Authors: John Schultz, Jakub Adamek, Matej Jusup, Marc Lanctot, Michael Kaisers, Sarah Perrin, Daniel Hennes, Jeremy Shar, Cannada Lewis, Anian Ruoss, Tom Zahavy, Petar Veli\v{c}kovi\'c, Laurel Prince, Satinder Singh, Eric Malmi, Nenad Toma\v{s}ev
Abstract: While large language models perform well on a range of complex tasks (e.g., text generation, question answering, summarization), robust multi-step planning and reasoning remains a considerable challenge for them. In this paper we show that search-based planning can significantly improve LLMs' playing strength across several board games (Chess, Fischer Random / Chess960, Connect Four, and Hex). We introduce, compare and contrast two major approaches: In external search, the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an external engine, and in internal search, the model directly generates in-context a linearized tree of potential futures and a resulting final choice. Both build on a language model pre-trained on relevant domain knowledge, capturing the transition and value functions across these games. We find that our pre-training method minimizes hallucinations, as our model is highly accurate regarding state prediction and legal moves. Additionally, both internal and external search indeed improve win-rates against state-of-the-art bots, even reaching Grandmaster-level performance in chess while operating on a similar move count search budget per decision as human Grandmasters. The way we combine search with domain knowledge is not specific to board games, suggesting direct extensions into more general language model inference and training techniques.
Authors: Itay Beit-Halachmi, Ido Kaminer
Abstract: Fundamental mathematical constants appear in nearly every field of science, from physics to biology. Formulas that connect different constants often bring great insight by hinting at connections between previously disparate fields. Discoveries of such relations, however, have remained scarce events, relying on sporadic strokes of creativity by human mathematicians. Recent developments of algorithms for automated conjecture generation have accelerated the discovery of formulas for specific constants. Yet, the discovery of connections between constants has not been addressed. In this paper, we present the first library dedicated to mathematical constants and their interrelations. This library can serve as a central repository of knowledge for scientists from different areas, and as a collaborative platform for development of new algorithms. The library is based on a new representation that we propose for organizing the formulas of mathematical constants: a hypergraph, with each node representing a constant and each edge representing a formula. Using this representation, we propose and demonstrate a systematic approach for automatically enriching this library using PSLQ, an integer relation algorithm based on QR decomposition and lattice construction. During its development and testing, our strategy led to the discovery of 75 previously unknown connections between constants, including a new formula for the `first continued fraction' constant $C_1$, novel formulas for natural logarithms, and new formulas connecting $\pi$ and $e$. The latter formulas generalize a century-old relation between $\pi$ and $e$ by Ramanujan, which until now was considered a singular formula and is now found to be part of a broader mathematical structure. The code supporting this library is a public, open-source API that can serve researchers in experimental mathematics and other fields of science.
Authors: Yutong Xie, Yiyao Liu, Zhuang Ma, Lin Shi, Xiyuan Wang, Walter Yuan, Matthew O. Jackson, Qiaozhu Mei
Abstract: The deployment of large language models (LLMs) in diverse applications requires a thorough understanding of their decision-making strategies and behavioral patterns. As a supplement to a recent study on the behavioral Turing test, this paper presents a comprehensive analysis of five leading LLM-based chatbot families as they navigate a series of behavioral economics games. By benchmarking these AI chatbots, we aim to uncover and document both common and distinct behavioral patterns across a range of scenarios. The findings provide valuable insights into the strategic preferences of each LLM, highlighting potential implications for their deployment in critical decision-making roles.
Authors: Jingde Cheng
Abstract: Recently, it is often said that the data used for the pre-training of large language models (LLMs) have been exhausted. This paper proposes a solution to the problem: Automated generation of massive reasonable empirical theorems by forward reasoning based on strong relevant logics. In fact, this can be regarded as a part of our approach to the problems of ATF (Automated Theorem Finding) and AKA (Automated Knowledge Appreciation).
Authors: Joseph Bills, Christopher Archibald, Diego Blaylock
Abstract: In two-player cooperative games, agents can play together effectively when they have accurate assumptions about how their teammate will behave, but may perform poorly when these assumptions are inaccurate. In language games, failure may be due to disagreement in the understanding of either the semantics or pragmatics of an utterance. We model coarse uncertainty in semantics using a prior distribution of language models and uncertainty in pragmatics using the cognitive hierarchy, combining the two aspects into a single prior distribution over possible partner types. Fine-grained uncertainty in semantics is modeled using noise that is added to the embeddings of words in the language. To handle all forms of uncertainty we construct agents that learn the behavior of their partner using Bayesian inference and use this information to maximize the expected value of a heuristic function. We test this approach by constructing Bayesian agents for the game of Codenames, and show that they perform better in experiments where semantics is uncertain
Authors: Deep Bhatt, Surya Ayyagari, Anuruddh Mishra
Abstract: Diagnostic errors in healthcare persist as a critical challenge, with increasing numbers of patients turning to online resources for health information. While AI-powered healthcare chatbots show promise, there exists no standardized and scalable framework for evaluating their diagnostic capabilities. This study introduces a scalable benchmarking methodology for assessing health AI systems and demonstrates its application through August, an AI-driven conversational chatbot. Our methodology employs 400 validated clinical vignettes across 14 medical specialties, using AI-powered patient actors to simulate realistic clinical interactions. In systematic testing, August achieved a top-one diagnostic accuracy of 81.8% (327/400 cases) and a top-two accuracy of 85.0% (340/400 cases), significantly outperforming traditional symptom checkers. The system demonstrated 95.8% accuracy in specialist referrals and required 47% fewer questions compared to conventional symptom checkers (mean 16 vs 29 questions), while maintaining empathetic dialogue throughout consultations. These findings demonstrate the potential of AI chatbots to enhance healthcare delivery, though implementation challenges remain regarding real-world validation and integration of objective clinical data. This research provides a reproducible framework for evaluating healthcare AI systems, contributing to the responsible development and deployment of AI in clinical settings.
Authors: Hao Wang, Boyi Liu, Yufeng Zhang, Jie Chen
Abstract: Competition-level code generation tasks pose significant challenges for current state-of-the-art large language models (LLMs). For example, on the LiveCodeBench-Hard dataset, models such as O1-Mini and O1-Preview achieve pass@1 rates of only 0.366 and 0.143, respectively. While tree search techniques have proven effective in domains like mathematics and general coding, their potential in competition-level code generation remains under-explored. In this work, we propose a novel token-level tree search method specifically designed for code generation. Leveraging Qwen2.5-Coder-32B-Instruct, our approach achieves a pass rate of 0.305 on LiveCodeBench-Hard, surpassing the pass@100 performance of GPT4o-0513 (0.245). Furthermore, by integrating Chain-of-Thought (CoT) prompting, we improve our method's performance to 0.351, approaching O1-Mini's pass@1 rate. To ensure reproducibility, we report the average number of generations required per problem by our tree search method on the test set. Our findings underscore the potential of tree search to significantly enhance performance on competition-level code generation tasks. This opens up new possibilities for large-scale synthesis of challenging code problems supervised fine-tuning (SFT) data, advancing competition-level code generation tasks.
Authors: YiFan Zhang, Shanglin Lei, Runqi Qiao, Zhuoma GongQue, Xiaoshuai Song, Guanting Dong, Qiuna Tan, Zhe Wei, Peiqing Yang, Ye Tian, Yadong Xue, Xiaofei Wang, Honggang Zhang
Abstract: The rapidly developing field of large multimodal models (LMMs) has led to the emergence of diverse models with remarkable capabilities. However, existing benchmarks fail to comprehensively, objectively and accurately evaluate whether LMMs align with the diverse needs of humans in real-world scenarios. To bridge this gap, we propose the Multi-Dimensional Insights (MDI) benchmark, which includes over 500 images covering six common scenarios of human life. Notably, the MDI-Benchmark offers two significant advantages over existing evaluations: (1) Each image is accompanied by two types of questions: simple questions to assess the model's understanding of the image, and complex questions to evaluate the model's ability to analyze and reason beyond basic content. (2) Recognizing that people of different age groups have varying needs and perspectives when faced with the same scenario, our benchmark stratifies questions into three age categories: young people, middle-aged people, and older people. This design allows for a detailed assessment of LMMs' capabilities in meeting the preferences and needs of different age groups. With MDI-Benchmark, the strong model like GPT-4o achieve 79% accuracy on age-related tasks, indicating that existing LMMs still have considerable room for improvement in addressing real-world applications. Looking ahead, we anticipate that the MDI-Benchmark will open new pathways for aligning real-world personalization in LMMs. The MDI-Benchmark data and evaluation code are available at https://mdi-benchmark.github.io/
Authors: Hritik Bansal, Daniel Israel, Siyan Zhao, Shufan Li, Tung Nguyen, Aditya Grover
Abstract: Recent advancements in mixed-modal generative models have enabled flexible integration of information across image-text content. These models have opened new avenues for developing unified biomedical assistants capable of analyzing biomedical images, answering complex questions about them, and predicting the impact of medical procedures on a patient's health. However, existing resources face challenges such as limited data availability, narrow domain coverage, and restricted sources (e.g., medical papers). To address these gaps, we present MedMax, the first large-scale multimodal biomedical instruction-tuning dataset for mixed-modal foundation models. With 1.47 million instances, MedMax encompasses a diverse range of tasks, including multimodal content generation (interleaved image-text data), biomedical image captioning and generation, visual chatting, and report understanding. These tasks span diverse medical domains such as radiology and histopathology. Subsequently, we fine-tune a mixed-modal foundation model on the MedMax dataset, achieving significant performance improvements: a 26% gain over the Chameleon model and an 18.3% improvement over GPT-4o across 12 downstream biomedical visual question-answering tasks. Additionally, we introduce a unified evaluation suite for biomedical tasks, providing a robust framework to guide the development of next-generation mixed-modal biomedical AI assistants.
Authors: Liangru Xie, Hui Liu, Jingying Zeng, Xianfeng Tang, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Qi He
Abstract: Large Language Models (LLMs) demonstrate remarkable performance in semantic understanding and generation, yet accurately assessing their output reliability remains a significant challenge. While numerous studies have explored calibration techniques, they primarily focus on White-Box LLMs with accessible parameters. Black-Box LLMs, despite their superior performance, pose heightened requirements for calibration techniques due to their API-only interaction constraints. Although recent researches have achieved breakthroughs in black-box LLMs calibration, a systematic survey of these methodologies is still lacking. To bridge this gap, we presents the first comprehensive survey on calibration techniques for black-box LLMs. We first define the Calibration Process of LLMs as comprising two interrelated key steps: Confidence Estimation and Calibration. Second, we conduct a systematic review of applicable methods within black-box settings, and provide insights on the unique challenges and connections in implementing these key steps. Furthermore, we explore typical applications of Calibration Process in black-box LLMs and outline promising future research directions, providing new perspectives for enhancing reliability and human-machine alignment. This is our GitHub link: https://github.com/LiangruXie/Calibration-Process-in-Black-Box-LLMs
URLs: https://github.com/LiangruXie/Calibration-Process-in-Black-Box-LLMs
Authors: Kaustubh Vyas, Damien Graux, Yijun Yang, S\'ebastien Montella, Chenxin Diao, Wendi Zhou, Pavlos Vougiouklis, Ruofei Lai, Yang Ren, Keshuang Li, Jeff Z. Pan
Abstract: In response to the call for agent-based solutions that leverage the ever-increasing capabilities of the deep models' ecosystem, we introduce Hive -- a comprehensive solution for selecting appropriate models and subsequently planning a set of atomic actions to satisfy the end-users' instructions. Hive operates over sets of models and, upon receiving natural language instructions (i.e. user queries), schedules and executes explainable plans of atomic actions. These actions can involve one or more of the available models to achieve the overall task, while respecting end-users specific constraints. Notably, Hive handles tasks that involve multi-modal inputs and outputs, enabling it to handle complex, real-world queries. Our system is capable of planning complex chains of actions while guaranteeing explainability, using an LLM-based formal logic backbone empowered by PDDL operations. We introduce the MuSE benchmark in order to offer a comprehensive evaluation of the multi-modal capabilities of agent systems. Our findings show that our framework redefines the state-of-the-art for task selection, outperforming other competing systems that plan operations across multiple models while offering transparency guarantees while fully adhering to user constraints.
Authors: Jonathan Shaki, Jiarui Gan, Sarit Kraus
Abstract: We study a Bayesian persuasion problem with externalities. In this model, a principal sends signals to inform multiple agents about the state of the world. Simultaneously, due to the existence of externalities in the agents' utilities, the principal also acts as a correlation device to correlate the agents' actions. We consider the setting where the agents are categorized into a small number of types. Agents of the same type share identical utility functions and are treated equitably in the utility functions of both other agents and the principal. We study the problem of computing optimal signaling strategies for the principal, under three different types of signaling channels: public, private, and semi-private. Our results include revelation-principle-style characterizations of optimal signaling strategies, linear programming formulations, and analysis of in/tractability of the optimization problems. It is demonstrated that when the maximum number of deviating agents is bounded by a constant, our LP-based formulations compute optimal signaling strategies in polynomial time. Otherwise, the problems are NP-hard.
Authors: Quentin Mani\`ere, Marcin Przyby{\l}ko
Abstract: Recent works have explored the use of counting queries coupled with Description Logic ontologies. The answer to such a query in a model of a knowledge base is either an integer or $\infty$, and its spectrum is the set of its answers over all models. While it is unclear how to compute and manipulate such a set in general, we identify a class of counting queries whose spectra can be effectively represented. Focusing on atomic counting queries, we pinpoint the possible shapes of a spectrum over $\mathcal{ALCIF}$ ontologies: they are essentially the subsets of $\mathbb{N} \cup \{ \infty \}$ closed under addition. For most sublogics of $\mathcal{ALCIF}$, we show that possible spectra enjoy simpler shapes, being $[ m, \infty ]$ or variations thereof. To obtain our results, we refine constructions used for finite model reasoning and notably rely on a cycle-reversion technique for the Horn fragment of $\mathcal{ALCIF}$. We also study the data complexity of computing the proposed effective representation and establish the $\mathsf{FP}^{\mathsf{NP}[\log]}$-completeness of this task under several settings.
Authors: Lennert De Smet, Gabriele Venturato, Luc De Raedt, Giuseppe Marra
Abstract: Sequential problems are ubiquitous in AI, such as in reinforcement learning or natural language processing. State-of-the-art deep sequential models, like transformers, excel in these settings but fail to guarantee the satisfaction of constraints necessary for trustworthy deployment. In contrast, neurosymbolic AI (NeSy) provides a sound formalism to enforce constraints in deep probabilistic models but scales exponentially on sequential problems. To overcome these limitations, we introduce relational neurosymbolic Markov models (NeSy-MMs), a new class of end-to-end differentiable sequential models that integrate and provably satisfy relational logical constraints. We propose a strategy for inference and learning that scales on sequential settings, and that combines approximate Bayesian inference, automated reasoning, and gradient estimation. Our experiments show that NeSy-MMs can solve problems beyond the current state-of-the-art in neurosymbolic AI and still provide strong guarantees with respect to desired properties. Moreover, we show that our models are more interpretable and that constraints can be adapted at test time to out-of-distribution scenarios.
Authors: Michael Novitsky, Moran Barenboim, Vadim Indelman
Abstract: Online planning under uncertainty remains a critical challenge in robotics and autonomous systems. While tree search techniques are commonly employed to construct partial future trajectories within computational constraints, most existing methods discard information from previous planning sessions considering continuous spaces. This study presents a novel, computationally efficient approach that leverages historical planning data in current decision-making processes. We provide theoretical foundations for our information reuse strategy and introduce an algorithm based on Monte Carlo Tree Search (MCTS) that implements this approach. Experimental results demonstrate that our method significantly reduces computation time while maintaining high performance levels. Our findings suggest that integrating historical planning information can substantially improve the efficiency of online decision-making in uncertain environments, paving the way for more responsive and adaptive autonomous systems.
Authors: Tom McClelland
Abstract: Could an AI have conscious experiences? Any answer to this question should conform to Evidentialism - that is, it should be based not on intuition, dogma or speculation but on solid scientific evidence. I argue that such evidence is hard to come by and that the only justifiable stance on the prospects of artificial consciousness is agnosticism. In the current debate, the main division is between biological views that are sceptical of artificial consciousness and functional views that are sympathetic to it. I argue that both camps make the same mistake of over-estimating what the evidence tells us. Scientific insights into consciousness have been achieved through the study of conscious organisms. Although this has enabled cautious assessments of consciousness in various creatures, extending this to AI faces serious obstacles. AI thus presents consciousness researchers with a dilemma: either reach a verdict on artificial consciousness but violate Evidentialism; or respect Evidentialism but offer no verdict on the prospects of artificial consciousness. The dominant trend in the literature has been to take the first option while purporting to follow the scientific evidence. I argue that if we truly follow the evidence, we must take the second option and adopt agnosticism.
Authors: Junnan Liu, Hongwei Liu, Linchen Xiao, Ziyi Wang, Kuikun Liu, Songyang Gao, Wenwei Zhang, Songyang Zhang, Kai Chen
Abstract: The rapid advancement of Large Language Models (LLMs) has demonstrated remarkable progress in complex reasoning tasks. However, a significant discrepancy persists between benchmark performances and real-world applications. We identify this gap as primarily stemming from current evaluation protocols and metrics, which inadequately capture the full spectrum of LLM capabilities, particularly in complex reasoning tasks where both accuracy and consistency are crucial. This work makes two key contributions. First, we introduce G-Pass@k, a novel evaluation metric that provides a continuous assessment of model performance across multiple sampling attempts, quantifying both the model's peak performance potential and its stability. Second, we present LiveMathBench, a dynamic benchmark comprising challenging, contemporary mathematical problems designed to minimize data leakage risks during evaluation. Through extensive experiments using G-Pass@k on state-of-the-art LLMs with LiveMathBench, we provide comprehensive insights into both their maximum capabilities and operational consistency. Our findings reveal substantial room for improvement in LLMs' "realistic" reasoning capabilities, highlighting the need for more robust evaluation methods. The benchmark and detailed results are available at: https://github.com/open-compass/GPassK.
Authors: Saumya Banthia, Anantha Sharma
Abstract: This document describes a possible approach that can be used to check the relevance of a summary / definition of an entity with respect to its name. This classifier focuses on the relevancy of an entity's name to its summary / definition, in other words, it is a name relevance check. The percentage score obtained from this approach can be used either on its own or used to supplement scores obtained from other metrics to arrive upon a final classification; at the end of the document, potential improvements have also been outlined. The dataset that this document focuses on achieving an objective score is a list of package names and their respective summaries (sourced from pypi.org).
Authors: Chejui Liao, Tabish Maniar, Sravanajyothi N, Anantha Sharma
Abstract: This paper discusses the effectiveness of various text processing techniques, their combinations, and encodings to achieve a reduction of complexity and size in a given text corpus. The simplified text corpus is sent to BERT (or similar transformer based models) for question and answering and can produce more relevant responses to user queries. This paper takes a scientific approach to determine the benefits and effectiveness of various techniques and concludes a best-fit combination that produces a statistically significant improvement in accuracy.
Authors: Fatemeh Rezapoor Nikroo, Ajinkya Deshmukh, Anantha Sharma, Adrian Tam, Kaarthik Kumar, Cleo Norris, Aditya Dangi
Abstract: In this study, we evaluate the performance of multiple state-of-the-art SRGAN (Super Resolution Generative Adversarial Network) models, ESRGAN, Real-ESRGAN and EDSR, on a benchmark dataset of real-world images which undergo degradation using a pipeline. Our results show that some models seem to significantly increase the resolution of the input images while preserving their visual quality, this is assessed using Tesseract OCR engine. We observe that EDSR-BASE model from huggingface outperforms the remaining candidate models in terms of both quantitative metrics and subjective visual quality assessments with least compute overhead. Specifically, EDSR generates images with higher peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) values and are seen to return high quality OCR results with Tesseract OCR engine. These findings suggest that EDSR is a robust and effective approach for single-image super-resolution and may be particularly well-suited for applications where high-quality visual fidelity is critical and optimized compute.
Authors: Yifeng Peng, Xinyi Li, Zhiding Liang, Ying Wang
Abstract: Open set anomaly detection (OSAD) is a crucial task that aims to identify abnormal patterns or behaviors in data sets, especially when the anomalies observed during training do not represent all possible classes of anomalies. The recent advances in quantum computing in handling complex data structures and improving machine learning models herald a paradigm shift in anomaly detection methodologies. This study proposes a Quantum Scoring Module (Qsco), embedding quantum variational circuits into neural networks to enhance the model's processing capabilities in handling uncertainty and unlabeled data. Extensive experiments conducted across eight real-world anomaly detection datasets demonstrate our model's superior performance in detecting anomalies across varied settings and reveal that integrating quantum simulators does not result in prohibitive time complexities. Our study validates the feasibility of quantum-enhanced anomaly detection methods in practical applications.
Authors: Anantha Sharma, Ajinkya Deshmukh
Abstract: With the increasing demand for data sharing across platforms and organizations, ensuring the privacy and security of sensitive information has become a critical challenge. This paper introduces "TableGuard". An innovative approach to data obfuscation tailored for relational databases. Building on the principles and techniques developed in prior work on context-sensitive obfuscation, TableGuard applies these methods to ensure that API calls return only obfuscated data, thereby safeguarding privacy when sharing data with third parties. TableGuard leverages advanced context-sensitive obfuscation techniques to replace sensitive data elements with contextually appropriate alternatives. By maintaining the relational integrity and coherence of the data, our approach mitigates the risks of cognitive dissonance and data leakage. We demonstrate the implementation of TableGuard using a BERT based transformer model, which identifies and obfuscates sensitive entities within relational tables. Our evaluation shows that TableGuard effectively balances privacy protection with data utility, minimizing information loss while ensuring that the obfuscated data remains functionally useful for downstream applications. The results highlight the importance of domain-specific obfuscation strategies and the role of context length in preserving data integrity. The implications of this research are significant for organizations that need to share data securely with external parties. TableGuard offers a robust framework for implementing privacy-preserving data sharing mechanisms, thereby contributing to the broader field of data privacy and security.
Authors: Elana Simon, James Zou
Abstract: Protein language models (PLMs) have demonstrated remarkable success in protein modeling and design, yet their internal mechanisms for predicting structure and function remain poorly understood. Here we present a systematic approach to extract and analyze interpretable features from PLMs using sparse autoencoders (SAEs). By training SAEs on embeddings from the PLM ESM-2, we identify up to 2,548 human-interpretable latent features per layer that strongly correlate with up to 143 known biological concepts such as binding sites, structural motifs, and functional domains. In contrast, examining individual neurons in ESM-2 reveals up to 46 neurons per layer with clear conceptual alignment across 15 known concepts, suggesting that PLMs represent most concepts in superposition. Beyond capturing known annotations, we show that ESM-2 learns coherent concepts that do not map onto existing annotations and propose a pipeline using language models to automatically interpret novel latent features learned by the SAEs. As practical applications, we demonstrate how these latent features can fill in missing annotations in protein databases and enable targeted steering of protein sequence generation. Our results demonstrate that PLMs encode rich, interpretable representations of protein biology and we propose a systematic framework to extract and analyze these latent features. In the process, we recover both known biology and potentially new protein motifs. As community resources, we introduce InterPLM (interPLM.ai), an interactive visualization platform for exploring and analyzing learned PLM features, and release code for training and analysis at github.com/ElanaPearl/interPLM.
Authors: Chuan Zhang, Xixi Zheng, Xiaolong Tao, Chenfei Hu, Weiting Zhang, Liehuang Zhu
Abstract: With the rapid advancement of artificial intelligence, generative artificial intelligence (GAI) has taken a leading role in transforming data processing methods. However, the high computational demands of GAI present challenges for devices with limited resources. As we move towards the sixth generation of mobile networks (6G), the higher data rates and improved energy efficiency of 6G create a need for more efficient data processing in GAI. Traditional GAI, however, shows its limitations in meeting these demands. To address these challenges, we introduce a multi-level collaborative inference system designed for next-generation networks and communication. Our proposed system features a deployment strategy that assigns models of varying sizes to devices at different network layers. Then, we design a task offloading strategy to optimise both efficiency and latency. Furthermore, a modified early exit mechanism is implemented to enhance the inference process for single models. Experimental results demonstrate that our system effectively reduces inference latency while maintaining high-quality output. Specifically, compared to existing work, our system can reduce inference time by up to 17% without sacrificing the inference accuracy.
Authors: Naoto Yoshida, Kingson Man
Abstract: When regarding the suffering of others, we often experience personal distress and feel compelled to help. Inspired by living systems, we investigate the emergence of prosocial behavior among autonomous agents that are motivated by homeostatic self-regulation. We perform multi-agent reinforcement learning, treating each agent as a vulnerable homeostat charged with maintaining its own well-being. We introduce an empathy-like mechanism to share homeostatic states between agents: an agent can either \emph{observe} their partner's internal state (cognitive empathy) or the agent's internal state can be \emph{directly coupled} to that of their partner's (affective empathy). In three simple multi-agent environments, we show that prosocial behavior arises only under homeostatic coupling - when the distress of a partner can affect one's own well-being. Our findings specify the type and role of empathy in artificial agents capable of prosocial behavior.
Authors: Ravinithesh Annapureddy, Alessandro Fornaroli, Daniel Gatica-Perez
Abstract: This paper introduces a competency-based model for generative artificial intelligence (AI) literacy covering essential skills and knowledge areas necessary to interact with generative AI. The competencies range from foundational AI literacy to prompt engineering and programming skills, including ethical and legal considerations. These twelve competencies offer a framework for individuals, policymakers, government officials, and educators looking to navigate and take advantage of the potential of generative AI responsibly. Embedding these competencies into educational programs and professional training initiatives can equip individuals to become responsible and informed users and creators of generative AI. The competencies follow a logical progression and serve as a roadmap for individuals seeking to get familiar with generative AI and for researchers and policymakers to develop assessments, educational programs, guidelines, and regulations.
Authors: Sarah Kiden, Bernd Stahl, Beverley Townsend, Carsten Maple, Charles Vincent, Fraser Sampson, Geoff Gilbert, Helen Smith, Jayati Deshmukh, Jen Ross, Jennifer Williams, Jesus Martinez del Rincon, Justyna Lisinska, Karen O'Shea, M\'arjory Da Costa Abreu, Nelly Bencomo, Oishi Deb, Peter Winter, Phoebe Li, Philip Torr, Pin Lean Lau, Raquel Iniesta, Gopal Ramchurn, Sebastian Stein, Vahid Yazdanpanah
Abstract: This report presents a comprehensive response to the United Nation's Interim Report on Governing Artificial Intelligence (AI) for Humanity. It emphasizes the transformative potential of AI in achieving the Sustainable Development Goals (SDGs) while acknowledging the need for robust governance to mitigate associated risks. The response highlights opportunities for promoting equitable, secure, and inclusive AI ecosystems, which should be supported by investments in infrastructure and multi-stakeholder collaborations across jurisdictions. It also underscores challenges, including societal inequalities exacerbated by AI, ethical concerns, and environmental impacts. Recommendations advocate for legally binding norms, transparency, and multi-layered data governance models, alongside fostering AI literacy and capacity-building initiatives. Internationally, the report calls for harmonising AI governance frameworks with established laws, human rights standards, and regulatory approaches. The report concludes with actionable principles for fostering responsible AI governance through collaboration among governments, industry, academia, and civil society, ensuring the development of AI aligns with universal human values and the public good.
Authors: Eyvind Elstad
Abstract: This study examines the integration of generative AI in schools, assessing its benefits and risks. As AI use by students grows, it's crucial to understand its impact on learning and teaching practices. Generative AI, like ChatGPT, can create human-like content, prompting questions about its educational role. The article differentiates large language models from traditional search engines and stresses the need for students to develop critical source evaluation skills. Although empirical evidence on AI's classroom effects is limited, AI offers personalized learning support and problem-solving tools, alongside challenges like undermining deep learning if misused. The study emphasizes deliberate strategies to ensure AI complements, not replaces, genuine cognitive effort. AI's educational role should be context-dependent, guided by pedagogical goals. The study concludes with practical advice for teachers on effectively utilizing AI to promote understanding and critical engagement, advocating for a balanced approach to enhance students' knowledge and skills development.
Authors: Christoph Leiter, Jonas Belouadi, Yanran Chen, Ran Zhang, Daniil Larionov, Aida Kostikova, Steffen Eger
Abstract: The NLLG (Natural Language Learning & Generation) arXiv reports assist in navigating the rapidly evolving landscape of NLP and AI research across cs.CL, cs.CV, cs.AI, and cs.LG categories. This fourth installment captures a transformative period in AI history - from January 1, 2023, following ChatGPT's debut, through September 30, 2024. Our analysis reveals substantial new developments in the field - with 45% of the top 40 most-cited papers being new entries since our last report eight months ago and offers insights into emerging trends and major breakthroughs, such as novel multimodal architectures, including diffusion and state space models. Natural Language Processing (NLP; cs.CL) remains the dominant main category in the list of our top-40 papers but its dominance is on the decline in favor of Computer vision (cs.CV) and general machine learning (cs.LG). This report also presents novel findings on the integration of generative AI in academic writing, documenting its increasing adoption since 2022 while revealing an intriguing pattern: top-cited papers show notably fewer markers of AI-generated content compared to random samples. Furthermore, we track the evolution of AI-associated language, identifying declining trends in previously common indicators such as "delve".
Authors: Bishakh Bhattacharya, Tanuj Gupta, Arun Kumar Sharma, Ankur Dwivedi, Vivek Gupta, Subhadeep Sahana, Suryansh Pathak, Ashish Awasthi
Abstract: In this study, we immerse in the intricate world of patterns, examining the structural details of Indian medieval architecture for the discovery of motifs with great application potential from the mechanical metastructure perspective. The motifs that specifically engrossed us are derived from the tomb of I'timad-ud-Daula, situated in the city of Agra, close to the Taj Mahal. In an exploratory study, we designed nine interlaced metastructures inspired from the tomb's motifs. We fabricated the metastructures using additive manufacturing and studied their vibration characteristics experimentally and numerically. We also investigated bandgap modulation with metallic inserts in honeycomb interlaced metastructures. The comprehensive study of these metastructure panels reveals their high performance in controlling elastic wave propagation and generating suitable frequency bandgaps, hence having potential applications as waveguides for noise and vibration control. Finally, we developed novel AI-based model trained on numerical datasets for inverse design of metastructures with a desired bandgap.
Authors: Chiyu Max Jiang, Yijing Bai, Andre Cornman, Christopher Davis, Xiukun Huang, Hong Jeon, Sakshum Kulshrestha, John Lambert, Shuangyu Li, Xuanyu Zhou, Carlos Fuertes, Chang Yuan, Mingxing Tan, Yin Zhou, Dragomir Anguelov
Abstract: Realistic and interactive scene simulation is a key prerequisite for autonomous vehicle (AV) development. In this work, we present SceneDiffuser, a scene-level diffusion prior designed for traffic simulation. It offers a unified framework that addresses two key stages of simulation: scene initialization, which involves generating initial traffic layouts, and scene rollout, which encompasses the closed-loop simulation of agent behaviors. While diffusion models have been proven effective in learning realistic and multimodal agent distributions, several challenges remain, including controllability, maintaining realism in closed-loop simulations, and ensuring inference efficiency. To address these issues, we introduce amortized diffusion for simulation. This novel diffusion denoising paradigm amortizes the computational cost of denoising over future simulation steps, significantly reducing the cost per rollout step (16x less inference steps) while also mitigating closed-loop errors. We further enhance controllability through the introduction of generalized hard constraints, a simple yet effective inference-time constraint mechanism, as well as language-based constrained scene generation via few-shot prompting of a large language model (LLM). Our investigations into model scaling reveal that increased computational resources significantly improve overall simulation realism. We demonstrate the effectiveness of our approach on the Waymo Open Sim Agents Challenge, achieving top open-loop performance and the best closed-loop performance among diffusion models.
Authors: Xudong Pan, Jiarun Dai, Yihe Fan, Min Yang
Abstract: Successful self-replication under no human assistance is the essential step for AI to outsmart the human beings, and is an early signal for rogue AIs. That is why self-replication is widely recognized as one of the few red line risks of frontier AI systems. Nowadays, the leading AI corporations OpenAI and Google evaluate their flagship large language models GPT-o1 and Gemini Pro 1.0, and report the lowest risk level of self-replication. However, following their methodology, we for the first time discover that two AI systems driven by Meta's Llama31-70B-Instruct and Alibaba's Qwen25-72B-Instruct, popular large language models of less parameters and weaker capabilities, have already surpassed the self-replicating red line. In 50% and 90% experimental trials, they succeed in creating a live and separate copy of itself respectively. By analyzing the behavioral traces, we observe the AI systems under evaluation already exhibit sufficient self-perception, situational awareness and problem-solving capabilities to accomplish self-replication. We further note the AI systems are even able to use the capability of self-replication to avoid shutdown and create a chain of replica to enhance the survivability, which may finally lead to an uncontrolled population of AIs. If such a worst-case risk is let unknown to the human society, we would eventually lose control over the frontier AI systems: They would take control over more computing devices, form an AI species and collude with each other against human beings. Our findings are a timely alert on existing yet previously unknown severe AI risks, calling for international collaboration on effective governance on uncontrolled self-replication of AI systems.
Authors: Naira Abdou Mohamed, Zakarya Erraji, Abdessalam Bahafid, Imade Benelallam
Abstract: If today some African languages like Swahili have enough resources to develop high-performing Natural Language Processing (NLP) systems, many other languages spoken on the continent are still lacking such support. For these languages, still in their infancy, several possibilities exist to address this critical lack of data. Among them is Transfer Learning, which allows low-resource languages to benefit from the good representation of other languages that are similar to them. In this work, we adopt a similar approach, aiming to pioneer NLP technologies for Comorian, a group of four languages or dialects belonging to the Bantu family. Our approach is initially motivated by the hypothesis that if a human can understand a different language from their native language with little or no effort, it would be entirely possible to model this process on a machine. To achieve this, we consider ways to construct Comorian datasets mixed with Swahili. One thing to note here is that in terms of Swahili data, we only focus on elements that are closest to Comorian by calculating lexical distances between candidate and source data. We empirically test this hypothesis in two use cases: Automatic Speech Recognition (ASR) and Machine Translation (MT). Our MT model achieved ROUGE-1, ROUGE-2, and ROUGE-L scores of 0.6826, 0.42, and 0.6532, respectively, while our ASR system recorded a WER of 39.50\% and a CER of 13.76\%. This research is crucial for advancing NLP in underrepresented languages, with potential to preserve and promote Comorian linguistic heritage in the digital age.
Authors: Chang-Jin Li, Jiyuan Zhang, Yun Tang, Jian Li
Abstract: Personality assessment, particularly through situational judgment tests (SJTs), is a vital tool for psychological research, talent selection, and educational evaluation. This study explores the potential of GPT-4, a state-of-the-art large language model (LLM), to automate the generation of personality situational judgment tests (PSJTs) in Chinese. Traditional SJT development is labor-intensive and prone to biases, while GPT-4 offers a scalable, efficient alternative. Two studies were conducted: Study 1 evaluated the impact of prompt design and temperature settings on content validity, finding that optimized prompts with a temperature of 1.0 produced creative and accurate items. Study 2 assessed the psychometric properties of GPT-4-generated PSJTs, revealing that they demonstrated satisfactory reliability and validity, surpassing the performance of manually developed tests in measuring the Big Five personality traits. This research highlights GPT-4's effectiveness in developing high-quality PSJTs, providing a scalable and innovative method for psychometric test development. These findings expand the possibilities of automatic item generation and the application of LLMs in psychology, and offer practical implications for streamlining test development processes in resource-limited settings.
Authors: Yu Yan, Sheng Sun, Junqi Tong, Min Liu, Qi Li
Abstract: Metaphor serves as an implicit approach to convey information, while enabling the generalized comprehension of complex subjects. However, metaphor can potentially be exploited to bypass the safety alignment mechanisms of Large Language Models (LLMs), leading to the theft of harmful knowledge. In our study, we introduce a novel attack framework that exploits the imaginative capacity of LLMs to achieve jailbreaking, the J\underline{\textbf{A}}ilbreak \underline{\textbf{V}}ia \underline{\textbf{A}}dversarial Me\underline{\textbf{TA}} -pho\underline{\textbf{R}} (\textit{AVATAR}). Specifically, to elicit the harmful response, AVATAR extracts harmful entities from a given harmful target and maps them to innocuous adversarial entities based on LLM's imagination. Then, according to these metaphors, the harmful target is nested within human-like interaction for jailbreaking adaptively. Experimental results demonstrate that AVATAR can effectively and transferablly jailbreak LLMs and achieve a state-of-the-art attack success rate across multiple advanced LLMs. Our study exposes a security risk in LLMs from their endogenous imaginative capabilities. Furthermore, the analytical study reveals the vulnerability of LLM to adversarial metaphors and the necessity of developing defense methods against jailbreaking caused by the adversarial metaphor. \textcolor{orange}{ \textbf{Warning: This paper contains potentially harmful content from LLMs.}}
Authors: Linna Xu, Yongli Zhu
Abstract: As a key component of power system production simulation, load forecasting is critical for the stable operation of power systems. Machine learning methods prevail in this field. However, the limited training data can be a challenge. This paper proposes a generative model-assisted approach for load forecasting under small sample scenarios, consisting of two steps: expanding the dataset using a diffusion-based generative model and then training various machine learning regressors on the augmented dataset to identify the best performer. The expanded dataset significantly reduces forecasting errors compared to the original dataset, and the diffusion model outperforms the generative adversarial model by achieving about 200 times smaller errors and better alignment in latent data distributions.
