Authors: Yuehong Cassandra Tai, Khushi Navin Patni, Nicholas Daniel Hemauer, Bruce Desmarais, Yu-Ru Lin
Abstract: Despite recent advances in understanding the capabilities and limits of generative artificial intelligence (GenAI) models, we are just beginning to understand their capacity to assess and reason about the veracity of content. We evaluate multiple GenAI models across tasks that involve the rating of, and perceived reasoning about, the credibility of information. The information in our experiments comes from content that subnational U.S. politicians post to Facebook. We find that GPT-4o, one of the most used AI models in consumer applications, outperforms other models, but all models exhibit only moderate agreement with human coders. Importantly, even when GenAI models accurately identify low-credibility content, their reasoning relies heavily on linguistic features and ``hard'' criteria, such as the level of detail, source reliability, and language formality, rather than an understanding of veracity. We also assess the effectiveness of summarized versus full content inputs, finding that summarized content holds promise for improving efficiency without sacrificing accuracy. While GenAI has the potential to support human fact-checkers in scaling misinformation detection, our results caution against relying solely on these models.
Authors: Shashank Sonkar, Naiming Liu, Xinghe Chen, Richard G. Baraniuk
Abstract: As artificial intelligence systems become increasingly prevalent in education, a fundamental challenge emerges: how can we verify if an AI truly understands how students think and reason? Traditional evaluation methods like measuring learning gains require lengthy studies confounded by numerous variables. We present a novel evaluation framework based on a two-phase Turing-like test. In Phase 1, students provide open-ended responses to questions, revealing natural misconceptions. In Phase 2, both AI and human experts, conditioned on each student's specific mistakes, generate distractors for new related questions. By analyzing whether students select AI-generated distractors at rates similar to human expert-generated ones, we can validate if the AI models student cognition. We prove this evaluation must be conditioned on individual responses - unconditioned approaches merely target common misconceptions. Through rigorous statistical sampling theory, we establish precise requirements for high-confidence validation. Our research positions conditioned distractor generation as a probe into an AI system's fundamental ability to model student thinking - a capability that enables adapting tutoring, feedback, and assessments to each student's specific needs.
Authors: Peter Cihon, Merlin Stein, Gagan Bansal, Sam Manning, Kevin Xu
Abstract: AI agents are AI systems that can achieve complex goals autonomously. Assessing the level of agent autonomy is crucial for understanding both their potential benefits and risks. Current assessments of autonomy often focus on specific risks and rely on run-time evaluations -- observations of agent actions during operation. We introduce a code-based assessment of autonomy that eliminates the need to run an AI agent to perform specific tasks, thereby reducing the costs and risks associated with run-time evaluations. Using this code-based framework, the orchestration code used to run an AI agent can be scored according to a taxonomy that assesses attributes of autonomy: impact and oversight. We demonstrate this approach with the AutoGen framework and select applications.
Authors: Kai Li, Fei Liu, Zhenkun Wang, Xialiang Tong, Xiongwei Han, Mingxuan Yuan
Abstract: Real-world Vehicle Routing Problems (VRPs) are characterized by a variety of practical constraints, making manual solver design both knowledge-intensive and time-consuming. Although there is increasing interest in automating the design of routing algorithms, existing research has explored only a limited array of VRP variants and fails to adequately address the complex and prevalent constraints encountered in real-world situations. To fill this gap, this paper introduces RoutBench, a benchmark of 1,000 VRP variants derived from 24 attributes, for evaluating the effectiveness of automatic routing solvers in addressing complex constraints. Along with RoutBench, we present the Automatic Routing Solver (ARS), which employs Large Language Model (LLM) agents to enhance a backbone algorithm framework by automatically generating constraint-aware heuristic code, based on problem descriptions and several representative constraints selected from a database. Our experiments show that ARS outperforms state-of-the-art LLM-based methods and commonly used solvers, automatically solving 91.67% of common VRPs and achieving at least a 30% improvement across all benchmarks.
