, and multi-round editing. Both subjective and objective evaluations indicate that our proposed method significantly surpasses preceding systems in music quality, text relevance and harmony. Demo samples are available at https://musicedit.github.io/
Authors: Souradeep Dutta, Michele Caprio, Vivian Lin, Matthew Cleaveland, Kuk Jin Jang, Ivan Ruchkin, Oleg Sokolsky, Insup Lee
A particularly challenging problem in AI safety is providing guarantees on the behavior of high-dimensional autonomous systems. Verification approaches centered around reachability analysis fail to scale, and purely statistical approaches are constrained by the distributional assumptions about the sampling process. Instead, we pose a distributionally robust version of the statistical verification problem for black-box systems, where our performance guarantees hold over a large family of distributions. This paper proposes a novel approach based on a combination of active learning, uncertainty quantification, and neural network verification. A central piece of our approach is an ensemble technique called Imprecise Neural Networks, which provides the uncertainty to guide active learning. The active learning uses an exhaustive neural-network verification tool Sherlock to collect samples. An evaluation on multiple physical simulators in the openAI gym Mujoco environments with reinforcement-learned controllers demonstrates that our approach can provide useful and scalable guarantees for high-dimensional systems.
Authors: Aranyak Maity, Ayan Banerjee, Sandeep Gupta
Unknown-unknowns are operational scenarios in systems that are not accounted for in the design and test phase. In such scenarios, the operational behavior of the Human-in-loop (HIL) Human-in-Plant (HIP) systems is not guaranteed to meet requirements such as safety and efficacy. We propose a novel framework for analyzing the operational output characteristics of safety-critical HIL-HIP systems that can discover unknown-unknown scenarios and evaluate potential safety hazards. We propose dynamics-induced hybrid recurrent neural networks (DiH-RNN) to mine a physics-guided surrogate model (PGSM) that checks for deviation of the cyber-physical system (CPS) from safety-certified operational characteristics. The PGSM enables early detection of unknown-unknowns based on the physical laws governing the system. We demonstrate the detection of operational changes in an Artificial Pancreas(AP) due to unknown insulin cartridge errors.
Authors: Yaning Jia, Chunhui Zhang
The Lipschitz bound, a technique from robust statistics, can limit the maximum changes in the output concerning the input, taking into account associated irrelevant biased factors. It is an efficient and provable method for examining the output stability of machine learning models without incurring additional computation costs. Recently, Graph Neural Networks (GNNs), which operate on non-Euclidean data, have gained significant attention. However, no previous research has investigated the GNN Lipschitz bounds to shed light on stabilizing model outputs, especially when working on non-Euclidean data with inherent biases. Given the inherent biases in common graph data used for GNN training, it poses a serious challenge to constraining the GNN output perturbations induced by input biases, thereby safeguarding fairness during training. Recently, despite the Lipschitz constant's use in controlling the stability of Euclideanneural networks, the calculation of the precise Lipschitz constant remains elusive for non-Euclidean neural networks like GNNs, especially within fairness contexts. To narrow this gap, we begin with the general GNNs operating on an attributed graph, and formulate a Lipschitz bound to limit the changes in the output regarding biases associated with the input. Additionally, we theoretically analyze how the Lipschitz constant of a GNN model could constrain the output perturbations induced by biases learned from data for fairness training. We experimentally validate the Lipschitz bound's effectiveness in limiting biases of the model output. Finally, from a training dynamics perspective, we demonstrate why the theoretical Lipschitz bound can effectively guide the GNN training to better trade-off between accuracy and fairness.
Authors: Ziqi Yang, Xuhai Xu, Bingsheng Yao, Shao Zhang, Ethan Rogers, Stephen Intille, Nawar Shara, Guodong Gordon Gao, Dakuo Wang
Despite the plethora of telehealth applications to assist home-based older adults and healthcare providers, basic messaging and phone calls are still the most common communication methods, which suffer from limited availability, information loss, and process inefficiencies. One promising solution to facilitate patient-provider communication is to leverage large language models (LLMs) with their powerful natural conversation and summarization capability. However, there is a limited understanding of LLMs' role during the communication. We first conducted two interview studies with both older adults (N=10) and healthcare providers (N=9) to understand their needs and opportunities for LLMs in patient-provider asynchronous communication. Based on the insights, we built an LLM-powered communication system, Talk2Care, and designed interactive components for both groups: (1) For older adults, we leveraged the convenience and accessibility of voice assistants (VAs) and built an LLM-powered VA interface for effective information collection. (2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system. The results showed that Talk2Care could facilitate the communication process, enrich the health information collected from older adults, and considerably save providers' efforts and time. We envision our work as an initial exploration of LLMs' capability in the intersection of healthcare and interpersonal communication.