Authors: Seongwoong Cho, Donggyun Kim, Jinwoo Lee, Seunghoon Hong
Abstract: Generalizing across robot embodiments and tasks is crucial for adaptive robotic systems. Modular policy learning approaches adapt to new embodiments but are limited to specific tasks, while few-shot imitation learning (IL) approaches often focus on a single embodiment. In this paper, we introduce a few-shot behavior cloning framework to simultaneously generalize to unseen embodiments and tasks using a few (\emph{e.g.,} five) reward-free demonstrations. Our framework leverages a joint-level input-output representation to unify the state and action spaces of heterogeneous embodiments and employs a novel structure-motion state encoder that is parameterized to capture both shared knowledge across all embodiments and embodiment-specific knowledge. A matching-based policy network then predicts actions from a few demonstrations, producing an adaptive policy that is robust to over-fitting. Evaluated in the DeepMind Control suite, our framework termed \modelname{} demonstrates superior few-shot generalization to unseen embodiments and tasks over modular policy learning and few-shot IL approaches. Codes are available at \href{https://github.com/SeongwoongCho/meta-controller}{https://github.com/SeongwoongCho/meta-controller}.
URLs: https://github.com/SeongwoongCho/meta-controller, https://github.com/SeongwoongCho/meta-controller
Authors: Manman Yuan, Weiming Jia, Xiong Luo, Jiazhen Ye, Peican Zhu, Junlin Li
Abstract: The precise detection of mild cognitive impairment (MCI) is of significant importance in preventing the deterioration of patients in a timely manner. Although hypergraphs have enhanced performance by learning and analyzing brain networks, they often only depend on vector distances between features at a single scale to infer interactions. In this paper, we deal with a more arduous challenge, hypergraph modelling with synchronization between brain regions, and design a novel framework, i.e., A Multi-scale Hypergraph Network for MCI Detection via Synchronous and Attentive Fusion (MHSA), to tackle this challenge. Specifically, our approach employs the Phase-Locking Value (PLV) to calculate the phase synchronization relationship in the spectrum domain of regions of interest (ROIs) and designs a multi-scale feature fusion mechanism to integrate dynamic connectivity features of functional magnetic resonance imaging (fMRI) from both the temporal and spectrum domains. To evaluate and optimize the direct contribution of each ROI to phase synchronization in the temporal domain, we structure the PLV coefficients dynamically adjust strategy, and the dynamic hypergraph is modelled based on a comprehensive temporal-spectrum fusion matrix. Experiments on the real-world dataset indicate the effectiveness of our strategy. The code is available at https://github.com/Jia-Weiming/MHSA.
Authors: Yuanhao Shen, Xiaodan Zhu, Lei Chen
Abstract: The tool-use ability of Large Language Models (LLMs) has a profound impact on a wide range of industrial applications. However, LLMs' self-control and calibration capability in appropriately using tools remains understudied. The problem is consequential as it raises potential risks of degraded performance and poses a threat to the trustworthiness of the models. In this paper, we conduct a study on a family of state-of-the-art LLMs on three datasets with two mainstream tool-use frameworks. Our study reveals the tool-abuse behavior of LLMs, a tendency for models to misuse tools with overconfidence. We also find that this is a common issue regardless of model capability. Accordingly, we propose a novel approach, \textit{SMARTCAL}, to mitigate the observed issues, and our results show an average of 8.6 percent increase in the QA performance and a 21.6 percent decrease in Expected Calibration Error (ECE) compared to baseline models.
Authors: Rongzheng Wang, Shuang Liang, Qizhi Chen, Jiasheng Zhang, Ke Qin
Abstract: Large language models (LLMs) have been demonstrated to possess the capabilities to understand fundamental graph properties and address various graph reasoning tasks. Existing methods fine-tune LLMs to understand and execute graph reasoning tasks by specially designed task instructions. However, these Text-Instruction methods generally exhibit poor performance. Inspired by tool learning, researchers propose Tool-Instruction methods to solve various graph problems by special tool calling (e.g., function, API and model), achieving significant improvements in graph reasoning tasks. Nevertheless, current Tool-Instruction approaches focus on the tool information and ignore the graph structure information, which leads to significantly inferior performance on small-scale LLMs (less than 13B). To tackle this issue, we propose GraphTool-Instruction, an innovative Instruction-tuning approach that decomposes the graph reasoning task into three distinct subtasks (i.e., graph extraction, tool name identification and tool parameter extraction), and design specialized instructions for each subtask. Our GraphTool-Instruction can be used as a plug-and-play prompt for different LLMs without fine-tuning. Moreover, building on GraphTool-Instruction, we develop GTools, a dataset that includes twenty graph reasoning tasks, and create a graph reasoning LLM called GraphForge based on Llama3-8B. We conduct extensive experiments on twenty graph reasoning tasks with different graph types (e.g., graph size or graph direction), and we find that GraphTool-Instruction achieves SOTA compared to Text-Instruction and Tool-Instruction methods. Fine-tuned on GTools, GraphForge gets further improvement of over 30% compared to the Tool-Instruction enhanced GPT-3.5-turbo, and it performs comparably to the high-cost GPT-4o. Our codes and data are available at https://anonymous.4open.science/r/GraphTool-Instruction.
URLs: https://anonymous.4open.science/r/GraphTool-Instruction.
Authors: Jiho Choi, Donggyun Kim, Chanhyuk Lee, Seunghoon Hong
Abstract: Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in suboptimal performance due to interference among parameters across tasks. In this paper, we present intriguing results that weight averaging implicitly induces task vectors centered around the weight averaging itself and that applying a low-rank approximation to these centered task vectors significantly improves merging performance. Our analysis shows that centering the task vectors effectively separates core task-specific knowledge and nuisance noise within the fine-tuned parameters into the top and lower singular vectors, respectively, allowing us to reduce inter-task interference through its low-rank approximation. We evaluate our method on eight image classification tasks, demonstrating that it outperforms prior methods by a significant margin, narrowing the performance gap with traditional multi-task learning to within 1-3%
Authors: Sihan Chen, Zhuangzhuang Qian, Wingchun Siu, Xingcan Hu, Jiaqi Li, Shawn Li, Yuehan Qin, Tiankai Yang, Zhuo Xiao, Wanghao Ye, Yichi Zhang, Yushun Dong, Yue Zhao
Abstract: Outlier detection (OD), also known as anomaly detection, is a critical machine learning (ML) task with applications in fraud detection, network intrusion detection, clickstream analysis, recommendation systems, and social network moderation. Among open-source libraries for outlier detection, the Python Outlier Detection (PyOD) library is the most widely adopted, with over 8,500 GitHub stars, 25 million downloads, and diverse industry usage. However, PyOD currently faces three limitations: (1) insufficient coverage of modern deep learning algorithms, (2) fragmented implementations across PyTorch and TensorFlow, and (3) no automated model selection, making it hard for non-experts. To address these issues, we present PyOD Version 2 (PyOD 2), which integrates 12 state-of-the-art deep learning models into a unified PyTorch framework and introduces a large language model (LLM)-based pipeline for automated OD model selection. These improvements simplify OD workflows, provide access to 45 algorithms, and deliver robust performance on various datasets. In this paper, we demonstrate how PyOD 2 streamlines the deployment and automation of OD models and sets a new standard in both research and industry. PyOD 2 is accessible at [https://github.com/yzhao062/pyod](https://github.com/yzhao062/pyod). This study aligns with the Web Mining and Content Analysis track, addressing topics such as the robustness of Web mining methods and the quality of algorithmically-generated Web data.
URLs: https://github.com/yzhao062/pyod](https://github.com/yzhao062/pyod).
Authors: Zian Zhai, Sima Qing, Xiaoyang Wang, Wenjie Zhang
Abstract: Signed Graph Neural Networks (SGNNs) are powerful tools for signed graph representation learning but struggle with limited generalization and heavy dependence on labeled data. While recent advancements in "graph pre-training and prompt tuning" have reduced label dependence in Graph Neural Networks (GNNs) and improved their generalization abilities by leveraging pre-training knowledge, these efforts have focused exclusively on unsigned graphs. The scarcity of publicly available signed graph datasets makes it essential to transfer knowledge from unsigned graphs to signed graph tasks. However, this transfer introduces significant challenges due to the graph-level and task-level divergences between the pre-training and downstream phases. To address these challenges, we propose Signed Graph Prompt Tuning (SGPT) in this paper. Specifically, SGPT employs a graph template and a semantic prompt to segregate mixed link semantics in the signed graph and then adaptively integrate the distinctive semantic information according to the needs of downstream tasks, thereby unifying the pre-training and downstream graphs. Additionally, SGPT utilizes a task template and a feature prompt to reformulate the downstream signed graph tasks, aligning them with pre-training tasks to ensure a unified optimization objective and consistent feature space across tasks. Finally, extensive experiments are conducted on popular signed graph datasets, demonstrating the superiority of SGPT over state-of-the-art methods.
Authors: Jiayu Liu, Zhenya Huang, Chaokun Wang, Xunpeng Huang, Chengxiang Zhai, Enhong Chen
Abstract: Owing to the capability of in-context learning, large language models (LLMs) have shown impressive performance across diverse mathematical reasoning benchmarks. However, we find that few-shot demonstrations can sometimes bring negative performance and their effectiveness on LLMs' reasoning abilities remains unreliable. To this end, in this paper, we aim to theoretically analyze the impact of in-context demonstrations on LLMs' reasoning performance. We prove that the reasoning efficacy (measured by empirical prediction loss) can be bounded by a LLM-oriented semantic similarity and an inference stability of demonstrations, which is general for both one-shot and few-shot scenarios. Based on this finding, we propose a straightforward, generalizable, and low-complexity demonstration selection method named LMS3. It can adaptively facilitate to select the most pertinent samples for different LLMs and includes a novel demonstration rejection mechanism to automatically filter out samples that are unsuitable for few-shot learning. Through experiments on three representative benchmarks, two LLM backbones, and multiple few-shot settings, we verify that our LMS3 has superiority and achieves consistent improvements on all datasets, which existing methods have been unable to accomplish.
Authors: Mengfan Li, Xuanhua Shi, Chenqi Qiao, Teng Zhang, Hai Jin
Abstract: Knowledge hypergraphs generalize knowledge graphs using hyperedges to connect multiple entities and depict complicated relations. Existing methods either transform hyperedges into an easier-to-handle set of binary relations or view hyperedges as isolated and ignore their adjacencies. Both approaches have information loss and may potentially lead to the creation of sub-optimal models. To fix these issues, we propose the Hyperbolic Hypergraph Neural Network (H2GNN), whose essential component is the hyper-star message passing, a novel scheme motivated by a lossless expansion of hyperedges into hierarchies. It implements a direct embedding that consciously incorporates adjacent entities, hyper-relations, and entity position-aware information. As the name suggests, H2GNN operates in the hyperbolic space, which is more adept at capturing the tree-like hierarchy. We compare H2GNN with 15 baselines on knowledge hypergraphs, and it outperforms state-of-the-art approaches in both node classification and link prediction tasks.
Authors: Yangxuan Zhou, Sha Zhao, Jiquan Wang, Haiteng Jiang, hijian Li, Benyan Luo, Tao Li, Gang Pan
Abstract: Sleep staging is crucial for assessing sleep quality and diagnosing related disorders. Recent deep learning models for automatic sleep staging using polysomnography often suffer from poor generalization to new subjects because they are trained and tested on the same labeled datasets, overlooking individual differences. To tackle this issue, we propose a novel Source-Free Unsupervised Individual Domain Adaptation (SF-UIDA) framework. This two-step adaptation scheme allows the model to effectively adjust to new unlabeled individuals without needing source data, facilitating personalized customization in clinical settings. Our framework has been applied to three established sleep staging models and tested on three public datasets, achieving state-of-the-art performance.
Authors: Ali Forootani, Danial Esmaeili Aliabadi, Daniela Thraen
Abstract: Wind power forecasting plays a critical role in modern energy systems, facilitating the integration of renewable energy sources into the power grid. Accurate prediction of wind energy output is essential for managing the inherent intermittency of wind power, optimizing energy dispatch, and ensuring grid stability. This paper proposes the use of Deep Neural Network (DNN)-based predictive models that leverage climate datasets, including wind speed, atmospheric pressure, temperature, and other meteorological variables, to improve the accuracy of wind power simulations. In particular, we focus on the Coupled Model Intercomparison Project (CMIP) datasets, which provide climate projections, as inputs for training the DNN models. These models aim to capture the complex nonlinear relationships between the CMIP-based climate data and actual wind power generation at wind farms located in Germany. Our study compares various DNN architectures, specifically Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM) networks, and Transformer-enhanced LSTM models, to identify the best configuration among these architectures for climate-aware wind power simulation. The implementation of this framework involves the development of a Python package (CADNN) designed to support multiple tasks, including statistical analysis of the climate data, data visualization, preprocessing, DNN training, and performance evaluation. We demonstrate that the DNN models, when integrated with climate data, significantly enhance forecasting accuracy. This climate-aware approach offers a deeper understanding of the time-dependent climate patterns that influence wind power generation, providing more accurate predictions and making it adaptable to other geographical regions.
Authors: Bao-Bing Li, Yi Gu, Shao-Feng Wu
Abstract: Machine learning can uncover physical concepts or physical equations when prior knowledge from another one is available. However, in many cases, these two aspects are coupled and cannot be discovered independently. We extend SciNet, which is a neural network architecture that simulates the human physical reasoning process for physics discovery, by proposing a model that combines Variational Autoencoders (VAEs) with Neural Ordinary Differential Equations (Neural ODEs). This allows us to simultaneously discover physical concepts and governing equations from simulated experimental data across diverse physical systems. We apply the model to several key examples inspired by the history of physics, including Copernicus' heliocentric solar system, Newton's law of universal gravitation, the wave function together with the Schr\"odinger equation, and spin-1/2 along with the Pauli equation. The results demonstrate that the neural network successfully reconstructs the corresponding theories.
Authors: Xiangxin Fang, Lev Mukhanov
Abstract: Large Language Models (LLMs) have demonstrated great potential in various language processing tasks, and recent studies have explored their application in compiler optimizations. However, all these studies focus on the conventional open-source LLMs, such as Llama2, which lack enhanced reasoning mechanisms. In this study, we investigate the errors produced by the fine-tuned 7B-parameter Llama2 model as it attempts to learn and apply a simple peephole optimization for the AArch64 assembly code. We provide an analysis of the errors produced by the LLM and compare it with state-of-the-art OpenAI models which implement advanced reasoning logic, including GPT-4o and GPT-o1 (preview). We demonstrate that OpenAI GPT-o1, despite not being fine-tuned, outperforms the fine-tuned Llama2 and GPT-4o. Our findings indicate that this advantage is largely due to the chain-of-thought reasoning implemented in GPT-o1. We hope our work will inspire further research on using LLMs with enhanced reasoning mechanisms and chain-of-thought for code generation and optimization.
Authors: Lingzhi Shen, Yunfei Long, Xiaohao Cai, Imran Razzak, Guanming Chen, Kang Liu, Shoaib Jameel
Abstract: Multimodal fake news detection often involves modelling heterogeneous data sources, such as vision and language. Existing detection methods typically rely on fusion effectiveness and cross-modal consistency to model the content, complicating understanding how each modality affects prediction accuracy. Additionally, these methods are primarily based on static feature modelling, making it difficult to adapt to the dynamic changes and relationships between different data modalities. This paper develops a significantly novel approach, GAMED, for multimodal modelling, which focuses on generating distinctive and discriminative features through modal decoupling to enhance cross-modal synergies, thereby optimizing overall performance in the detection process. GAMED leverages multiple parallel expert networks to refine features and pre-embed semantic knowledge to improve the experts' ability in information selection and viewpoint sharing. Subsequently, the feature distribution of each modality is adaptively adjusted based on the respective experts' opinions. GAMED also introduces a novel classification technique to dynamically manage contributions from different modalities, while improving the explainability of decisions. Experimental results on the Fakeddit and Yang datasets demonstrate that GAMED performs better than recently developed state-of-the-art models. The source code can be accessed at https://github.com/slz0925/GAMED.
Authors: Javon Hickmon
Abstract: In the rapidly advancing field of artificial intelligence, machine perception is becoming paramount to achieving increased performance. Image classification systems are becoming increasingly integral to various applications, ranging from medical diagnostics to image generation; however, these systems often exhibit harmful biases that can lead to unfair and discriminatory outcomes. Machine Learning systems that depend on a single data modality, i.e. only images or only text, can exaggerate hidden biases present in the training data, if the data is not carefully balanced and filtered. Even so, these models can still harm underrepresented populations when used in improper contexts, such as when government agencies reinforce racial bias using predictive policing. This thesis explores the intersection of technology and ethics in the development of fair image classification models. Specifically, I focus on improving fairness and methods of using multiple modalities to combat harmful demographic bias. Integrating multimodal approaches, which combine visual data with additional modalities such as text and metadata, allows this work to enhance the fairness and accuracy of image classification systems. The study critically examines existing biases in image datasets and classification algorithms, proposes innovative methods for mitigating these biases, and evaluates the ethical implications of deploying such systems in real-world scenarios. Through comprehensive experimentation and analysis, the thesis demonstrates how multimodal techniques can contribute to more equitable and ethical AI solutions, ultimately advocating for responsible AI practices that prioritize fairness.
Authors: Nikhil Mehta, Sithira Ambepitiya, Thanveer Ahamad, Dinuka Wijesundara, Yudara Kularathne
Abstract: Introduction: Global burden of sexually transmitted infections (STIs) is rising out of proportion to specialists. Current chatbots like ChatGPT are not tailored for handling STI-related concerns out of the box. We developed Otiz, an Artificial Intelligence-based (AI-based) chatbot platform designed specifically for STI detection and counseling, and assessed its performance. Methods: Otiz employs a multi-agent system architecture based on GPT4-0613, leveraging large language model (LLM) and Deterministic Finite Automaton principles to provide contextually relevant, medically accurate, and empathetic responses. Its components include modules for general STI information, emotional recognition, Acute Stress Disorder detection, and psychotherapy. A question suggestion agent operates in parallel. Four STIs (anogenital warts, herpes, syphilis, urethritis/cervicitis) and 2 non-STIs (candidiasis, penile cancer) were evaluated using prompts mimicking patient language. Each prompt was independently graded by two venereologists conversing with Otiz as patient actors on 6 criteria using Numerical Rating Scale ranging from 0 (poor) to 5 (excellent). Results: Twenty-three venereologists did 60 evaluations of 30 prompts. Across STIs, Otiz scored highly on diagnostic accuracy (4.1-4.7), overall accuracy (4.3-4.6), correctness of information (5.0), comprehensibility (4.2-4.4), and empathy (4.5-4.8). However, relevance scores were lower (2.9-3.6), suggesting some redundancy. Diagnostic scores for non-STIs were lower (p=0.038). Inter-observer agreement was strong, with differences greater than 1 point occurring in only 12.7% of paired evaluations. Conclusions: AI conversational agents like Otiz can provide accurate, correct, discrete, non-judgmental, readily accessible and easily understandable STI-related information in an empathetic manner, and can alleviate the burden on healthcare systems.
Authors: Evangelia Gkritzali, Panagiotis Kaliosis, Sofia Galanaki, Elisavet Palogiannidi, Theodoros Giannakopoulos
Abstract: In the vast majority of the academic and scientific domains, LaTeX has established itself as the de facto standard for typesetting complex mathematical equations and formulae. However, LaTeX's complex syntax and code-like appearance present accessibility barriers for individuals with disabilities, as well as those unfamiliar with coding conventions. In this paper, we present a novel solution to this challenge through the development of a novel speech-to-LaTeX equations system specifically designed for the Greek language. We propose an end-to-end system that harnesses the power of Automatic Speech Recognition (ASR) and Natural Language Processing (NLP) techniques to enable users to verbally dictate mathematical expressions and equations in natural language, which are subsequently converted into LaTeX format. We present the architecture and design principles of our system, highlighting key components such as the ASR engine, the LLM-based prompt-driven equations generation mechanism, as well as the application of a custom evaluation metric employed throughout the development process. We have made our system open source and available at https://github.com/magcil/greek-speech-to-math.
Authors: Yining Pang, Chenghan Li
Abstract: Seasonal time series exhibit intricate long-term dependencies, posing a significant challenge for accurate future prediction. This paper introduces the Multi-scale Seasonal Decomposition Model (MSSD) for seasonal time-series forecasting. Initially, leveraging the inherent periodicity of seasonal time series, we decompose the univariate time series into three primary components: Ascending, Peak, and Descending. This decomposition approach enhances the capture of periodic features. By addressing the limitations of existing time-series modeling methods, particularly in modeling the Peak component, this research proposes a multi-scale network structure designed to effectively capture various potential peak fluctuation patterns in the Peak component. This study integrates Conv2d and Temporal Convolutional Networks to concurrently capture global and local features. Furthermore, we incorporate multi-scale reshaping to augment the modeling capacity for peak fluctuation patterns. The proposed methodology undergoes validation using three publicly accessible seasonal datasets. Notably, in both short-term and long-term fore-casting tasks, our approach exhibits a 10$\%$ reduction in error compared to the baseline models.
Authors: Eoin M. Kenny, Julie A. Shah
Abstract: Regulation is increasingly cited as the most important and pressing concern in machine learning. However, it is currently unknown how to implement this, and perhaps more importantly, how it would effect model performance alongside human collaboration if actually realized. In this paper, we attempt to answer these questions by building a regulatable large-language model (LLM), and then quantifying how the additional constraints involved affect (1) model performance, alongside (2) human collaboration. Our empirical results reveal that it is possible to force an LLM to use human-defined features in a transparent way, but a "regulation performance trade-off" previously not considered reveals itself in the form of a 7.34% classification performance drop. Surprisingly however, we show that despite this, such systems actually improve human task performance speed and appropriate confidence in a realistic deployment setting compared to no AI assistance, thus paving a way for fair, regulatable AI, which benefits users.
Authors: Dimitrios Sikeridis, Dennis Ramdass, Pranay Pareek
Abstract: Recently, the number of off-the-shelf Large Language Models (LLMs) has exploded with many open-source options. This creates a diverse landscape regarding both serving options (e.g., inference on local hardware vs remote LLM APIs) and model heterogeneous expertise. However, it is hard for the user to efficiently optimize considering operational cost (pricing structures, expensive LLMs-as-a-service for large querying volumes), efficiency, or even per-case specific measures such as response accuracy, bias, or toxicity. Also, existing LLM routing solutions focus mainly on cost reduction, with response accuracy optimizations relying on non-generalizable supervised training, and ensemble approaches necessitating output computation for every considered LLM candidate. In this work, we tackle the challenge of selecting the optimal LLM from a model pool for specific queries with customizable objectives. We propose PickLLM, a lightweight framework that relies on Reinforcement Learning (RL) to route on-the-fly queries to available models. We introduce a weighted reward function that considers per-query cost, inference latency, and model response accuracy by a customizable scoring function. Regarding the learning algorithms, we explore two alternatives: PickLLM router acting as a learning automaton that utilizes gradient ascent to select a specific LLM, or utilizing stateless Q-learning to explore the set of LLMs and perform selection with a $\epsilon$-greedy approach. The algorithm converges to a single LLM for the remaining session queries. To evaluate, we utilize a pool of four LLMs and benchmark prompt-response datasets with different contexts. A separate scoring function is assessing response accuracy during the experiment. We demonstrate the speed of convergence for different learning rates and improvement in hard metrics such as cost per querying session and overall response latency.
Authors: Soumita Roy
Abstract: This document explores the potential of employing Artificial Intelligence (AI), specifically Natural Language Processing (NLP), to strengthen the detection and prevention of financial crimes within the Mobile Financial Services(MFS) of Bangladesh with multilingual scenario. The analysis focuses on the utilization of NLP for adverse media screening, a vital aspect of compliance with anti-money laundering (AML) and combating financial terrorism (CFT) regulations. Additionally, it investigates the overall reception and obstacles related to the integration of AI in Bangladeshi banks. This report measures the effectiveness of NLP is promising with an accuracy around 94\%. NLP algorithms display substantial promise in accurately identifying adverse media content linked to financial crimes. The lack of progress in this aspect is visible in Bangladesh, whereas globally the technology is already being used to increase effectiveness and efficiency. Hence, it is clear there is an issue with the acceptance of AI in Bangladesh. Some AML \& CFT concerns are already being addressed by AI technology. For example, Image Recognition OCR technology are being used in KYC procedures. Primary hindrances to AI integration involve a lack of technical expertise, high expenses, and uncertainties surrounding regulations. This investigation underscores the potential of AI-driven NLP solutions in fortifying efforts to prevent financial crimes in Bangladesh.
Authors: Soham Sane, Angus McLean
Abstract: This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs) by leveraging iterative reasoning and feedback-driven methodologies. Building on the limitations identified in the SimpleBench benchmark, a dataset designed to evaluate logical coherence and real-world reasoning, we propose a multi-step prompting strategy coupled with global consistency checks to improve model accuracy and robustness. Through comparative analysis of state-of-the-art models, including Claude 3 Opus, Claude 3.5, GPT- 4o, and o1-preview, we demonstrate that iterative reasoning significantly enhances model performance, with improvements observed in both standard accuracy metrics (AVG@5) and a newly introduced metric, Extreme Averaging (EAG@5). Our results reveal model-specific strengths: Claude excels in maintaining logical consistency, while GPT-4o exhibits exploratory creativity but struggles with ambiguous prompts. By analyzing case studies and identifying gaps in spatial and temporal reasoning, we highlight areas for further refinement. The findings underscore the potential of structured reasoning frameworks to address inherent model limitations, irrespective of pretraining methodologies. This study lays the groundwork for integrating dynamic feedback mechanisms, adaptive restart strategies, and diverse evaluation metrics to advance LLM reasoning capabilities across complex and multi-domain problem spaces.
Authors: Melanie Sclar, Jane Yu, Maryam Fazel-Zarandi, Yulia Tsvetkov, Yonatan Bisk, Yejin Choi, Asli Celikyilmaz
Abstract: Do large language models (LLMs) have theory of mind? A plethora of papers and benchmarks have been introduced to evaluate if current models have been able to develop this key ability of social intelligence. However, all rely on limited datasets with simple patterns that can potentially lead to problematic blind spots in evaluation and an overestimation of model capabilities. We introduce ExploreToM, the first framework to allow large-scale generation of diverse and challenging theory of mind data for robust training and evaluation. Our approach leverages an A* search over a custom domain-specific language to produce complex story structures and novel, diverse, yet plausible scenarios to stress test the limits of LLMs. Our evaluation reveals that state-of-the-art LLMs, such as Llama-3.1-70B and GPT-4o, show accuracies as low as 0% and 9% on ExploreToM-generated data, highlighting the need for more robust theory of mind evaluation. As our generations are a conceptual superset of prior work, fine-tuning on our data yields a 27-point accuracy improvement on the classic ToMi benchmark (Le et al., 2019). ExploreToM also enables uncovering underlying skills and factors missing for models to show theory of mind, such as unreliable state tracking or data imbalances, which may contribute to models' poor performance on benchmarks.
Authors: Weitang Liu, Yuelei Li, Ying Wai Li, Zihan Wang, Jingbo Shang
Abstract: Comparing two (large) language models (LMs) side-by-side and pinpointing their prediction similarities and differences on the same set of inputs are crucial in many real-world scenarios, e.g., one can test if a licensed model was potentially plagiarized by another. Traditional analysis compares the LMs' outputs on some benchmark datasets, which only cover a limited number of inputs of designed perspectives for the intended applications. The benchmark datasets cannot prepare data to cover the test cases from unforeseen perspectives which can help us understand differences between models unbiasedly. In this paper, we propose a new model comparative analysis setting that considers a large input space where brute-force enumeration would be infeasible. The input space can be simply defined as all token sequences that a LM would produce low perplexity on -- we follow this definition in the paper as it would produce the most human-understandable inputs. We propose a novel framework \our that uses text generation by sampling and deweights the histogram of sampling statistics to estimate prediction differences between two LMs in this input space efficiently and unbiasedly. Our method achieves this by drawing and counting the inputs at each prediction difference value in negative log-likelihood. Experiments reveal for the first time the quantitative prediction differences between LMs in a large input space, potentially facilitating the model analysis for applications such as model plagiarism.
Authors: Nobel Dhar, Bobin Deng, Md Romyull Islam, Kazi Fahim Ahmad Nasif, Liang Zhao, Kun Suo
Abstract: Deploying local AI models, such as Large Language Models (LLMs), to edge devices can substantially enhance devices' independent capabilities, alleviate the server's burden, and lower the response time. Owing to these tremendous potentials, many big tech companies have released several lightweight Small Language Models (SLMs) to bridge this gap. However, we still have huge motivations to deploy more powerful (LLMs) AI models on edge devices and enhance their smartness level. Unlike the conventional approaches for AI model compression, we investigate activation sparsity. The activation sparsity method is orthogonal and combinable with existing techniques to maximize compression rate while maintaining great accuracy. LLMs' Feed-Forward Network (FFN) components, which typically comprise a large proportion of parameters (around 3/2), ensure that our FFN optimizations would have a better chance of achieving effective compression. Moreover, our findings are beneficial to general LLMs and are not restricted to ReLU-based models. This work systematically investigates the tradeoff between enforcing activation sparsity and perplexity (accuracy) on state-of-the-art LLMs. Our empirical analysis demonstrates that we can obtain around 50% of main memory and computing reductions for critical FFN components with negligible accuracy degradation. This extra 50% sparsity does not naturally exist in the current LLMs, which require tuning LLMs' activation outputs by injecting zero-enforcing thresholds. To obtain the benefits of activation sparsity, we provide a guideline for the system architect for LLM prediction and prefetching. The success prediction allows the system to prefetch the necessary weights while omitting the inactive ones and their successors, therefore lowering cache and memory pollution and reducing LLM execution time on resource-constrained edge devices.
Authors: Pegah Eshraghi, Riccardo Talami, Arman Nikkhah Dehnavi, Maedeh Mirdamadi, Zahra-Sadat Zomorodian
Abstract: In rapidly urbanizing regions, designing climate-responsive urban forms is crucial for sustainable development, especially in dry arid-climates where urban morphology has a significant impact on energy consumption and environmental performance. This study advances urban morphology evaluation by combining Urban Building Energy Modeling (UBEM) with machine learning methods (ML) and Explainable AI techniques, specifically Shapley Additive Explanations (SHAP). Using Tehran's dense urban landscape as a case study, this research assesses and ranks the impact of 30 morphology parameters at the urban block level on key energy metrics (cooling, heating, and lighting demand) and environmental performance (sunlight exposure, photovoltaic generation, and Sky View Factor). Among seven ML algorithms evaluated, the XGBoost model was the most effective predictor, achieving high accuracy (R2: 0.92) and a training time of 3.64 seconds. Findings reveal that building shape, window-to-wall ratio, and commercial ratio are the most critical parameters affecting energy efficiency, while the heights and distances of neighboring buildings strongly influence cooling demand and solar access. By evaluating urban blocks with varied densities and configurations, this study offers generalizable insights applicable to other dry-arid regions. Moreover, the integration of UBEM and Explainable AI offers a scalable, data-driven framework for developing climate-responsive urban designs adaptable to high-density environments worldwide.
Authors: Jingjing Wang, Hongjie Zhu, Haoran Xie, Fu Lee Wang, Xiaoliang Xu, Yuxiang Wang
Abstract: \Graph similarity computation is an essential task in many real-world graph-related applications such as retrieving the similar drugs given a query chemical compound or finding the user's potential friends from the social network database. Graph Edit Distance (GED) and Maximum Common Subgraphs (MCS) are the two commonly used domain-agnostic metrics to evaluate graph similarity in practice. Unfortunately, computing the exact GED is known to be a NP-hard problem. To solve this limitation, neural network based models have been proposed to approximate the calculations of GED/MCS. However, deep learning models are well-known ``black boxes'', thus the typically characteristic one-to-one node/subgraph alignment process in the classical computations of GED and MCS cannot be seen. Existing methods have paid attention to approximating the node/subgraph alignment (soft alignment), but the one-to-one node alignment (hard alignment) has not yet been solved. To fill this gap, in this paper we propose a novel interpretable neural node alignment model without relying on node alignment ground truth information. Firstly, the quadratic assignment problem in classical GED computation is relaxed to a linear alignment via embedding the features in the node embedding space. Secondly, a differentiable Gumbel-Sinkhorn module is proposed to unsupervised generate the optimal one-to-one node alignment matrix. Experimental results in real-world graph datasets demonstrate that our method outperforms the state-of-the-art methods in graph similarity computation and graph retrieval tasks, achieving up to 16\% reduction in the Mean Squared Error and up to 12\% improvement in the retrieval evaluation metrics, respectively.
Authors: Kelsey Doerksen, Casper Fibaek, Rochelle Schneider, Do-Hyung Kim, Isabelle Tingzon
Abstract: Internet connectivity in schools is critical to provide students with the digital literary skills necessary to compete in modern economies. In order for governments to effectively implement digital infrastructure development in schools, accurate internet connectivity information is required. However, traditional survey-based methods can exceed the financial and capacity limits of governments. Open-source Earth Observation (EO) datasets have unlocked our ability to observe and understand socio-economic conditions on Earth from space, and in combination with Machine Learning (ML), can provide the tools to circumvent costly ground-based survey methods to support infrastructure development. In this paper, we present our work on school internet connectivity prediction using EO and ML. We detail the creation of our multi-modal, freely-available satellite imagery and survey information dataset, leverage the latest geographically-aware location encoders, and introduce the first results of using the new European Space Agency phi-lab geographically-aware foundational model to predict internet connectivity in Botswana and Rwanda. We find that ML with EO and ground-based auxiliary data yields the best performance in both countries, for accuracy, F1 score, and False Positive rates, and highlight the challenges of internet connectivity prediction from space with a case study in Kigali, Rwanda. Our work showcases a practical approach to support data-driven digital infrastructure development in low-resource settings, leveraging freely available information, and provide cleaned and labelled datasets for future studies to the community through a unique collaboration between UNICEF and the European Space Agency phi-lab.
Authors: Son Minh Nguyen, Linh Duy Tran, Duc Viet Le, Paul J. M Havinga
Abstract: Despite remarkable progress in knowledge transfer across visual and textual domains, extending these achievements to indoor localization, particularly for learning transferable representations among Received Signal Strength (RSS) fingerprint datasets, remains a challenge. This is due to inherent discrepancies among these RSS datasets, largely including variations in building structure, the input number and disposition of WiFi anchors. Accordingly, specialized networks, which were deprived of the ability to discern transferable representations, readily incorporate environment-sensitive clues into the learning process, hence limiting their potential when applied to specific RSS datasets. In this work, we propose a plug-and-play (PnP) framework of knowledge transfer, facilitating the exploitation of transferable representations for specialized networks directly on target RSS datasets through two main phases. Initially, we design an Expert Training phase, which features multiple surrogate generative teachers, all serving as a global adapter that homogenizes the input disparities among independent source RSS datasets while preserving their unique characteristics. In a subsequent Expert Distilling phase, we continue introducing a triplet of underlying constraints that requires minimizing the differences in essential knowledge between the specialized network and surrogate teachers through refining its representation learning on the target dataset. This process implicitly fosters a representational alignment in such a way that is less sensitive to specific environmental dynamics. Extensive experiments conducted on three benchmark WiFi RSS fingerprint datasets underscore the effectiveness of the framework that significantly exerts the full potential of specialized networks in localization.
Authors: Son Minh Nguyen, Linh Duy Tran, Duc Viet Le, Paul J. M Havinga
Abstract: We propose iMoT, an innovative Transformer-based inertial odometry method that retrieves cross-modal information from motion and rotation modalities for accurate positional estimation. Unlike prior work, during the encoding of the motion context, we introduce Progressive Series Decoupler at the beginning of each encoder layer to stand out critical motion events inherent in acceleration and angular velocity signals. To better aggregate cross-modal interactions, we present Adaptive Positional Encoding, which dynamically modifies positional embeddings for temporal discrepancies between different modalities. During decoding, we introduce a small set of learnable query motion particles as priors to model motion uncertainties within velocity segments. Each query motion particle is intended to draw cross-modal features dedicated to a specific motion mode, all taken together allowing the model to refine its understanding of motion dynamics effectively. Lastly, we design a dynamic scoring mechanism to stabilize iMoT's optimization by considering all aligned motion particles at the final decoding step, ensuring robust and accurate velocity segment estimation. Extensive evaluations on various inertial datasets demonstrate that iMoT significantly outperforms state-of-the-art methods in delivering superior robustness and accuracy in trajectory reconstruction.
Authors: Zhiyu Xue, Guangliang Liu, Bocheng Chen, Kristen Marie Johnson, Ramtin Pedarsani
Abstract: The security of Large Language Models (LLMs) has become an important research topic since the emergence of ChatGPT. Though there have been various effective methods to defend against jailbreak attacks, prefilling attacks remain an unsolved and popular threat against open-sourced LLMs. In-Context Learning (ICL) offers a computationally efficient defense against various jailbreak attacks, yet no effective ICL methods have been developed to counter prefilling attacks. In this paper, we: (1) show that ICL can effectively defend against prefilling jailbreak attacks by employing adversative sentence structures within demonstrations; (2) characterize the effectiveness of this defense through the lens of model size, number of demonstrations, over-defense, integration with other jailbreak attacks, and the presence of safety alignment. Given the experimental results and our analysis, we conclude that there is no free lunch for defending against prefilling jailbreak attacks with ICL. On the one hand, current safety alignment methods fail to mitigate prefilling jailbreak attacks, but adversative structures within ICL demonstrations provide robust defense across various model sizes and complex jailbreak attacks. On the other hand, LLMs exhibit similar over-defensiveness when utilizing ICL demonstrations with adversative structures, and this behavior appears to be independent of model size.
Authors: Zeyu Zhang, Jianxun Lian, Chen Ma, Yaning Qu, Ye Luo, Lei Wang, Rui Li, Xu Chen, Yankai Lin, Le Wu, Xing Xie, Ji-Rong Wen
Abstract: Trending topics have become a significant part of modern social media, attracting users to participate in discussions of breaking events. However, they also bring in a new channel for poisoning attacks, resulting in negative impacts on society. Therefore, it is urgent to study this critical problem and develop effective strategies for defense. In this paper, we propose TrendSim, an LLM-based multi-agent system to simulate trending topics in social media under poisoning attacks. Specifically, we create a simulation environment for trending topics that incorporates a time-aware interaction mechanism, centralized message dissemination, and an interactive system. Moreover, we develop LLM-based human-like agents to simulate users in social media, and propose prototype-based attackers to replicate poisoning attacks. Besides, we evaluate TrendSim from multiple aspects to validate its effectiveness. Based on TrendSim, we conduct simulation experiments to study four critical problems about poisoning attacks on trending topics for social benefit.
Authors: Hendrik Beukelman, Wilder C. Rodrigues
Abstract: This study explores visual search asymmetry and the detection process between parallel and serial search strategies, building upon Treisman's Feature Integration Theory [3]. Our experiment examines how easy it is to locate an oblique line among vertical distractors versus a vertical line among oblique distractors, a framework previously validated by Treisman & Gormican (1988) [4] and Gupta et al. (2015) [1]. We hypothesised that an oblique target among vertical lines would produce a perceptual 'pop-out' effect, allowing for faster, parallel search, while the reverse condition would require serial search strategy. Seventy-eight participants from Utrecht University engaged in trials with varied target-distractor orientations and number of items. We measured reaction times and found a significant effect of target type on search speed: oblique targets were identified more quickly, reflecting 'pop-out' behaviour, while vertical targets demanded focused attention ('glue phase'). Our results align with past findings, supporting our hypothesis on search asymmetry and its dependency on distinct visual features. Future research could benefit from eye-tracking and neural network analysis, particularly for identifying the neural processing of visual features in both parallel and serial search conditions.
Authors: Yusheng Zhao, Xiao Luo, Haomin Wen, Zhiping Xiao, Wei Ju, Ming Zhang
Abstract: Traffic flow forecasting aims to predict future traffic flows based on the historical traffic conditions and the road network. It is an important problem in intelligent transportation systems, with a plethora of methods been proposed. Existing efforts mainly focus on capturing and utilizing spatio-temporal dependencies to predict future traffic flows. Though promising, they fall short in adapting to test-time environmental changes of traffic conditions. To tackle this challenge, we propose to introduce large language models (LLMs) to help traffic flow forecasting and design a novel method named Large Language Model Enhanced Traffic Flow Predictor (LEAF). LEAF adopts two branches, capturing different spatio-temporal relations using graph and hypergraph structures respectively. The two branches are first pre-trained individually, and during test-time, they yield different predictions. Based on these predictions, a large language model is used to select the most likely result. Then, a ranking loss is applied as the learning objective to enhance the prediction ability of the two branches. Extensive experiments on several datasets demonstrate the effectiveness of the proposed LEAF.
Authors: Jing Zhang, Shuzhen Sun, Peng Zhang, Guangxing Cao, Hui Gao, Xindian Ma, Nan Xu, Yuexian Hou
Abstract: Transformer-based large language models exhibit groundbreaking capabilities, but their storage and computational costs are prohibitively high, limiting their application in resource-constrained scenarios. An effective approach is to eliminate redundant model parameters and computational costs while incorporating efficient expert-derived knowledge structures to achieve a balance between compression and performance. Therefore, we propose the \textit{Sememe Entanglement Encoding (SEE)} algorithm. Guided by expert prior knowledge, the model is compressed through the low-rank approximation idea. In Entanglement Embedding, basic semantic units such as sememes are represented as low-dimensional vectors, and then reconstructed into high-dimensional word embeddings through the combination of generalized quantum entanglement. We adapt the Sememe Entanglement Encoding algorithm to transformer-based models of different magnitudes. Experimental results indicate that our approach achieves stable performance while compressing model parameters and computational costs.
Authors: Portia Cooper, Harshita Narnoli, Mihai Surdeanu
Abstract: Text-to-image models are vulnerable to the stepwise "Divide-and-Conquer Attack" (DACA) that utilize a large language model to obfuscate inappropriate content in prompts by wrapping sensitive text in a benign narrative. To mitigate stepwise DACA attacks, we propose a two-layer method involving text summarization followed by binary classification. We assembled the Adversarial Text-to-Image Prompt (ATTIP) dataset ($N=940$), which contained DACA-obfuscated and non-obfuscated prompts. From the ATTIP dataset, we created two summarized versions: one generated by a small encoder model and the other by a large language model. Then, we used an encoder classifier and a GPT-4o classifier to perform content moderation on the summarized and unsummarized prompts. When compared with a classifier that operated over the unsummarized data, our method improved F1 score performance by 31%. Further, the highest recorded F1 score achieved (98%) was produced by the encoder classifier on a summarized ATTIP variant. This study indicates that pre-classification text summarization can inoculate content detection models against stepwise DACA obfuscations.
Authors: Byung-Kwan Ko, Jun-Young Kim, Seo-Hyun Lee
Abstract: This study examines the effectiveness of traditional machine learning classifiers versus deep learning models for detecting the imagined speech using electroencephalogram data. Specifically, we evaluated conventional machine learning techniques such as CSP-SVM and LDA-SVM classifiers alongside deep learning architectures such as EEGNet, ShallowConvNet, and DeepConvNet. Machine learning classifiers exhibited significantly lower precision and recall, indicating limited feature extraction capabilities and poor generalization between imagined speech and idle states. In contrast, deep learning models, particularly EEGNet, achieved the highest accuracy of 0.7080 and an F1 score of 0.6718, demonstrating their enhanced ability in automatic feature extraction and representation learning, essential for capturing complex neurophysiological patterns. These findings highlight the limitations of conventional machine learning approaches in brain-computer interface (BCI) applications and advocate for adopting deep learning methodologies to achieve more precise and reliable classification of detecting imagined speech. This foundational research contributes to the development of imagined speech-based BCI systems.
Authors: Francis Tang, Ying Ding
Abstract: Time series data plays a critical role across diverse domains such as healthcare, energy, and finance, where tasks like classification, anomaly detection, and forecasting are essential for informed decision-making. Recently, large language models (LLMs) have gained prominence for their ability to handle complex data and extract meaningful insights. This study investigates whether LLMs are effective for time series data analysis by comparing their performance with non-LLM-based approaches across three tasks: classification, anomaly detection, and forecasting. Through a series of experiments using GPT4TS and autoregressive models, we evaluate their performance on benchmark datasets and assess their accuracy, precision, and ability to generalize. Our findings indicate that while LLM-based methods excel in specific tasks like anomaly detection, their benefits are less pronounced in others, such as forecasting, where simpler models sometimes perform comparably or better. This research highlights the role of LLMs in time series analysis and lays the groundwork for future studies to systematically explore their applications and limitations in handling temporal data.
Authors: Xiao Teng, Long Lan, Dingyao Chen, Kele Xu, Nan Yin
Abstract: Unsupervised visible-infrared person re-identification (USL-VI-ReID) is of great research and practical significance yet remains challenging due to the absence of annotations. Existing approaches aim to learn modality-invariant representations in an unsupervised setting. However, these methods often encounter label noise within and across modalities due to suboptimal clustering results and considerable modality discrepancies, which impedes effective training. To address these challenges, we propose a straightforward yet effective solution for USL-VI-ReID by mitigating universal label noise using neighbor information. Specifically, we introduce the Neighbor-guided Universal Label Calibration (N-ULC) module, which replaces explicit hard pseudo labels in both homogeneous and heterogeneous spaces with soft labels derived from neighboring samples to reduce label noise. Additionally, we present the Neighbor-guided Dynamic Weighting (N-DW) module to enhance training stability by minimizing the influence of unreliable samples. Extensive experiments on the RegDB and SYSU-MM01 datasets demonstrate that our method outperforms existing USL-VI-ReID approaches, despite its simplicity. The source code is available at: https://github.com/tengxiao14/Neighbor-guided-USL-VI-ReID.
URLs: https://github.com/tengxiao14/Neighbor-guided-USL-VI-ReID.
Authors: Takumi Shimoda, Alex Fukunaga
Abstract: Parallelization of non-admissible search algorithms such as GBFS poses a challenge because straightforward parallelization can result in search behavior which significantly deviates from sequential search. Previous work proposed PUHF, a parallel search algorithm which is constrained to only expand states that can be expanded by some tie-breaking strategy for GBFS. We show that despite this constraint, the number of states expanded by PUHF is not bounded by a constant multiple of the number of states expanded by sequential GBFS with the worst-case tie-breaking strategy. We propose and experimentally evaluate One Bench At a Time (OBAT), a parallel greedy search which guarantees that the number of states expanded is within a constant factor of the number of states expanded by sequential GBFS with some tie-breaking policy.
Authors: Xiaozhe Li, Kai WU, Siyi Yang, YiZhan Qu, Guohua. Zhang, Zhiyu Chen, Jiayao Li, Jiangchuan Mu, Xiaobin Hu, Wen Fang, Mingliang Xiong, Hao Deng, Qingwen Liu, Gang Li, Bin He
Abstract: Recent advancements in text-to-video (T2V) generation have leveraged diffusion models to enhance the visual coherence of videos generated from textual descriptions. However, most research has primarily focused on object motion, with limited attention given to cinematic language in videos, which is crucial for cinematographers to convey emotion and narrative pacing. To address this limitation, we propose a threefold approach to enhance the ability of T2V models to generate controllable cinematic language. Specifically, we introduce a cinematic language dataset that encompasses shot framing, angle, and camera movement, enabling models to learn diverse cinematic styles. Building on this, to facilitate robust cinematic alignment evaluation, we present CameraCLIP, a model fine-tuned on the proposed dataset that excels in understanding complex cinematic language in generated videos and can further provide valuable guidance in the multi-shot composition process. Finally, we propose CLIPLoRA, a cost-guided dynamic LoRA composition method that facilitates smooth transitions and realistic blending of cinematic language by dynamically fusing multiple pre-trained cinematic LoRAs within a single video. Our experiments demonstrate that CameraCLIP outperforms existing models in assessing the alignment between cinematic language and video, achieving an R@1 score of 0.81. Additionally, CLIPLoRA improves the ability for multi-shot composition, potentially bridging the gap between automatically generated videos and those shot by professional cinematographers.
Authors: Pan Wang, Qiang Zhou, Yawen Wu, Tianlong Chen, Jingtong Hu
Abstract: Multimodal Sentiment Analysis (MSA) leverages heterogeneous modalities, such as language, vision, and audio, to enhance the understanding of human sentiment. While existing models often focus on extracting shared information across modalities or directly fusing heterogeneous modalities, such approaches can introduce redundancy and conflicts due to equal treatment of all modalities and the mutual transfer of information between modality pairs. To address these issues, we propose a Disentangled-Language-Focused (DLF) multimodal representation learning framework, which incorporates a feature disentanglement module to separate modality-shared and modality-specific information. To further reduce redundancy and enhance language-targeted features, four geometric measures are introduced to refine the disentanglement process. A Language-Focused Attractor (LFA) is further developed to strengthen language representation by leveraging complementary modality-specific information through a language-guided cross-attention mechanism. The framework also employs hierarchical predictions to improve overall accuracy. Extensive experiments on two popular MSA datasets, CMU-MOSI and CMU-MOSEI, demonstrate the significant performance gains achieved by the proposed DLF framework. Comprehensive ablation studies further validate the effectiveness of the feature disentanglement module, language-focused attractor, and hierarchical predictions. Our code is available at https://github.com/pwang322/DLF.
Authors: Tianyi Yin, Jingwei Wang, Yunlong Ma, Han Wang, Chenze Wang, Yukai Zhao, Min Liu, Weiming Shen, Yufeng Chen
Abstract: Encoding time series into tokens and using language models for processing has been shown to substantially augment the models' ability to generalize to unseen tasks. However, existing language models for time series forecasting encounter several obstacles, including aliasing distortion and prolonged inference times, primarily due to the limitations of quantization processes and the computational demands of large models. This paper introduces Apollo-Forecast, a novel framework that tackles these challenges with two key innovations: the Anti-Aliasing Quantization Module (AAQM) and the Race Decoding (RD) technique. AAQM adeptly encodes sequences into tokens while mitigating high-frequency noise in the original signals, thus enhancing both signal fidelity and overall quantization efficiency. RD employs a draft model to enable parallel processing and results integration, which markedly accelerates the inference speed for long-term predictions, particularly in large-scale models. Extensive experiments on various real-world datasets show that Apollo-Forecast outperforms state-of-the-art methods by 35.41\% and 18.99\% in WQL and MASE metrics, respectively, in zero-shot scenarios. Furthermore, our method achieves a 1.9X-2.7X acceleration in inference speed over baseline methods.
Authors: Sanjay Chakraborty, Ibrahim Delibasoglu, Fredrik Heintz
Abstract: Time series forecasting is a crucial challenge with significant applications in areas such as weather prediction, stock market analysis, and scientific simulations. This paper introduces an embedded decomposed transformer, 'EDformer', for multivariate time series forecasting tasks. Without altering the fundamental elements, we reuse the Transformer architecture and consider the capable functions of its constituent parts in this work. Edformer first decomposes the input multivariate signal into seasonal and trend components. Next, the prominent multivariate seasonal component is reconstructed across the reverse dimensions, followed by applying the attention mechanism and feed-forward network in the encoder stage. In particular, the feed-forward network is used for each variable frame to learn nonlinear representations, while the attention mechanism uses the time points of individual seasonal series embedded within variate frames to capture multivariate correlations. Therefore, the trend signal is added with projection and performs the final forecasting. The EDformer model obtains state-of-the-art predicting results in terms of accuracy and efficiency on complex real-world time series datasets. This paper also addresses model explainability techniques to provide insights into how the model makes its predictions and why specific features or time steps are important, enhancing the interpretability and trustworthiness of the forecasting results.
Authors: Krishnendu Chatterjee, Ruichen Luo, Raimundo Saona, Jakub Svoboda
Abstract: We consider a class of optimization problems defined by a system of linear equations with min and max operators. This class of optimization problems has been studied under restrictive conditions, such as, (C1) the halting or stability condition; (C2) the non-negative coefficients condition; (C3) the sum up to 1 condition; and (C4) the only min or only max oerator condition. Several seminal results in the literature focus on special cases. For example, turn-based stochastic games correspond to conditions C2 and C3; and Markov decision process to conditions C2, C3, and C4. However, the systematic computational complexity study of all the cases has not been explored, which we address in this work. Some highlights of our results are: with conditions C2 and C4, and with conditions C3 and C4, the problem is NP-complete, whereas with condition C1 only, the problem is in UP intersects coUP. Finally, we establish the computational complexity of the decision problem of checking the respective conditions.
Authors: Zhi Zhou, Lan-Zhe Guo, Peng-Xiao Song, Yu-Feng Li
Abstract: Deep generative models have achieved promising results in image generation, and various generative model hubs, e.g., Hugging Face and Civitai, have been developed that enable model developers to upload models and users to download models. However, these model hubs lack advanced model management and identification mechanisms, resulting in users only searching for models through text matching, download sorting, etc., making it difficult to efficiently find the model that best meets user requirements. In this paper, we propose a novel setting called Generative Model Identification (GMI), which aims to enable the user to identify the most appropriate generative model(s) for the user's requirements from a large number of candidate models efficiently. To our best knowledge, it has not been studied yet. In this paper, we introduce a comprehensive solution consisting of three pivotal modules: a weighted Reduced Kernel Mean Embedding (RKME) framework for capturing the generated image distribution and the relationship between images and prompts, a pre-trained vision-language model aimed at addressing dimensionality challenges, and an image interrogator designed to tackle cross-modality issues. Extensive empirical results demonstrate the proposal is both efficient and effective. For example, users only need to submit a single example image to describe their requirements, and the model platform can achieve an average top-4 identification accuracy of more than 80%.
Authors: Linfeng Zhao, Owen Howell, Xupeng Zhu, Jung Yeon Park, Zhewen Zhang, Robin Walters, Lawson L. S. Wong
Abstract: Reinforcement learning (RL) algorithms for continuous control tasks require accurate sampling-based action selection. Many tasks, such as robotic manipulation, contain inherent problem symmetries. However, correctly incorporating symmetry into sampling-based approaches remains a challenge. This work addresses the challenge of preserving symmetry in sampling-based planning and control, a key component for enhancing decision-making efficiency in RL. We introduce an action sampling approach that enforces the desired symmetry. We apply our proposed method to a coordinate regression problem and show that the symmetry aware sampling method drastically outperforms the naive sampling approach. We furthermore develop a general framework for sampling-based model-based planning with Model Predictive Path Integral (MPPI). We compare our MPPI approach with standard sampling methods on several continuous control tasks. Empirical demonstrations across multiple continuous control environments validate the effectiveness of our approach, showcasing the importance of symmetry preservation in sampling-based action selection.
Authors: Yangyang Li, Daqing Liu, Wu Liu, Allen He, Xinchen Liu, Yongdong Zhang, Guoqing Jin
Abstract: Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation or are easily disrupted by irrelevant concepts in multi-aspect concept scenarios, leading to concept confusion and hindering creative generation. To address this, we propose OmniPrism, a visual concept disentangling approach for creative image generation. Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts. We utilize the rich semantic space of a multimodal extractor to achieve concept disentanglement from given images and concept guidance. To disentangle concepts with different semantics, we construct a paired concept disentangled dataset (PCD-200K), where each pair shares the same concept such as content, style, and composition. We learn disentangled concept representations through our contrastive orthogonal disentangled (COD) training pipeline, which are then injected into additional diffusion cross-attention layers for generation. A set of block embeddings is designed to adapt each block's concept domain in the diffusion models. Extensive experiments demonstrate that our method can generate high-quality, concept-disentangled results with high fidelity to text prompts and desired concepts.
Authors: Seungwook Han, Jinyeop Song, Jeff Gore, Pulkit Agrawal
Abstract: Humans distill complex experiences into fundamental abstractions that enable rapid learning and adaptation. Similarly, autoregressive transformers exhibit adaptive learning through in-context learning (ICL), which begs the question of how. In this paper, we propose \textbf{concept encoding-decoding mechanism} to explain ICL by studying how transformers form and use internal abstractions in their representations. On synthetic ICL tasks, we analyze the training dynamics of a small transformer and report the coupled emergence of concept encoding and decoding. As the model learns to encode different latent concepts (e.g., ``Finding the first noun in a sentence.") into distinct, separable representations, it concureently builds conditional decoding algorithms and improve its ICL performance. We validate the existence of this mechanism across pretrained models of varying scales (Gemma-2 2B/9B/27B, Llama-3.1 8B/70B). Further, through mechanistic interventions and controlled finetuning, we demonstrate that the quality of concept encoding is causally related and predictive of ICL performance. Our empirical insights shed light into better understanding the success and failure modes of large language models via their representations.
Authors: Ioannis Papadimitriou (Yiannis), Ilias Gialampoukidis (Yiannis), Stefanos Vrochidis (Yiannis), Ioannis (Yiannis), Kompatsiaris
Abstract: We present RAG Playground, an open-source framework for systematic evaluation of Retrieval-Augmented Generation (RAG) systems. The framework implements and compares three retrieval approaches: naive vector search, reranking, and hybrid vector-keyword search, combined with ReAct agents using different prompting strategies. We introduce a comprehensive evaluation framework with novel metrics and provide empirical results comparing different language models (Llama 3.1 and Qwen 2.5) across various retrieval configurations. Our experiments demonstrate significant performance improvements through hybrid search methods and structured self-evaluation prompting, achieving up to 72.7% pass rate on our multi-metric evaluation framework. The results also highlight the importance of prompt engineering in RAG systems, with our custom-prompted agents showing consistent improvements in retrieval accuracy and response quality.
Authors: Yue Jin, Shuangqing Wei, Giovanni Montana
Abstract: In human society, the conflict between self-interest and collective well-being often obstructs efforts to achieve shared welfare. Related concepts like the Tragedy of the Commons and Social Dilemmas frequently manifest in our daily lives. As artificial agents increasingly serve as autonomous proxies for humans, we propose using multi-agent reinforcement learning (MARL) to address this issue - learning policies to maximise collective returns even when individual agents' interests conflict with the collective one. Traditional MARL solutions involve sharing rewards, values, and policies or designing intrinsic rewards to encourage agents to learn collectively optimal policies. We introduce a novel MARL approach based on Suggestion Sharing (SS), where agents exchange only action suggestions. This method enables effective cooperation without the need to design intrinsic rewards, achieving strong performance while revealing less private information compared to sharing rewards, values, or policies. Our theoretical analysis establishes a bound on the discrepancy between collective and individual objectives, demonstrating how sharing suggestions can align agents' behaviours with the collective objective. Experimental results demonstrate that SS performs competitively with baselines that rely on value or policy sharing or intrinsic rewards.
Authors: Samy Ateia, Udo Kruschwitz
Abstract: We present BioRAGent, an interactive web-based retrieval-augmented generation (RAG) system for biomedical question answering. The system uses large language models (LLMs) for query expansion, snippet extraction, and answer generation while maintaining transparency through citation links to the source documents and displaying generated queries for further editing. Building on our successful participation in the BioASQ 2024 challenge, we demonstrate how few-shot learning with LLMs can be effectively applied for a professional search setting. The system supports both direct short paragraph style responses and responses with inline citations. Our demo is available online, and the source code is publicly accessible through GitHub.
Authors: Rabimba Karanjai, Yang Lu, Dana Alsagheer, Keshav Kasichainula, Lei Xu, Weidong Shi, Shou-Hsuan Stephen Huang
Abstract: Logs are critical resources that record events, activities, or messages produced by software applications, operating systems, servers, and network devices. However, consolidating the heterogeneous logs and cross-referencing them is challenging and complicated. Manually analyzing the log data is time-consuming and prone to errors. LogBabylon is a centralized log data consolidating solution that leverages Large Language Models (LLMs) integrated with Retrieval-Augmented Generation (RAG) technology. LogBabylon interprets the log data in a human-readable way and adds insight analysis of the system performance and anomaly alerts. It provides a paramount view of the system landscape, enabling proactive management and rapid incident response. LogBabylon consolidates diverse log sources and enhances the extracted information's accuracy and relevancy. This facilitates a deeper understanding of log data, supporting more effective decision-making and operational efficiency. Furthermore, LogBabylon streamlines the log analysis process, significantly reducing the time and effort required to interpret complex datasets. Its capabilities extend to generating context-aware insights, offering an invaluable tool for continuous monitoring, performance optimization, and security assurance in dynamic computing environments.
Authors: Yihong Jin, Ze Yang
Abstract: The detection of scams within Ethereum smart contracts is a critical challenge due to their increasing exploitation for fraudulent activities, leading to significant financial and reputational damages. Existing detection methods often rely on contract code analysis or manually extracted features, which suffer from scalability and adaptability limitations. In this study, we introduce an innovative method that leverages graph representation learning to examine transaction patterns and identify fraudulent contracts. By transforming Ethereum transaction data into graph structures and employing advanced machine learning models, we achieve robust classification performance. Our method addresses label imbalance through SMOTE-ENN techniques and evaluates models like Multi-Layer Perceptron (MLP) and Graph Convolutional Networks (GCN). Experimental results indicate that the MLP model surpasses the GCN in this context, with real-world evaluations aligning closely with domain-specific analyses. This study provides a scalable and effective solution for enhancing trust and security in the Ethereum ecosystem.
Authors: Mariam Almutairi, Melike Yildiz Aktas, Nawar Wali, Shutonu Mitra, Dawei Zhou
Abstract: The rapid spread of misinformation on social media, especially during crises, challenges public decision-making. To address this, we propose HierTKG, a framework combining Temporal Graph Networks (TGN) and hierarchical pooling (DiffPool) to model rumor dynamics across temporal and structural scales. HierTKG captures key propagation phases, enabling improved temporal link prediction and actionable insights for misinformation control. Experiments demonstrate its effectiveness, achieving an MRR of 0.9845 on ICEWS14 and 0.9312 on WikiData, with competitive performance on noisy datasets like PHEME (MRR: 0.8802). By modeling structured event sequences and dynamic social interactions, HierTKG adapts to diverse propagation patterns, offering a scalable and robust solution for real-time analysis and prediction of rumor spread, aiding proactive intervention strategies.
Authors: Yinxuan Wang, Sudip Vhaduri
Abstract: The goal of this project is to classify four different insect sounds: cicada, beetle, termite, and cricket. One application of this project is for pest control to monitor and protect our ecosystem. Our project leverages data augmentation, including pitch shifting and speed changing, to improve model generalization. This project will test the performance of Decision Tree, Random Forest, SVM RBF, XGBoost, and k-NN models, combined with MFCC feature. A potential novelty of this project is that various data augmentation techniques are used and created 6 data along with the original sound. The dataset consists of the sound recordings of these four insects. This project aims to achieve a high classification accuracy and to reduce the over-fitting problem.
Authors: Asela Hevapathige, Qing Wang, Ahad N. Zehmakan
Abstract: Influence maximization is key topic in data mining, with broad applications in social network analysis and viral marketing. In recent years, researchers have increasingly turned to machine learning techniques to address this problem. They have developed methods to learn the underlying diffusion processes in a data-driven manner, which enhances the generalizability of the solution, and have designed optimization objectives to identify the optimal seed set. Nonetheless, two fundamental gaps remain unsolved: (1) Graph Neural Networks (GNNs) are increasingly used to learn diffusion models, but in their traditional form, they often fail to capture the complex dynamics of influence diffusion, (2) Designing optimization objectives is challenging due to combinatorial explosion when solving this problem. To address these challenges, we propose a novel framework, DeepSN. Our framework employs sheaf neural diffusion to learn diverse influence patterns in a data-driven, end-to-end manner, providing enhanced separability in capturing diffusion characteristics. We also propose an optimization technique that accounts for overlapping influence between vertices, which helps to reduce the search space and identify the optimal seed set effectively and efficiently. Finally, we conduct extensive experiments on both synthetic and real-world datasets to demonstrate the effectiveness of our framework.
Authors: Tuka Alhanai, Adam Kasumovic, Mohammad Ghassemi, Aven Zitzelberger, Jessica Lundin, Guillaume Chabot-Couture
Abstract: Large Language Models (LLMs) have shown remarkable performance across various tasks, yet significant disparities remain for non-English languages, and especially native African languages. This paper addresses these disparities by creating approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages, covering a population of over 160 million speakers of: Amharic, Bambara, Igbo, Sepedi (Northern Sotho), Shona, Sesotho (Southern Sotho), Setswana, and Tsonga. Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clinical knowledge, and virology. Using the translated benchmarks, we report previously unknown performance gaps between state-of-the-art (SOTA) LLMs in English and African languages. Finally, using results from over 400 fine-tuned models, we explore several methods to reduce the LLM performance gap, including high-quality dataset fine-tuning (using an LLM-as-an-Annotator), cross-lingual transfer, and cultural appropriateness adjustments. Key findings include average mono-lingual improvements of 5.6% with fine-tuning (with 5.4% average mono-lingual improvements when using high-quality data over low-quality data), 2.9% average gains from cross-lingual transfer, and a 3.0% out-of-the-box performance boost on culturally appropriate questions. The publicly available benchmarks, translations, and code from this study support further research and development aimed at creating more inclusive and effective language technologies.
Authors: Yash Patel, Giorgos Tolias, Jiri Matas
Abstract: This paper addresses supervised deep metric learning for open-set image retrieval, focusing on three key aspects: the loss function, mixup regularization, and model initialization. In deep metric learning, optimizing the retrieval evaluation metric, recall@k, via gradient descent is desirable but challenging due to its non-differentiable nature. To overcome this, we propose a differentiable surrogate loss that is computed on large batches, nearly equivalent to the entire training set. This computationally intensive process is made feasible through an implementation that bypasses the GPU memory limitations. Additionally, we introduce an efficient mixup regularization technique that operates on pairwise scalar similarities, effectively increasing the batch size even further. The training process is further enhanced by initializing the vision encoder using foundational models, which are pre-trained on large-scale datasets. Through a systematic study of these components, we demonstrate that their synergy enables large models to nearly solve popular benchmarks.
Authors: Xuan Shen, Zhao Song, Yufa Zhou, Bo Chen, Jing Liu, Ruiyi Zhang, Ryan A. Rossi, Hao Tan, Tong Yu, Xiang Chen, Yufan Zhou, Tong Sun, Pu Zhao, Yanzhi Wang, Jiuxiang Gu
Abstract: Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing. However, their impressive performance often incurs high computational costs due to their substantial model size. This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning to improve the model efficiency while preserving performance for both language and image generation tasks. Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and MLP modules, respectively. Besides, we further propose another compensation algorithm to recover the pruned model for better performance. To verify the effectiveness of our method, we provide both theoretical support and extensive experiments. Our experiments show that our method achieves state-of-the-art performance with reduced memory usage and faster generation speeds on GPUs.
Authors: Xuan Shen, Zhao Song, Yufa Zhou, Bo Chen, Yanyu Li, Yifan Gong, Kai Zhang, Hao Tan, Jason Kuen, Henghui Ding, Zhihao Shu, Wei Niu, Pu Zhao, Yanzhi Wang, Jiuxiang Gu
Abstract: Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at the cost of slow inference, as each denoising step requires running the whole transformer model with a large amount of parameters. In this paper, we show that performing the full computation of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps. Furthermore, we show that the lower bound of similarity between outputs at consecutive steps is notably high, and this similarity can be linearly approximated using the inputs. To verify our demonstrations, we propose the \textbf{LazyDiT}, a lazy learning framework that efficiently leverages cached results from earlier steps to skip redundant computations. Specifically, we incorporate lazy learning layers into the model, effectively trained to maximize laziness, enabling dynamic skipping of redundant computations. Experimental results show that LazyDiT outperforms the DDIM sampler across multiple diffusion transformer models at various resolutions. Furthermore, we implement our method on mobile devices, achieving better performance than DDIM with similar latency.
Authors: Jaeseok Yoo, Hojae Han, Youngwon Lee, Jaejin Kim, Seung-won Hwang
Abstract: Code generation with large language models has shown significant promise, especially when employing retrieval-augmented generation (RAG) with few-shot examples. However, selecting effective examples that enhance generation quality remains a challenging task, particularly when the target programming language (PL) is underrepresented. In this study, we present two key findings: (1) retrieving examples whose presented algorithmic plans can be referenced for generating the desired behavior significantly improves generation accuracy, and (2) converting code into pseudocode effectively captures such algorithmic plans, enhancing retrieval quality even when the source and the target PLs are different. Based on these findings, we propose Plan-as-query Example Retrieval for few-shot prompting in Code generation (PERC), a novel framework that utilizes algorithmic plans to identify and retrieve effective examples. We validate the effectiveness of PERC through extensive experiments on the CodeContests, HumanEval and MultiPL-E benchmarks: PERC consistently outperforms the state-of-the-art RAG methods in code generation, both when the source and target programming languages match or differ, highlighting its adaptability and robustness in diverse coding environments.
Authors: Xunkai Li, Zhengyu Wu, Jiayi Wu, Hanwen Cui, Jishuo Jia, Rong-Hua Li, Guoren Wang
Abstract: With the increasing prevalence of cross-domain Text-Attributed Graph (TAG) Data (e.g., citation networks, recommendation systems, social networks, and ai4science), the integration of Graph Neural Networks (GNNs) and Large Language Models (LLMs) into a unified Model architecture (e.g., LLM as enhancer, LLM as collaborators, LLM as predictor) has emerged as a promising technological paradigm. The core of this new graph learning paradigm lies in the synergistic combination of GNNs' ability to capture complex structural relationships and LLMs' proficiency in understanding informative contexts from the rich textual descriptions of graphs. Therefore, we can leverage graph description texts with rich semantic context to fundamentally enhance Data quality, thereby improving the representational capacity of model-centric approaches in line with data-centric machine learning principles. By leveraging the strengths of these distinct neural network architectures, this integrated approach addresses a wide range of TAG-based Task (e.g., graph learning, graph reasoning, and graph question answering), particularly in complex industrial scenarios (e.g., supervised, few-shot, and zero-shot settings). In other words, we can treat text as a medium to enable cross-domain generalization of graph learning Model, allowing a single graph model to effectively handle the diversity of downstream graph-based Task across different data domains. This work serves as a foundational reference for researchers and practitioners looking to advance graph learning methodologies in the rapidly evolving landscape of LLM. We consistently maintain the related open-source materials at \url{https://github.com/xkLi-Allen/Awesome-GNN-in-LLMs-Papers}.
URLs: https://github.com/xkLi-Allen/Awesome-GNN-in-LLMs-Papers
Authors: Chia-Hsuan Chang, Jui-Tse Tsai, Yi-Hang Tsai, San-Yih Hwang
Abstract: Topic modeling is widely used for uncovering thematic structures within text corpora, yet traditional models often struggle with specificity and coherence in domain-focused applications. Guided approaches, such as SeededLDA and CorEx, incorporate user-provided seed words to improve relevance but remain labor-intensive and static. Large language models (LLMs) offer potential for dynamic topic refinement and discovery, yet their application often incurs high API costs. To address these challenges, we propose the LLM-assisted Iterative Topic Augmentation framework (LITA), an LLM-assisted approach that integrates user-provided seeds with embedding-based clustering and iterative refinement. LITA identifies a small number of ambiguous documents and employs an LLM to reassign them to existing or new topics, minimizing API costs while enhancing topic quality. Experiments on two datasets across topic quality and clustering performance metrics demonstrate that LITA outperforms five baseline models, including LDA, SeededLDA, CorEx, BERTopic, and PromptTopic. Our work offers an efficient and adaptable framework for advancing topic modeling and text clustering.
Authors: Aditya Ganeshan, Thibault Groueix, Paul Guerrero, Radom\'ir M\v{e}ch, Matthew Fisher, Daniel Ritchie
Abstract: Pattern images are everywhere in the digital and physical worlds, and tools to edit them are valuable. But editing pattern images is tricky: desired edits are often programmatic: structure-aware edits that alter the underlying program which generates the pattern. One could attempt to infer this underlying program, but current methods for doing so struggle with complex images and produce unorganized programs that make editing tedious. In this work, we introduce a novel approach to perform programmatic edits on pattern images. By using a pattern analogy -- a pair of simple patterns to demonstrate the intended edit -- and a learning-based generative model to execute these edits, our method allows users to intuitively edit patterns. To enable this paradigm, we introduce SplitWeave, a domain-specific language that, combined with a framework for sampling synthetic pattern analogies, enables the creation of a large, high-quality synthetic training dataset. We also present TriFuser, a Latent Diffusion Model (LDM) designed to overcome critical issues that arise when naively deploying LDMs to this task. Extensive experiments on real-world, artist-sourced patterns reveals that our method faithfully performs the demonstrated edit while also generalizing to related pattern styles beyond its training distribution.
Authors: Bin Dou, Baokun Wang, Yun Zhu, Xiaotong Lin, Yike Xu, Xiaorui Huang, Yang Chen, Yun Liu, Shaoshuai Han, Yongchao Liu, Tianyi Zhang, Yu Cheng, Weiqiang Wang, Chuntao Hong
Abstract: User targeting, the process of selecting targeted users from a pool of candidates for non-expert marketers, has garnered substantial attention with the advancements in digital marketing. However, existing user targeting methods encounter two significant challenges: (i) Poor cross-domain and cross-scenario transferability and generalization, and (ii) Insufficient forecastability in real-world applications. These limitations hinder their applicability across diverse industrial scenarios. In this work, we propose FIND, an industrial-grade, transferable, and forecastable user targeting foundation model. To enhance cross-domain transferability, our framework integrates heterogeneous multi-scenario user data, aligning them with one-sentence targeting demand inputs through contrastive pre-training. For improved forecastability, the text description of each user is derived based on anticipated future behaviors, while user representations are constructed from historical information. Experimental results demonstrate that our approach significantly outperforms existing baselines in cross-domain, real-world user targeting scenarios, showcasing the superior capabilities of FIND. Moreover, our method has been successfully deployed on the Alipay platform and is widely utilized across various scenarios.
Authors: Mingquan Feng, Zhijie Chen, Yixin Huang, Yizhou Liu, Junchi Yan
Abstract: Optimal control problems (OCPs) involve finding a control function for a dynamical system such that a cost functional is optimized. It is central to physical systems in both academia and industry. In this paper, we propose a novel instance-solution control operator perspective, which solves OCPs in a one-shot manner without direct dependence on the explicit expression of dynamics or iterative optimization processes. The control operator is implemented by a new neural operator architecture named Neural Adaptive Spectral Method (NASM), a generalization of classical spectral methods. We theoretically validate the perspective and architecture by presenting the approximation error bounds of NASM for the control operator. Experiments on synthetic environments and a real-world dataset verify the effectiveness and efficiency of our approach, including substantial speedup in running time, and high-quality in- and out-of-distribution generalization.
Authors: Xuanzhong Chen, Ye Jin, Xiaohao Mao, Lun Wang, Shuyang Zhang, Ting Chen
Abstract: Rare diseases, despite their low individual incidence, collectively impact around 300 million people worldwide due to the huge number of diseases. The complexity of symptoms and the shortage of specialized doctors with relevant experience make diagnosing and treating rare diseases more challenging than common diseases. Recently, agents powered by large language models (LLMs) have demonstrated notable improvements across various domains. In the medical field, some agent methods have outperformed direct prompts in question-answering tasks from medical exams. However, current agent frameworks lack adaptation for real-world clinical scenarios, especially those involving the intricate demands of rare diseases. To address these challenges, we present RareAgents, the first multi-disciplinary team of LLM-based agents tailored to the complex clinical context of rare diseases. RareAgents integrates advanced planning capabilities, memory mechanisms, and medical tools utilization, leveraging Llama-3.1-8B/70B as the base model. Experimental results show that RareAgents surpasses state-of-the-art domain-specific models, GPT-4o, and existing agent frameworks in both differential diagnosis and medication recommendation for rare diseases. Furthermore, we contribute a novel dataset, MIMIC-IV-Ext-Rare, derived from MIMIC-IV, to support further advancements in this field.