Authors: Shaheer Mohamed, Maryam Haghighat, Tharindu Fernando, Sridha Sridharan, Clinton Fookes, Peyman Moghadam
Hyperspectral images (HSIs) contain rich spectral and spatial information. Motivated by the success of transformers in the field of natural language processing and computer vision where they have shown the ability to learn long range dependencies within input data, recent research has focused on using transformers for HSIs. However, current state-of-the-art hyperspectral transformers only tokenize the input HSI sample along the spectral dimension, resulting in the under-utilization of spatial information. Moreover, transformers are known to be data-hungry and their performance relies heavily on large-scale pre-training, which is challenging due to limited annotated hyperspectral data. Therefore, the full potential of HSI transformers has not been fully realized. To overcome these limitations, we propose a novel factorized spectral-spatial transformer that incorporates factorized self-supervised pre-training procedures, leading to significant improvements in performance. The factorization of the inputs allows the spectral and spatial transformers to better capture the interactions within the hyperspectral data cubes. Inspired by masked image modeling pre-training, we also devise efficient masking strategies for pre-training each of the spectral and spatial transformers. We conduct experiments on six publicly available datasets for HSI classification task and demonstrate that our model achieves state-of-the-art performance in all the datasets. The code for our model will be made available at https://github.com/csiro-robotics/factoformer.
Authors: Abdulkadir Canatar, Jenelle Feather, Albert Wakhloo, SueYeon Chung
The representations of neural networks are often compared to those of biological systems by performing regression between the neural network responses and those measured from biological systems. Many different state-of-the-art deep neural networks yield similar neural predictions, but it remains unclear how to differentiate among models that perform equally well at predicting neural responses. To gain insight into this, we use a recent theoretical framework that relates the generalization error from regression to the spectral properties of the model and the target. We apply this theory to the case of regression between model activations and neural responses and decompose the neural prediction error in terms of the model eigenspectra, alignment of model eigenvectors and neural responses, and the training set size. Using this decomposition, we introduce geometrical measures to interpret the neural prediction error. We test a large number of deep neural networks that predict visual cortical activity and show that there are multiple types of geometries that result in low neural prediction error as measured via regression. The work demonstrates that carefully decomposing representational metrics can provide interpretability of how models are capturing neural activity and points the way towards improved models of neural activity.
Authors: Canyu Chen, Kai Shu
The advent of Large Language Models (LLMs) has made a transformative impact. However, the potential that LLMs such as ChatGPT can be exploited to generate misinformation has posed a serious concern to online safety and public trust. A fundamental research question is: will LLM-generated misinformation cause more harm than human-written misinformation? We propose to tackle this question from the perspective of detection difficulty. We first build a taxonomy of LLM-generated misinformation. Then we categorize and validate the potential real-world methods for generating misinformation with LLMs. Then, through extensive empirical investigation, we discover that LLM-generated misinformation can be harder to detect for humans and detectors compared to human-written misinformation with the same semantics, which suggests it can have more deceptive styles and potentially cause more harm. We also discuss the implications of our discovery on combating misinformation in the age of LLMs and the countermeasures.
Authors: Mert Pilanci
In this paper, we introduce a novel analysis of neural networks based on geometric (Clifford) algebra and convex optimization. We show that optimal weights of deep ReLU neural networks are given by the wedge product of training samples when trained with standard regularized loss. Furthermore, the training problem reduces to convex optimization over wedge product features, which encode the geometric structure of the training dataset. This structure is given in terms of signed volumes of triangles and parallelotopes generated by data vectors. The convex problem finds a small subset of samples via $\ell_1$ regularization to discover only relevant wedge product features. Our analysis provides a novel perspective on the inner workings of deep neural networks and sheds light on the role of the hidden layers.
Authors: Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike Lewis
Deploying Large Language Models (LLMs) in streaming applications such as multi-round dialogue, where long interactions are expected, is urgently needed but poses two major challenges. Firstly, during the decoding stage, caching previous tokens' Key and Value states (KV) consumes extensive memory. Secondly, popular LLMs cannot generalize to longer texts than the training sequence length. Window attention, where only the most recent KVs are cached, is a natural approach -- but we show that it fails when the text length surpasses the cache size. We observe an interesting phenomenon, namely attention sink, that keeping the KV of initial tokens will largely recover the performance of window attention. In this paper, we first demonstrate that the emergence of attention sink is due to the strong attention scores towards initial tokens as a ``sink'' even if they are not semantically important. Based on the above analysis, we introduce StreamingLLM, an efficient framework that enables LLMs trained with a finite length attention window to generalize to infinite sequence lengths without any fine-tuning. We show that StreamingLLM can enable Llama-2, MPT, Falcon, and Pythia to perform stable and efficient language modeling with up to 4 million tokens and more. In addition, we discover that adding a placeholder token as a dedicated attention sink during pre-training can further improve streaming deployment. In streaming settings, StreamingLLM outperforms the sliding window recomputation baseline by up to 22.2x speedup. Code and datasets are provided at https://github.com/mit-han-lab/streaming-llm.
Authors: Giacomo Aldegheri, Alina Rogalska, Ahmed Youssef, Eugenia Iofinova
In this work, we propose a method to 'hack' generative models, pushing their outputs away from the original training distribution towards a new objective. We inject a small-scale trainable module between the intermediate layers of the model and train it for a low number of iterations, keeping the rest of the network frozen. The resulting output images display an uncanny quality, given by the tension between the original and new objectives that can be exploited for artistic purposes.
Authors: Xinyi Gao, Wentao Zhang, Junliang Yu, Yingxia Shao, Quoc Viet Hung Nguyen, Bin Cui, Hongzhi Yin
Graph neural networks (GNNs) have exhibited exceptional efficacy in a diverse array of applications. However, the sheer size of large-scale graphs presents a significant challenge to real-time inference with GNNs. Although existing Scalable GNNs leverage linear propagation to preprocess the features and accelerate the training and inference procedure, these methods still suffer from scalability issues when making inferences on unseen nodes, as the feature preprocessing requires the graph to be known and fixed. To further accelerate Scalable GNNs inference in this inductive setting, we propose an online propagation framework and two novel node-adaptive propagation methods that can customize the optimal propagation depth for each node based on its topological information and thereby avoid redundant feature propagation. The trade-off between accuracy and latency can be flexibly managed through simple hyper-parameters to accommodate various latency constraints. Moreover, to compensate for the inference accuracy loss caused by the potential early termination of propagation, we further propose Inception Distillation to exploit the multi-scale receptive field information within graphs. The rigorous and comprehensive experimental study on public datasets with varying scales and characteristics demonstrates that the proposed inference acceleration framework outperforms existing state-of-the-art graph inference acceleration methods in terms of accuracy and efficiency. Particularly, the superiority of our approach is notable on datasets with larger scales, yielding a 75x inference speedup on the largest Ogbn-products dataset.
Authors: Aditya Kannan, Kenneth Shaw, Shikhar Bahl, Pragna Mannam, Deepak Pathak
Dexterity is often seen as a cornerstone of complex manipulation. Humans are able to perform a host of skills with their hands, from making food to operating tools. In this paper, we investigate these challenges, especially in the case of soft, deformable objects as well as complex, relatively long-horizon tasks. However, learning such behaviors from scratch can be data inefficient. To circumvent this, we propose a novel approach, DEFT (DExterous Fine-Tuning for Hand Policies), that leverages human-driven priors, which are executed directly in the real world. In order to improve upon these priors, DEFT involves an efficient online optimization procedure. With the integration of human-based learning and online fine-tuning, coupled with a soft robotic hand, DEFT demonstrates success across various tasks, establishing a robust, data-efficient pathway toward general dexterous manipulation. Please see our website at https://dexterous-finetuning.github.io for video results.
Authors: Simon Sinong Zhan, Yixuan Wang, Qingyuan Wu, Ruochen Jiao, Chao Huang, Qi Zhu
In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex environments with contact-rich or non-smooth dynamics, and when dealing with high-dimensional pixel observations. Furthermore, incorporating state-wise safety constraints in the exploration and learning process, where the agent must avoid unsafe regions without prior knowledge, adds another layer of complexity. In this paper, we propose a novel pixel-observation safe RL algorithm that efficiently encodes state-wise safety constraints with unknown hazard regions through a newly introduced latent barrier-like function learning mechanism. As a joint learning framework, our approach begins by constructing a latent dynamics model with low-dimensional latent spaces derived from pixel observations. We then build and learn a latent barrier-like function on top of the latent dynamics and conduct policy optimization simultaneously, thereby improving both safety and the total expected return. Experimental evaluations on the safety-gym benchmark suite demonstrate that our proposed method significantly reduces safety violations throughout the training process, and demonstrates faster safety convergence compared to existing methods while achieving competitive results in reward return.