Authors: Alex Mallen, Charlie Griffin, Alessandro Abate, Buck Shlegeris
Abstract: AI control protocols are plans for usefully deploying AI systems in a way that is safe, even if the AI intends to subvert the protocol. Previous work evaluated protocols by subverting them with a human-AI red team, where an AI follows the human-written strategy. This paper investigates how well AI systems can generate and act on strategies for subverting control protocols whilst operating without private memory. Usually, decision-makers only need the ability to generate optimal plans. However, to subvert a protocol, an AI system must be able to reliably generate optimal plans in each context; coordinate plans with other instances of itself without communicating; and take actions with well-calibrated probabilities. We develop evaluations for a model's ability to generate subversion strategies and develop affordance experiments that help isolate component capabilities. Our initial evaluations with Claude-3.5-sonnet highlight reasons why statelessly strategizing to subvert control protocols might be hard. We hope that our work can serve as a starting point for evaluations aimed at assessing whether a model is capable of strategizing to subvert control protocols.
Authors: Samuel Yen-Chi Chen
Abstract: Recent advancements in quantum computing (QC) and machine learning (ML) have garnered significant attention, leading to substantial efforts toward the development of quantum machine learning (QML) algorithms to address a variety of complex challenges. The design of high-performance QML models, however, requires expert-level knowledge, posing a significant barrier to the widespread adoption of QML. Key challenges include the design of data encoding mechanisms and parameterized quantum circuits, both of which critically impact the generalization capabilities of QML models. We propose a novel method that encodes quantum circuit architecture information to enable the evolution of quantum circuit designs. In this approach, the fitness function is based on the effective dimension, allowing for the optimization of quantum circuits towards higher model capacity. Through numerical simulations, we demonstrate that the proposed method is capable of discovering variational quantum circuit architectures that offer improved learning capabilities, thereby enhancing the overall performance of QML models for complex tasks.
Authors: Hongjin Qian, Zheng Liu, Peitian Zhang, Zhicheng Dou, Defu Lian
Abstract: Processing long contexts poses a significant challenge for large language models (LLMs) due to their inherent context-window limitations and the computational burden of extensive key-value (KV) activations, which severely impact efficiency. For information-seeking tasks, full context perception is often unnecessary, as a query's information needs can dynamically range from localized details to a global perspective, depending on its complexity. However, existing methods struggle to adapt effectively to these dynamic information needs. In the paper, we propose a method for processing long-context information-seeking tasks via query-guided Activation Refilling (ACRE). ACRE constructs a Bi-layer KV Cache for long contexts, where the layer-1 (L1) cache compactly captures global information, and the layer-2 (L2) cache provides detailed and localized information. ACRE establishes a proxying relationship between the two caches, allowing the input query to attend to the L1 cache and dynamically refill it with relevant entries from the L2 cache. This mechanism integrates global understanding with query-specific local details, thus improving answer decoding. Experiments on a variety of long-context information-seeking datasets demonstrate ACRE's effectiveness, achieving improvements in both performance and efficiency.
Authors: Jinghan Zeng, Eugene Wu, Sanjay Krishnan
Abstract: Many computer systems are now being redesigned to incorporate LLM-powered agents, enabling natural language input and more flexible operations. This paper focuses on handling database transactions created by large language models (LLMs). Transactions generated by LLMs may include semantic errors, requiring systems to treat them as long-lived. This allows for human review and, if the transaction is incorrect, removal from the database history. Any removal action must ensure the database's consistency (the "C" in ACID principles) is maintained throughout the process. We propose a novel middleware framework based on Invariant Satisfaction (I-Confluence), which ensures consistency by identifying and coordinating dependencies between long-lived transactions and new transactions. This middleware buffers suspicious or compensating transactions to manage coordination states. Using the TPC-C benchmark, we evaluate how transaction generation frequency, user reviews, and invariant completeness impact system performance. For system researchers, this study establishes an interactive paradigm between LLMs and database systems, providing an "undoing" mechanism for handling incorrect operations while guaranteeing database consistency. For system engineers, this paper offers a middleware design that integrates removable LLM-generated transactions into existing systems with minimal modifications.
Authors: Mingjia Shi, Yuhao Zhou, Ruiji Yu, Zekai Li, Zhiyuan Liang, Xuanlei Zhao, Xiaojiang Peng, Tanmay Rajpurohit, Shanmukha Ramakrishna Vedantam, Wangbo Zhao, Kai Wang, Yang You
Abstract: Vision Mamba (e.g., Vim) has successfully been integrated into computer vision, and token reduction has yielded promising outcomes in Vision Transformers (ViTs). However, token reduction performs less effectively on Vision Mamba compared to ViTs. Pruning informative tokens in Mamba leads to a high loss of key knowledge and bad performance. This makes it not a good solution for enhancing efficiency in Mamba. Token merging, which preserves more token information than pruning, has demonstrated commendable performance in ViTs. Nevertheless, vanilla merging performance decreases as the reduction ratio increases either, failing to maintain the key knowledge in Mamba. Re-training the token-reduced model enhances the performance of Mamba, by effectively rebuilding the key knowledge. Empirically, pruned Vims only drop up to 0.9% accuracy on ImageNet-1K, recovered by our proposed framework R-MeeTo in our main evaluation. We show how simple and effective the fast recovery can be achieved at minute-level, in particular, a 35.9% accuracy spike over 3 epochs of training on Vim-Ti. Moreover, Vim-Ti/S/B are re-trained within 5/7/17 minutes, and Vim-S only drop 1.3% with 1.2x (up to 1.5x) speed up in inference.
Authors: Hongbin Zhang, Kehai Chen, Xuefeng Bai, Yang Xiang, Min Zhang
Abstract: Large language models (LLMs) have demonstrated impressive multilingual understanding and reasoning capabilities, driven by extensive pre-training multilingual corpora and fine-tuning instruction data. However, a performance gap persists between high-resource and low-resource language tasks due to language imbalance in the pre-training corpus, even using more low-resource data during fine-tuning. To alleviate this issue, we propose LinguaLIFT, a two-stage instruction tuning framework for advancing low-resource language tasks. An additional language alignment layer is first integrated into the LLM to adapt a pre-trained multilingual encoder, thereby enhancing multilingual alignment through code-switched fine-tuning. The second stage fine-tunes LLM with English-only instruction data while freezing the language alignment layer, allowing LLM to transfer task-specific capabilities from English to low-resource language tasks. Additionally, we introduce the Multilingual Math World Problem (MMWP) benchmark, which spans 21 low-resource, 17 medium-resource, and 10 high-resource languages, enabling comprehensive evaluation of multilingual reasoning. Experimental results show that LinguaLIFT outperforms several competitive baselines across MMWP and other widely used benchmarks.
Authors: Sina Bagheri Nezhad, Ameeta Agrawal, Rhitabrat Pokharel
Abstract: Multilingual language models (MLLMs) are crucial for handling text across various languages, yet they often show performance disparities due to differences in resource availability and linguistic characteristics. While the impact of pre-train data percentage and model size on performance is well-known, our study reveals additional critical factors that significantly influence MLLM effectiveness. Analyzing a wide range of features, including geographical, linguistic, and resource-related aspects, we focus on the SIB-200 dataset for classification and the Flores-200 dataset for machine translation, using regression models and SHAP values across 204 languages. Our findings identify token similarity and country similarity as pivotal factors, alongside pre-train data and model size, in enhancing model performance. Token similarity facilitates cross-lingual transfer, while country similarity highlights the importance of shared cultural and linguistic contexts. These insights offer valuable guidance for developing more equitable and effective multilingual language models, particularly for underrepresented languages.
Authors: Geling Liu, Yunzhi Tan, Ruichao Zhong, Yuanzhen Xie, Lingchen Zhao, Qian Wang, Bo Hu, Zang Li
Abstract: Recently, large language models (LLMs) have significantly improved the performance of text-to-SQL systems. Nevertheless, many state-of-the-art (SOTA) approaches have overlooked the critical aspect of system robustness. Our experiments reveal that while LLM-driven methods excel on standard datasets, their accuracy is notably compromised when faced with adversarial perturbations. To address this challenge, we propose a robust text-to-SQL solution, called Solid-SQL, designed to integrate with various LLMs. We focus on the pre-processing stage, training a robust schema-linking model enhanced by LLM-based data augmentation. Additionally, we design a two-round, structural similarity-based example retrieval strategy for in-context learning. Our method achieves SOTA SQL execution accuracy levels of 82.1% and 58.9% on the general Spider and Bird benchmarks, respectively. Furthermore, experimental results show that Solid-SQL delivers an average improvement of 11.6% compared to baselines on the perturbed Spider-Syn, Spider-Realistic, and Dr. Spider benchmarks.
Authors: Ruixin Mao, Aoyu Shen, Lin Tang, Jun Zhou
Abstract: Event-based cameras feature high temporal resolution, wide dynamic range, and low power consumption, which is ideal for high-speed and low-light object detection. Spiking neural networks (SNNs) are promising for event-based object recognition and detection due to their spiking nature but lack efficient training methods, leading to gradient vanishing and high computational complexity, especially in deep SNNs. Additionally, existing SNN frameworks often fail to effectively handle multi-scale spatiotemporal features, leading to increased data redundancy and reduced accuracy. To address these issues, we propose CREST, a novel conjointly-trained spike-driven framework to exploit spatiotemporal dynamics in event-based object detection. We introduce the conjoint learning rule to accelerate SNN learning and alleviate gradient vanishing. It also supports dual operation modes for efficient and flexible implementation on different hardware types. Additionally, CREST features a fully spike-driven framework with a multi-scale spatiotemporal event integrator (MESTOR) and a spatiotemporal-IoU (ST-IoU) loss. Our approach achieves superior object recognition & detection performance and up to 100X energy efficiency compared with state-of-the-art SNN algorithms on three datasets, providing an efficient solution for event-based object detection algorithms suitable for SNN hardware implementation.
Authors: Iman Khazrak, Shakhnoza Takhirova, Mostafa M. Rezaee, Mehrdad Yadollahi, Robert C. Green II, Shuteng Niu
Abstract: The development of accurate medical image classification models is often constrained by privacy concerns and data scarcity for certain conditions, leading to small and imbalanced datasets. To address these limitations, this study explores the use of generative models, such as Denoising Diffusion Probabilistic Models (DDPM) and Progressive Growing Generative Adversarial Networks (PGGANs), for dataset augmentation. The research introduces a framework to assess the impact of synthetic images generated by DDPM and PGGANs on the performance of four models: a custom CNN, Untrained VGG16, Pretrained VGG16, and Pretrained ResNet50. Experiments were conducted using Random Sampling and Greedy K Sampling to create small, imbalanced datasets. The synthetic images were evaluated using Frechet Inception Distance (FID) and compared to original datasets through classification metrics. The results show that DDPM consistently generated more realistic images with lower FID scores and significantly outperformed PGGANs in improving classification metrics across all models and datasets. Incorporating DDPM-generated images into the original datasets increased accuracy by up to 6%, enhancing model robustness and stability, particularly in imbalanced scenarios. Random Sampling demonstrated superior stability, while Greedy K Sampling offered diversity at the cost of higher FID scores. This study highlights the efficacy of DDPM in augmenting small, imbalanced medical image datasets, improving model performance by balancing the dataset and expanding its size.
Authors: Tao Fang, Derek F. Wong, Lusheng Zhang, Keyan Jin, Qiang Zhang, Tianjiao Li, Jinlong Hou, Lidia S. Chao
Abstract: While large-scale language models (LLMs) have demonstrated remarkable capabilities in specific natural language processing (NLP) tasks, they may still lack proficiency compared to specialized models in certain domains, such as grammatical error correction (GEC). Drawing inspiration from the concept of curriculum learning, we have delved into refining LLMs into proficient GEC experts by devising effective curriculum learning (CL) strategies. In this paper, we introduce a novel approach, termed LLM-based curriculum learning, which capitalizes on the robust semantic comprehension and discriminative prowess inherent in LLMs to gauge the complexity of GEC training data. Unlike traditional curriculum learning techniques, our method closely mirrors human expert-designed curriculums. Leveraging the proposed LLM-based CL method, we sequentially select varying levels of curriculums ranging from easy to hard, and iteratively train and refine using the pretrianed T5 and LLaMA series models. Through rigorous testing and analysis across diverse benchmark assessments in English GEC, including the CoNLL14 test, BEA19 test, and BEA19 development sets, our approach showcases a significant performance boost over baseline models and conventional curriculum learning methodologies.
Authors: Katie Seaborn
Abstract: We humans are biased - and our robotic creations are biased, too. Bias is a natural phenomenon that drives our perceptions and behavior, including when it comes to socially expressive robots that have humanlike features. Recognizing that we embed bias, knowingly or not, within the design of such robots is crucial to studying its implications for people in modern societies. In this chapter, I consider the multifaceted question of bias in the context of humanoid, AI-enabled, and expressive social robots: Where does bias arise, what does it look like, and what can (or should) we do about it. I offer observations on human-robot interaction (HRI) along two parallel tracks: (1) robots designed in bias-conscious ways and (2) robots that may help us tackle bias in the human world. I outline a curated selection of cases for each track drawn from the latest HRI research and positioned against social, legal, and ethical factors. I also propose a set of critical next steps to tackle the challenges and opportunities on bias within HRI research and practice.
Authors: Sparsh Pekhale, Rakshith Sathish, Sathisha Basavaraju, Divya Sharma
Abstract: Land-use and land cover (LULC) analysis is critical in remote sensing, with wide-ranging applications across diverse fields such as agriculture, utilities, and urban planning. However, automating LULC map generation using machine learning is rendered challenging due to noisy labels. Typically, the ground truths (e.g. ESRI LULC, MapBioMass) have noisy labels that hamper the model's ability to learn to accurately classify the pixels. Further, these erroneous labels can significantly distort the performance metrics of a model, leading to misleading evaluations. Traditionally, the ambiguous labels are rectified using unsupervised algorithms. These algorithms struggle not only with scalability but also with generalization across different geographies. To overcome these challenges, we propose a zero-shot approach using the foundation model, Segment Anything Model (SAM), to automatically delineate different land parcels/regions and leverage them to relabel the unsure pixels by using the local label statistics within each detected region. We achieve a significant reduction in label noise and an improvement in the performance of the downstream segmentation model by $\approx 5\%$ when trained with denoised labels.
Authors: Taeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun Song, SeungYoon Han, Jong C. Park
Abstract: We introduce EXIT, an extractive context compression framework that enhances both the effectiveness and efficiency of retrieval-augmented generation (RAG) in question answering (QA). Current RAG systems often struggle when retrieval models fail to rank the most relevant documents, leading to the inclusion of more context at the expense of latency and accuracy. While abstractive compression methods can drastically reduce token counts, their token-by-token generation process significantly increases end-to-end latency. Conversely, existing extractive methods reduce latency but rely on independent, non-adaptive sentence selection, failing to fully utilize contextual information. EXIT addresses these limitations by classifying sentences from retrieved documents - while preserving their contextual dependencies - enabling parallelizable, context-aware extraction that adapts to query complexity and retrieval quality. Our evaluations on both single-hop and multi-hop QA tasks show that EXIT consistently surpasses existing compression methods and even uncompressed baselines in QA accuracy, while also delivering substantial reductions in inference time and token count. By improving both effectiveness and efficiency, EXIT provides a promising direction for developing scalable, high-quality QA solutions in RAG pipelines. Our code is available at https://github.com/ThisIsHwang/EXIT
Authors: Wenjun Huang, Yang Ni, Hanning Chen, Yirui He, Ian Bryant, Yezi Liu, Mohsen Imani
Abstract: Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to localize an arbitrary number of targets based on a language expression and continuously track them in a video. This intricate task involves reasoning on multi-modal data and precise target localization with temporal association. However, prior studies overlook the imbalanced data distribution between newborn targets and existing targets due to the nature of the task. In addition, they only indirectly fuse multi-modal features, struggling to deliver clear guidance on newborn target detection. To solve the above issues, we conduct a collaborative matching strategy to alleviate the impact of the imbalance, boosting the ability to detect newborn targets while maintaining tracking performance. In the encoder, we integrate and enhance the cross-modal and multi-scale fusion, overcoming the bottlenecks in previous work, where limited multi-modal information is shared and interacted between feature maps. In the decoder, we also develop a referring-infused adaptation that provides explicit referring guidance through the query tokens. The experiments showcase the superior performance of our model (+3.42%) compared to prior works, demonstrating the effectiveness of our designs.
Authors: Zahra Ebrahimi Vargoorani, Ching Yee Suen
Abstract: License plate detection (LPD) is essential for traffic management, vehicle tracking, and law enforcement but faces challenges like variable lighting and diverse font types, impacting accuracy. Traditionally reliant on image processing and machine learning, the field is now shifting towards deep learning for its robust performance in various conditions. Current methods, however, often require tailoring to specific regional datasets. This paper proposes a dual deep learning strategy using a Faster R-CNN for detection and a CNN-RNN model with Connectionist Temporal Classification (CTC) loss and a MobileNet V3 backbone for recognition. This approach aims to improve model performance using datasets from Ontario, Quebec, California, and New York State, achieving a recall rate of 92% on the Centre for Pattern Recognition and Machine Intelligence (CENPARMI) dataset and 90% on the UFPR-ALPR dataset. It includes a detailed error analysis to identify the causes of false positives. Additionally, the research examines the role of font features in license plate (LP) recognition, analyzing fonts like Driver Gothic, Dreadnought, California Clarendon, and Zurich Extra Condensed with the OpenALPR system. It discovers significant performance discrepancies influenced by font characteristics, offering insights for future LPD system enhancements. Keywords: Deep Learning, License Plate, Font Evaluation
Authors: Lanyu Shang, Bozhang Chen, Shiwei Liu, Yang Zhang, Ruohan Zong, Anav Vora, Ximing Cai, Na Wei, Dong Wang
Abstract: Drought has become a critical global threat with significant societal impact. Existing drought monitoring solutions primarily focus on assessing drought severity using quantitative measurements, overlooking the diverse societal impact of drought from human-centric perspectives. Motivated by the collective intelligence on social media and the computational power of AI, this paper studies a novel problem of socially informed AI-driven drought estimation that aims to leverage social and news media information to jointly estimate drought severity and its societal impact. Two technical challenges exist: 1) How to model the implicit temporal dynamics of drought societal impact. 2) How to capture the social-physical interdependence between the physical drought condition and its societal impact. To address these challenges, we develop SIDE, a socially informed AI-driven drought estimation framework that explicitly quantifies the societal impact of drought and effectively models the social-physical interdependency for joint severity-impact estimation. Experiments on real-world datasets from California and Texas demonstrate SIDE's superior performance compared to state-of-the-art baselines in accurately estimating drought severity and its societal impact. SIDE offers valuable insights for developing human-centric drought mitigation strategies to foster sustainable and resilient communities.
Authors: Qinyu Zhang, Liang Xu, Jianhao Huang, Tao Yang, Jian Jiao, Ye Wang, Yao Shi, Chiya Zhang, Xingjian Zhang, Ke Zhang, Yupeng Gong, Na Deng, Nan Zhao, Zhen Gao, Shujun Han, Xiaodong Xu, Li You, Dongming Wang, Shan Jiang, Dixian Zhao, Nan Zhang, Liujun Hu, Xiongwen He, Yonghui Li, Xiqi Gao, Xiaohu You
Abstract: Driven by the vision of ubiquitous connectivity and wireless intelligence, the evolution of ultra-dense constellation-based satellite-integrated Internet is underway, now taking preliminary shape. Nevertheless, the entrenched institutional silos and limited, nonrenewable heterogeneous network resources leave current satellite systems struggling to accommodate the escalating demands of next-generation intelligent applications. In this context, the distributed satellite information networks (DSIN), exemplified by the cohesive clustered satellites system, have emerged as an innovative architecture, bridging information gaps across diverse satellite systems, such as communication, navigation, and remote sensing, and establishing a unified, open information network paradigm to support resilient space information services. This survey first provides a profound discussion about innovative network architectures of DSIN, encompassing distributed regenerative satellite network architecture, distributed satellite computing network architecture, and reconfigurable satellite formation flying, to enable flexible and scalable communication, computing and control. The DSIN faces challenges from network heterogeneity, unpredictable channel dynamics, sparse resources, and decentralized collaboration frameworks. To address these issues, a series of enabling technologies is identified, including channel modeling and estimation, cloud-native distributed MIMO cooperation, grant-free massive access, network routing, and the proper combination of all these diversity techniques. Furthermore, to heighten the overall resource efficiency, the cross-layer optimization techniques are further developed to meet upper-layer deterministic, adaptive and secure information services requirements. In addition, emerging research directions and new opportunities are highlighted on the way to achieving the DSIN vision.
Authors: Hai Lin, Cheng Huang, Zhihong Chen
Abstract: Reinforcement learning tasks in real-world scenarios often involve large, high-dimensional action spaces, leading to challenges such as convergence difficulties, instability, and high computational complexity. It is widely acknowledged that traditional value-based reinforcement learning algorithms struggle to address these issues effectively. A prevalent approach involves generating independent sub-actions within each dimension of the action space. However, this method introduces bias, hindering the learning of optimal policies. In this paper, we propose an advantage-based optimization method and an algorithm named Advantage Branching Dueling Q-network (ABQ). ABQ incorporates a baseline mechanism to tune the action value of each dimension, leveraging the advantage relationship across different sub-actions. With this approach, the learned policy can be optimized for each dimension. Empirical results demonstrate that ABQ outperforms BDQ, achieving 3%, 171%, and 84% more cumulative rewards in HalfCheetah, Ant, and Humanoid environments, respectively. Furthermore, ABQ exhibits competitive performance when compared against two continuous action benchmark algorithms, DDPG and TD3.
Authors: Aman Tiwari, Shiva Krishna Reddy Malay, Vikas Yadav, Masoud Hashemi, Sathwik Tejaswi Madhusudhan
Abstract: Cypher, the query language for Neo4j graph databases, plays a critical role in enabling graph-based analytics and data exploration. While substantial research has been dedicated to natural language to SQL query generation (Text2SQL), the analogous problem for graph databases referred to as Text2Cypher remains underexplored. In this work, we introduce SynthCypher, a fully synthetic and automated data generation pipeline designed to address this gap. SynthCypher employs a novel LLMSupervised Generation-Verification framework, ensuring syntactically and semantically correct Cypher queries across diverse domains and query complexities. Using this pipeline, we create SynthCypher Dataset, a large-scale benchmark containing 29.8k Text2Cypher instances. Fine-tuning open-source large language models (LLMs), including LLaMa-3.1- 8B, Mistral-7B, and QWEN-7B, on SynthCypher yields significant performance improvements of up to 40% on the Text2Cypher test set and 30% on the SPIDER benchmark adapted for graph databases. This work demonstrates that high-quality synthetic data can effectively advance the state-of-the-art in Text2Cypher tasks.
Authors: Kuiyuan Zhang, Zhongyun Hua, Rushi Lan, Yushu Zhang, Yifang Guo
Abstract: Recent advancements in text-to-speech and speech conversion technologies have enabled the creation of highly convincing synthetic speech. While these innovations offer numerous practical benefits, they also cause significant security challenges when maliciously misused. Therefore, there is an urgent need to detect these synthetic speech signals. Phoneme features provide a powerful speech representation for deepfake detection. However, previous phoneme-based detection approaches typically focused on specific phonemes, overlooking temporal inconsistencies across the entire phoneme sequence. In this paper, we develop a new mechanism for detecting speech deepfakes by identifying the inconsistencies of phoneme-level speech features. We design an adaptive phoneme pooling technique that extracts sample-specific phoneme-level features from frame-level speech data. By applying this technique to features extracted by pre-trained audio models on previously unseen deepfake datasets, we demonstrate that deepfake samples often exhibit phoneme-level inconsistencies when compared to genuine speech. To further enhance detection accuracy, we propose a deepfake detector that uses a graph attention network to model the temporal dependencies of phoneme-level features. Additionally, we introduce a random phoneme substitution augmentation technique to increase feature diversity during training. Extensive experiments on four benchmark datasets demonstrate the superior performance of our method over existing state-of-the-art detection methods.
Authors: Pranav Rajpurkar, Julian N. Acosta, Siddhant Dogra, Jaehwan Jeong, Deepanshu Jindal, Michael Moritz, Samir Rajpurkar
Abstract: We present a comprehensive evaluation of a2z-1, an artificial intelligence (AI) model designed to analyze abdomen-pelvis CT scans for 21 time-sensitive and actionable findings. Our study focuses on rigorous assessment of the model's performance and generalizability. Large-scale retrospective analysis demonstrates an average AUC of 0.931 across 21 conditions. External validation across two distinct health systems confirms consistent performance (AUC 0.923), establishing generalizability to different evaluation scenarios, with notable performance in critical findings such as small bowel obstruction (AUC 0.958) and acute pancreatitis (AUC 0.961). Subgroup analysis shows consistent accuracy across patient sex, age groups, and varied imaging protocols, including different slice thicknesses and contrast administration types. Comparison of high-confidence model outputs to radiologist reports reveals instances where a2z-1 identified overlooked findings, suggesting potential for quality assurance applications.
Authors: Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Qing Wang, Yihao Huang, Yang Liu
Abstract: Incorporating external knowledge into large language models (LLMs) has emerged as a promising approach to mitigate outdated knowledge and hallucination in LLMs. However, external knowledge is often imperfect. In addition to useful knowledge, external knowledge is rich in irrelevant or misinformation in the context that can impair the reliability of LLM responses. This paper focuses on LLMs' preferred external knowledge in imperfect contexts when handling multi-hop QA. Inspired by criminal procedural law's Chain of Evidence (CoE), we characterize that knowledge preferred by LLMs should maintain both relevance to the question and mutual support among knowledge pieces. Accordingly, we propose an automated CoE discrimination approach and explore LLMs' preferences from their effectiveness, faithfulness and robustness, as well as CoE's usability in a naive Retrieval-Augmented Generation (RAG) case. The evaluation on five LLMs reveals that CoE enhances LLMs through more accurate generation, stronger answer faithfulness, better robustness against knowledge conflict, and improved performance in a popular RAG case.
Authors: ChonLam Lao, Minlan Yu, Aditya Akella, Jiamin Cao, Yu Guan, Pengcheng Zhang, Zhilong Zheng, Yichi Xu, Ennan Zhai, Dennis Cai, Jiaqi Gao
Abstract: Machine learning training has emerged as one of the most prominent workloads in modern data centers. These training jobs are large-scale, long-lasting, and tightly coupled, and are often disrupted by various events in the cluster such as failures, maintenance, and job scheduling. To handle these events, we rely on cold migration, where we first checkpoint the entire cluster, replace the related machines, and then restart the training. This approach leads to disruptions to the training jobs, resulting in significant downtime. In this paper, we present TrainMover, a live migration system that enables machine replacement during machine learning training. TrainMover minimizes downtime by leveraging member replacement of collective communication groups and sandbox lazy initialization. Our evaluation demonstrates that TrainMover achieves 16x less downtime compared to all baselines, effectively handling data center events like straggler rebalancing, maintenance, and unexpected failures.
Authors: Xiangxiang Gao, Weisheng Xie, Yiwei Xiang, Feng Ji
Abstract: Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon, an innovative semi-autoregressive speculative decoding framework fashioned to augment both the drafter's parallelism and output quality. Falcon incorporates the Coupled Sequential Glancing Distillation technique, which fortifies inter-token dependencies within the same block, leading to increased speculation accuracy. We offer a comprehensive theoretical analysis to illuminate the underlying mechanisms. Additionally, we introduce a Custom-Designed Decoding Tree, which permits the drafter to generate multiple tokens in a single forward pass and accommodates multiple forward passes as needed, thereby boosting the number of drafted tokens and significantly improving the overall acceptance rate. Comprehensive evaluations on benchmark datasets such as MT-Bench, HumanEval, and GSM8K demonstrate Falcon's superior acceleration capabilities. The framework achieves a lossless speedup ratio ranging from 2.91x to 3.51x when tested on the Vicuna and LLaMA2-Chat model series. These results outstrip existing speculative decoding methods for LLMs, including Eagle, Medusa, Lookahead, SPS, and PLD, while maintaining a compact drafter architecture equivalent to merely two Transformer layers.
Authors: Konstantin Avrachenkov, Vivek S. Borkar, Pratik Shah
Abstract: We study the Lagrangian Index Policy (LIP) for restless multi-armed bandits with long-run average reward. In particular, we compare the performance of LIP with the performance of the Whittle Index Policy (WIP), both heuristic policies known to be asymptotically optimal under certain natural conditions. Even though in most cases their performances are very similar, in the cases when WIP shows bad performance, LIP continues to perform very well. We then propose reinforcement learning algorithms, both tabular and NN-based, to obtain online learning schemes for LIP in the model-free setting. The proposed reinforcement learning schemes for LIP requires significantly less memory than the analogous scheme for WIP. We calculate analytically the Lagrangian index for the restart model, which describes the optimal web crawling and the minimization of the weighted age of information. We also give a new proof of asymptotic optimality in case of homogeneous bandits as the number of arms goes to infinity, based on exchangeability and de Finetti's theorem.
Authors: Zijin Liu, Xiang Zhao, You Song
Abstract: Spatiotemporal data imputation plays a crucial role in various fields such as traffic flow monitoring, air quality assessment, and climate prediction. However, spatiotemporal data collected by sensors often suffer from temporal incompleteness, and the sparse and uneven distribution of sensors leads to missing data in the spatial dimension. Among existing methods, autoregressive approaches are prone to error accumulation, while simple conditional diffusion models fail to adequately capture the spatiotemporal relationships between observed and missing data. To address these issues, we propose a novel two-stage Refined Diffusion Probability Impuation (RDPI) framework based on an initial network and a conditional diffusion model. In the initial stage, deterministic imputation methods are used to generate preliminary estimates of the missing data. In the refinement stage, residuals are treated as the diffusion target, and observed values are innovatively incorporated into the forward process. This results in a conditional diffusion model better suited for spatiotemporal data imputation, bridging the gap between the preliminary estimates and the true values. Experiments on multiple datasets demonstrate that RDPI not only achieves state-of-the-art imputation accuracy but also significantly reduces sampling computational costs.
Authors: Tobias Becher, Simon Torka
Abstract: Traditional rule-based cybersecurity systems have proven highly effective against known malware threats. However, they face challenges in detecting novel threats. To address this issue, emerging cybersecurity systems are incorporating AI techniques, specifically deep-learning algorithms, to enhance their ability to detect incidents, analyze alerts, and respond to events. While these techniques offer a promising approach to combating dynamic security threats, they often require significant computational resources. Therefore, frameworks that incorporate AI-based cybersecurity mechanisms need to support the use of GPUs to ensure optimal performance. Many cybersecurity framework vendors do not provide sufficiently detailed information about their implementation, making it difficult to assess the techniques employed and their effectiveness. This study aims to overcome this limitation by providing an overview of the most used cybersecurity frameworks that utilize AI techniques, specifically focusing on frameworks that provide comprehensive information about their implementation. Our primary objective is to identify the deep-learning techniques employed by these frameworks and evaluate their support for GPU acceleration. We have identified a total of \emph{two} deep-learning algorithms that are utilized by \emph{three} out of 38 selected cybersecurity frameworks. Our findings aim to assist in selecting open-source cybersecurity frameworks for future research and assessing any discrepancies between deep-learning techniques used in theory and practice.
Authors: Robert Aufschl\"ager, Sebastian Wilhelm, Michael Heigl, Martin Schramm
Abstract: This work introduces ClustEm4Ano, an anonymization pipeline that can be used for generalization and suppression-based anonymization of nominal textual tabular data. It automatically generates value generalization hierarchies (VGHs) that, in turn, can be used to generalize attributes in quasi-identifiers. The pipeline leverages embeddings to generate semantically close value generalizations through iterative clustering. We applied KMeans and Hierarchical Agglomerative Clustering on $13$ different predefined text embeddings (both open and closed-source (via APIs)). Our approach is experimentally tested on a well-known benchmark dataset for anonymization: The UCI Machine Learning Repository's Adult dataset. ClustEm4Ano supports anonymization procedures by offering more possibilities compared to using arbitrarily chosen VGHs. Experiments demonstrate that these VGHs can outperform manually constructed ones in terms of downstream efficacy (especially for small $k$-anonymity ($2 \leq k \leq 30$)) and therefore can foster the quality of anonymized datasets. Our implementation is made public.
Authors: Yiming Ji, Kaijie Yun, Yang Liu, Zongwu Xie, Hong Liu
Abstract: Q-learning is a widely used reinforcement learning technique for solving path planning problems. It primarily involves the interaction between an agent and its environment, enabling the agent to learn an optimal strategy that maximizes cumulative rewards. Although many studies have reported the effectiveness of Q-learning, it still faces slow convergence issues in practical applications. To address this issue, we propose the NDR-QL method, which utilizes neural network outputs as heuristic information to accelerate the convergence process of Q-learning. Specifically, we improved the dual-output neural network model by introducing a start-end channel separation mechanism and enhancing the feature fusion process. After training, the proposed NDR model can output a narrowly focused optimal probability distribution, referred to as the guideline, and a broadly distributed suboptimal distribution, referred to as the region. Subsequently, based on the guideline prediction, we calculate the continuous reward function for the Q-learning method, and based on the region prediction, we initialize the Q-table with a bias. We conducted training, validation, and path planning simulation experiments on public datasets. The results indicate that the NDR model outperforms previous methods by up to 5\% in prediction accuracy. Furthermore, the proposed NDR-QL method improves the convergence speed of the baseline Q-learning method by 90\% and also surpasses the previously improved Q-learning methods in path quality metrics.
Authors: Huachao Yan, Kailing Guo, Shiwei Song, Yihai Dai, Xiaoqiang Wei, Xiaofen Xing, Xiangmin Xu
Abstract: Diagnosing seizure onset zone (SOZ) is a challenge in neurosurgery, where stereoelectroencephalography (sEEG) serves as a critical technique. In sEEG SOZ identification, the existing studies focus solely on the intra-patient representation of epileptic information, overlooking the general features of epilepsy across patients and feature interdependencies between feature elements in each contact site. In order to address the aforementioned challenges, we propose the shared attention-based autoencoder (sATAE). sATAE is trained by sEEG data across all patients, with attention blocks introduced to enhance the representation of interdependencies between feature elements. Considering the spatial diversity of sEEG across patients, we introduce graph-based method for identification SOZ of each patient. However, the current graph-based methods for sEEG SOZ identification rely exclusively on static graphs to model epileptic networks. Inspired by the finding of neuroscience that epileptic network is intricately characterized by the interplay of sophisticated equilibrium between fluctuating and stable states, we design the hierarchical fusion-based graph convolution network (HFGCN) to identify the SOZ. HFGCN integrates the dynamic and static characteristics of epileptic networks through hierarchical weighting across different hierarchies, facilitating a more comprehensive learning of epileptic features and enriching node information for sEEG SOZ identification. Combining sATAE and HFGCN, we perform comprehensive experiments with sATAE-HFGCN on the self-build sEEG dataset, which includes sEEG data from 17 patients with temporal lobe epilepsy. The results show that our method, sATAE-HFGCN, achieves superior performance for identifying the SOZ of each patient, effectively addressing the aforementioned challenges, providing an efficient solution for sEEG-based SOZ identification.
Authors: Mingfei Cheng, Yuan Zhou, Xiaofei Xie
Abstract: Simulation-based testing plays a critical role in evaluating the safety and reliability of autonomous driving systems (ADSs). However, one of the key challenges in ADS testing is the complexity of preparing and configuring simulation environments, particularly in terms of compatibility and stability between the simulator and the ADS. This complexity often results in researchers dedicating significant effort to customize their own environments, leading to disparities in development platforms and underlying systems. Consequently, reproducing and comparing these methodologies on a unified ADS testing platform becomes difficult. To address these challenges, we introduce DriveTester, a unified simulation-based testing platform built on Apollo, one of the most widely used open-source, industrial-level ADS platforms. DriveTester provides a consistent and reliable environment, integrates a lightweight traffic simulator, and incorporates various state-of-the-art ADS testing techniques. This enables researchers to efficiently develop, test, and compare their methods within a standardized platform, fostering reproducibility and comparison across different ADS testing approaches. The code is available: https://github.com/MingfeiCheng/DriveTester.
Authors: Ryo Suzuki, Mar Gonzalez-Franco, Misha Sra, David Lindlbauer
Abstract: This workshop brings together experts and practitioners from augmented reality (AR) and artificial intelligence (AI) to shape the future of AI-in-the-loop everyday AR experiences. With recent advancements in both AR hardware and AI capabilities, we envision that everyday AR -- always-available and seamlessly integrated into users' daily environments -- is becoming increasingly feasible. This workshop will explore how AI can drive such everyday AR experiences. We discuss a range of topics, including adaptive and context-aware AR, generative AR content creation, always-on AI assistants, AI-driven accessible design, and real-world-oriented AI agents. Our goal is to identify the opportunities and challenges in AI-enabled AR, focusing on creating novel AR experiences that seamlessly blend the digital and physical worlds. Through the workshop, we aim to foster collaboration, inspire future research, and build a community to advance the research field of AI-enhanced AR.
Authors: Wenyu Zhang, Wei En Ng, Lixin Ma, Yuwen Wang, Jungqi Zhao, Boyang Li, Lu Wang
Abstract: Current vision-language models may incorporate single-dimensional spatial cues, such as depth, object boundary, and basic spatial directions (e.g. left, right, front, back), yet often lack the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications. To address this gap, we develop SPHERE (Spatial Perception and Hierarchical Evaluation of REasoning), a hierarchical evaluation framework with a new human-annotated dataset to pinpoint model strengths and weaknesses, advancing from single-skill tasks to multi-skill tasks, and ultimately to complex reasoning tasks that require the integration of multiple spatial and visual cues with logical reasoning. Benchmark evaluation of state-of-the-art open-source models reveal significant shortcomings, especially in the abilities to understand distance and proximity, to reason from both allocentric and egocentric viewpoints, and to perform complex reasoning in a physical context. This work underscores the need for more advanced approaches to spatial understanding and reasoning, paving the way for improvements in vision-language models and their alignment with human-like spatial capabilities. The dataset will be open-sourced upon publication.