Authors: Aaditya K. Singh, Stephanie C.Y. Chan, Ted Moskovitz, Erin Grant, Andrew M. Saxe, Felix Hill
Transformer neural networks can exhibit a surprising capacity for in-context learning (ICL) despite not being explicitly trained for it. Prior work has provided a deeper understanding of how ICL emerges in transformers, e.g. through the lens of mechanistic interpretability, Bayesian inference, or by examining the distributional properties of training data. However, in each of these cases, ICL is treated largely as a persistent phenomenon; namely, once ICL emerges, it is assumed to persist asymptotically. Here, we show that the emergence of ICL during transformer training is, in fact, often transient. We train transformers on synthetic data designed so that both ICL and in-weights learning (IWL) strategies can lead to correct predictions. We find that ICL first emerges, then disappears and gives way to IWL, all while the training loss decreases, indicating an asymptotic preference for IWL. The transient nature of ICL is observed in transformers across a range of model sizes and datasets, raising the question of how much to "overtrain" transformers when seeking compact, cheaper-to-run models. We find that L2 regularization may offer a path to more persistent ICL that removes the need for early stopping based on ICL-style validation tasks. Finally, we present initial evidence that ICL transience may be caused by competition between ICL and IWL circuits.
Authors: Melanie Mitchell, Alessandro B. Palmarini, Arseny Moskvichev
We explore the abstract reasoning abilities of text-only and multimodal versions of GPT-4, using the ConceptARC benchmark [10], which is designed to evaluate robust understanding and reasoning with core-knowledge concepts. We extend the work of Moskvichev et al. [10] by evaluating GPT-4 on more detailed, one-shot prompting (rather than simple, zero-shot prompts) with text versions of ConceptARC tasks, and by evaluating GPT-4V, the multimodal version of GPT-4, on zero- and one-shot prompts using image versions of the simplest tasks. Our experimental results support the conclusion that neither version of GPT-4 has developed robust abstraction abilities at humanlike levels.
Authors: Gabriel De Araujo, Shanlin Sun, Xiaohui Xie
Image registration has traditionally been done using two distinct approaches: learning based methods, relying on robust deep neural networks, and optimization-based methods, applying complex mathematical transformations to warp images accordingly. Of course, both paradigms offer advantages and disadvantages, and, in this work, we seek to combine their respective strengths into a single streamlined framework, using the outputs of the learning based method as initial parameters for optimization while prioritizing computational power for the image pairs that offer the greatest loss. Our investigations showed that an improvement of 1.5% in testing when utilizing the best performing state-of-the-art model as the backbone of the framework, while maintaining the same inference time and a substantial 0.94% points performance gain in deformation field smoothness.
Authors: Ajitabh Kumar
Climate change has led to an increase in frequency of extreme weather events. Early warning systems can prevent disasters and loss of life. Managing such events remain a challenge for both public and private institutions. Precipitation nowcasting can help relevant institutions to better prepare for such events. Numerical weather prediction (NWP) has traditionally been used to make physics based forecasting, and recently deep learning based approaches have been used to reduce turn-around time for nowcasting. In this work, recently proposed Swin-UNETR (Swin UNEt TRansformer) is used for precipitation nowcasting for ten different regions of Europe. Swin-UNETR utilizes a U-shaped network within which a swin transformer-based encoder extracts multi-scale features from multiple input channels of satellite image, while CNN-based decoder makes the prediction. Trained model is capable of nowcasting not only for the regions for which data is available, but can also be used for new regions for which data is not available.
Authors: Xin Li, Yeqi Bai, Pinlong Cai, Licheng Wen, Daocheng Fu, Bo Zhang, Xuemeng Yang, Xinyu Cai, Tao Ma, Jianfei Guo, Xing Gao, Min Dou, Botian Shi, Yong Liu, Liang He, Yu Qiao
This paper explores the emerging knowledge-driven autonomous driving technologies. Our investigation highlights the limitations of current autonomous driving systems, in particular their sensitivity to data bias, difficulty in handling long-tail scenarios, and lack of interpretability. Conversely, knowledge-driven methods with the abilities of cognition, generalization and life-long learning emerge as a promising way to overcome these challenges. This paper delves into the essence of knowledge-driven autonomous driving and examines its core components: dataset \& benchmark, environment, and driver agent. By leveraging large language models, world models, neural rendering, and other advanced artificial intelligence techniques, these components collectively contribute to a more holistic, adaptive, and intelligent autonomous driving system. The paper systematically organizes and reviews previous research efforts in this area, and provides insights and guidance for future research and practical applications of autonomous driving. We will continually share the latest updates on cutting-edge developments in knowledge-driven autonomous driving along with the relevant valuable open-source resources at: \url{https://github.com/PJLab-ADG/awesome-knowledge-driven-AD}.
Authors: Pengcheng Chen, Ziyan Huang, Zhongying Deng, Tianbin Li, Yanzhou Su, Haoyu Wang, Jin Ye, Yu Qiao, Junjun He
OpenAI's latest large vision-language model (LVLM), GPT-4V(ision), has piqued considerable interest for its potential in medical applications. Despite its promise, recent studies and internal reviews highlight its underperformance in specialized medical tasks. This paper explores the boundary of GPT-4V's capabilities in medicine, particularly in processing complex imaging data from endoscopies, CT scans, and MRIs etc. Leveraging open-source datasets, we assessed its foundational competencies, identifying substantial areas for enhancement. Our research emphasizes prompt engineering, an often-underutilized strategy for improving AI responsiveness. Through iterative testing, we refined the model's prompts, significantly improving its interpretative accuracy and relevance in medical imaging. From our comprehensive evaluations, we distilled 10 effective prompt engineering techniques, each fortifying GPT-4V's medical acumen. These methodical enhancements facilitate more reliable, precise, and clinically valuable insights from GPT-4V, advancing its operability in critical healthcare environments. Our findings are pivotal for those employing AI in medicine, providing clear, actionable guidance on harnessing GPT-4V's full diagnostic potential.
Authors: Victor Agostinelli, Max Wild, Matthew Raffel, Kazi Ahmed Asif Fuad, Lizhong Chen
Large language models (LLMs) with billions of parameters and pretrained on massive amounts of data are now capable of near or better than state-of-the-art performance in a variety of downstream natural language processing tasks. Neural machine translation (NMT) is one such task that LLMs have been applied to with great success. However, little research has focused on applying LLMs to the more difficult subset of NMT called simultaneous translation (SimulMT), where translation begins before the entire source context is available to the model. In this paper, we address key challenges facing LLMs fine-tuned for SimulMT, validate classical SimulMT concepts and practices in the context of LLMs, explore adapting LLMs that are fine-tuned for NMT to the task of SimulMT, and introduce Simul-LLM, the first open-source fine-tuning and evaluation pipeline development framework for LLMs focused on SimulMT.
Authors: Jae Sung Park, Jack Hessel, Khyathi Raghavi Chandu, Paul Pu Liang, Ximing Lu, Peter West, Youngjae Yu, Qiuyuan Huang, Jianfeng Gao, Ali Farhadi, Yejin Choi
Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images do not directly enable the user to "point to" and access specific regions within images. This capability is important not only to support reference-grounded VL benchmarks, but also, for practical applications that require precise within-image reasoning. We build Localized Visual Commonsense models, which allow users to specify (multiple) regions as input. We train our model by sampling localized commonsense knowledge from a large language model (LLM): specifically, we prompt an LLM to collect commonsense knowledge given a global literal image description and a local literal region description automatically generated by a set of VL models. With a separately trained critic model that selects high-quality examples, we find that training on the localized commonsense corpus can successfully distill existing VL models to support a reference-as-input interface. Empirical results and human evaluations in a zero-shot setup demonstrate that our distillation method results in more precise VL models of reasoning compared to a baseline of passing a generated referring expression to an LLM.
Authors: Talfan Evans, Shreya Pathak, Hamza Merzic, Jonathan Schwarz, Ryutaro Tanno, Olivier J. Henaff
We propose a method for accelerating large-scale pre-training with online data selection policies. For the first time, we demonstrate that model-based data selection can reduce the total computation needed to reach the performance of models trained with uniform sampling. The key insight which enables this "compute-positive" regime is that small models provide good proxies for the loss of much larger models, such that computation spent on scoring data can be drastically scaled down but still significantly accelerate training of the learner.. These data selection policies also strongly generalize across datasets and tasks, opening an avenue for further amortizing the overhead of data scoring by re-using off-the-shelf models and training sequences. Our methods, ClassAct and ActiveCLIP, require 46% and 51% fewer training updates and up to 25% less total computation when training visual classifiers on JFT and multimodal models on ALIGN, respectively. Finally, our paradigm seamlessly applies to the curation of large-scale image-text datasets, yielding a new state-of-the-art in several multimodal transfer tasks and pre-training regimes.
Authors: Caoyun Fan, Jindou Chen, Yaohui Jin, Hao He
Game theory, as an analytical tool, is frequently utilized to analyze human behavior in social science research. With the high alignment between the behavior of Large Language Models (LLMs) and humans, a promising research direction is to employ LLMs as substitutes for humans in game experiments, enabling social science research. However, despite numerous empirical researches on the combination of LLMs and game theory, the capability boundaries of LLMs in game theory remain unclear. In this research, we endeavor to systematically analyze LLMs in the context of game theory. Specifically, rationality, as the fundamental principle of game theory, serves as the metric for evaluating players' behavior -- building a clear desire, refining belief about uncertainty, and taking optimal actions. Accordingly, we select three classical games (dictator game, Rock-Paper-Scissors, and ring-network game) to analyze to what extent LLMs can achieve rationality in these three aspects. The experimental results indicate that even the current state-of-the-art LLM (GPT-4) exhibits substantial disparities compared to humans in game theory. For instance, LLMs struggle to build desires based on uncommon preferences, fail to refine belief from many simple patterns, and may overlook or modify refined belief when taking actions. Therefore, we consider that introducing LLMs into game experiments in the field of social science should be approached with greater caution.