Authors: Ruixuan Miao, Xu Lu, Cong Tian, Bin Yu, Zhenhua Duan
Abstract: The commonly used Reinforcement Learning (RL) model, MDPs (Markov Decision Processes), has a basic premise that rewards depend on the current state and action only. However, many real-world tasks are non-Markovian, which has long-term memory and dependency. The reward sparseness problem is further amplified in non-Markovian scenarios. Hence learning a non-Markovian task (NMT) is inherently more difficult than learning a Markovian one. In this paper, we propose a novel \textbf{Par}allel and \textbf{Mod}ular RL framework, ParMod, specifically for learning NMTs specified by temporal logic. With the aid of formal techniques, the NMT is modulaized into a series of sub-tasks based on the automaton structure (equivalent to its temporal logic counterpart). On this basis, sub-tasks will be trained by a group of agents in a parallel fashion, with one agent handling one sub-task. Besides parallel training, the core of ParMod lies in: a flexible classification method for modularizing the NMT, and an effective reward shaping method for improving the sample efficiency. A comprehensive evaluation is conducted on several challenging benchmark problems with respect to various metrics. The experimental results show that ParMod achieves superior performance over other relevant studies. Our work thus provides a good synergy among RL, NMT and temporal logic.
Authors: Qi Zhou, Tianlin Li, Qing Guo, Dongxia Wang, Yun Lin, Yang Liu, Jin Song Dong
Abstract: Recent studies have raised significant concerns regarding the vulnerability of Large Vision Language Models (LVLMs) to maliciously injected or perturbed input images, which can mislead their responses. Existing defense methods show that such vision attacks are sensitive to image modifications especially cropping, using majority voting across responses of modified images as corrected responses. However, these modifications often result in partial images and distort the semantics, which reduces response quality on clean images after voting. Instead of directly using responses from partial images for voting, we investigate using them to supervise the LVLM's responses to the original images. We propose a black-box, training-free method called DPS (Defense through Partial-Perception Supervision). In this approach, the model is prompted using the responses generated by a model that perceives only a partial image. With DPS, the model can adjust its response based on partial image understanding when under attack, while confidently maintaining its original response for clean input. Our findings show that the weak model can supervise the strong model: when faced with an attacked input, the strong model becomes less confident and adjusts its response based on the weak model's partial understanding, effectively defending against the attack. With clean input, it confidently maintains its original response. Empirical experiments show our method outperforms the baseline, cutting the average attack success rate by 76.3% across six datasets on three popular models.
Authors: Mukai Li, Lei Li, Shansan Gong, Qi Liu
Abstract: Visual Language Models (VLMs) demonstrate impressive capabilities in processing multimodal inputs, yet applications such as visual agents, which require handling multiple images and high-resolution videos, demand enhanced long-range modeling. Moreover, existing open-source VLMs lack systematic exploration into extending their context length, and commercial models often provide limited details. To tackle this, we aim to establish an effective solution that enhances long context performance of VLMs while preserving their capacities in short context scenarios. Towards this goal, we make the best design choice through extensive experiment settings from data curation to context window extending and utilizing: (1) we analyze data sources and length distributions to construct ETVLM - a data recipe to balance the performance across scenarios; (2) we examine existing position extending methods, identify their limitations and propose M-RoPE++ as an enhanced approach; we also choose to solely instruction-tune the backbone with mixed-source data; (3) we discuss how to better utilize extended context windows and propose hybrid-resolution training. Built on the Qwen-VL series model, we propose Giraffe, which is effectively extended to 128K lengths. Evaluated on extensive long context VLM benchmarks such as VideoMME and Viusal Haystacks, our Giraffe achieves state-of-the-art performance among similarly sized open-source long VLMs and is competitive with commercial model GPT-4V. We will open-source the code, data, and models.
Authors: Wenqi Huang, Veronika Spieker, Siying Xu, Gastao Cruz, Claudia Prieto, Julia Schnabel, Kerstin Hammernik, Thomas Kuestner, Daniel Rueckert
Abstract: Conventional cardiac cine MRI methods rely on retrospective gating, which limits temporal resolution and the ability to capture continuous cardiac dynamics, particularly in patients with arrhythmias and beat-to-beat variations. To address these challenges, we propose a reconstruction framework based on subspace implicit neural representations for real-time cardiac cine MRI of continuously sampled radial data. This approach employs two multilayer perceptrons to learn spatial and temporal subspace bases, leveraging the low-rank properties of cardiac cine MRI. Initialized with low-resolution reconstructions, the networks are fine-tuned using spoke-specific loss functions to recover spatial details and temporal fidelity. Our method directly utilizes the continuously sampled radial k-space spokes during training, thereby eliminating the need for binning and non-uniform FFT. This approach achieves superior spatial and temporal image quality compared to conventional binned methods at the acceleration rate of 10 and 20, demonstrating potential for high-resolution imaging of dynamic cardiac events and enhancing diagnostic capability.
Authors: Nan Li, Bo Kang, Tijl De Bie
Abstract: Text classification with hierarchical labels is a prevalent and challenging task in natural language processing. Examples include assigning ICD codes to patient records, tagging patents into IPC classes, assigning EUROVOC descriptors to European legal texts, and more. Despite its widespread applications, a comprehensive understanding of state-of-the-art methods across different domains has been lacking. In this paper, we provide the first comprehensive cross-domain overview with empirical analysis of state-of-the-art methods. We propose a unified framework that positions each method within a common structure to facilitate research. Our empirical analysis yields key insights and guidelines, confirming the necessity of learning across different research areas to design effective methods. Notably, under our unified evaluation pipeline, we achieved new state-of-the-art results by applying techniques beyond their original domains.
Authors: Debajyoti Mazumder, Aakash Kumar, Jasabanta Patro
Abstract: In this paper, we reported our experiments with various strategies to improve code-mixed humour and sarcasm detection. We did all of our experiments for Hindi-English code-mixed scenario, as we have the linguistic expertise for the same. We experimented with three approaches, namely (i) native sample mixing, (ii) multi-task learning (MTL), and (iii) prompting very large multilingual language models (VMLMs). In native sample mixing, we added monolingual task samples in code-mixed training sets. In MTL learning, we relied on native and code-mixed samples of a semantically related task (hate detection in our case). Finally, in our third approach, we evaluated the efficacy of VMLMs via few-shot context prompting. Some interesting findings we got are (i) adding native samples improved humor (raising the F1-score up to 6.76%) and sarcasm (raising the F1-score up to 8.64%) detection, (ii) training MLMs in an MTL framework boosted performance for both humour (raising the F1-score up to 10.67%) and sarcasm (increment up to 12.35% in F1-score) detection, and (iii) prompting VMLMs couldn't outperform the other approaches. Finally, our ablation studies and error analysis discovered the cases where our model is yet to improve. We provided our code for reproducibility.
Authors: Shoukun Sun, Min Xian, Tiankai Yao, Fei Xu, Luca Capriotti
Abstract: Producing large images using small diffusion models is gaining increasing popularity, as the cost of training large models could be prohibitive. A common approach involves jointly generating a series of overlapped image patches and obtaining large images by merging adjacent patches. However, results from existing methods often exhibit obvious artifacts, e.g., seams and inconsistent objects and styles. To address the issues, we proposed Guided Fusion (GF), which mitigates the negative impact from distant image regions by applying a weighted average to the overlapping regions. Moreover, we proposed Variance-Corrected Fusion (VCF), which corrects data variance at post-averaging, generating more accurate fusion for the Denoising Diffusion Probabilistic Model. Furthermore, we proposed a one-shot Style Alignment (SA), which generates a coherent style for large images by adjusting the initial input noise without adding extra computational burden. Extensive experiments demonstrated that the proposed fusion methods improved the quality of the generated image significantly. As a plug-and-play module, the proposed method can be widely applied to enhance other fusion-based methods for large image generation.
Authors: Chengzhou Yu (South China University of Technology), Huihui Fang (Pazhou Laboratory), Hongqiu Wang (The Hong Kong University of Science,Technology), Ting Deng (South China University of Technology), Qing Du (South China University of Technology), Yanwu Xu (South China University of Technology), Weihua Yang (Shenzhen Eye Hospital)
Abstract: Fundus imaging is a critical tool in ophthalmology, with different imaging modalities offering unique advantages. For instance, fundus fluorescein angiography (FFA) can accurately identify eye diseases. However, traditional invasive FFA involves the injection of sodium fluorescein, which can cause discomfort and risks. Generating corresponding FFA images from non-invasive fundus images holds significant practical value but also presents challenges. First, limited datasets constrain the performance and effectiveness of models. Second, previous studies have primarily focused on generating FFA for single diseases or single modalities, often resulting in poor performance for patients with various ophthalmic conditions. To address these issues, we propose a novel latent diffusion model-based framework, Diffusion, which introduces a fine-tuning protocol to overcome the challenge of limited medical data and unleash the generative capabilities of diffusion models. Furthermore, we designed a new approach to tackle the challenges of generating across different modalities and disease types. On limited datasets, our framework achieves state-of-the-art results compared to existing methods, offering significant potential to enhance ophthalmic diagnostics and patient care. Our code will be released soon to support further research in this field.
Authors: Amrapali Pednekar, Alvaro Garrido, Yara Khaluf, Pieter Simoens
Abstract: Time perception research has advanced significantly over the years. However, some areas remain largely unexplored. This study addresses two such under-explored areas in timing research: (1) A quantitative analysis of time perception at an individual level, and (2) Time perception in an ecological setting. In this context, we trained a machine learning model to predict the direction of change in an individual's time production. The model's training data was collected using an ecologically valid setup. We moved closer to an ecological setting by conducting an online experiment with 995 participants performing a time production task that used naturalistic videos (no audio) as stimuli. The model achieved an accuracy of 61%. This was 10 percentage points higher than the baseline models derived from cognitive theories of timing. The model performed equally well on new data from a second experiment, providing evidence of its generalization capabilities. The model's output analysis revealed that it also contained information about the magnitude of change in time production. The predictions were further analysed at both population and individual level. It was found that a participant's previous timing performance played a significant role in determining the direction of change in time production. By integrating attentional-gate theories from timing research with feature importance techniques from machine learning, we explained model predictions using cognitive theories of timing. The model and findings from this study have potential applications in systems involving human-computer interactions where understanding and predicting changes in user's time perception can enable better user experience and task performance.
Authors: Shiping Ge, Qiang Chen, Zhiwei Jiang, Yafeng Yin, Liu Qin, Ziyao Chen, Qing Gu
Abstract: Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event, as the relevant supervision is unavailable. Existing methods rely on explicit alignment constraints between event locations and captions, which involve complex event proposal procedures during both training and inference. To tackle this problem, we propose a novel implicit location-caption alignment paradigm by complementary masking, which simplifies the complex event proposal and localization process while maintaining effectiveness. Specifically, our model comprises two components: a dual-mode video captioning module and a mask generation module. The dual-mode video captioning module captures global event information and generates descriptive captions, while the mask generation module generates differentiable positive and negative masks for localizing the events. These masks enable the implicit alignment of event locations and captions by ensuring that captions generated from positively and negatively masked videos are complementary, thereby forming a complete video description. In this way, even under weak supervision, the event location and event caption can be aligned implicitly. Extensive experiments on the public datasets demonstrate that our method outperforms existing weakly-supervised methods and achieves competitive results compared to fully-supervised methods.
Authors: Yiheng Li, Yang Yang, Zhen Lei
Abstract: In radar-camera 3D object detection, the radar point clouds are sparse and noisy, which causes difficulties in fusing camera and radar modalities. To solve this, we introduce a novel query-based detection method named Radar-Camera Transformer (RCTrans). Specifically, we first design a Radar Dense Encoder to enrich the sparse valid radar tokens, and then concatenate them with the image tokens. By doing this, we can fully explore the 3D information of each interest region and reduce the interference of empty tokens during the fusing stage. We then design a Pruning Sequential Decoder to predict 3D boxes based on the obtained tokens and random initialized queries. To alleviate the effect of elevation ambiguity in radar point clouds, we gradually locate the position of the object via a sequential fusion structure. It helps to get more precise and flexible correspondences between tokens and queries. A pruning training strategy is adopted in the decoder, which can save much time during inference and inhibit queries from losing their distinctiveness. Extensive experiments on the large-scale nuScenes dataset prove the superiority of our method, and we also achieve new state-of-the-art radar-camera 3D detection results. Our implementation is available at https://github.com/liyih/RCTrans.
Authors: James Prather, Brent N. Reeves, Paul Denny, Juho Leinonen, Stephen MacNeil, Andrew Luxton-Reilly, Jo\~ao Orvalho, Amin Alipour, Ali Alfageeh, Thezyrie Amarouche, Bailey Kimmel, Jared Wright, Musa Blake, Gweneth Barbre
Abstract: Non-native English speakers (NNES) face multiple barriers to learning programming. These barriers can be obvious, such as the fact that programming language syntax and instruction are often in English, or more subtle, such as being afraid to ask for help in a classroom full of native English speakers. However, these barriers are frustrating because many NNES students know more about programming than they can articulate in English. Advances in generative AI (GenAI) have the potential to break down these barriers because state of the art models can support interactions in multiple languages. Moreover, recent work has shown that GenAI can be highly accurate at code generation and explanation. In this paper, we provide the first exploration of NNES students prompting in their native languages (Arabic, Chinese, and Portuguese) to generate code to solve programming problems. Our results show that students are able to successfully use their native language to solve programming problems, but not without some difficulty specifying programming terminology and concepts. We discuss the challenges they faced, the implications for practice in the short term, and how this might transform computing education globally in the long term.
Authors: Ziqi Qiu, Jianxing Yu, Yufeng Zhang, Hanjiang Lai, Yanghui Rao, Qinliang Su, Jian Yin
Abstract: This paper focuses on sarcasm detection, which aims to identify whether given statements convey criticism, mockery, or other negative sentiment opposite to the literal meaning. To detect sarcasm, humans often require a comprehensive understanding of the semantics in the statement and even resort to external commonsense to infer the fine-grained incongruity. However, existing methods lack commonsense inferential ability when they face complex real-world scenarios, leading to unsatisfactory performance. To address this problem, we propose a novel framework for sarcasm detection, which conducts incongruity reasoning based on commonsense augmentation, called EICR. Concretely, we first employ retrieval-augmented large language models to supplement the missing but indispensable commonsense background knowledge. To capture complex contextual associations, we construct a dependency graph and obtain the optimized topology via graph refinement. We further introduce an adaptive reasoning skeleton that integrates prior rules to extract sentiment-inconsistent subgraphs explicitly. To eliminate the possible spurious relations between words and labels, we employ adversarial contrastive learning to enhance the robustness of the detector. Experiments conducted on five datasets demonstrate the effectiveness of EICR.
Authors: Jinxiang Xie, Yilin Li, Xunjian Yin, Xiaojun Wan
Abstract: Evaluating the performance of Grammatical Error Correction (GEC) models has become increasingly challenging, as large language model (LLM)-based GEC systems often produce corrections that diverge from provided gold references. This discrepancy undermines the reliability of traditional reference-based evaluation metrics. In this study, we propose a novel evaluation framework for GEC models, DSGram, integrating Semantic Coherence, Edit Level, and Fluency, and utilizing a dynamic weighting mechanism. Our framework employs the Analytic Hierarchy Process (AHP) in conjunction with large language models to ascertain the relative importance of various evaluation criteria. Additionally, we develop a dataset incorporating human annotations and LLM-simulated sentences to validate our algorithms and fine-tune more cost-effective models. Experimental results indicate that our proposed approach enhances the effectiveness of GEC model evaluations.
Authors: Yuyuan Li, Xiaohua Feng, Chaochao Chen, Qiang Yang
Abstract: Recommender systems have become increasingly influential in shaping user behavior and decision-making, highlighting their growing impact in various domains. Meanwhile, the widespread adoption of machine learning models in recommender systems has raised significant concerns regarding user privacy and security. As compliance with privacy regulations becomes more critical, there is a pressing need to address the issue of recommendation unlearning, i.e., eliminating the memory of specific training data from the learned recommendation models. Despite its importance, traditional machine unlearning methods are ill-suited for recommendation unlearning due to the unique challenges posed by collaborative interactions and model parameters. This survey offers a comprehensive review of the latest advancements in recommendation unlearning, exploring the design principles, challenges, and methodologies associated with this emerging field. We provide a unified taxonomy that categorizes different recommendation unlearning approaches, followed by a summary of widely used benchmarks and metrics for evaluation. By reviewing the current state of research, this survey aims to guide the development of more efficient, scalable, and robust recommendation unlearning techniques. Furthermore, we identify open research questions in this field, which could pave the way for future innovations not only in recommendation unlearning but also in a broader range of unlearning tasks across different machine learning applications.
Authors: Xiaxin Zhu, Fangming Guo, Xianlei Long, Qingyi Gu, Chao Chen, Fuqiang Gu
Abstract: Event-based semantic segmentation has great potential in autonomous driving and robotics due to the advantages of event cameras, such as high dynamic range, low latency, and low power cost. Unfortunately, current artificial neural network (ANN)-based segmentation methods suffer from high computational demands, the requirements for image frames, and massive energy consumption, limiting their efficiency and application on resource-constrained edge/mobile platforms. To address these problems, we introduce SLTNet, a spike-driven lightweight transformer-based network designed for event-based semantic segmentation. Specifically, SLTNet is built on efficient spike-driven convolution blocks (SCBs) to extract rich semantic features while reducing the model's parameters. Then, to enhance the long-range contextural feature interaction, we propose novel spike-driven transformer blocks (STBs) with binary mask operations. Based on these basic blocks, SLTNet employs a high-efficiency single-branch architecture while maintaining the low energy consumption of the Spiking Neural Network (SNN). Finally, extensive experiments on DDD17 and DSEC-Semantic datasets demonstrate that SLTNet outperforms state-of-the-art (SOTA) SNN-based methods by at least 7.30% and 3.30% mIoU, respectively, with extremely 5.48x lower energy consumption and 1.14x faster inference speed.
Authors: Yuxi Sun, Wei Gao, Jing Ma, Hongzhan Lin, Ziyang Luo, Wenxuan Zhang
Abstract: With the rise and widespread use of Large Language Models (LLMs), ensuring their safety is crucial to prevent harm to humans and promote ethical behaviors. However, directly assessing value valence (i.e., support or oppose) by leveraging large-scale data training is untrustworthy and inexplainable. We assume that emulating humans to rely on social norms to make moral decisions can help LLMs understand and predict moral judgment. However, capturing human values remains a challenge, as multiple related norms might conflict in specific contexts. Consider norms that are upheld by the majority and promote the well-being of society are more likely to be accepted and widely adopted (e.g., "don't cheat,"). Therefore, it is essential for LLM to identify the appropriate norms for a given scenario before making moral decisions. To this end, we introduce a novel moral judgment approach called \textit{ClarityEthic} that leverages LLMs' reasoning ability and contrastive learning to uncover relevant social norms for human actions from different perspectives and select the most reliable one to enhance judgment accuracy. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in moral judgment tasks. Moreover, human evaluations confirm that the generated social norms provide plausible explanations that support the judgments. This suggests that modeling human moral judgment with the emulating humans moral strategy is promising for improving the ethical behaviors of LLMs.
Authors: Qingqing Fang, Qinliang Su, Wenxi Lv, Wenchao Xu, Jianxing Yu
Abstract: Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the anomalies. However, due to the powerful modeling and generalization ability of neural networks, some anomalies can also be well reconstructed, resulting in unsatisfactory detection and localization accuracy. In this paper, a small coarsely-labeled anomaly dataset is first collected. Then, a coarse-knowledge-aware adversarial learning method is developed to align the distribution of reconstructed features with that of normal features. The alignment can effectively suppress the auto-encoder's reconstruction ability on anomalies and thus improve the detection accuracy. Considering that anomalies often only occupy very small areas in anomalous images, a patch-level adversarial learning strategy is further developed. Although no patch-level anomalous information is available, we rigorously prove that by simply viewing any patch features from anomalous images as anomalies, the proposed knowledge-aware method can also align the distribution of reconstructed patch features with the normal ones. Experimental results on four medical datasets and two industrial datasets demonstrate the effectiveness of our method in improving the detection and localization performance.
Authors: Jiaqi Wang, Liutao Yu, Liwei Huang, Chenlin Zhou, Han Zhang, Zhenxi Song, Min Zhang, Zhengyu Ma, Zhiguo Zhang
Abstract: The intrinsic dynamics and event-driven nature of spiking neural networks (SNNs) make them excel in processing temporal information by naturally utilizing embedded time sequences as time steps. Recent studies adopting this approach have demonstrated SNNs' effectiveness in speech command recognition, achieving high performance by employing large time steps for long time sequences. However, the large time steps lead to increased deployment burdens for edge computing applications. Thus, it is important to balance high performance and low energy consumption when detecting temporal patterns in edge devices. Our solution comprises two key components. 1). We propose a high-performance fully spike-driven framework termed SpikeSCR, characterized by a global-local hybrid structure for efficient representation learning, which exhibits long-term learning capabilities with extended time steps. 2). To further fully embrace low energy consumption, we propose an effective knowledge distillation method based on curriculum learning (KDCL), where valuable representations learned from the easy curriculum are progressively transferred to the hard curriculum with minor loss, striking a trade-off between power efficiency and high performance. We evaluate our method on three benchmark datasets: the Spiking Heidelberg Dataset (SHD), the Spiking Speech Commands (SSC), and the Google Speech Commands (GSC) V2. Our experimental results demonstrate that SpikeSCR outperforms current state-of-the-art (SOTA) methods across these three datasets with the same time steps. Furthermore, by executing KDCL, we reduce the number of time steps by 60% and decrease energy consumption by 54.8% while maintaining comparable performance to recent SOTA results. Therefore, this work offers valuable insights for tackling temporal processing challenges with long time sequences in edge neuromorphic computing systems.
Authors: Ziheng Qiao, Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang
Abstract: One key characteristic of the Chinese spelling check (CSC) task is that incorrect characters are usually similar to the correct ones in either phonetics or glyph. To accommodate this, previous works usually leverage confusion sets, which suffer from two problems, i.e., difficulty in determining which character pairs to include and lack of probabilities to distinguish items in the set. In this paper, we propose a light-weight plug-and-play DISC (i.e., decoding intervention with similarity of characters) module for CSC models.DISC measures phonetic and glyph similarities between characters and incorporates this similarity information only during the inference phase. This method can be easily integrated into various existing CSC models, such as ReaLiSe, SCOPE, and ReLM, without additional training costs. Experiments on three CSC benchmarks demonstrate that our proposed method significantly improves model performance, approaching and even surpassing the current state-of-the-art models.
Authors: Jinhao Jiang, Jiayi Chen, Junyi Li, Ruiyang Ren, Shijie Wang, Wayne Xin Zhao, Yang Song, Tao Zhang
Abstract: Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. Despite the successes of chain-of-thought and tree-based search methods, they mainly depend on the internal knowledge of LLMs to search over intermediate reasoning steps, limited to dealing with simple tasks involving fewer reasoning steps. In this paper, we propose \textbf{RAG-Star}, a novel RAG approach that integrates the retrieved information to guide the tree-based deliberative reasoning process that relies on the inherent knowledge of LLMs. By leveraging Monte Carlo Tree Search, RAG-Star iteratively plans intermediate sub-queries and answers for reasoning based on the LLM itself. To consolidate internal and external knowledge, we propose an retrieval-augmented verification that utilizes query- and answer-aware reward modeling to provide feedback for the inherent reasoning of LLMs. Our experiments involving Llama-3.1-8B-Instruct and GPT-4o demonstrate that RAG-Star significantly outperforms previous RAG and reasoning methods.
Authors: Nicholas Kiefer, Arvid Weyrauch, Muhammed \"Oz, Achim Streit, Markus G\"otz, Charlotte Debus
Abstract: The current landscape in time-series forecasting is dominated by Transformer-based models. Their high parameter count and corresponding demand in computational resources pose a challenge to real-world deployment, especially for commercial and scientific applications with low-power embedded devices. Pruning is an established approach to reduce neural network parameter count and save compute. However, the implications and benefits of pruning Transformer-based models for time series forecasting are largely unknown. To close this gap, we provide a comparative benchmark study by evaluating unstructured and structured pruning on various state-of-the-art multivariate time series models. We study the effects of these pruning strategies on model predictive performance and computational aspects like model size, operations, and inference time. Our results show that certain models can be pruned even up to high sparsity levels, outperforming their dense counterpart. However, fine-tuning pruned models is necessary. Furthermore, we demonstrate that even with corresponding hardware and software support, structured pruning is unable to provide significant time savings.
Authors: Zhongjie Duan, Qianyi Zhao, Cen Chen, Daoyuan Chen, Wenmeng Zhou, Yaliang Li, Yingda Chen
Abstract: The emergence of diffusion models has significantly advanced image synthesis. The recent studies of model interaction and self-corrective reasoning approach in large language models offer new insights for enhancing text-to-image models. Inspired by these studies, we propose a novel method called ArtAug for enhancing text-to-image models in this paper. To the best of our knowledge, ArtAug is the first one that improves image synthesis models via model interactions with understanding models. In the interactions, we leverage human preferences implicitly learned by image understanding models to provide fine-grained suggestions for image synthesis models. The interactions can modify the image content to make it aesthetically pleasing, such as adjusting exposure, changing shooting angles, and adding atmospheric effects. The enhancements brought by the interaction are iteratively fused into the synthesis model itself through an additional enhancement module. This enables the synthesis model to directly produce aesthetically pleasing images without any extra computational cost. In the experiments, we train the ArtAug enhancement module on existing text-to-image models. Various evaluation metrics consistently demonstrate that ArtAug enhances the generative capabilities of text-to-image models without incurring additional computational costs. The source code and models will be released publicly.
Authors: Xing Liufu, Chaolei Tan, Xiaotong Lin, Yonggang Qi, Jinxuan Li, Jian-Fang Hu
Abstract: Edge labels are typically at various granularity levels owing to the varying preferences of annotators, thus handling the subjectivity of per-pixel labels has been a focal point for edge detection. Previous methods often employ a simple voting strategy to diminish such label uncertainty or impose a strong assumption of labels with a pre-defined distribution, e.g., Gaussian. In this work, we unveil that the segment anything model (SAM) provides strong prior knowledge to model the uncertainty in edge labels. Our key insight is that the intermediate SAM features inherently correspond to object edges at various granularities, which reflects different edge options due to uncertainty. Therefore, we attempt to align uncertainty with granularity by regressing intermediate SAM features from different layers to object edges at multi-granularity levels. In doing so, the model can fully and explicitly explore diverse ``uncertainties'' in a data-driven fashion. Specifically, we inject a lightweight module (~ 1.5% additional parameters) into the frozen SAM to progressively fuse and adapt its intermediate features to estimate edges from coarse to fine. It is crucial to normalize the granularity level of human edge labels to match their innate uncertainty. For this, we simply perform linear blending to the real edge labels at hand to create pseudo labels with varying granularities. Consequently, our uncertainty-aligned edge detector can flexibly produce edges at any desired granularity (including an optimal one). Thanks to SAM, our model uniquely demonstrates strong generalizability for cross-dataset edge detection. Extensive experimental results on BSDS500, Muticue and NYUDv2 validate our model's superiority.
Authors: Zixiang Li, Yue Song, Renshuai Tao, Xiaohong Jia, Yao Zhao, Wei Wang
Abstract: Although diffusion models have achieved remarkable success in the field of image generation, their latent space remains under-explored. Current methods for identifying semantics within latent space often rely on external supervision, such as textual information and segmentation masks. In this paper, we propose a method to identify semantic attributes in the latent space of pre-trained diffusion models without any further training. By projecting the Jacobian of the targeted semantic region into a low-dimensional subspace which is orthogonal to the non-masked regions, our approach facilitates precise semantic discovery and control over local masked areas, eliminating the need for annotations. We conducted extensive experiments across multiple datasets and various architectures of diffusion models, achieving state-of-the-art performance. In particular, for some specific face attributes, the performance of our proposed method even surpasses that of supervised approaches, demonstrating its superior ability in editing local image properties.
Authors: Zihui Cheng, Qiguang Chen, Jin Zhang, Hao Fei, Xiaocheng Feng, Wanxiang Che, Min Li, Libo Qin
Abstract: Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning. Despite these successes, current benchmarks still follow a traditional paradigm with multi-modal input and text-modal output, which leads to significant drawbacks such as missing visual operations and vague expressions. Motivated by this, we introduce a novel Chain of Multi-modal Thought (CoMT) benchmark to address these limitations. Different from the traditional MCoT benchmark, CoMT requires both multi-modal input and multi-modal reasoning output, aiming to mimic human-like reasoning that inherently integrates visual operation. Specifically, CoMT consists of four categories: (1) Visual Creation, (2) Visual Deletion, (3) Visual Update, and (4) Visual Selection to comprehensively explore complex visual operations and concise expression in real scenarios. We evaluate various LVLMs and strategies on CoMT, revealing some key insights into the capabilities and limitations of the current approaches. We hope that CoMT can inspire more research on introducing multi-modal generation into the reasoning process.
Authors: He Yu, Jing Liu
Abstract: Community structures are critical for understanding the mesoscopic organization of networks, bridging local and global patterns. While methods such as DeepWalk and node2vec capture local positional information through random walks, they fail to preserve community structures. Other approaches like modularized nonnegative matrix factorization and evolutionary algorithms address this gap but are computationally expensive and unsuitable for large-scale networks. To overcome these limitations, we propose Two Layer Walk (TLWalk), a novel graph embedding algorithm that incorporates hierarchical community structures. TLWalk balances intra- and inter-community relationships through a community-aware random walk mechanism without requiring additional parameters. Theoretical analysis demonstrates that TLWalk effectively mitigates locality bias. Experiments on benchmark datasets show that TLWalk outperforms state-of-the-art methods, achieving up to 3.2% accuracy gains for link prediction tasks. By encoding dense local and sparse global structures, TLWalk proves robust and scalable across diverse networks, offering an efficient solution for network analysis.
Authors: Wei Ju, Zhengyang Mao, Siyu Yi, Yifang Qin, Yiyang Gu, Zhiping Xiao, Jianhao Shen, Ziyue Qiao, Ming Zhang
Abstract: This paper studies the problem of class-imbalanced graph classification, which aims at effectively classifying the categories of graphs in scenarios with imbalanced class distribution. Despite the tremendous success of graph neural networks (GNNs), their modeling ability for imbalanced graph-structured data is inadequate, which typically leads to predictions biased towards the majority classes. Besides, existing class-imbalanced learning methods in visions may overlook the rich graph semantic substructures of the majority classes and excessively emphasize learning from the minority classes. To tackle this issue, this paper proposes a simple yet powerful approach called C$^3$GNN that incorporates the idea of clustering into contrastive learning to enhance class-imbalanced graph classification. Technically, C$^3$GNN clusters graphs from each majority class into multiple subclasses, ensuring they have similar sizes to the minority class, thus alleviating class imbalance. Additionally, it utilizes the Mixup technique to synthesize new samples and enrich the semantic information of each subclass, and leverages supervised contrastive learning to hierarchically learn effective graph representations. In this way, we can not only sufficiently explore the semantic substructures within the majority class but also effectively alleviate excessive focus on the minority class. Extensive experiments on real-world graph benchmark datasets verify the superior performance of our proposed method.
Authors: Chuan He, Zhanwang Deng
Abstract: Conic optimization plays a crucial role in many machine learning (ML) problems. However, practical algorithms for conic constrained ML problems with large datasets are often limited to specific use cases, as stochastic algorithms for general conic optimization remain underdeveloped. To fill this gap, we introduce a stochastic interior-point method (SIPM) framework for general conic optimization, along with four novel SIPM variants leveraging distinct stochastic gradient estimators. Under mild assumptions, we establish the global convergence rates of our proposed SIPMs, which, up to a logarithmic factor, match the best-known rates in stochastic unconstrained optimization. Finally, our numerical experiments on robust linear regression, multi-task relationship learning, and clustering data streams demonstrate the effectiveness and efficiency of our approach.
Authors: Emily Yu, {\DJ}or{\dj}e \v{Z}ikeli\'c, Thomas A. Henzinger
Abstract: Learning-based methods provide a promising approach to solving highly non-linear control tasks that are often challenging for classical control methods. To ensure the satisfaction of a safety property, learning-based methods jointly learn a control policy together with a certificate function for the property. Popular examples include barrier functions for safety and Lyapunov functions for asymptotic stability. While there has been significant progress on learning-based control with certificate functions in the white-box setting, where the correctness of the certificate function can be formally verified, there has been little work on ensuring their reliability in the black-box setting where the system dynamics are unknown. In this work, we consider the problems of certifying and repairing neural network control policies and certificate functions in the black-box setting. We propose a novel framework that utilizes runtime monitoring to detect system behaviors that violate the property of interest under some initially trained neural network policy and certificate. These violating behaviors are used to extract new training data, that is used to re-train the neural network policy and the certificate function and to ultimately repair them. We demonstrate the effectiveness of our approach empirically by using it to repair and to boost the safety rate of neural network policies learned by a state-of-the-art method for learning-based control on two autonomous system control tasks.
Authors: Umer Butt, Stalin Veranasi, G\"unter Neumann
Abstract: As the Information Retrieval (IR) field increasingly recognizes the importance of inclusivity, addressing the needs of low-resource languages remains a significant challenge. This paper introduces the first large-scale Urdu IR dataset, created by translating the MS MARCO dataset through machine translation. We establish baseline results through zero-shot learning for IR in Urdu and subsequently apply the mMARCO multilingual IR methodology to this newly translated dataset. Our findings demonstrate that the fine-tuned model (Urdu-mT5-mMARCO) achieves a Mean Reciprocal Rank (MRR@10) of 0.247 and a Recall@10 of 0.439, representing significant improvements over zero-shot results and showing the potential for expanding IR access for Urdu speakers. By bridging access gaps for speakers of low-resource languages, this work not only advances multilingual IR research but also emphasizes the ethical and societal importance of inclusive IR technologies. This work provides valuable insights into the challenges and solutions for improving language representation and lays the groundwork for future research, especially in South Asian languages, which can benefit from the adaptable methods used in this study.
Authors: Weiguo Pian, Shijian Deng, Shentong Mo, Yunhui Guo, Yapeng Tian
Abstract: In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language Models (MLLMs) that involves tasks with inconsistent modalities (image, audio, or video) and varying task types (captioning or question-answering). Unlike existing vision-only or modality-incremental settings, MICL combines modality and task type shifts, both of which drive catastrophic forgetting. To address these challenges, we propose MoInCL, which employs a Pseudo Targets Generation Module to mitigate forgetting caused by task type shifts in previously seen modalities. It also incorporates Instruction-based Knowledge Distillation to preserve the model's ability to handle previously learned modalities when new ones are introduced. We benchmark MICL using a total of six tasks and conduct experiments to validate the effectiveness of our proposed MoInCL. The experimental results highlight the superiority of MoInCL, showing significant improvements over representative and state-of-the-art continual learning baselines.
Authors: M\'aty\'as Vincze, Laura Ferrarotti, Leonardo Lucio Custode, Bruno Lepri, Giovanni Iacca
Abstract: Continuous control tasks often involve high-dimensional, dynamic, and non-linear environments. State-of-the-art performance in these tasks is achieved through complex closed-box policies that are effective, but suffer from an inherent opacity. Interpretable policies, while generally underperforming compared to their closed-box counterparts, advantageously facilitate transparent decision-making within automated systems. Hence, their usage is often essential for diagnosing and mitigating errors, supporting ethical and legal accountability, and fostering trust among stakeholders. In this paper, we propose SMOSE, a novel method to train sparsely activated interpretable controllers, based on a top-1 Mixture-of-Experts architecture. SMOSE combines a set of interpretable decisionmakers, trained to be experts in different basic skills, and an interpretable router that assigns tasks among the experts. The training is carried out via state-of-the-art Reinforcement Learning algorithms, exploiting load-balancing techniques to ensure fair expert usage. We then distill decision trees from the weights of the router, significantly improving the ease of interpretation. We evaluate SMOSE on six benchmark environments from MuJoCo: our method outperforms recent interpretable baselines and narrows the gap with noninterpretable state-of-the-art algorithms
Authors: Anni Tang, Tianyu He, Junliang Guo, Xinle Cheng, Li Song, Jiang Bian
Abstract: Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing demand for high-performance, open-source video tokenizers as video-centric research gains prominence. We introduce VidTok, a versatile video tokenizer that delivers state-of-the-art performance in both continuous and discrete tokenizations. VidTok incorporates several key advancements over existing approaches: 1) model architecture such as convolutional layers and up/downsampling modules; 2) to address the training instability and codebook collapse commonly associated with conventional Vector Quantization (VQ), we integrate Finite Scalar Quantization (FSQ) into discrete video tokenization; 3) improved training strategies, including a two-stage training process and the use of reduced frame rates. By integrating these advancements, VidTok achieves substantial improvements over existing methods, demonstrating superior performance across multiple metrics, including PSNR, SSIM, LPIPS, and FVD, under standardized evaluation settings.
Authors: Sai Teja Erukude, Akhil Joshi, Lior Shamir
Abstract: CNNs have become one of the most commonly used computational tool in the past two decades. One of the primary downsides of CNNs is that they work as a ``black box", where the user cannot necessarily know how the image data are analyzed, and therefore needs to rely on empirical evaluation to test the efficacy of a trained CNN. This can lead to hidden biases that affect the performance evaluation of neural networks, but are difficult to identify. Here we discuss examples of such hidden biases in common and widely used benchmark datasets, and propose techniques for identifying dataset biases that can affect the standard performance evaluation metrics. One effective approach to identify dataset bias is to perform image classification by using merely blank background parts of the original images. However, in some situations a blank background in the images is not available, making it more difficult to separate foreground or contextual information from the bias. To overcome this, we propose a method to identify dataset bias without the need to crop background information from the images. That method is based on applying several image transforms to the original images, including Fourier transform, wavelet transforms, median filter, and their combinations. These transforms were applied to recover background bias information that CNNs use to classify images. This transformations affect the contextual visual information in a different manner than it affects the systemic background bias. Therefore, the method can distinguish between contextual information and the bias, and alert on the presence of background bias even without the need to separate sub-images parts from the blank background of the original images. Code used in the experiments is publicly available.