Authors: Shuhe Wang, Beiming Cao, Shengyu Zhang, Xiaoya Li, Jiwei Li, Fei Wu, Guoyin Wang, Eduard Hovy
Due to the lack of a large collection of high-quality labeled sentence pairs with textual similarity scores, existing approaches for Semantic Textual Similarity (STS) mostly rely on unsupervised techniques or training signals that are only partially correlated with textual similarity, e.g., NLI-based datasets. To tackle this issue, in this paper, we propose the strategy of measuring text similarity via GPT annotated data (Sim-GPT for short). The core idea of Sim-GPT is to generate data with STS labels using GPT-4, based on which an STS model is trained. Sim-GPT framework utilizes LLMs to provide a substantial amount of reliable annotated data filling the gap of the lack of training signals for STS. Sim-GPT is trained on a one-time generated dataset using BERT or RoBERTa as the backbone, which offers long-term savings in cost and speed compared to repeatedly invoking LLMs for each sentence pair. Trained on the examples from GPT-4 (371K), Sim-GPT yields SOTA performances on the widely-used seven STS benchmarks: +0.99 over supervised-SimCSE, and +0.42 over the current SOTA PromCSE model. To encourage further advancements of the field, we release both models and the 371K annotated examples from GPT-4. Code, models and annotated data are available at: https://github.com/ShuheWang1998/Sim-GPT.
Authors: Tianjin Huang, Tianlong Chen, Zhangyang Wang, Shiwei Liu
Vision Transformers have been rapidly uprising in computer vision thanks to their outstanding scaling trends, and gradually replacing convolutional neural networks (CNNs). Recent works on self-supervised learning (SSL) introduce siamese pre-training tasks, on which Transformer backbones continue to demonstrate ever stronger results than CNNs. People come to believe that Transformers or self-attention modules are inherently more suitable than CNNs in the context of SSL. However, it is noteworthy that most if not all prior arts of SSL with CNNs chose the standard ResNets as their backbones, whose architecture effectiveness is known to already lag behind advanced Vision Transformers. Therefore, it remains unclear whether the self-attention operation is crucial for the recent advances in SSL - or CNNs can deliver the same excellence with more advanced designs, too? Can we close the SSL performance gap between Transformers and CNNs? To answer these intriguing questions, we apply self-supervised pre-training to the recently proposed, stronger lager-kernel CNN architecture and conduct an apple-to-apple comparison with Transformers, in their SSL performance. Our results show that we are able to build pure CNN SSL architectures that perform on par with or better than the best SSL-trained Transformers, by just scaling up convolutional kernel sizes besides other small tweaks. Impressively, when transferring to the downstream tasks \texttt{MS COCO} detection and segmentation, our SSL pre-trained CNN model (trained in 100 epochs) achieves the same good performance as the 300-epoch pre-trained Transformer counterpart. We hope this work can help to better understand what is essential (or not) for self-supervised learning backbones.
Authors: Jianwei Li, Tianchi Zhang, Ian En-Hsu Yen, Dongkuan Xu
Transformer-based models, such as BERT, have been widely applied in a wide range of natural language processing tasks. However, one inevitable side effect is that they require massive memory storage and inference cost when deployed in production. Quantization is one of the popularized ways to alleviate the cost. However, the previous 8-bit quantization strategy based on INT8 data format either suffers from the degradation of accuracy in a Post-Training Quantization (PTQ) fashion or requires an expensive Quantization-Aware Training (QAT) process. Recently, a new numeric format FP8 (i.e. floating-point of 8-bits) has been proposed and supported in commercial AI computing platforms such as H100. In this paper, we empirically validate the effectiveness of FP8 as a way to do Post-Training Quantization without significant loss of accuracy, with a simple calibration and format conversion process. We adopt the FP8 standard proposed by NVIDIA Corp. (2022) in our extensive experiments of BERT variants on GLUE and SQuAD v1.1 datasets, and show that PTQ with FP8 can significantly improve the accuracy upon that with INT8, to the extent of the full-precision model.