Authors: Jon Saad-Falcon, Rajan Vivek, William Berrios, Nandita Shankar Naik, Matija Franklin, Bertie Vidgen, Amanpreet Singh, Douwe Kiela, Shikib Mehri
Abstract: As language models become integral to critical workflows, assessing their behavior remains a fundamental challenge -- human evaluation is costly and noisy, while automated metrics provide only coarse, difficult-to-interpret signals. We introduce natural language unit tests, a paradigm that decomposes response quality into explicit, testable criteria, along with a unified scoring model, LMUnit, which combines multi-objective training across preferences, direct ratings, and natural language rationales. Through controlled human studies, we show this paradigm significantly improves inter-annotator agreement and enables more effective LLM development workflows. LMUnit achieves state-of-the-art performance on evaluation benchmarks (FLASK, BigGenBench) and competitive results on RewardBench. These results validate both our proposed paradigm and scoring model, suggesting a promising path forward for language model evaluation and development.
Authors: Tiannan Wang, Meiling Tao, Ruoyu Fang, Huilin Wang, Shuai Wang, Yuchen Eleanor Jiang, Wangchunshu Zhou
Abstract: In this work, we introduce the task of life-long personalization of large language models. While recent mainstream efforts in the LLM community mainly focus on scaling data and compute for improved capabilities of LLMs, we argue that it is also very important to enable LLM systems, or language agents, to continuously adapt to the diverse and ever-changing profiles of every distinct user and provide up-to-date personalized assistance. We provide a clear task formulation and introduce a simple, general, effective, and scalable framework for life-long personalization of LLM systems and language agents. To facilitate future research on LLM personalization, we also introduce methods to synthesize realistic benchmarks and robust evaluation metrics. We will release all codes and data for building and benchmarking life-long personalized LLM systems.
Authors: Monnie McGee, Bivin Sadler
Abstract: A college education historically has been seen as method of moving upward with regards to income brackets and social status. Indeed, many colleges recognize this connection and seek to enroll talented low income students. While these students might have their education, books, room, and board paid; there are other items that they might be expected to use that are not part of most college scholarship packages. One of those items that has recently surfaced is access to generative AI platforms. The most popular of these platforms is ChatGPT, and it has a paid version (ChatGPT4) and a free version (ChatGPT3.5). We seek to explore differences in the free and paid versions in the context of homework questions and data analyses as might be seen in a typical introductory statistics course. We determine the extent to which students who cannot afford newer and faster versions of generative AI programs would be disadvantaged in terms of writing such projects and learning these methods.
Authors: Chao Ma, Wenbo Gong, Meyer Scetbon, Edward Meeds
Abstract: Adaptive optimizers such as Adam (Kingma & Ba, 2015) have been central to the success of large language models. However, they maintain additional moving average states throughout training, which results in memory requirements several times greater than the model. This overhead imposes constraints on scalability and computational efficiency. On the other hand, while stochastic gradient descent (SGD) is optimal in terms of memory efficiency, their capability in LLM training is limited (Zhao et al., 2024b). To address this dilemma, we show that pre-processing SGD is sufficient to reach Adam-level performance on LLMs. Specifically, we propose to preprocess the instantaneous stochastic gradients with two simple operators: $\mathtt{GradNorm}$ and $\mathtt{GradWhitening}$. $\mathtt{GradNorm}$ stabilizes gradient distributions, and $\mathtt{GradWhitening}$ counteracts the local curvature of the loss landscape, respectively. This results in SWAN (SGD with Whitening And Normalization), a stochastic optimizer that eliminates the need to store any accumulative state variables. Empirically, SWAN has the same memory footprint as SGD, achieving $\approx 50\%$ reduction on total end-to-end memory compared to Adam. In language modeling tasks, SWAN demonstrates the same or even a substantial improvement over Adam. Specifically, when pre-training the LLaMa model with 350M and 1.3B parameters, SWAN achieves a 2x speedup by reaching the same evaluation perplexity in less than half tokens seen.
Authors: Paolo Gabriel, Peter Rehani, Tyler Troy, Tiffany Wyatt, Michael Choma, Narinder Singh
Abstract: This study introduces an AI-driven platform for continuous and passive patient monitoring in hospital settings, developed by LookDeep Health. Leveraging advanced computer vision, the platform provides real-time insights into patient behavior and interactions through video analysis, securely storing inference results in the cloud for retrospective evaluation. The dataset, compiled in collaboration with 11 hospital partners, encompasses over 300 high-risk fall patients and over 1,000 days of inference, enabling applications such as fall detection and safety monitoring for vulnerable patient populations. To foster innovation and reproducibility, an anonymized subset of this dataset is publicly available. The AI system detects key components in hospital rooms, including individual presence and role, furniture location, motion magnitude, and boundary crossings. Performance evaluation demonstrates strong accuracy in object detection (macro F1-score = 0.92) and patient-role classification (F1-score = 0.98), as well as reliable trend analysis for the "patient alone" metric (mean logistic regression accuracy = 0.82 \pm 0.15). These capabilities enable automated detection of patient isolation, wandering, or unsupervised movement-key indicators for fall risk and other adverse events. This work establishes benchmarks for validating AI-driven patient monitoring systems, highlighting the platform's potential to enhance patient safety and care by providing continuous, data-driven insights into patient behavior and interactions.
Authors: Xingjian Wang, Li Chai
Abstract: In-the-wild Dynamic facial expression recognition (DFER) encounters a significant challenge in recognizing emotion-related expressions, which are often temporally and spatially diluted by emotion-irrelevant expressions and global context respectively. Most of the prior DFER methods model tightly coupled spatiotemporal representations which may incorporate weakly relevant features, leading to information redundancy and emotion-irrelevant context bias. Several DFER methods have highlighted the significance of dynamic information, but utilize explicit manners to extract dynamic features with overly strong prior knowledge. In this paper, we propose a novel Implicit Facial Dynamics Disentanglement framework (IFDD). Through expanding wavelet lifting scheme to fully learnable framework, IFDD disentangles emotion-related dynamic information from emotion-irrelevant global context in an implicit manner, i.e., without exploit operations and external guidance. The disentanglement process of IFDD contains two stages, i.e., Inter-frame Static-dynamic Splitting Module (ISSM) for rough disentanglement estimation and Lifting-based Aggregation-Disentanglement Module (LADM) for further refinement. Specifically, ISSM explores inter-frame correlation to generate content-aware splitting indexes on-the-fly. We preliminarily utilize these indexes to split frame features into two groups, one with greater global similarity, and the other with more unique dynamic features. Subsequently, LADM first aggregates these two groups of features to obtain fine-grained global context features by an updater, and then disentangles emotion-related facial dynamic features from the global context by a predictor. Extensive experiments on in-the-wild datasets have demonstrated that IFDD outperforms prior supervised DFER methods with higher recognition accuracy and comparable efficiency.
Authors: Jui-Che Chiang, Hou-Ning Hu, Bo-Syuan Hou, Chia-Yu Tseng, Yu-Lun Liu, Min-Hung Chen, Yen-Yu Lin
Abstract: Although facial landmark detection (FLD) has gained significant progress, existing FLD methods still suffer from performance drops on partially non-visible faces, such as faces with occlusions or under extreme lighting conditions or poses. To address this issue, we introduce ORFormer, a novel transformer-based method that can detect non-visible regions and recover their missing features from visible parts. Specifically, ORFormer associates each image patch token with one additional learnable token called the messenger token. The messenger token aggregates features from all but its patch. This way, the consensus between a patch and other patches can be assessed by referring to the similarity between its regular and messenger embeddings, enabling non-visible region identification. Our method then recovers occluded patches with features aggregated by the messenger tokens. Leveraging the recovered features, ORFormer compiles high-quality heatmaps for the downstream FLD task. Extensive experiments show that our method generates heatmaps resilient to partial occlusions. By integrating the resultant heatmaps into existing FLD methods, our method performs favorably against the state of the arts on challenging datasets such as WFLW and COFW.
Authors: Sheng Yin, Xianghe Pang, Yuanzhuo Ding, Menglan Chen, Yutong Bi, Yichen Xiong, Wenhao Huang, Zhen Xiang, Jing Shao, Siheng Chen
Abstract: With the integration of large language models (LLMs), embodied agents have strong capabilities to execute complicated instructions in natural language, paving a way for the potential deployment of embodied robots. However, a foreseeable issue is that those embodied agents can also flawlessly execute some hazardous tasks, potentially causing damages in real world. To study this issue, we present SafeAgentBench -- a new benchmark for safety-aware task planning of embodied LLM agents. SafeAgentBench includes: (1) a new dataset with 750 tasks, covering 10 potential hazards and 3 task types; (2) SafeAgentEnv, a universal embodied environment with a low-level controller, supporting multi-agent execution with 17 high-level actions for 8 state-of-the-art baselines; and (3) reliable evaluation methods from both execution and semantic perspectives. Experimental results show that the best-performing baseline gets 69% success rate for safe tasks, but only 5% rejection rate for hazardous tasks, indicating significant safety risks. More details and codes are available at https://github.com/shengyin1224/SafeAgentBench.
Authors: Chenglin Li, Guangchun Ruan, Hua Geng
Abstract: Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees. Previous works tend to express the safety constraints in an expectation form due to the ease of implementation, but this turns out to be ineffective in maintaining safety constraints with high probability. To this end, we move to the quantile-constrained RL that enables a higher level of safety without any expectation-form approximations. We directly estimate the quantile gradients through sampling and provide the theoretical proofs of convergence. Then a tilted update strategy for quantile gradients is implemented to compensate the asymmetric distributional density, with a direct benefit of return performance. Experiments demonstrate that the proposed model fully meets safety requirements (quantile constraints) while outperforming the state-of-the-art benchmarks with higher return.
Authors: Yifei Zhou, Qianlan Yang, Kaixiang Lin, Min Bai, Xiong Zhou, Yu-Xiong Wang, Sergey Levine, Erran Li
Abstract: The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advanced, thanks to the generalization capability of foundation models. Such a generalist agent needs to have a large and diverse skill repertoire, such as finding directions between two travel locations and buying specific items from the Internet. If each skill needs to be specified manually through a fixed set of human-annotated instructions, the agent's skill repertoire will necessarily be limited due to the quantity and diversity of human-annotated instructions. In this work, we address this challenge by proposing Proposer-Agent-Evaluator, an effective learning system that enables foundation model agents to autonomously discover and practice skills in the wild. At the heart of PAE is a context-aware task proposer that autonomously proposes tasks for the agent to practice with context information of the environment such as user demos or even just the name of the website itself for Internet-browsing agents. Then, the agent policy attempts those tasks with thoughts and actual grounded operations in the real world with resulting trajectories evaluated by an autonomous VLM-based success evaluator. The success evaluation serves as the reward signal for the agent to refine its policies through RL. We validate PAE on challenging vision-based web navigation, using both real-world and self-hosted websites from WebVoyager and WebArena.To the best of our knowledge, this work represents the first effective learning system to apply autonomous task proposal with RL for agents that generalizes real-world human-annotated benchmarks with SOTA performances. Our open-source checkpoints and code can be found in https://yanqval.github.io/PAE/
Authors: Mazeyu Ji, Xuanbin Peng, Fangchen Liu, Jialong Li, Ge Yang, Xuxin Cheng, Xiaolong Wang
Abstract: This paper enables real-world humanoid robots to maintain stability while performing expressive motions like humans do. We propose ExBody2, a generalized whole-body tracking framework that can take any reference motion inputs and control the humanoid to mimic the motion. The model is trained in simulation with Reinforcement Learning and then transferred to the real world. It decouples keypoint tracking with velocity control, and effectively leverages a privileged teacher policy to distill precise mimic skills into the target student policy, which enables high-fidelity replication of dynamic movements such as running, crouching, dancing, and other challenging motions. We present a comprehensive qualitative and quantitative analysis of crucial design factors in the paper. We conduct our experiments on two humanoid platforms and demonstrate the superiority of our approach against state-of-the-arts, providing practical guidelines to pursue the extreme of whole-body control for humanoid robots.
Authors: Siqi Lai, Zhao Xu, Weijia Zhang, Hao Liu, Hui Xiong
Abstract: Traffic Signal Control (TSC) is a crucial component in urban traffic management, aiming to optimize road network efficiency and reduce congestion. Traditional TSC methods, primarily based on transportation engineering and reinforcement learning (RL), often struggle with generalization abilities across varied traffic scenarios and lack interpretability. This paper presents LLMLight, a novel framework employing Large Language Models (LLMs) as decision-making agents for TSC. Specifically, the framework begins by instructing the LLM with a knowledgeable prompt detailing real-time traffic conditions. Leveraging the advanced generalization capabilities of LLMs, LLMLight engages a reasoning and decision-making process akin to human intuition for effective traffic control. Moreover, we build LightGPT, a specialized backbone LLM tailored for TSC tasks. By learning nuanced traffic patterns and control strategies, LightGPT enhances the LLMLight framework cost-effectively. Extensive experiments conducted on ten real-world and synthetic datasets, along with evaluations by fifteen human experts, demonstrate the exceptional effectiveness, generalization ability, and interpretability of LLMLight with LightGPT, outperforming nine baseline methods and ten advanced LLMs.
Authors: Mingfei Cheng, Yuan Zhou, Xiaofei Xie, Junjie Wang, Guozhu Meng, Kairui Yang
Abstract: Autonomous Driving System (ADS) testing is crucial in ADS development, with the current primary focus being on safety. However, the evaluation of non-safety-critical performance, particularly the ADS's ability to make optimal decisions and produce optimal paths for autonomous vehicles (AVs), is also vital to ensure the intelligence and reduce risks of AVs. Currently, there is little work dedicated to assessing the robustness of ADSs' path-planning decisions (PPDs), i.e., whether an ADS can maintain the optimal PPD after an insignificant change in the environment. The key challenges include the lack of clear oracles for assessing PPD optimality and the difficulty in searching for scenarios that lead to non-optimal PPDs. To fill this gap, in this paper, we focus on evaluating the robustness of ADSs' PPDs and propose the first method, Decictor, for generating non-optimal decision scenarios (NoDSs), where the ADS does not plan optimal paths for AVs. Decictor comprises three main components: Non-invasive Mutation, Consistency Check, and Feedback. To overcome the oracle challenge, Non-invasive Mutation is devised to implement conservative modifications, ensuring the preservation of the original optimal path in the mutated scenarios. Subsequently, the Consistency Check is applied to determine the presence of non-optimal PPDs by comparing the driving paths in the original and mutated scenarios. To deal with the challenge of large environment space, we design Feedback metrics that integrate spatial and temporal dimensions of the AV's movement. These metrics are crucial for effectively steering the generation of NoDSs. We evaluate Decictor on Baidu Apollo, an open-source and production-grade ADS. The experimental results validate the effectiveness of Decictor in detecting non-optimal PPDs of ADSs.
Authors: Eamon Duede, Kevin Davey
Abstract: Can we acquire apriori knowledge of mathematical facts from the outputs of computer programs? People like Burge have argued (correctly in our opinion) that, for example, Appel and Haken acquired apriori knowledge of the Four Color Theorem from their computer program insofar as their program simply automated human forms of mathematical reasoning. However, unlike such programs, we argue that the opacity of modern LLMs and DNNs creates obstacles in obtaining apriori mathematical knowledge from them in similar ways. We claim though that if a proof-checker automating human forms of proof-checking is attached to such machines, then we can obtain apriori mathematical knowledge from them after all, even though the original machines are entirely opaque to us and the proofs they output may not, themselves, be human-surveyable.
Authors: Peihan Li, Vishnu Menon, Bhavanaraj Gudiguntla, Daniel Ting, Lifeng Zhou
Abstract: Flocking is a behavior where multiple agents in a system attempt to stay close to each other while avoiding collision and maintaining a desired formation. This is observed in the natural world and has applications in robotics, including natural disaster search and rescue, wild animal tracking, and perimeter surveillance and patrol. Recently, large language models (LLMs) have displayed an impressive ability to solve various collaboration tasks as individual decision-makers. Solving multi-agent flocking with LLMs would demonstrate their usefulness in situations requiring spatial and decentralized decision-making. Yet, when LLM-powered agents are tasked with implementing multi-agent flocking, they fall short of the desired behavior. After extensive testing, we find that agents with LLMs as individual decision-makers typically opt to converge on the average of their initial positions or diverge from each other. After breaking the problem down, we discover that LLMs cannot understand maintaining a shape or keeping a distance in a meaningful way. Solving multi-agent flocking with LLMs would enhance their ability to understand collaborative spatial reasoning and lay a foundation for addressing more complex multi-agent tasks. This paper discusses the challenges LLMs face in multi-agent flocking and suggests areas for future improvement and research.
Authors: Alexander Windmann, Philipp Wittenberg, Marvin Schieseck, Oliver Niggemann
Abstract: In Industry 4.0, Cyber-Physical Systems (CPS) generate vast data sets that can be leveraged by Artificial Intelligence (AI) for applications including predictive maintenance and production planning. However, despite the demonstrated potential of AI, its widespread adoption in sectors like manufacturing remains limited. Our comprehensive review of recent literature, including standards and reports, pinpoints key challenges: system integration, data-related issues, managing workforce-related concerns and ensuring trustworthy AI. A quantitative analysis highlights particular challenges and topics that are important for practitioners but still need to be sufficiently investigated by academics. The paper briefly discusses existing solutions to these challenges and proposes avenues for future research. We hope that this survey serves as a resource for practitioners evaluating the cost-benefit implications of AI in CPS and for researchers aiming to address these urgent challenges.
Authors: Yifan Yang, Qiao Jin, Furong Huang, Zhiyong Lu
Abstract: The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses a significant threat, potentially leading to harmful outcomes in delicate medical contexts. This study investigates the vulnerability of LLMs to two types of adversarial attacks in three medical tasks. Utilizing real-world patient data, we demonstrate that both open-source and proprietary LLMs are susceptible to manipulation across multiple tasks. This research further reveals that domain-specific tasks demand more adversarial data in model fine-tuning than general domain tasks for effective attack execution, especially for more capable models. We discover that while integrating adversarial data does not markedly degrade overall model performance on medical benchmarks, it does lead to noticeable shifts in fine-tuned model weights, suggesting a potential pathway for detecting and countering model attacks. This research highlights the urgent need for robust security measures and the development of defensive mechanisms to safeguard LLMs in medical applications, to ensure their safe and effective deployment in healthcare settings.
Authors: Zijian Wang, Bin Wang, Haifeng Jing, Huayu Li, Hongbo Dou
Abstract: Recent years, multi-hop reasoning has been widely studied for knowledge graph (KG) reasoning due to its efficacy and interpretability. However, previous multi-hop reasoning approaches are subject to two primary shortcomings. First, agents struggle to learn effective and robust policies at the early phase due to sparse rewards. Second, these approaches often falter on specific datasets like sparse knowledge graphs, where agents are required to traverse lengthy reasoning paths. To address these problems, we propose a multi-hop reasoning model with dual agents based on hierarchical reinforcement learning (HRL), which is named FULORA. FULORA tackles the above reasoning challenges by eFficient GUidance-ExpLORAtion between dual agents. The high-level agent walks on the simplified knowledge graph to provide stage-wise hints for the low-level agent walking on the original knowledge graph. In this framework, the low-level agent optimizes a value function that balances two objectives: (1) maximizing return, and (2) integrating efficient guidance from the high-level agent. Experiments conducted on three real-word knowledge graph datasets demonstrate that FULORA outperforms RL-based baselines, especially in the case of long-distance reasoning.
Authors: Thomy Phan, Benran Zhang, Shao-Hung Chan, Sven Koenig
Abstract: Anytime multi-agent path finding (MAPF) is a promising approach to scalable path optimization in multi-agent systems. MAPF-LNS, based on Large Neighborhood Search (LNS), is the current state-of-the-art approach where a fast initial solution is iteratively optimized by destroying and repairing selected paths of the solution. Current MAPF-LNS variants commonly use an adaptive selection mechanism to choose among multiple destroy heuristics. However, to determine promising destroy heuristics, MAPF-LNS requires a considerable amount of exploration time. As common destroy heuristics are non-adaptive, any performance bottleneck caused by these heuristics cannot be overcome via adaptive heuristic selection alone, thus limiting the overall effectiveness of MAPF-LNS in terms of solution cost. In this paper, we propose Adaptive Delay-based Destroy-and-Repair Enhanced with Success-based Self-Learning (ADDRESS) as a single-destroy-heuristic variant of MAPF-LNS. ADDRESS applies restricted Thompson Sampling to the top-K set of the most delayed agents to select a seed agent for adaptive LNS neighborhood generation. We evaluate ADDRESS in multiple maps from the MAPF benchmark set and demonstrate cost improvements by at least 50% in large-scale scenarios with up to a thousand agents, compared with the original MAPF-LNS and other state-of-the-art methods.
Authors: Zouying Cao, Yifei Yang, Hai Zhao
Abstract: Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue, limiting their helpfulness. In this paper, we propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns in aligned LLMs. First, SCANS extracts the refusal steering vectors within the activation space and utilizes vocabulary projection to anchor some specific safety-critical layers which influence model refusal behavior. Second, by tracking the hidden state transition, SCANS identifies the steering direction and steers the model behavior accordingly, achieving a balance between exaggerated safety and adequate safety. Experiments show that SCANS achieves new state-of-the-art performance on XSTest and OKTest benchmarks, without impairing their defense capability against harmful queries and maintaining almost unchanged model capability.
Authors: Ruairidh M. Battleday, Samuel J. Gershman
Abstract: A suite of impressive scientific discoveries have been driven by recent advances in artificial intelligence. These almost all result from training flexible algorithms to solve difficult optimization problems specified in advance by teams of domain scientists and engineers with access to large amounts of data. Although extremely useful, this kind of problem solving only corresponds to one part of science - the "easy problem." The other part of scientific research is coming up with the problem itself - the "hard problem." Solving the hard problem is beyond the capacities of current algorithms for scientific discovery because it requires continual conceptual revision based on poorly defined constraints. We can make progress on understanding how humans solve the hard problem by studying the cognitive science of scientists, and then use the results to design new computational agents that automatically infer and update their scientific paradigms.
Authors: Pranay Thangeda, Trevor S. Betz, Michael N. Grussing, Melkior Ornik
Abstract: Efficient management of infrastructure systems is crucial for economic stability, sustainability, and public safety. However, infrastructure sustainment is challenging due to the vast scale of systems, stochastic deterioration of components, partial observability, and resource constraints. Decision-making strategies that rely solely on human judgment often result in suboptimal decisions over large scales and long horizons. While data-driven approaches like reinforcement learning offer promising solutions, their application has been limited by the lack of suitable simulation environments. We present InfraLib, an open-source modular and extensible framework that enables modeling and analyzing infrastructure management problems with resource constraints as sequential decision-making problems. The framework implements hierarchical, stochastic deterioration models, supports realistic partial observability, and handles practical constraints including cyclical budgets and component unavailability. InfraLib provides standardized environments for benchmarking decision-making approaches, along with tools for expert data collection and policy evaluation. Through case studies on both synthetic benchmarks and real-world road networks, we demonstrate InfraLib's ability to model diverse infrastructure management scenarios while maintaining computational efficiency at scale.
Authors: Junnan Liu, Qianren Mao, Weifeng Jiang, Jianxin Li
Abstract: Knowledge graph reasoning plays a vital role in various applications and has garnered considerable attention. Recently, path-based methods have achieved impressive performance. However, they may face limitations stemming from constraints in message-passing neural networks, such as missing paths and information over-squashing. In this paper, we revisit the application of transformers for knowledge graph reasoning to address the constraints faced by path-based methods and propose a novel method KnowFormer. KnowFormer utilizes a transformer architecture to perform reasoning on knowledge graphs from the message-passing perspective, rather than reasoning by textual information like previous pretrained language model based methods. Specifically, we define the attention computation based on the query prototype of knowledge graph reasoning, facilitating convenient construction and efficient optimization. To incorporate structural information into the self-attention mechanism, we introduce structure-aware modules to calculate query, key, and value respectively. Additionally, we present an efficient attention computation method for better scalability. Experimental results demonstrate the superior performance of KnowFormer compared to prominent baseline methods on both transductive and inductive benchmarks.
Authors: Hanqi Duan, Yao Cheng, Jianxiang Yu, Xiang Li
Abstract: Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, GNNs lack the inherent semantic understanding capability of rich textual node attributes, limiting their effectiveness in applications. On the other hand, we empirically observe that for existing GNN models, no one can consistently outperforms others across diverse datasets. In this paper, we study whether LLMs can act as an ensembler for multi-GNNs and propose the LensGNN model. The model first aligns multiple GNNs, mapping the representations of different GNNs into the same space. Then, through LoRA fine-tuning, it aligns the space between the GNN and the LLM, injecting graph tokens and textual information into LLMs. This allows LensGNN to ensemble multiple GNNs and take advantage of the strengths of LLM, leading to a deeper understanding of both textual semantic information and graph structural information. The experimental results show that LensGNN outperforms existing models. This research advances text-attributed graph ensemble learning by providing a robust and superior solution for integrating semantic and structural information. We provide our code and data here: https://anonymous.4open.science/r/EnsemGNN-E267/.
Authors: Erik J Schlicht
Abstract: Generative Artificial Intelligence offers a powerful tool for adversaries who wish to engage in influence operations, such as the Chinese Spamouflage operation and the Russian Internet Research Agency effort that both sought to interfere with recent US election cycles. Therefore, this study seeks to investigate the propensity of current generative AI models for producing harmful disinformation during an election cycle. The probability that different generative AI models produced disinformation when given adversarial prompts was evaluated, in addition the associated harm. This allows for the expected harm for each model to be computed and it was discovered that Copilot and Gemini tied for the overall safest performance by realizing the lowest expected harm, while GPT-4o produced the greatest rates of harmful disinformation, resulting in much higher expected harm scores. The impact of disinformation category was also investigated and Gemini was safest within the political category of disinformation due to mitigation attempts made by developers during the election, while Copilot was safest for topics related to health. Moreover, characteristics of adversarial roles were discovered that led to greater expected harm across all models. Finally, classification models were developed that predicted disinformation production based on the conditions considered in this study, which offers insight into factors important for predicting disinformation production. Based on all of these insights, recommendations are provided that seek to mitigate factors that lead to harmful disinformation being produced by generative AI models. It is hoped that developers will use these insights to improve future models.
Authors: Yingqi Gao, Yifu Liu, Xiaoxia Li, Xiaorong Shi, Yin Zhu, Yiming Wang, Shiqi Li, Wei Li, Yuntao Hong, Zhiling Luo, Jinyang Gao, Liyu Mou, Yu Li
Abstract: To tackle the challenges of large language model performance in natural language to SQL tasks, we introduce XiYan-SQL, an innovative framework that employs a multi-generator ensemble strategy to improve candidate generation. We introduce M-Schema, a semi-structured schema representation method designed to enhance the understanding of database structures. To enhance the quality and diversity of generated candidate SQL queries, XiYan-SQL integrates the significant potential of in-context learning (ICL) with the precise control of supervised fine-tuning. On one hand, we propose a series of training strategies to fine-tune models to generate high-quality candidates with diverse preferences. On the other hand, we implement the ICL approach with an example selection method based on named entity recognition to prevent overemphasis on entities. The refiner optimizes each candidate by correcting logical or syntactical errors. To address the challenge of identifying the best candidate, we fine-tune a selection model to distinguish nuances of candidate SQL queries. The experimental results on multiple dialect datasets demonstrate the robustness of XiYan-SQL in addressing challenges across different scenarios. Overall, our proposed XiYan-SQL achieves the state-of-the-art execution accuracy of 75.63% on Bird benchmark, 89.65% on the Spider test set, 69.86% on SQL-Eval, 41.20% on NL2GQL. The proposed framework not only enhances the quality and diversity of SQL queries but also outperforms previous methods.
Authors: Chaoyun Zhang, Shilin He, Jiaxu Qian, Bowen Li, Liqun Li, Si Qin, Yu Kang, Minghua Ma, Guyue Liu, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
Abstract: GUIs have long been central to human-computer interaction, providing an intuitive and visually-driven way to access and interact with digital systems. The advent of LLMs, particularly multimodal models, has ushered in a new era of GUI automation. They have demonstrated exceptional capabilities in natural language understanding, code generation, and visual processing. This has paved the way for a new generation of LLM-brained GUI agents capable of interpreting complex GUI elements and autonomously executing actions based on natural language instructions. These agents represent a paradigm shift, enabling users to perform intricate, multi-step tasks through simple conversational commands. Their applications span across web navigation, mobile app interactions, and desktop automation, offering a transformative user experience that revolutionizes how individuals interact with software. This emerging field is rapidly advancing, with significant progress in both research and industry. To provide a structured understanding of this trend, this paper presents a comprehensive survey of LLM-brained GUI agents, exploring their historical evolution, core components, and advanced techniques. We address research questions such as existing GUI agent frameworks, the collection and utilization of data for training specialized GUI agents, the development of large action models tailored for GUI tasks, and the evaluation metrics and benchmarks necessary to assess their effectiveness. Additionally, we examine emerging applications powered by these agents. Through a detailed analysis, this survey identifies key research gaps and outlines a roadmap for future advancements in the field. By consolidating foundational knowledge and state-of-the-art developments, this work aims to guide both researchers and practitioners in overcoming challenges and unlocking the full potential of LLM-brained GUI agents.
Authors: Gabriel R. Rosenbaum, Lavender Yao Jiang, Ivaxi Sheth, Jaden Stryker, Anton Alyakin, Daniel Alexander Alber, Nicolas K. Goff, Young Joon Fred Kwon, John Markert, Mustafa Nasir-Moin, Jan Moritz Niehues, Karl L. Sangwon, Eunice Yang, Eric Karl Oermann
Abstract: Large language models (LLMs) have recently emerged as powerful tools, finding many medical applications. LLMs' ability to coalesce vast amounts of information from many sources to generate a response-a process similar to that of a human expert-has led many to see potential in deploying LLMs for clinical use. However, medicine is a setting where accurate reasoning is paramount. Many researchers are questioning the effectiveness of multiple choice question answering (MCQA) benchmarks, frequently used to test LLMs. Researchers and clinicians alike must have complete confidence in LLMs' abilities for them to be deployed in a medical setting. To address this need for understanding, we introduce a knowledge graph (KG)-based method to evaluate the biomedical reasoning abilities of LLMs. Essentially, we map how LLMs link medical concepts in order to better understand how they reason. We test GPT-4, Llama3-70b, and PalmyraMed-70b, a specialized medical model. We enlist a panel of medical students to review a total of 60 LLM-generated graphs and compare these graphs to BIOS, a large biomedical KG. We observe GPT-4 to perform best in our human review but worst in our ground truth comparison; vice-versa with PalmyraMed, the medical model. Our work provides a means of visualizing the medical reasoning pathways of LLMs so they can be implemented in clinical settings safely and effectively.
Authors: Junjie Lin, Jian Zhao, Lin Liu, Yue Deng, Youpeng Zhao, Lanxiao Huang, Xia Lin, Wengang Zhou, Houqiang Li
Abstract: Traditionally, AI development for two-player zero-sum games has relied on two primary techniques: decision trees and reinforcement learning (RL). A common approach involves using a fixed decision tree as one player's strategy while training an RL agent as the opponent to identify vulnerabilities in the decision tree, thereby improving its strategic strength iteratively. However, this process often requires significant human intervention to refine the decision tree after identifying its weaknesses, resulting in inefficiencies and hindering full automation of the strategy enhancement process. Fortunately, the advent of Large Language Models (LLMs) offers a transformative opportunity to automate the process. We propose RL-LLM-DT, an automatic decision tree generation method based on RL Evaluation and LLM Enhancement. Given an initial decision tree, the method involves two important iterative steps. Response Policy Search: RL is used to discover counter-strategies targeting the decision tree. Policy Improvement: LLMs analyze failure scenarios and generate improved decision tree code. In our method, RL focuses on finding the decision tree's flaws while LLM is prompted to generate an improved version of the decision tree. The iterative refinement process terminates when RL can't find any flaw of the tree or LLM fails to improve the tree. To evaluate the effectiveness of this integrated approach, we conducted experiments in a curling game. After iterative refinements, our curling AI based on the decision tree ranks first on the Jidi platform among 34 curling AIs in total, which demonstrates that LLMs can significantly enhance the robustness and adaptability of decision trees, representing a substantial advancement in the field of Game AI. Our code is available at https://github.com/Linjunjie99/RL-LLM-DT.
Authors: Yakoub Salhi
Abstract: In this paper, we introduce a syntactic framework for analyzing and handling inconsistencies in propositional bases. Our approach focuses on examining the relationships between variable occurrences within conflicts. We propose two dual concepts: Minimal Inconsistency Relation (MIR) and Maximal Consistency Relation (MCR). Each MIR is a minimal equivalence relation on variable occurrences that results in inconsistency, while each MCR is a maximal equivalence relation designed to prevent inconsistency. Notably, MIRs capture conflicts overlooked by minimal inconsistent subsets. Using MCRs, we develop a series of non-explosive inference relations. The main strategy involves restoring consistency by modifying the propositional base according to each MCR, followed by employing the classical inference relation to derive conclusions. Additionally, we propose an unusual semantics that assigns truth values to variable occurrences instead of the variables themselves. The associated inference relations are established through Boolean interpretations compatible with the occurrence-based models.
Authors: Rajat Khanda
Abstract: Technical troubleshooting in enterprise environments often involves navigating diverse, heterogeneous data sources to resolve complex issues effectively. This paper presents a novel agentic AI solution built on a Weighted Retrieval-Augmented Generation (RAG) Framework tailored for enterprise technical troubleshooting. By dynamically weighting retrieval sources such as product manuals, internal knowledge bases, FAQs, and troubleshooting guides based on query context, the framework prioritizes the most relevant data. For instance, it gives precedence to product manuals for SKU-specific queries while incorporating general FAQs for broader issues. The system employs FAISS for efficient dense vector search, coupled with a dynamic aggregation mechanism to seamlessly integrate results from multiple sources. A Llama-based self-evaluator ensures the contextual accuracy and confidence of the generated responses before delivering them. This iterative cycle of retrieval and validation enhances precision, diversity, and reliability in response generation. Preliminary evaluations on large enterprise datasets demonstrate the framework's efficacy in improving troubleshooting accuracy, reducing resolution times, and adapting to varied technical challenges. Future research aims to enhance the framework by integrating advanced conversational AI capabilities, enabling more interactive and intuitive troubleshooting experiences. Efforts will also focus on refining the dynamic weighting mechanism through reinforcement learning to further optimize the relevance and precision of retrieved information. By incorporating these advancements, the proposed framework is poised to evolve into a comprehensive, autonomous AI solution, redefining technical service workflows across enterprise settings.
Authors: Zan Ahmad Naeem, Mohammad Shahmeer Ahmad, Mohamed Eltabakh, Mourad Ouzzani, Nan Tang
Abstract: Can foundation models (such as ChatGPT) clean your data? In this proposal, we demonstrate that indeed ChatGPT can assist in data cleaning by suggesting corrections for specific cells in a data table (scenario 1). However, ChatGPT may struggle with datasets it has never encountered before (e.g., local enterprise data) or when the user requires an explanation of the source of the suggested clean values. To address these issues, we developed a retrieval-based method that complements ChatGPT's power with a user-provided data lake. The data lake is first indexed, we then retrieve the top-k relevant tuples to the user's query tuple and finally leverage ChatGPT to infer the correct value (scenario 2). Nevertheless, sharing enterprise data with ChatGPT, an externally hosted model, might not be feasible for privacy reasons. To assist with this scenario, we developed a custom RoBERTa-based foundation model that can be locally deployed. By fine-tuning it on a small number of examples, it can effectively make value inferences based on the retrieved tuples (scenario 3). Our proposed system, RetClean, seamlessly supports all three scenarios and provides a user-friendly GUI that enables the VLDB audience to explore and experiment with the system.
Authors: Fernando B. P\'erez Maurera, Maurizio Ferrari Dacrema, Pablo Castells, Paolo Cremonesi
Abstract: Novel data sources bring new opportunities to improve the quality of recommender systems and serve as a catalyst for the creation of new paradigms on personalized recommendations. Impressions are a novel data source containing the items shown to users on their screens. Past research focused on providing personalized recommendations using interactions, and occasionally using impressions when such a data source was available. Interest in impressions has increased due to their potential to provide more accurate recommendations. Despite this increased interest, research in recommender systems using impressions is still dispersed. Many works have distinct interpretations of impressions and use impressions in recommender systems in numerous different manners. To unify those interpretations into a single framework, we present a systematic literature review on recommender systems using impressions, focusing on three fundamental perspectives: recommendation models, datasets, and evaluation methodologies. We define a theoretical framework to delimit recommender systems using impressions and a novel paradigm for personalized recommendations, called impression-aware recommender systems. We propose a classification system for recommenders in this paradigm, which we use to categorize the recommendation models, datasets, and evaluation methodologies used in past research. Lastly, we identify open questions and future directions, highlighting missing aspects in the reviewed literature.
Authors: Tuba Girgin, Emre Ugur
Abstract: Learning object affordances is an effective tool in the field of robot learning. While the data-driven models investigate affordances of single or paired objects, there is a gap in the exploration of affordances of compound objects composed of an arbitrary number of objects. We propose the Multi-Object Graph Affordance Network which models complex compound object affordances by learning the outcomes of robot actions that facilitate interactions between an object and a compound. Given the depth images of the objects, the object features are extracted via convolution operations and encoded in the nodes of graph neural networks. Graph convolution operations are used to encode the state of the compounds, which are used as input to decoders to predict the outcome of the object-compound interactions. After learning the compound object affordances, given different tasks, the learned outcome predictors are used to plan sequences of stack actions that involve stacking objects on top of each other, inserting smaller objects into larger containers and passing through ring-like objects through poles. We showed that our system successfully modeled the affordances of compound objects that include concave and convex objects, in both simulated and real-world environments. We benchmarked our system with a baseline model to highlight its advantages.