Authors: Huajian Li, Longjian Li, Jiajian Liang, Weinan Dai
In recent years, machine learning (ML) has brought effective approaches and novel techniques to economic decision, investment forecasting, and risk management, etc., coping the variable and intricate nature of economic and financial environments. For the investment in stock market, this research introduces a pioneering quantitative fusion model combining stock timing and picking strategy by leveraging the Multivariate Gaussian-Hidden Markov Model (MGHMM) and Back Propagation Neural Network optimized by Particle Swarm (PSO-BPNN). After the information coefficients (IC) between fifty-two factors that have been winsorized, neutralized and standardized and the return of CSI 300 index are calculated, a given amount of factors that rank ahead are choose to be candidate factors heading for the input of PSO-BPNN after dimension reduction by Principal Component Analysis (PCA), followed by a certain amount of constituent stocks outputted. Subsequently, we conduct the prediction and trading on the basis of the screening stocks and stock market state outputted by MGHMM trained using inputting CSI 300 index data after Box-Cox transformation, bespeaking eximious performance during the period of past four years. Ultimately, some conventional forecast and trading methods are compared with our strategy in Chinese stock market. Our fusion strategy incorporating stock picking and timing presented in this article provide a innovative technique for financial analysis.
Authors: Gyeong-Geon Lee, Lehong Shi, Ehsan Latif, Yizhu Gao, Arne Bewersdorff, Matthew Nyaaba, Shuchen Guo, Zihao Wu, Zhengliang Liu, Hui Wang, Gengchen Mai, Tiaming Liu, Xiaoming Zhai
This paper presents a comprehensive examination of how multimodal artificial intelligence (AI) approaches are paving the way towards the realization of Artificial General Intelligence (AGI) in educational contexts. It scrutinizes the evolution and integration of AI in educational systems, emphasizing the crucial role of multimodality, which encompasses auditory, visual, kinesthetic, and linguistic modes of learning. This research delves deeply into the key facets of AGI, including cognitive frameworks, advanced knowledge representation, adaptive learning mechanisms, strategic planning, sophisticated language processing, and the integration of diverse multimodal data sources. It critically assesses AGI's transformative potential in reshaping educational paradigms, focusing on enhancing teaching and learning effectiveness, filling gaps in existing methodologies, and addressing ethical considerations and responsible usage of AGI in educational settings. The paper also discusses the implications of multimodal AI's role in education, offering insights into future directions and challenges in AGI development. This exploration aims to provide a nuanced understanding of the intersection between AI, multimodality, and education, setting a foundation for future research and development in AGI.
Authors: Tao Chen, Enwei Zhang, Yuting Gao, Ke Li, Xing Sun, Yan Zhang, Hui Li
Although In-Context Learning (ICL) brings remarkable performance gains to Large Language Models (LLMs), the improvements remain lower than fine-tuning on downstream tasks. This paper introduces Multi-Modal In-Context Tuning (MMICT), a novel multi-modal fine-tuning paradigm that boosts multi-modal fine-tuning by fully leveraging the promising ICL capability of multi-modal LLMs (MM-LLMs). We propose the Multi-Modal Hub (M-Hub), a unified module that captures various multi-modal features according to different inputs and objectives. Based on M-Hub, MMICT enables MM-LLMs to learn from in-context visual-guided textual features and subsequently generate outputs conditioned on the textual-guided visual features. Moreover, leveraging the flexibility of M-Hub, we design a variety of in-context demonstrations. Extensive experiments on a diverse range of downstream multi-modal tasks demonstrate that MMICT significantly outperforms traditional fine-tuning strategy and the vanilla ICT method that directly takes the concatenation of all information from different modalities as input.
Authors: Ronghui Mu, Leandro Soriano Marcolino, Tianle Zhang, Yanghao Zhang, Xiaowei Huang, Wenjie Ruan
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks. Recent studies have introduced "smoothed policies" in order to enhance its robustness. Yet, it is still challenging to establish a provable guarantee to certify the bound of its total reward. Prior methods relied primarily on computing bounds using Lipschitz continuity or calculating the probability of cumulative reward above specific thresholds. However, these techniques are only suited for continuous perturbations on the RL agent's observations and are restricted to perturbations bounded by the $l_2$-norm. To address these limitations, this paper proposes a general black-box certification method capable of directly certifying the cumulative reward of the smoothed policy under various $l_p$-norm bounded perturbations. Furthermore, we extend our methodology to certify perturbations on action spaces. Our approach leverages f-divergence to measure the distinction between the original distribution and the perturbed distribution, subsequently determining the certification bound by solving a convex optimisation problem. We provide a comprehensive theoretical analysis and run sufficient experiments in multiple environments. Our results show that our method not only improves the certified lower bound of mean cumulative reward but also demonstrates better efficiency than state-of-the-art techniques.