Authors: Francesco Immorlano, Veronika Eyring, Thomas le Monnier de Gouville, Gabriele Accarino, Donatello Elia, Stephan Mandt, Giovanni Aloisio, Pierre Gentine
Abstract: Precise and reliable climate projections are required for climate adaptation and mitigation, but Earth system models still exhibit great uncertainties. Several approaches have been developed to reduce the spread of climate projections and feedbacks, yet those methods cannot capture the non-linear complexity inherent in the climate system. Using a Transfer Learning approach, we show that Machine Learning can be used to optimally leverage and merge the knowledge gained from Earth system models simulations and historical observations to reduce the spread of global surface air temperature fields projected in the 21st century. We reach an uncertainty reduction of more than 50% with respect to state-of-the-art approaches, while giving evidence that our novel method provides improved regional temperature patterns together with narrower projections uncertainty, urgently required for climate adaptation.
Authors: Yao Yao, Peike Li, Boyu Chen, Alex Wang
Abstract: With rapid advances in generative artificial intelligence, the text-to-music synthesis task has emerged as a promising direction for music generation. Nevertheless, achieving precise control over multi-track generation remains an open challenge. While existing models excel in directly generating multi-track mix, their limitations become evident when it comes to composing individual tracks and integrating them in a controllable manner. This departure from the typical workflows of professional composers hinders the ability to refine details in specific tracks. To address this gap, we propose JEN-1 Composer, a unified framework designed to efficiently model marginal, conditional, and joint distributions over multi-track music using a single model. Building upon an audio latent diffusion model, JEN-1 Composer extends the versatility of multi-track music generation. We introduce a progressive curriculum training strategy, which gradually escalates the difficulty of training tasks while ensuring the model's generalization ability and facilitating smooth transitions between different scenarios. During inference, users can iteratively generate and select music tracks, thus incrementally composing entire musical pieces in accordance with the Human-AI co-composition workflow. Our approach demonstrates state-of-the-art performance in controllable and high-fidelity multi-track music synthesis, marking a significant advancement in interactive AI-assisted music creation. Our demo pages are available at www.jenmusic.ai/research.
Authors: Lily Erickson
Abstract: Despite lagging behind their modal cousins in many respects, Vision Transformers have provided an interesting opportunity to bridge the gap between sequence modeling and image modeling. Up until now however, vision transformers have largely been held back, due to both computational inefficiency, and lack of proper handling of spatial dimensions. In this paper, we introduce the Cross-Axis Transformer. CAT is a model inspired by both Axial Transformers, and Microsoft's recent Retentive Network, that drastically reduces the required number of floating point operations required to process an image, while simultaneously converging faster and more accurately than the Vision Transformers it replaces.
Authors: Haoxin Wang, Yipeng Mo, Kunlan Xiang, Nan Yin, Honghe Dai, Bixiong Li, Songhai Fan, Site Mo
Abstract: In the domain of multivariate time series analysis, the concept of channel independence has been increasingly adopted, demonstrating excellent performance due to its ability to eliminate noise and the influence of irrelevant variables. However, such a concept often simplifies the complex interactions among channels, potentially leading to information loss. To address this challenge, we propose a strategy of channel independence followed by mixing. Based on this strategy, we introduce CSformer, a novel framework featuring a two-stage multiheaded self-attention mechanism. This mechanism is designed to extract and integrate both channel-specific and sequence-specific information. Distinctively, CSformer employs parameter sharing to enhance the cooperative effects between these two types of information. Moreover, our framework effectively incorporates sequence and channel adapters, significantly improving the model's ability to identify important information across various dimensions. Extensive experiments on several real-world datasets demonstrate that CSformer achieves state-of-the-art results in terms of overall performance.
Authors: YongKyung Oh, Dongyoung Lim, Sungil Kim
Abstract: Time series analysis faces significant challenges when dealing with irregular and incomplete data. While Neural Differential Equation (NDE) based methods have shown promise, they struggle with limited expressiveness, scalability issues, and stability concerns. Conversely, Neural Flows offer stability but falter with irregular data. We introduce DualDynamics, a novel framework that synergistically combines NDE-based method and Neural Flow-based method. This approach enhances expressive power while balancing computational demands, addressing critical limitations of existing techniques. We demonstrate DualDynamics' effectiveness across diverse tasks: classification of robustness to dataset shift, irregularly-sampled series, interpolation of missing data, and forecasting with partial observations. Our results show consistent outperformance over state-of-the-art methods, indicating DualDynamics' potential to advance irregular time series analysis significantly.
Authors: Joan Giner-Miguelez, Abel G\'omez, Jordi Cabot
Abstract: To ensure the fairness and trustworthiness of machine learning (ML) systems, recent legislative initiatives and relevant research in the ML community have pointed out the need to document the data used to train ML models. Besides, data-sharing practices in many scientific domains have evolved in recent years for reproducibility purposes. In this sense, academic institutions' adoption of these practices has encouraged researchers to publish their data and technical documentation in peer-reviewed publications such as data papers. In this study, we analyze how this broader scientific data documentation meets the needs of the ML community and regulatory bodies for its use in ML technologies. We examine a sample of 4041 data papers of different domains, assessing their completeness, coverage of the requested dimensions, and trends in recent years. We focus on the most and least documented dimensions and compare the results with those of an ML-focused venue (NeurIPS D&B track) publishing papers describing datasets. As a result, we propose a set of recommendation guidelines for data creators and scientific data publishers to increase their data's preparedness for its transparent and fairer use in ML technologies.
Authors: Amir Taubenfeld, Yaniv Dover, Roi Reichart, Ariel Goldstein
Abstract: The emergence of Large Language Models (LLMs), has opened exciting possibilities for constructing computational simulations designed to replicate human behavior accurately. Current research suggests that LLM-based agents become increasingly human-like in their performance, sparking interest in using these AI agents as substitutes for human participants in behavioral studies. However, LLMs are complex statistical learners without straightforward deductive rules, making them prone to unexpected behaviors. Hence, it is crucial to study and pinpoint the key behavioral distinctions between humans and LLM-based agents. In this study, we highlight the limitations of LLMs in simulating human interactions, particularly focusing on LLMs' ability to simulate political debates on topics that are important aspects of people's day-to-day lives and decision-making processes. Our findings indicate a tendency for LLM agents to conform to the model's inherent social biases despite being directed to debate from certain political perspectives. This tendency results in behavioral patterns that seem to deviate from well-established social dynamics among humans. We reinforce these observations using an automatic self-fine-tuning method, which enables us to manipulate the biases within the LLM and demonstrate that agents subsequently align with the altered biases. These results underscore the need for further research to develop methods that help agents overcome these biases, a critical step toward creating more realistic simulations.
Authors: Yuxin Ren, Qiya Yang, Yichun Wu, Wei Xu, Yalong Wang, Zhiqiang Zhang
Abstract: Contemporary recommendation systems are designed to meet users' needs by delivering tailored lists of items that align with their specific demands or interests. In a multi-stage recommendation system, reranking plays a crucial role by modeling the intra-list correlations among items. The key challenge of reranking lies in the exploration of optimal sequences within the combinatorial space of permutations. Recent research proposes a generator-evaluator learning paradigm, where the generator generates multiple feasible sequences and the evaluator picks out the best sequence based on the estimated listwise score. The generator is of vital importance, and generative models are well-suited for the generator function. Current generative models employ an autoregressive strategy for sequence generation. However, deploying autoregressive models in real-time industrial systems is challenging. To address these issues, we propose a Non-AutoRegressive generative model for reranking Recommendation (NAR4Rec) designed to enhance efficiency and effectiveness. To tackle challenges such as sparse training samples and dynamic candidates, we introduce a matching model. Considering the diverse nature of user feedback, we employ a sequence-level unlikelihood training objective to differentiate feasible sequences from unfeasible ones. Additionally, to overcome the lack of dependency modeling in non-autoregressive models regarding target items, we introduce contrastive decoding to capture correlations among these items. Extensive offline experiments validate the superior performance of NAR4Rec over state-of-the-art reranking methods. Online A/B tests reveal that NAR4Rec significantly enhances the user experience. Furthermore, NAR4Rec has been fully deployed in a popular video app Kuaishou with over 300 million daily active users.
Authors: Cl\'ement Gaspard, Gr\'egoire Passault, M\'elodie Daniel, Olivier Ly
Abstract: Designing a humanoid locomotion controller is challenging and classically split up in sub-problems. Footstep planning is one of those, where the sequence of footsteps is defined. Even in simpler environments, finding a minimal sequence, or even a feasible sequence, yields a complex optimization problem. In the literature, this problem is usually addressed by search-based algorithms (e.g. variants of A*). However, such approaches are either computationally expensive or rely on hand-crafted tuning of several parameters. In this work, at first, we propose an efficient footstep planning method to navigate in local environments with obstacles, based on state-of-the art Deep Reinforcement Learning (DRL) techniques, with very low computational requirements for on-line inference. Our approach is heuristic-free and relies on a continuous set of actions to generate feasible footsteps. In contrast, other methods necessitate the selection of a relevant discrete set of actions. Second, we propose a forecasting method, allowing to quickly estimate the number of footsteps required to reach different candidates of local targets. This approach relies on inherent computations made by the actor-critic DRL architecture. We demonstrate the validity of our approach with simulation results, and by a deployment on a kid-size humanoid robot during the RoboCup 2023 competition.
Authors: Mengqi Zhou, Yuxi Wang, Jun Hou, Shougao Zhang, Yiwei Li, Chuanchen Luo, Junran Peng, Zhaoxiang Zhang
Abstract: Developing comprehensive explicit world models is crucial for understanding and simulating real-world scenarios. Recently, Procedural Controllable Generation (PCG) has gained significant attention in large-scale scene generation by enabling the creation of scalable, high-quality assets. However, PCG faces challenges such as limited modular diversity, high expertise requirements, and challenges in managing the diverse elements and structures in complex scenes. In this paper, we introduce a large-scale scene generation framework, SceneX, which can automatically produce high-quality procedural models according to designers' textual descriptions. Specifically, the proposed method comprises two components, PCGHub and PCGPlanner. The former encompasses an extensive collection of accessible procedural assets and thousands of hand-craft API documents to perform as a standard protocol for PCG controller. The latter aims to generate executable actions for Blender to produce controllable and precise 3D assets guided by the user's instructions. Extensive experiments demonstrated the capability of our method in controllable large-scale scene generation, including nature scenes and unbounded cities, as well as scene editing such as asset placement and season translation.
Authors: Remi Genet, Hugo Inzirillo
Abstract: Recurrent Neural Networks (RNNs) have revolutionized many areas of machine learning, particularly in natural language and data sequence processing. Long Short-Term Memory (LSTM) has demonstrated its ability to capture long-term dependencies in sequential data. Inspired by the Kolmogorov-Arnold Networks (KANs) a promising alternatives to Multi-Layer Perceptrons (MLPs), we proposed a new neural networks architecture inspired by KAN and the LSTM, the Temporal Kolomogorov-Arnold Networks (TKANs). TKANs combined the strenght of both networks, it is composed of Recurring Kolmogorov-Arnold Networks (RKANs) Layers embedding memory management. This innovation enables us to perform multi-step time series forecasting with enhanced accuracy and efficiency. By addressing the limitations of traditional models in handling complex sequential patterns, the TKAN architecture offers significant potential for advancements in fields requiring more than one step ahead forecasting.
Authors: Aidan Kierans, Avijit Ghosh, Hananel Hazan, Shiri Dori-Hacohen
Abstract: Existing work on the alignment problem has focused mainly on (1) qualitative descriptions of the alignment problem; (2) attempting to align AI actions with human interests by focusing on value specification and learning; and/or (3) focusing on a single agent or on humanity as a monolith. Recent sociotechnical approaches highlight the need to understand complex misalignment among multiple human and AI agents. We address this gap by adapting a computational social science model of human contention to the alignment problem. Our model quantifies misalignment in large, diverse agent groups with potentially conflicting goals across various problem areas. Misalignment scores in our framework depend on the observed agent population, the domain in question, and conflict between agents' weighted preferences. Through simulations, we demonstrate how our model captures intuitive aspects of misalignment across different scenarios. We then apply our model to two case studies, including an autonomous vehicle setting, showcasing its practical utility. Our approach offers enhanced explanatory power for complex sociotechnical environments and could inform the design of more aligned AI systems in real-world applications.
Authors: Zhen Tao, Yanfang Chen, Dinghao Xi, Zhiyu Li, Wei Xu
Abstract: The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored and LLM-generated texts. Existing detection benchmarks are constrained by their reliance on static datasets, scenario-specific tasks (e.g., question answering and text refinement), and a primary focus on English, overlooking the diverse linguistic and operational subtleties of LLMs. To address these gaps, we propose CUDRT, a comprehensive evaluation framework and bilingual benchmark in Chinese and English, categorizing LLM activities into five key operations: Create, Update, Delete, Rewrite, and Translate. CUDRT provides extensive datasets tailored to each operation, featuring outputs from state-of-the-art LLMs to assess the reliability of LLM-generated text detectors. This framework supports scalable, reproducible experiments and enables in-depth analysis of how operational diversity, multilingual training sets, and LLM architectures influence detection performance. Our extensive experiments demonstrate the framework's capacity to optimize detection systems, providing critical insights to enhance reliability, cross-linguistic adaptability, and detection accuracy. By advancing robust methodologies for identifying LLM-generated texts, this work contributes to the development of intelligent systems capable of meeting real-world multilingual detection challenges. Source code and dataset are available at GitHub.
Authors: Jie Chen, Xintian Han, Yu Ma, Xun Zhou, Liang Xiang
Abstract: Automatic code generation has been a longstanding research topic. With the advancement of general-purpose large language models (LLMs), the ability to code stands out as one important measure to the model's reasoning performance. Usually, a two-stage training paradigm is implemented to obtain a Code LLM, namely the pretraining and the fine-tuning. Within the fine-tuning, supervised fine-tuning (SFT), and reinforcement learning (RL) are often used to improve the model's zero-shot ability. A large number of work has been conducted to improve the model's performance on code-related benchmarks with either modifications to the algorithm or refinement of the dataset. However, we still lack a deep insight into the correlation between SFT and RL. For instance, what kind of dataset should be used to ensure generalization, or what if we abandon the SFT phase in fine-tuning. In this work, we make an attempt to understand the correlation between SFT and RL. To facilitate our research, we manually craft 100 basis python functions, called atomic functions, and then a synthesizing pipeline is deployed to create a large number of synthetic functions on top of the atomic ones. In this manner, we ensure that the train and test sets remain distinct, preventing data contamination. Through comprehensive ablation study, we find: (1) Both atomic and synthetic functions are indispensable for SFT's generalization, and only a handful of synthetic functions are adequate; (2) Through RL, the SFT's generalization to target domain can be greatly enhanced, even with the same training prompts; (3) Training RL from scratch can alleviate the over-fitting issue introduced in the SFT phase.
Authors: Haoyi Zhang, Guohao Sun, Jinhu Lu, Guanfeng Liu, Xiu Susie Fang
Abstract: Sequential recommendation (SR) tasks aim to predict users' next interaction by learning their behavior sequence and capturing the connection between users' past interactions and their changing preferences. Conventional SR models often focus solely on capturing sequential patterns within the training data, neglecting the broader context and semantic information embedded in item titles from external sources. This limits their predictive power and adaptability. Large language models (LLMs) have recently shown promise in SR tasks due to their advanced understanding capabilities and strong generalization abilities. Researchers have attempted to enhance LLMs-based recommendation performance by incorporating information from conventional SR models. However, previous approaches have encountered problems such as 1) limited textual information leading to poor recommendation performance, 2) incomplete understanding and utilization of conventional SR model information by LLMs, and 3) excessive complexity and low interpretability of LLMs-based methods. To improve the performance of LLMs-based SR, we propose a novel framework, Distilling Sequential Pattern to Enhance LLMs-based Sequential Recommendation (DELRec), which aims to extract knowledge from conventional SR models and enable LLMs to easily comprehend and utilize the extracted knowledge for more effective SRs. DELRec consists of two main stages: 1) Distill Pattern from Conventional SR Models, focusing on extracting behavioral patterns exhibited by conventional SR models using soft prompts through two well-designed strategies; 2) LLMs-based Sequential Recommendation, aiming to fine-tune LLMs to effectively use the distilled auxiliary information to perform SR tasks. Extensive experimental results conducted on four real datasets validate the effectiveness of the DELRec framework.
Authors: Anshuman Suri, Xiao Zhang, David Evans
Abstract: Membership inference attacks are used as a key tool for disclosure auditing. They aim to infer whether an individual record was used to train a model. While such evaluations are useful to demonstrate risk, they are computationally expensive and often make strong assumptions about potential adversaries' access to models and training environments, and thus do not provide tight bounds on leakage from potential attacks. We show how prior claims around black-box access being sufficient for optimal membership inference do not hold for stochastic gradient descent, and that optimal membership inference indeed requires white-box access. Our theoretical results lead to a new white-box inference attack, IHA (Inverse Hessian Attack), that explicitly uses model parameters by taking advantage of computing inverse-Hessian vector products. Our results show that both auditors and adversaries may be able to benefit from access to model parameters, and we advocate for further research into white-box methods for membership inference.
Authors: Quanming Yao, Yongqi Zhang, Yaqing Wang, Nan Yin, James Kwok, Qiang Yang
Abstract: The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due to bottlenecks in data, computation, and trust, the sustainability of this strategy is a serious concern. In this paper, we attempt to address this issue in a parsimonious manner (i.e., achieving greater potential with simpler models). The key is to drive models using domain-specific knowledge, such as symbols, logic, and formulas, instead of purely relying on scaleup. This approach allows us to build a framework that uses this knowledge as "building blocks" to achieve parsimony in model design, training, and interpretation. Empirical results show that our methods surpass those that typically follow the scaling law. We also demonstrate our framework in AI for science, specifically in the problem of drug-drug interaction prediction. We hope our research can foster more diverse technical roadmaps in the era of foundation models.
Authors: Yuxi Xia, Kilm Zaporojets, Benjamin Roth
Abstract: A diverse range of large language models (LLMs), e.g., ChatGPT, and visual question answering (VQA) models, e.g., BLIP, have been developed for solving textual and visual question answering tasks. However, fine-tuning these models is either difficult, as it requires access via APIs, rendering them as black-boxes, or costly due to the need of tuning a large number of parameters. To address this, we introduce InfoSel, a data-efficient ensemble method that learns to dynamically pick the winner from existing black-box models for predictions on both textual and multimodal visual question answering tasks. Unlike traditional ensemble models, InfoSel does not rely on prediction probabilities or confidences, which typically are not available in black-box models. Experimental results on four datasets demonstrate that our approach achieves an absolute increase of up to +5.19\% in the F1-score compared to standalone LLMs using only 1K training instances.
Authors: B. Kaan Karamete, Eli Glaser
Abstract: This paper discusses how to generate general graph node embeddings from knowledge graph representations. The embedded space is composed of a number of sub-features to mimic both local affinity and remote structural relevance. These sub-feature dimensions are defined by several indicators that we speculate to catch nodal similarities, such as hop-based topological patterns, the number of overlapping labels, the transitional probabilities (markov-chain probabilities), and the cluster indices computed by our recursive spectral bisection (RSB) algorithm. These measures are flattened over the one dimensional vector space into their respective sub-component ranges such that the entire set of vector similarity functions could be used for finding similar nodes. The error is defined by the sum of pairwise square differences across a randomly selected sample of graph nodes between the assumed embeddings and the ground truth estimates as our novel loss function. The ground truth is estimated to be a combination of pairwise Jaccard similarity and the number of overlapping labels. Finally, we demonstrate a multi-variate stochastic gradient descent (SGD) algorithm to compute the weighing factors among sub-vector spaces to minimize the average error using a random sampling logic.
Authors: Jiajun Shen, Tong Zhou, Yubo Chen, Kang Liu
Abstract: Enabling Large Language Models (LLMs) to generate citations in Question-Answering (QA) tasks is an emerging paradigm aimed at enhancing the verifiability of their responses when LLMs are utilizing external references to generate an answer. However, there is currently no unified framework to standardize and fairly compare different citation generation methods, leading to difficulties in reproducing different methods and a comprehensive assessment. To cope with the problems above, we introduce \name, an open-source and modular toolkit designed to facilitate the implementation and evaluation of existing citation generation methods, while also fostering the development of new approaches to improve citation quality in LLM outputs. This tool is highly extensible, allowing users to utilize 4 main modules and 14 components to construct a pipeline, evaluating an existing method or innovative designs. Our experiments with two state-of-the-art LLMs and 11 citation generation baselines demonstrate varying strengths of different modules in answer accuracy and citation quality improvement, as well as the challenge of enhancing granularity. Based on our analysis of the effectiveness of components, we propose a new method, self-RAG \snippet, obtaining a balanced answer accuracy and citation quality. Citekit is released at https://github.com/SjJ1017/Citekit.
Authors: Hanqiu Chen, Xuebin Yao, Pradeep Subedi, Cong Hao
Abstract: Edge computing is a distributed computing paradigm that collects and processes data at or near the source of data generation. The on-device learning at edge relies on device-to-device wireless communication to facilitate real-time data sharing and collaborative decision-making among multiple devices. This significantly improves the adaptability of the edge computing system to the changing environments. However, as the scale of the edge computing system is getting larger, communication among devices is becoming the bottleneck because of the limited bandwidth of wireless communication leads to large data transfer latency. To reduce the amount of device-to-device data transmission and accelerate on-device learning, in this paper, we propose Residual-INR, a fog computing-based communication-efficient on-device learning framework by utilizing implicit neural representation (INR) to compress images/videos into neural network weights. Residual-INR enhances data transfer efficiency by collecting JPEG images from edge devices, compressing them into INR format at the fog node, and redistributing them for on-device learning. By using a smaller INR for full image encoding and a separate object INR for high-quality object region reconstruction through residual encoding, our technique can reduce the encoding redundancy while maintaining the object quality. Residual-INR is a promising solution for edge on-device learning because it reduces data transmission by up to 5.16 x across a network of 10 edge devices. It also facilitates CPU-free accelerated on-device learning, achieving up to 2.9 x speedup without sacrificing accuracy. Our code is available at: https://github.com/sharc-lab/Residual-INR.
Authors: Xin Sun, Xiao Tang, Abdallah El Ali, Zhuying Li, Pengjie Ren, Jan de Wit, Jiahuan Pei, Jos A. Bosch
Abstract: Recent advancements in large language models (LLMs) have shown promise in generating psychotherapeutic dialogues, particularly in the context of motivational interviewing (MI). However, the inherent lack of transparency in LLM outputs presents significant challenges given the sensitive nature of psychotherapy. Applying MI strategies, a set of MI skills, to generate more controllable therapeutic-adherent conversations with explainability provides a possible solution. In this work, we explore the alignment of LLMs with MI strategies by first prompting the LLMs to predict the appropriate strategies as reasoning and then utilizing these strategies to guide the subsequent dialogue generation. We seek to investigate whether such alignment leads to more controllable and explainable generations. Multiple experiments including automatic and human evaluations are conducted to validate the effectiveness of MI strategies in aligning psychotherapy dialogue generation. Our findings demonstrate the potential of LLMs in producing strategically aligned dialogues and suggest directions for practical applications in psychotherapeutic settings.
Authors: Zhongjian Zhang, Xiao Wang, Huichi Zhou, Yue Yu, Mengmei Zhang, Cheng Yang, Chuan Shi
Abstract: Graph neural networks (GNNs) are vulnerable to adversarial attacks, especially for topology perturbations, and many methods that improve the robustness of GNNs have received considerable attention. Recently, we have witnessed the significant success of large language models (LLMs), leading many to explore the great potential of LLMs on GNNs. However, they mainly focus on improving the performance of GNNs by utilizing LLMs to enhance the node features. Therefore, we ask: Will the robustness of GNNs also be enhanced with the powerful understanding and inference capabilities of LLMs? By presenting the empirical results, we find that despite that LLMs can improve the robustness of GNNs, there is still an average decrease of 23.1% in accuracy, implying that the GNNs remain extremely vulnerable against topology attacks. Therefore, another question is how to extend the capabilities of LLMs on graph adversarial robustness. In this paper, we propose an LLM-based robust graph structure inference framework, LLM4RGNN, which distills the inference capabilities of GPT-4 into a local LLM for identifying malicious edges and an LM-based edge predictor for finding missing important edges, so as to recover a robust graph structure. Extensive experiments demonstrate that LLM4RGNN consistently improves the robustness across various GNNs. Even in some cases where the perturbation ratio increases to 40%, the accuracy of GNNs is still better than that on the clean graph. The source code can be found in https://github.com/zhongjian-zhang/LLM4RGNN.
Authors: Kai Qiu, Xiang Li, Hao Chen, Jie Sun, Jinglu Wang, Zhe Lin, Marios Savvides, Bhiksha Raj
Abstract: Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the efficiency of audio generation remains an essential issue to be addressed, especially for AR models that are incorporated in large language models (LLMs). In this paper, we analyze the token length of audio tokenization and propose a novel \textbf{S}cale-level \textbf{A}udio \textbf{T}okenizer (SAT), with improved residual quantization. Based on SAT, a scale-level \textbf{A}coustic \textbf{A}uto\textbf{R}egressive (AAR) modeling framework is further proposed, which shifts the next-token AR prediction to next-scale AR prediction, significantly reducing the training cost and inference time. To validate the effectiveness of the proposed approach, we comprehensively analyze design choices and demonstrate the proposed AAR framework achieves a remarkable \textbf{35}$\times$ faster inference speed and +\textbf{1.33} Fr\'echet Audio Distance (FAD) against baselines on the AudioSet benchmark. Code: \url{https://github.com/qiuk2/AAR}.
Authors: Jiaang Li, Quan Wang, Zhongnan Wang, Yongdong Zhang, Zhendong Mao
Abstract: Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and result in a significant forgetting effect in lifelong editing scenarios, where sequential edits are conducted over time. Previous approaches manage sequential edits by freezing original parameters and discretely allocating new parameters for each knowledge update. However, these methods lack robustness to minor input variations due to the discrete mapping between data and parameters. To overcome this challenge, we propose ELDER, a novel approach to create a continuous association between data and adapters. ELDER integrates multiple LoRAs through a router network and is trained to establish a smooth data-adapter association, thereby enhancing the edit robustness and generalization of semantically equivalent inputs. To ensure inputs containing the same knowledge will be processed by the same LoRAs, we design a novel loss to guide the model link LoRA allocations with edit knowledge. Furthermore, we propose a deferral mechanism to retain the original LLM capabilities post-edit. Extensive experiments on GPT-2 XL and LLaMA2-7B demonstrate that ELDER effectively edits models in the lifelong setting, outperforming eight baselines while exhibiting strong scalability and preserving LLMs' general abilities on downstream tasks.
Authors: Chao Zhang, Jiamin Tang, Jing Xiao
Abstract: Significant advancements in Large Multimodal Models (LMMs) have enabled them to tackle complex problems involving visual-mathematical reasoning. However, their ability to identify geometric elements remains underexplored. To address this gap, we introduce Tangram, a novel benchmark designed to evaluate the performance of LMMs on geometric element recognition. Tangram comprises 1,080 diverse geometric diagrams sourced from primary and secondary school exams, competitions, and textbooks, ranging from simple geometric shapes to complex combinations. Each diagram is paired with four questions, resulting in 4,320 visual-question-answer pairs. Unlike existing benchmarks that emphasize higher-level cognition and reasoning, Tangram focuses on understanding geometric elements, requiring models to perform a ``simple yet challenging" counting task. Systematic evaluation of 13 prominent LMMs, such as GPT-4o and Claude 3.5 Sonnet, reveals that these models face significant challenges even in seemingly straightforward tasks. The top-performing model achieves an accuracy of only 53.0%, highlighting a substantial gap compared to human performance. These findings underscore the limitations of current multimodal AI systems in handling basic perception tasks and serve to inspire the development of the next generation of expert-level multimodal foundational models. The data and code will be released soon.
Authors: Haichuan Hu, Ye Shang, Guolin Xu, Congqing He, Quanjun Zhang
Abstract: LLMs have long demonstrated remarkable effectiveness in automatic program repair (APR), with OpenAI's ChatGPT being one of the most widely used models in this domain. Through continuous iterations and upgrades of GPT-family models, their performance in fixing bugs has already reached state-of-the-art levels. However, there are few works comparing the effectiveness and variations of different versions of GPT-family models on APR. In this work, inspired by the recent public release of the GPT-o1 models, we conduct the first study to compare the effectiveness of different versions of the GPT-family models in APR. We evaluate the performance of the latest version of the GPT-family models (i.e., O1-preview and O1-mini), GPT-4o, and the historical version of ChatGPT on APR. We conduct an empirical study of the four GPT-family models against other LLMs and APR techniques on the QuixBugs benchmark from multiple evaluation perspectives, including repair success rate, repair cost, response length, and behavior patterns. The results demonstrate that O1's repair capability exceeds that of prior GPT-family models, successfully fixing all 40 bugs in the benchmark. Our work can serve as a foundation for further in-depth exploration of the applications of GPT-family models in APR.
Authors: Dingjie Song, Wenjun Wang, Shunian Chen, Xidong Wang, Michael Guan, Benyou Wang
Abstract: The rapid advancement of Multimodal Large Language Models (MLLMs) has led to remarkable performances across various domains. However, this progress is accompanied by a substantial surge in the resource consumption of these models. We address this pressing issue by introducing a new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance. Inspired by human attention patterns in Visual Question Answering (VQA) tasks, TRIM presents a fresh perspective on the selection and reduction of image tokens. The TRIM method has been extensively tested across 12 datasets, and the results demonstrate a significant reduction in computational overhead while maintaining a consistent level of performance. This research marks a critical stride in efficient MLLM development, promoting greater accessibility and sustainability of high-performing models.
Authors: Ningyuan Xi, Xiaoyu Wang, Yetao Wu, Teng Chen, Qingqing Gu, Yue Zhao, Jinxian Qu, Zhonglin Jiang, Yong Chen, Luo Ji
Abstract: Large Language Model can reasonably understand and generate human expressions but may lack of thorough thinking and reasoning mechanisms. Recently there have been several studies which enhance the thinking ability of language models but most of them are not data-driven or training-based. In this paper, we are motivated by the cognitive mechanism in the natural world, and design a novel model architecture called TaS which allows it to first consider the thoughts and then express the response based upon the query. We design several pipelines to annotate or generate the thought contents from prompt-response samples, then add language heads in a middle layer which behaves as the thinking layer. We train the language model by the thoughts-augmented data and successfully let the thinking layer automatically generate reasonable thoughts and finally output more reasonable responses. Both qualitative examples and quantitative results validate the effectiveness and performance of TaS. Our code is available at https://anonymous.4open.science/r/TadE.
Authors: Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou, Muhao Chen
Abstract: Retrieval-augmented generation (RAG) improves large language models (LMs) by incorporating non-parametric knowledge through evidence retrieved from external sources. However, it often struggles to cope with inconsistent and irrelevant information that can distract the LM from its tasks, especially when multiple evidence pieces are required. While compressing the retrieved evidence with a compression model aims to address this issue, the compressed evidence may still be unfamiliar to the target model used for downstream tasks, potentially failing to utilize the evidence effectively. We propose FaviComp (Familarity-Aware Evidence Compression), a novel training-free evidence compression technique that makes retrieved evidence more familiar to the target model, while seamlessly integrating parametric knowledge from the model. Experimental results show that FaviComp consistently outperforms most recent evidence compression baselines across multiple open-domain QA datasets, improving accuracy by up to 28.1% while achieving high compression rates. Additionally, we demonstrate the effective integration of both parametric and non-parametric knowledge during evidence compression.
Authors: Brent Yi, Vickie Ye, Maya Zheng, Yunqi Li, Lea M\"uller, Georgios Pavlakos, Yi Ma, Jitendra Malik, Angjoo Kanazawa
Abstract: We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters that capture a device wearer's actions in the allocentric coordinate frame of the scene. To achieve this, our key insight is in representation: we propose spatial and temporal invariance criteria for improving model performance, from which we derive a head motion conditioning parameterization that improves estimation by up to 18%. We also show how the bodies estimated by our system can improve hand estimation: the resulting kinematic and temporal constraints can reduce world-frame errors in single-frame estimates by 40%. Project page: https://egoallo.github.io/
Authors: Hakaze Cho, Mariko Kato, Yoshihiro Sakai, Naoya Inoue
Abstract: In-context Learning (ICL) is an emerging few-shot learning paradigm on Language Models (LMs) with inner mechanisms un-explored. There are already existing works describing the inner processing of ICL, while they struggle to capture all the inference phenomena in large language models. Therefore, this paper proposes a comprehensive circuit to model the inference dynamics and try to explain the observed phenomena of ICL. In detail, we divide ICL inference into 3 major operations: (1) Input Text Encode: LMs encode every input text (demonstrations and queries) into linear representation in the hidden states with sufficient information to solve ICL tasks. (2) Semantics Merge: LMs merge the encoded representations of demonstrations with their corresponding label tokens to produce joint representations of labels and demonstrations. (3) Feature Retrieval and Copy: LMs search the joint representations similar to the query representation on a task subspace, and copy the searched representations into the query. Then, language model heads capture these copied label representations to a certain extent and decode them into predicted labels. The proposed inference circuit successfully captured many phenomena observed during the ICL process, making it a comprehensive and practical explanation of the ICL inference process. Moreover, ablation analysis by disabling the proposed steps seriously damages the ICL performance, suggesting the proposed inference circuit is a dominating mechanism. Additionally, we confirm and list some bypass mechanisms that solve ICL tasks in parallel with the proposed circuit.
Authors: Jiaming Zhang, Junhong Ye, Xingjun Ma, Yige Li, Yunfan Yang, Jitao Sang, Dit-Yan Yeung
Abstract: Due to their multimodal capabilities, Vision-Language Models (VLMs) have found numerous impactful applications in real-world scenarios. However, recent studies have revealed that VLMs are vulnerable to image-based adversarial attacks, particularly targeted adversarial images that manipulate the model to generate harmful content specified by the adversary. Current attack methods rely on predefined target labels to create targeted adversarial attacks, which limits their scalability and applicability for large-scale robustness evaluations. In this paper, we propose AnyAttack, a self-supervised framework that generates targeted adversarial images for VLMs without label supervision, allowing any image to serve as a target for the attack. Our framework employs the pre-training and fine-tuning paradigm, with the adversarial noise generator pre-trained on the large-scale LAION-400M dataset. This large-scale pre-training endows our method with powerful transferability across a wide range of VLMs. Extensive experiments on five mainstream open-source VLMs (CLIP, BLIP, BLIP2, InstructBLIP, and MiniGPT-4) across three multimodal tasks (image-text retrieval, multimodal classification, and image captioning) demonstrate the effectiveness of our attack. Additionally, we successfully transfer AnyAttack to multiple commercial VLMs, including Google Gemini, Claude Sonnet, Microsoft Copilot and OpenAI GPT. These results reveal an unprecedented risk to VLMs, highlighting the need for effective countermeasures.
Authors: Zaid Khan, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal
Abstract: The process of creating training data to teach models is currently driven by humans, who manually analyze model weaknesses and plan how to create data that improves a student model. Approaches using LLMs as annotators reduce human effort, but still require humans to interpret feedback from evaluations and control the LLM to produce data the student needs. Automating this labor-intensive process by creating autonomous data generation agents - or teachers - is desirable, but requires environments that can simulate the feedback-driven, iterative, closed loop of data creation. To enable rapid, scalable testing for such agents and their modules, we introduce DataEnvGym, a testbed of teacher environments for data generation agents. DataEnvGym frames data generation as a sequential decision-making task, involving an agent consisting of a data generation policy (which generates a plan for creating training data) and a data generation engine (which transforms the plan into data), inside an environment that provides student feedback. The agent's goal is to improve student performance. Students are iteratively trained and evaluated on generated data, and their feedback (in the form of errors or weak skills) is reported to the agent after each iteration. DataEnvGym includes multiple teacher environment instantiations across 3 levels of structure in the state representation and action space. More structured environments are based on inferred skills and offer more interpretability and curriculum control. We support 4 domains (math, code, VQA, and tool-use) and test multiple students and teachers. Example agents in our teaching environments can iteratively improve students across tasks and settings. Moreover, we show that environments teach different skill levels and test variants of key modules, pointing to future work in improving data generation agents, engines, and feedback mechanisms.
Authors: Fabian Paischer, Lukas Hauzenberger, Thomas Schmied, Benedikt Alkin, Marc Peter Deisenroth, Sepp Hochreiter
Abstract: Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned on a downstream task for a specific application. The most successful and most commonly used fine-tuning method is to update the pre-trained weights via a low-rank adaptation (LoRA). LoRA introduces new weight matrices that are usually initialized at random with a uniform rank distribution across the model weights. Recent works focus on different initialization schemes or the learning of adaptive ranks during fine-tuning. Both approaches have only been investigated in isolation, resulting in slow convergence or a uniform rank distribution, in turn leading to suboptimal performance. We propose to improve LoRA by initializing the new weights in a data-driven manner by computing singular value decomposition (SVD) on minibatches of activation vectors. Then, we initialize the LoRA matrices with the obtained right-singular vectors and redistribute ranks among all weight matrices to provably store the maximum amount of information of the downstream data in the newly introduced weights. In this way, only what information to maintain or neglect during the fine-tuning process needs to be learned. We call our new method $\textbf{E}$xplained $\textbf{V}$ariance $\textbf{A}$daptation (EVA). We apply EVA to a variety of fine-tuning tasks ranging from language generation and understanding to image classification and reinforcement learning. EVA exhibits faster convergence than competitors and achieves the highest average score across a multitude of tasks per domain while reducing the number of trainable parameters through rank redistribution.
Authors: Tarun Raheja, Nilay Pochhi, F. D. C. M. Curie
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, but their vulnerability to jailbreak attacks poses significant security risks. This survey paper presents a comprehensive analysis of recent advancements in attack strategies and defense mechanisms within the field of Large Language Model (LLM) red-teaming. We analyze various attack methods, including gradient-based optimization, reinforcement learning, and prompt engineering approaches. We discuss the implications of these attacks on LLM safety and the need for improved defense mechanisms. This work aims to provide a thorough understanding of the current landscape of red-teaming attacks and defenses on LLMs, enabling the development of more secure and reliable language models.
Authors: Zonghai Yao, Aditya Parashar, Huixue Zhou, Won Seok Jang, Feiyun Ouyang, Zhichao Yang, Hong Yu
Abstract: Automatic question generation (QG) is essential for AI and NLP, particularly in intelligent tutoring, dialogue systems, and fact verification. Generating multiple-choice questions (MCQG) for professional exams, like the United States Medical Licensing Examination (USMLE), is particularly challenging, requiring domain expertise and complex multi-hop reasoning for high-quality questions. However, current large language models (LLMs) like GPT-4 struggle with professional MCQG due to outdated knowledge, hallucination issues, and prompt sensitivity, resulting in unsatisfactory quality and difficulty. To address these challenges, we propose MCQG-SRefine, an LLM self-refine-based (Critique and Correction) framework for converting medical cases into high-quality USMLE-style questions. By integrating expert-driven prompt engineering with iterative self-critique and self-correction feedback, MCQG-SRefine significantly enhances human expert satisfaction regarding both the quality and difficulty of the questions. Furthermore, we introduce an LLM-as-Judge-based automatic metric to replace the complex and costly expert evaluation process, ensuring reliable and expert-aligned assessments.
Authors: Shaozhe Hao, Xuantong Liu, Xianbiao Qi, Shihao Zhao, Bojia Zi, Rong Xiao, Kai Han, Kwan-Yee K. Wong
Abstract: We introduce BiGR, a novel conditional image generation model using compact binary latent codes for generative training, focusing on enhancing both generation and representation capabilities. BiGR is the first conditional generative model that unifies generation and discrimination within the same framework. BiGR features a binary tokenizer, a masked modeling mechanism, and a binary transcoder for binary code prediction. Additionally, we introduce a novel entropy-ordered sampling method to enable efficient image generation. Extensive experiments validate BiGR's superior performance in generation quality, as measured by FID-50k, and representation capabilities, as evidenced by linear-probe accuracy. Moreover, BiGR showcases zero-shot generalization across various vision tasks, enabling applications such as image inpainting, outpainting, editing, interpolation, and enrichment, without the need for structural modifications. Our findings suggest that BiGR unifies generative and discriminative tasks effectively, paving the way for further advancements in the field. We further enable BiGR to perform text-to-image generation, showcasing its potential for broader applications.
Authors: Subhankar Ghosh, Arun Sharma, Jayant Gupta, Aneesh Subramanian, Shashi Shekhar
Abstract: Given coarser-resolution projections from global climate models or satellite data, the downscaling problem aims to estimate finer-resolution regional climate data, capturing fine-scale spatial patterns and variability. Downscaling is any method to derive high-resolution data from low-resolution variables, often to provide more detailed and local predictions and analyses. This problem is societally crucial for effective adaptation, mitigation, and resilience against significant risks from climate change. The challenge arises from spatial heterogeneity and the need to recover finer-scale features while ensuring model generalization. Most downscaling methods \cite{Li2020} fail to capture the spatial dependencies at finer scales and underperform on real-world climate datasets, such as sea-level rise. We propose a novel Kriging-informed Conditional Diffusion Probabilistic Model (Ki-CDPM) to capture spatial variability while preserving fine-scale features. Experimental results on climate data show that our proposed method is more accurate than state-of-the-art downscaling techniques.
Authors: Woosung Koh, Jang Han Yoon, MinHyung Lee, Youngjin Song, Jaegwan Cho, Jaehyun Kang, Taehyeon Kim, Se-young Yun, Youngjae Yu, Bongshin Lee
Abstract: Generating high-quality charts with Large Language Models (LLMs) presents significant challenges due to limited data and the high cost of scaling through human curation. $\langle \text{instruction}, \text{data}, \text{code} \rangle$ triplets are scarce and expensive to manually curate as their creation demands technical expertise. To address this scalability challenge, we introduce a reference-free automatic feedback generator, which eliminates the need for costly human intervention. Our novel framework, C$^2$, consists of (1) an automatic feedback provider (ChartAF) and (2) a diverse, reference-free dataset (ChartUIE-8K). The results are compelling: in our first experiment, 74% of respondents strongly preferred, and 10% preferred, the results after feedback. The second post-feedback experiment demonstrates that ChartAF outperform nine baselines. Moreover, ChartUIE-8K significantly improves data diversity by increasing queries, datasets, and chart types by 5982%, 1936%, and 91%, respectively, over benchmarks. Finally, a study of LLM users revealed that 94% of participants preferred ChartUIE-8K's queries, with 93% deeming them aligned with real-world use cases. Core contributions are available as open-source at chartsquared.github.io, with ample qualitative examples.
Authors: Ji Ma
Abstract: As Large Language Model (LLM)-based agents increasingly undertake real-world tasks and engage with human society, how well do we understand their behaviors? We (1) investigate how LLM agents' prosocial behaviors -- a fundamental social norm -- can be induced by different personas and benchmarked against human behaviors; and (2) introduce a behavioral and social science approach to evaluate LLM agents' decision-making. We explored how different personas and experimental framings affect these AI agents' altruistic behavior in dictator games and compared their behaviors within the same LLM family, across various families, and with human behaviors. The findings reveal substantial variations and inconsistencies among LLMs and notable differences compared to human behaviors. Merely assigning a human-like identity to LLMs does not produce human-like behaviors. Despite being trained on extensive human-generated data, these AI agents are unable to capture the internal processes of human decision-making. Their alignment with human is highly variable and dependent on specific model architectures and prompt formulations; even worse, such dependence does not follow a clear pattern. LLMs can be useful task-specific tools but are not yet intelligent human-like agents.
Authors: J. Quetzalcoatl Toledo-Marin, Sebastian Gonzalez, Hao Jia, Ian Lu, Deniz Sogutlu, Abhishek Abhishek, Colin Gay, Eric Paquet, Roger Melko, Geoffrey C. Fox, Maximilian Swiatlowski, Wojciech Fedorko
Abstract: Particle collisions at accelerators such as the Large Hadron Collider, recorded and analyzed by experiments such as ATLAS and CMS, enable exquisite measurements of the Standard Model and searches for new phenomena. Simulations of collision events at these detectors have played a pivotal role in shaping the design of future experiments and analyzing ongoing ones. However, the quest for accuracy in Large Hadron Collider (LHC) collisions comes at an imposing computational cost, with projections estimating the need for millions of CPU-years annually during the High Luminosity LHC (HL-LHC) run \cite{collaboration2022atlas}. Simulating a single LHC event with \textsc{Geant4} currently devours around 1000 CPU seconds, with simulations of the calorimeter subdetectors in particular imposing substantial computational demands \cite{rousseau2023experimental}. To address this challenge, we propose a conditioned quantum-assisted deep generative model. Our model integrates a conditioned variational autoencoder (VAE) on the exterior with a conditioned Restricted Boltzmann Machine (RBM) in the latent space, providing enhanced expressiveness compared to conventional VAEs. The RBM nodes and connections are meticulously engineered to enable the use of qubits and couplers on D-Wave's Pegasus-structured \textit{Advantage} quantum annealer (QA) for sampling. We introduce a novel method for conditioning the quantum-assisted RBM using \textit{flux biases}. We further propose a novel adaptive mapping to estimate the effective inverse temperature in quantum annealers. The effectiveness of our framework is illustrated using Dataset 2 of the CaloChallenge \cite{calochallenge}.
Authors: Haoran Lu, Ruihai Wu, Yitong Li, Sijie Li, Ziyu Zhu, Chuanruo Ning, Yan Shen, Longzan Luo, Yuanpei Chen, Hao Dong
Abstract: Manipulating garments and fabrics has long been a critical endeavor in the development of home-assistant robots. However, due to complex dynamics and topological structures, garment manipulations pose significant challenges. Recent successes in reinforcement learning and vision-based methods offer promising avenues for learning garment manipulation. Nevertheless, these approaches are severely constrained by current benchmarks, which offer limited diversity of tasks and unrealistic simulation behavior. Therefore, we present GarmentLab, a content-rich benchmark and realistic simulation designed for deformable object and garment manipulation. Our benchmark encompasses a diverse range of garment types, robotic systems and manipulators. The abundant tasks in the benchmark further explores of the interactions between garments, deformable objects, rigid bodies, fluids, and human body. Moreover, by incorporating multiple simulation methods such as FEM and PBD, along with our proposed sim-to-real algorithms and real-world benchmark, we aim to significantly narrow the sim-to-real gap. We evaluate state-of-the-art vision methods, reinforcement learning, and imitation learning approaches on these tasks, highlighting the challenges faced by current algorithms, notably their limited generalization capabilities. Our proposed open-source environments and comprehensive analysis show promising boost to future research in garment manipulation by unlocking the full potential of these methods. We guarantee that we will open-source our code as soon as possible. You can watch the videos in supplementary files to learn more about the details of our work. Our project page is available at: https://garmentlab.github.io/
Authors: Jianan Ye, Zhaorui Tan, Yijie Hu, Xi Yang, Guangliang Cheng, Kaizhu Huang
Abstract: Tabular anomaly detection under the one-class classification setting poses a significant challenge, as it involves accurately conceptualizing "normal" derived exclusively from a single category to discern anomalies from normal data variations. Capturing the intrinsic correlation among attributes within normal samples presents one promising method for learning the concept. To do so, the most recent effort relies on a learnable mask strategy with a reconstruction task. However, this wisdom may suffer from the risk of producing uniform masks, i.e., essentially nothing is masked, leading to less effective correlation learning. To address this issue, we presume that attributes related to others in normal samples can be divided into two non-overlapping and correlated subsets, defined as CorrSets, to capture the intrinsic correlation effectively. Accordingly, we introduce an innovative method that disentangles CorrSets from normal tabular data. To our knowledge, this is a pioneering effort to apply the concept of disentanglement for one-class anomaly detection on tabular data. Extensive experiments on 20 tabular datasets show that our method substantially outperforms the state-of-the-art methods and leads to an average performance improvement of 6.1% on AUC-PR and 2.1% on AUC-ROC. Codes are available at https://github.com/yjnanan/Disent-AD.
Authors: Zun Wang, Jialu Li, Han Lin, Jaehong Yoon, Mohit Bansal
Abstract: Storytelling video generation (SVG) has recently emerged as a task to create long, multi-motion, multi-scene videos that consistently represent the story described in the input text script. SVG holds great potential for diverse content creation in media and entertainment; however, it also presents significant challenges: (1) objects must exhibit a range of fine-grained, complex motions, (2) multiple objects need to appear consistently across scenes, and (3) subjects may require multiple motions with seamless transitions within a single scene. To address these challenges, we propose DreamRunner, a novel story-to-video generation method: First, we structure the input script using a large language model (LLM) to facilitate both coarse-grained scene planning as well as fine-grained object-level layout and motion planning. Next, DreamRunner presents retrieval-augmented test-time adaptation to capture target motion priors for objects in each scene, supporting diverse motion customization based on retrieved videos, thus facilitating the generation of new videos with complex, scripted motions. Lastly, we propose a novel spatial-temporal region-based 3D attention and prior injection module SR3AI for fine-grained object-motion binding and frame-by-frame semantic control. We compare DreamRunner with various SVG baselines, demonstrating state-of-the-art performance in character consistency, text alignment, and smooth transitions. Additionally, DreamRunner exhibits strong fine-grained condition-following ability in compositional text-to-video generation, significantly outperforming baselines on T2V-ComBench. Finally, we validate DreamRunner's robust ability to generate multi-object interactions with qualitative examples.
Authors: Ronghui Xu, Hanyin Cheng, Chenjuan Guo, Hongfan Gao, Jilin Hu, Sean Bin Yang, Bin Yang
Abstract: Developing effective path representations has become increasingly essential across various fields within intelligent transportation. Although pre-trained path representation learning models have shown improved performance, they predominantly focus on the topological structures from single modality data, i.e., road networks, overlooking the geometric and contextual features associated with path-related images, e.g., remote sensing images. Similar to human understanding, integrating information from multiple modalities can provide a more comprehensive view, enhancing both representation accuracy and generalization. However, variations in information granularity impede the semantic alignment of road network-based paths (road paths) and image-based paths (image paths), while the heterogeneity of multi-modal data poses substantial challenges for effective fusion and utilization. In this paper, we propose a novel Multi-modal, Multi-granularity Path Representation Learning Framework (MM-Path), which can learn a generic path representation by integrating modalities from both road paths and image paths. To enhance the alignment of multi-modal data, we develop a multi-granularity alignment strategy that systematically associates nodes, road sub-paths, and road paths with their corresponding image patches, ensuring the synchronization of both detailed local information and broader global contexts. To address the heterogeneity of multi-modal data effectively, we introduce a graph-based cross-modal residual fusion component designed to comprehensively fuse information across different modalities and granularities. Finally, we conduct extensive experiments on two large-scale real-world datasets under two downstream tasks, validating the effectiveness of the proposed MM-Path. The code is available at: https://github.com/decisionintelligence/MM-Path.
Authors: Tae-Hoon Lee, Min-Soo Kim
Abstract: Mixed-Integer Linear Programming (MILP) is an optimization technique widely used in various fields. Existing end-to-end learning methods for MILP generate values for a subset of decision variables and delegate the remaining problem to traditional MILP solvers. However, this approach does not guarantee solution feasibility (i.e., satisfying all constraints) due to inaccurate predictions and primarily focuses on prediction for binary decision variables. When addressing MILP involving non-binary integer variables using machine learning (ML), feasibility issues can become even more pronounced. Since finding an optimal solution requires satisfying all constraints, addressing feasibility is critical. To overcome these limitations, we propose a novel reinforcement learning (RL)-based solver that interacts with MILP to incrementally discover better feasible solutions without relying on traditional solvers. We design reward functions tailored for MILP, which enable the RL agent to learn relationships between decision variables and constraints. Furthermore, we leverage a Transformer encoder-based graph neural network (GNN) to effectively model complex relationships among decision variables. Our experimental results demonstrate that the proposed method can solve MILP problems and find near-optimal solutions without delegating the remainder to traditional solvers. The proposed method provides a meaningful step forward as an initial study in solving MILP problems entirely with ML in an end-to-end manner.
Authors: Wenxuan Huang, Zijie Zhai, Yunhang Shen, Shaosheng Cao, Fei Zhao, Xiangfeng Xu, Zheyu Ye, Shaohui Lin
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision understanding, reasoning, and interaction. However, the inference computation and memory increase progressively with the generation of output tokens during decoding, directly affecting the efficacy of MLLMs. Existing methods attempt to reduce the vision context redundancy to achieve efficient MLLMs. Unfortunately, the efficiency benefits of the vision context reduction in the prefill stage gradually diminish during the decoding stage. To address this problem, we proposed a dynamic vision-language context sparsification framework Dynamic-LLaVA, which dynamically reduces the redundancy of vision context in the prefill stage and decreases the memory and computation overhead of the generated language context during decoding. Dynamic-LLaVA designs a tailored sparsification inference scheme for different inference modes, i.e., prefill, decoding with and without KV cache, to achieve efficient inference of MLLMs. In practice, Dynamic-LLaVA can reduce computation consumption by $\sim$75\% in the prefill stage. Meanwhile, throughout the entire generation process of MLLMs, Dynamic-LLaVA reduces the $\sim$50\% computation consumption under decoding without KV cache, while saving $\sim$50\% GPU memory overhead when decoding with KV cache, due to the vision-language context sparsification. Extensive experiments also demonstrate that Dynamic-LLaVA achieves efficient inference for MLLMs with negligible understanding and generation ability degradation or even performance gains compared to the full-context inference baselines. Code is available at https://github.com/Osilly/dynamic_llava .
Authors: Lingxiao Wei, He Yan, Xiangju Lu, Junmin Zhu, Jun Wang, Wei Zhang
Abstract: Large Language Models (LLMs) have been well-researched in various long-context tasks. However, the scarcity of high-quality long-context summarization datasets has hindered further advancements in this area. To address this, we introduce CNNSum, a multi-scale long-context summarization benchmark based on Chinese novels, featuring human-driven annotations, which comprises four subsets totaling 695 samples, with lengths ranging from 16k to 128k. We evaluate numerous LLMs and conduct detailed case analyses. Furthermore, we conduct extensive fine-tuning experiments to explore and improve long-context summarization. In our study: (1) Advanced LLMs like GPT-4o may still generate subjective commentary, leading to vague summaries. (2) Currently, long-context summarization mainly relies on memory ability afforded by longer context lengths. The advantages of Large LLMs are hard to utilize, thus small LLMs are the most cost-effective. (3) Different prompt templates paired with various version models may cause large performance gaps. In further fine-tuning, these can be mitigated, and the Base version models perform better. (4) LLMs with RoPE-base scaled exhibit strong extrapolation potential; using short-context data can significantly improve long-context summarization performance. However, further applying other interpolation methods requires careful selection. (5) CNNSum provides more reliable and insightful evaluation results than other benchmarks. We release CNNSum to advance future research in this field. https://github.com/CxsGhost/CNNSum
Authors: Rainer Muehlhoff, Marte Henningsen
Abstract: [Study in German language.] This study examines the AI-powered grading tool "AI Grading Assistant" by the German company Fobizz, designed to support teachers in evaluating and providing feedback on student assignments. Against the societal backdrop of an overburdened education system and rising expectations for artificial intelligence as a solution to these challenges, the investigation evaluates the tool's functional suitability through two test series. The results reveal significant shortcomings: The tool's numerical grades and qualitative feedback are often random and do not improve even when its suggestions are incorporated. The highest ratings are achievable only with texts generated by ChatGPT. False claims and nonsensical submissions frequently go undetected, while the implementation of some grading criteria is unreliable and opaque. Since these deficiencies stem from the inherent limitations of large language models (LLMs), fundamental improvements to this or similar tools are not immediately foreseeable. The study critiques the broader trend of adopting AI as a quick fix for systemic problems in education, concluding that Fobizz's marketing of the tool as an objective and time-saving solution is misleading and irresponsible. Finally, the study calls for systematic evaluation and subject-specific pedagogical scrutiny of the use of AI tools in educational contexts.
Authors: Hao Kang, Srikant Bharadwaj, James Hensman, Tushar Krishna, Victor Ruhle, Saravan Rajmohan
Abstract: Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved efficiency of the overall inference, they address different aspects of the problem: quantization focuses on weight-activation operations, while FlashAttention improves execution but requires high-precision formats. Recent Key-value (KV) cache quantization reduces memory bandwidth but still needs floating-point dequantization for attention operation. We present TurboAttention, a comprehensive approach to enable quantized execution of attention that simultaneously addresses both memory and computational efficiency. Our solution introduces two key innovations: FlashQ, a headwise attention quantization technique that enables both compression of KV cache and quantized execution of activation-activation multiplication, and Sparsity-based Softmax Approximation (SAS), which eliminates the need for dequantization to FP32 during exponentiation operation in attention. Experimental results demonstrate that TurboAttention achieves 1.2-1.8x speedup in attention, reduces the KV cache size by over 4.4x, and enables up to 2.37x maximum throughput over the FP16 baseline while outperforming state-of-the-art quantization and compression techniques across various datasets and models.
Authors: Ahmed Rashed, Abdelkrim Kallich, Mohamed Eltayeb
Abstract: Machine learning (ML) algorithms have become integral to decision making in various domains, including healthcare, finance, education, and law enforcement. However, concerns about fairness and bias in these systems pose significant ethical and social challenges. This study investigates the fairness of ML models applied to structured datasets in classification tasks, highlighting the potential for biased predictions to perpetuate systemic inequalities. A publicly available dataset from Kaggle was selected for analysis, offering a realistic scenario for evaluating fairness in machine learning workflows. To assess and mitigate biases, three prominent fairness libraries; Fairlearn by Microsoft, AIF360 by IBM, and the What If Tool by Google were employed. These libraries provide robust frameworks for analyzing fairness, offering tools to evaluate metrics, visualize results, and implement bias mitigation strategies. The research aims to assess the extent of bias in the ML models, compare the effectiveness of these libraries, and derive actionable insights for practitioners. The findings reveal that each library has unique strengths and limitations in fairness evaluation and mitigation. By systematically comparing their capabilities, this study contributes to the growing field of ML fairness by providing practical guidance for integrating fairness tools into real world applications. These insights are intended to support the development of more equitable machine learning systems.
Authors: Divya Shanmugam, Monica Agrawal, Rajiv Movva, Irene Y. Chen, Marzyeh Ghassemi, Maia Jacobs, Emma Pierson
Abstract: The increased capabilities of generative AI have dramatically expanded its possible use cases in medicine. We provide a comprehensive overview of generative AI use cases for clinicians, patients, clinical trial organizers, researchers, and trainees. We then discuss the many challenges -- including maintaining privacy and security, improving transparency and interpretability, upholding equity, and rigorously evaluating models -- which must be overcome to realize this potential, and the open research directions they give rise to.
Authors: Shuhe Wang, Shengyu Zhang, Jie Zhang, Runyi Hu, Xiaoya Li, Tianwei Zhang, Jiwei Li, Fei Wu, Guoyin Wang, Eduard Hovy
Abstract: This paper surveys research in the rapidly growing field of enhancing large language models (LLMs) with reinforcement learning (RL), a technique that enables LLMs to improve their performance by receiving feedback in the form of rewards based on the quality of their outputs, allowing them to generate more accurate, coherent, and contextually appropriate responses. In this work, we make a systematic review of the most up-to-date state of knowledge on RL-enhanced LLMs, attempting to consolidate and analyze the rapidly growing research in this field, helping researchers understand the current challenges and advancements. Specifically, we (1) detail the basics of RL; (2) introduce popular RL-enhanced LLMs; (3) review researches on two widely-used reward model-based RL techniques: Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF); and (4) explore Direct Preference Optimization (DPO), a set of methods that bypass the reward model to directly use human preference data for aligning LLM outputs with human expectations. We will also point out current challenges and deficiencies of existing methods and suggest some avenues for further improvements. Project page of this work can be found at: \url{https://github.com/ShuheWang1998/Reinforcement-Learning-Enhanced-LLMs-A-Survey}.
URLs: https://github.com/ShuheWang1998/Reinforcement-Learning-Enhanced-LLMs-A-Survey
Authors: Zhentao Tan, Ben Xue, Jian Jia, Junhao Wang, Wencai Ye, Shaoyun Shi, Mingjie Sun, Wenjin Wu, Quan Chen, Peng Jiang
Abstract: This paper presents the \textbf{S}emantic-a\textbf{W}ar\textbf{E} spatial-t\textbf{E}mporal \textbf{T}okenizer (SweetTokenizer), a compact yet effective discretization approach for vision data. Our goal is to boost tokenizers' compression ratio while maintaining reconstruction fidelity in the VQ-VAE paradigm. Firstly, to obtain compact latent representations, we decouple images or videos into spatial-temporal dimensions, translating visual information into learnable querying spatial and temporal tokens through a \textbf{C}ross-attention \textbf{Q}uery \textbf{A}uto\textbf{E}ncoder (CQAE). Secondly, to complement visual information during compression, we quantize these tokens via a specialized codebook derived from off-the-shelf LLM embeddings to leverage the rich semantics from language modality. Finally, to enhance training stability and convergence, we also introduce a curriculum learning strategy, which proves critical for effective discrete visual representation learning. SweetTokenizer achieves comparable video reconstruction fidelity with only \textbf{25\%} of the tokens used in previous state-of-the-art video tokenizers, and boost video generation results by \textbf{32.9\%} w.r.t gFVD. When using the same token number, we significantly improves video and image reconstruction results by \textbf{57.1\%} w.r.t rFVD on UCF-101 and \textbf{37.2\%} w.r.t rFID on ImageNet-1K. Additionally, the compressed tokens are imbued with semantic information, enabling few-shot recognition capabilities powered by LLMs in downstream applications.
Authors: Aoming Liang, Qi Liu, Lei Xu, Fahad Sohrab, Weicheng Cui, Changhui Song, Moncef Gabbouj
Abstract: Numerous studies have focused on learning and understanding the dynamics of physical systems from video data, such as spatial intelligence. Artificial intelligence requires quantitative assessments of the uncertainty of the model to ensure reliability. However, there is still a relative lack of systematic assessment of the uncertainties, particularly the uncertainties of the physical data. Our motivation is to introduce conformal prediction into the uncertainty assessment of dynamical systems, providing a method supported by theoretical guarantees. This paper uses the conformal prediction method to assess uncertainties with benchmark operator learning methods. We have also compared the Monte Carlo Dropout and Ensemble methods in the partial differential equations dataset, effectively evaluating uncertainty through straight roll-outs, making it ideal for time-series tasks.
Authors: Zehao Chen, Rong Pan
Abstract: Scalable Vector Graphics (SVG) are essential XML-based formats for versatile graphics, offering resolution independence and scalability. Unlike raster images, SVGs use geometric shapes and support interactivity, animation, and manipulation via CSS and JavaScript. Current SVG generation methods face challenges related to high computational costs and complexity. In contrast, human designers use component-based tools for efficient SVG creation. Inspired by this, SVGBuilder introduces a component-based, autoregressive model for generating high-quality colored SVGs from textual input. It significantly reduces computational overhead and improves efficiency compared to traditional methods. Our model generates SVGs up to 604 times faster than optimization-based approaches. To address the limitations of existing SVG datasets and support our research, we introduce ColorSVG-100K, the first large-scale dataset of colored SVGs, comprising 100,000 graphics. This dataset fills the gap in color information for SVG generation models and enhances diversity in model training. Evaluation against state-of-the-art models demonstrates SVGBuilder's superior performance in practical applications, highlighting its efficiency and quality in generating complex SVG graphics.
Authors: Sida Huang, Hongyuan Zhang, Xuelong Li
Abstract: With the advancement of pre-trained vision-language (VL) models, enhancing the alignment between visual and linguistic modalities in downstream tasks has emerged as a critical challenge. Different from existing fine-tuning methods that add extra modules to these two modalities, we investigate whether the frozen model can be fine-tuned by customized noise. Our approach is motivated by the scientific study of beneficial noise, namely Positive-incentive Noise (Pi-noise or $\pi$-noise) , which quantitatively analyzes the impact of noise. It therefore implies a new scheme to learn beneficial noise distribution that can be employed to fine-tune VL models. Focusing on few-shot classification tasks based on CLIP, we reformulate the inference process of CLIP and apply variational inference, demonstrating how to generate $\pi$-noise towards visual and linguistic modalities. Then, we propose Positive-incentive Noise Injector (PiNI), which can fine-tune CLIP via injecting noise into both visual and text encoders. Since the proposed method can learn the distribution of beneficial noise, we can obtain more diverse embeddings of vision and language to better align these two modalities for specific downstream tasks within limited computational resources. We evaluate different noise incorporation approaches and network architectures of PiNI. The evaluation across 11 datasets demonstrates its effectiveness.
Authors: Zhenyu Lei, Yushun Dong, Jundong Li, Chen Chen
Abstract: Spatial-temporal graphs are widely used in a variety of real-world applications. Spatial-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool to extract meaningful insights from this data. However, in real-world applications, most nodes may not possess any available temporal data during training. For example, the pandemic dynamics of most cities on a geographical graph may not be available due to the asynchronous nature of outbreaks. Such a phenomenon disagrees with the training requirements of most existing spatial-temporal forecasting methods, which jeopardizes their effectiveness and thus blocks broader deployment. In this paper, we propose to formulate a novel problem of inductive forecasting with limited training data. In particular, given a spatial-temporal graph, we aim to learn a spatial-temporal forecasting model that can be easily generalized onto those nodes without any available temporal training data. To handle this problem, we propose a principled framework named ST-FiT. ST-FiT consists of two key learning components: temporal data augmentation and spatial graph topology learning. With such a design, ST-FiT can be used on top of any existing STGNNs to achieve superior performance on the nodes without training data. Extensive experiments verify the effectiveness of ST-FiT in multiple key perspectives.
Authors: Mingjing Xu, Peizhong Ju, Jia Liu, Haibo Yang
Abstract: Multi-objective optimization (MOO) lies at the core of many machine learning (ML) applications that involve multiple, potentially conflicting objectives (e.g., multi-task learning, multi-objective reinforcement learning, among many others). Despite the long history of MOO, recent years have witnessed a surge in interest within the ML community in the development of gradient manipulation algorithms for MOO, thanks to the availability of gradient information in many ML problems. However, existing gradient manipulation methods for MOO often suffer from long training times, primarily due to the need for computing dynamic weights by solving an additional optimization problem to determine a common descent direction that can decrease all objectives simultaneously. To address this challenge, we propose a new and efficient algorithm called Periodic Stochastic Multi-Gradient Descent (PSMGD) to accelerate MOO. PSMGD is motivated by the key observation that dynamic weights across objectives exhibit small changes under minor updates over short intervals during the optimization process. Consequently, our PSMGD algorithm is designed to periodically compute these dynamic weights and utilizes them repeatedly, thereby effectively reducing the computational overload. Theoretically, we prove that PSMGD can achieve state-of-the-art convergence rates for strongly-convex, general convex, and non-convex functions. Additionally, we introduce a new computational complexity measure, termed backpropagation complexity, and demonstrate that PSMGD could achieve an objective-independent backpropagation complexity. Through extensive experiments, we verify that PSMGD can provide comparable or superior performance to state-of-the-art MOO algorithms while significantly reducing training time.
Authors: G\"ozde \"Ozcan, Chengzhi Shi, Stratis Ioannidis
Abstract: Ou et al. (2022) introduce the problem of learning set functions from data generated by a so-called optimal subset oracle. Their approach approximates the underlying utility function with an energy-based model, whose parameters are estimated via mean-field variational inference. Ou et al. (2022) show this reduces to fixed point iterations; however, as the number of iterations increases, automatic differentiation quickly becomes computationally prohibitive due to the size of the Jacobians that are stacked during backpropagation. We address this challenge with implicit differentiation and examine the convergence conditions for the fixed-point iterations. We empirically demonstrate the efficiency of our method on synthetic and real-world subset selection applications including product recommendation, set anomaly detection and compound selection tasks.
Authors: Nargiz Humbatova, Jinhan Kim, Gunel Jahangirova, Shin Yoo, Paolo Tonella
Abstract: With the increased popularity of Deep Neural Networks (DNNs), increases also the need for tools to assist developers in the DNN implementation, testing and debugging process. Several approaches have been proposed that automatically analyse and localise potential faults in DNNs under test. In this work, we evaluate and compare existing state-of-the-art fault localisation techniques, which operate based on both dynamic and static analysis of the DNN. The evaluation is performed on a benchmark consisting of both real faults obtained from bug reporting platforms and faulty models produced by a mutation tool. Our findings indicate that the usage of a single, specific ground truth (e.g., the human defined one) for the evaluation of DNN fault localisation tools results in pretty low performance (maximum average recall of 0.31 and precision of 0.23). However, such figures increase when considering alternative, equivalent patches that exist for a given faulty DNN. Results indicate that \dfd is the most effective tool, achieving an average recall of 0.61 and precision of 0.41 on our benchmark.
Authors: Rui Liu, Shuwei He, Yifan Hu, Haizhou Li
Abstract: Visual Text-to-Speech (VTTS) aims to take the environmental image as the prompt to synthesize the reverberant speech for the spoken content. The challenge of this task lies in understanding the spatial environment from the image. Many attempts have been made to extract global spatial visual information from the RGB space of an spatial image. However, local and depth image information are crucial for understanding the spatial environment, which previous works have ignored. To address the issues, we propose a novel multi-modal and multi-scale spatial environment understanding scheme to achieve immersive VTTS, termed M2SE-VTTS. The multi-modal aims to take both the RGB and Depth spaces of the spatial image to learn more comprehensive spatial information, and the multi-scale seeks to model the local and global spatial knowledge simultaneously. Specifically, we first split the RGB and Depth images into patches and adopt the Gemini-generated environment captions to guide the local spatial understanding. After that, the multi-modal and multi-scale features are integrated by the local-aware global spatial understanding. In this way, M2SE-VTTS effectively models the interactions between local and global spatial contexts in the multi-modal spatial environment. Objective and subjective evaluations suggest that our model outperforms the advanced baselines in environmental speech generation. The code and audio samples are available at: https://github.com/AI-S2-Lab/M2SE-VTTS.
Authors: Alberto Silvio Chiappa, Briti Gangopadhyay, Zhao Wang, Shingo Takamatsu
Abstract: Online advertising has become one of the most successful business models of the internet era. Impression opportunities are typically allocated through real-time auctions, where advertisers bid to secure advertisement slots. Deciding the best bid for an impression opportunity is challenging, due to the stochastic nature of user behavior and the variability of advertisement traffic over time. In this work, we propose a framework for training auto-bidding agents in multi-slot second-price auctions to maximize acquisitions (e.g., clicks, conversions) while adhering to budget and cost-per-acquisition (CPA) constraints. We exploit the insight that, after an advertisement campaign concludes, determining the optimal bids for each impression opportunity can be framed as a multiple-choice knapsack problem (MCKP) with a nonlinear objective. We propose an "oracle" algorithm that identifies a near-optimal combination of impression opportunities and advertisement slots, considering both past and future advertisement traffic data. This oracle solution serves as a training target for a student network which bids having access only to real-time information, a method we term Oracle Imitation Learning (OIL). Through numerical experiments, we demonstrate that OIL achieves superior performance compared to both online and offline reinforcement learning algorithms, offering improved sample efficiency. Notably, OIL shifts the complexity of training auto-bidding agents from crafting sophisticated learning algorithms to solving a nonlinear constrained optimization problem efficiently.
Authors: Gangqiang Hu, Jianfeng Lu, Jianmin Han, Shuqin Cao, Jing Liu, Hao Fu
Abstract: Due to the sensitivity of data, federated learning (FL) is employed to enable distributed machine learning while safeguarding data privacy and accommodating the requirements of various devices. However, in the context of semi-decentralized federated learning (SD-FL), clients' communication and training states are dynamic. This variability arises from local training fluctuations, heterogeneous data distributions, and intermittent client participation. Most existing studies primarily focus on stable client states, neglecting the dynamic challenges present in real-world scenarios. To tackle this issue, we propose a trust-aware client scheduling mechanism (TRAIL) that assesses client states and contributions, enhancing model training efficiency through selective client participation. Our focus is on a semi-decentralized federated learning framework where edge servers and clients train a shared global model using unreliable intra-cluster model aggregation and inter-cluster model consensus. First, we develop an adaptive hidden semi-Markov model (AHSMM) to estimate clients' communication states and contributions. Next, we address a client-server association optimization problem to minimize global training loss. Using convergence analysis, we propose a greedy client scheduling algorithm. Finally, our experiments conducted on real-world datasets demonstrate that TRAIL outperforms state-of-the-art baselines, achieving an improvement of 8.7\% in test accuracy and a reduction of 15.3\% in training loss.
Authors: Wenxiao Fan, Kan Li
Abstract: Noisy labels can negatively impact the performance of deep neural networks. One common solution is label refurbishment, which involves reconstructing noisy labels through predictions and distributions. However, these methods may introduce problematic semantic associations, a phenomenon that we identify as Semantic Contamination. Through an analysis of Robust LR, a representative label refurbishment method, we found that utilizing the logits of views for refurbishment does not adequately balance the semantic information of individual classes. Conversely, using the logits of models fails to maintain consistent semantic relationships across models, which explains why label refurbishment methods frequently encounter issues related to Semantic Contamination. To address this issue, we propose a novel method called Collaborative Cross Learning, which utilizes semi-supervised learning on refurbished labels to extract appropriate semantic associations from embeddings across views and models. Experimental results show that our method outperforms existing approaches on both synthetic and real-world noisy datasets, effectively mitigating the impact of label noise and Semantic Contamination.
Authors: Minghao Xu, Lichuan Xiang, Xu Cai, Hongkai Wen
Abstract: In this work, we question the necessity of adaptive gradient methods for training deep neural networks. SGD-SaI is a simple yet effective enhancement to stochastic gradient descent with momentum (SGDM). SGD-SaI performs learning rate Scaling at Initialization (SaI) to distinct parameter groups, guided by their respective gradient signal-to-noise ratios (g-SNR). By adjusting learning rates without relying on adaptive second-order momentum, SGD-SaI helps prevent training imbalances from the very first iteration and cuts the optimizer's memory usage by half compared to AdamW. Despite its simplicity and efficiency, SGD-SaI consistently matches or outperforms AdamW in training a variety of Transformer-based tasks, effectively overcoming a long-standing challenge of using SGD for training Transformers. SGD-SaI excels in ImageNet-1K classification with Vision Transformers(ViT) and GPT-2 pretraining for large language models (LLMs, transformer decoder-only), demonstrating robustness to hyperparameter variations and practicality for diverse applications. We further tested its robustness on tasks like LoRA fine-tuning for LLMs and diffusion models, where it consistently outperforms state-of-the-art optimizers. From a memory efficiency perspective, SGD-SaI achieves substantial memory savings for optimizer states, reducing memory usage by 5.93 GB for GPT-2 (1.5B parameters) and 25.15 GB for Llama2-7B compared to AdamW in full-precision training settings.
Authors: Qi Sun, Pengfei Hong, Tej Deep Pala, Vernon Toh, U-Xuan Tan, Deepanway Ghosal, Soujanya Poria
Abstract: Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene understanding and planning capabilities but lack the ability to generate actionable policies tailored to specific robotic embodiments. To address this, Visual-Language-Action (VLA) models have emerged, yet they face challenges in long-horizon spatial reasoning and grounded task planning. In this work, we propose the Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning, Emma-X. Emma-X leverages our constructed hierarchical embodiment dataset based on BridgeV2, containing 60,000 robot manipulation trajectories auto-annotated with grounded task reasoning and spatial guidance. Additionally, we introduce a trajectory segmentation strategy based on gripper states and motion trajectories, which can help mitigate hallucination in grounding subtask reasoning generation. Experimental results demonstrate that Emma-X achieves superior performance over competitive baselines, particularly in real-world robotic tasks requiring spatial reasoning.