Authors: Francesco Leofante, Nico Potyka
Counterfactual explanations shed light on the decisions of black-box models by explaining how an input can be altered to obtain a favourable decision from the model (e.g., when a loan application has been rejected). However, as noted recently, counterfactual explainers may lack robustness in the sense that a minor change in the input can cause a major change in the explanation. This can cause confusion on the user side and open the door for adversarial attacks. In this paper, we study some sources of non-robustness. While there are fundamental reasons for why an explainer that returns a single counterfactual cannot be robust in all instances, we show that some interesting robustness guarantees can be given by reporting multiple rather than a single counterfactual. Unfortunately, the number of counterfactuals that need to be reported for the theoretical guarantees to hold can be prohibitively large. We therefore propose an approximation algorithm that uses a diversity criterion to select a feasible number of most relevant explanations and study its robustness empirically. Our experiments indicate that our method improves the state-of-the-art in generating robust explanations, while maintaining other desirable properties and providing competitive computational performance.
Authors: Pooja Prajod, Matteo Lavit Nicora, Marta Mondellini, Giovanni Tauro, Rocco Vertechy, Matteo Malosio, Elisabeth André
Collaborative robots (cobots) are widely used in industrial applications, yet extensive research is still needed to enhance human-robot collaborations and operator experience. A potential approach to improve the collaboration experience involves adapting cobot behavior based on natural cues from the operator. Inspired by the literature on human-human interactions, we conducted a wizard-of-oz study to examine whether a gaze towards the cobot can serve as a trigger for initiating joint activities in collaborative sessions. In this study, 37 participants engaged in an assembly task while their gaze behavior was analyzed. We employ a gaze-based attention recognition model to identify when the participants look at the cobot. Our results indicate that in most cases (84.88\%), the joint activity is preceded by a gaze towards the cobot. Furthermore, during the entire assembly cycle, the participants tend to look at the cobot around the time of the joint activity. To the best of our knowledge, this is the first study to analyze the natural gaze behavior of participants working on a joint activity with a robot during a collaborative assembly task.
Authors: Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Hongming Zhang, Dong Yu
Dense retrieval has become a prominent method to obtain relevant context or world knowledge in open-domain NLP tasks. When we use a learned dense retriever on a retrieval corpus at inference time, an often-overlooked design choice is the retrieval unit in which the corpus is indexed, e.g. document, passage, or sentence. We discover that the retrieval unit choice significantly impacts the performance of both retrieval and downstream tasks. Distinct from the typical approach of using passages or sentences, we introduce a novel retrieval unit, proposition, for dense retrieval. Propositions are defined as atomic expressions within text, each encapsulating a distinct factoid and presented in a concise, self-contained natural language format. We conduct an empirical comparison of different retrieval granularity. Our results reveal that proposition-based retrieval significantly outperforms traditional passage or sentence-based methods in dense retrieval. Moreover, retrieval by proposition also enhances the performance of downstream QA tasks, since the retrieved texts are more condensed with question-relevant information, reducing the need for lengthy input tokens and minimizing the inclusion of extraneous, irrelevant information.
Authors: Zhongang Cai, Jianping Jiang, Zhongfei Qing, Xinying Guo, Mingyuan Zhang, Zhengyu Lin, Haiyi Mei, Chen Wei, Ruisi Wang, Wanqi Yin, Xiangyu Fan, Han Du, Liang Pan, Peng Gao, Zhitao Yang, Yang Gao, Jiaqi Li, Tianxiang Ren, Yukun Wei, Xiaogang Wang, Chen Change Loy, Lei Yang, Ziwei Liu
In this work, we present Digital Life Project, a framework utilizing language as the universal medium to build autonomous 3D characters, who are capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life in a digital environment. Our framework comprises two primary components: 1) SocioMind: a meticulously crafted digital brain that models personalities with systematic few-shot exemplars, incorporates a reflection process based on psychology principles, and emulates autonomy by initiating dialogue topics; 2) MoMat-MoGen: a text-driven motion synthesis paradigm for controlling the character's digital body. It integrates motion matching, a proven industry technique to ensure motion quality, with cutting-edge advancements in motion generation for diversity. Extensive experiments demonstrate that each module achieves state-of-the-art performance in its respective domain. Collectively, they enable virtual characters to initiate and sustain dialogues autonomously, while evolving their socio-psychological states. Concurrently, these characters can perform contextually relevant bodily movements. Additionally, a motion captioning module further allows the virtual character to recognize and appropriately respond to human players' actions. Homepage: https://digital-life-project.com/