Authors: Shaharukh Khan, Ayush Tarun, Abhinav Ravi, Ali Faraz, Akshat Patidar, Praveen Kumar Pokala, Anagha Bhangare, Raja Kolla, Chandra Khatri, Shubham Agarwal
Abstract: Recent multimodal foundation models are primarily trained on English or high resource European language data, which hinders their applicability to other medium and low-resource languages. To address this limitation, we introduce Chitrarth (Chitra: Image; Artha: Meaning), an inclusive Vision-Language Model (VLM), specifically targeting the rich linguistic diversity and visual reasoning across 10 prominent Indian languages. Our model effectively integrates a state-of-the-art (SOTA) multilingual Large Language Model (LLM) with a vision module, primarily trained on multilingual image-text data. Furthermore, we also introduce BharatBench, a comprehensive framework for evaluating VLMs across various Indian languages, ultimately contributing to more diverse and effective AI systems. Our model achieves SOTA results for benchmarks across low resource languages while retaining its efficiency in English. Through our research, we aim to set new benchmarks in multilingual-multimodal capabilities, offering substantial improvements over existing models and establishing a foundation to facilitate future advancements in this arena.
Authors: Giuseppe Paolo, Abdelhakim Benechehab, Hamza Cherkaoui, Albert Thomas, Bal\'azs K\'egl
Abstract: Hierarchical organization is fundamental to biological systems and human societies, yet artificial intelligence systems often rely on monolithic architectures that limit adaptability and scalability. Current hierarchical reinforcement learning (HRL) approaches typically restrict hierarchies to two levels or require centralized training, which limits their practical applicability. We introduce TAME Agent Framework (TAG), a framework for constructing fully decentralized hierarchical multi-agent systems.TAG enables hierarchies of arbitrary depth through a novel LevelEnv concept, which abstracts each hierarchy level as the environment for the agents above it. This approach standardizes information flow between levels while preserving loose coupling, allowing for seamless integration of diverse agent types. We demonstrate the effectiveness of TAG by implementing hierarchical architectures that combine different RL agents across multiple levels, achieving improved performance over classical multi-agent RL baselines on standard benchmarks. Our results show that decentralized hierarchical organization enhances both learning speed and final performance, positioning TAG as a promising direction for scalable multi-agent systems.
Authors: Wei Lin. Hsueh, Tsan Sheng. Hsu
Abstract: This paper introduces Zweistein, a dynamic programming evaluation function for Einstein W\"urfelt Nicht! (EWN). Instead of relying on human knowledge to craft an evaluation function, Zweistein uses a data-centric approach that eliminates the need for parameter tuning. The idea is to use a vector recording the distance to the corner of all pieces. This distance vector captures the essence of EWN. It not only outperforms many traditional EWN evaluation functions but also won first place in the TCGA 2023 competition.
Authors: John Burden, Marko Te\v{s}i\'c, Lorenzo Pacchiardi, Jos\'e Hern\'andez-Orallo
Abstract: Research in AI evaluation has grown increasingly complex and multidisciplinary, attracting researchers with diverse backgrounds and objectives. As a result, divergent evaluation paradigms have emerged, often developing in isolation, adopting conflicting terminologies, and overlooking each other's contributions. This fragmentation has led to insular research trajectories and communication barriers both among different paradigms and with the general public, contributing to unmet expectations for deployed AI systems. To help bridge this insularity, in this paper we survey recent work in the AI evaluation landscape and identify six main paradigms. We characterise major recent contributions within each paradigm across key dimensions related to their goals, methodologies and research cultures. By clarifying the unique combination of questions and approaches associated with each paradigm, we aim to increase awareness of the breadth of current evaluation approaches and foster cross-pollination between different paradigms. We also identify potential gaps in the field to inspire future research directions.
Authors: Fengxiang Cheng, Haoxuan Li, Fenrong Liu, Robert van Rooij, Kun Zhang, Zhouchen Lin
Abstract: Large language models (LLMs) have achieved remarkable successes on various natural language tasks. However, recent studies have found that there are still significant challenges to the logical reasoning abilities of LLMs. This paper summarizes and categorizes the main challenges into two aspects: (1) Logical question answering, LLMs often fail to generate the correct answer within complex logical problem which requires sophisticated deductive, inductive or abductive reasoning given a collection of premises and constrains. (2) Logical consistency, LLMs are prone to producing responses contradicting themselves across different questions. For example, a state-of-the-art Macaw question-answering LLM answers Yes to both questions Is a magpie a bird? and Does a bird have wings? but answers No to Does a magpie have wings?. To facilitate this research direction, we comprehensively investigate the most cutting-edge methods and propose detailed taxonomies of these methods. Specifically, to accurately answer complex logic questions, previous methods can be categorized based on reliance on external solvers, prompts, pretraining, and fine-tuning. To avoid logical contradictions, we discuss concepts and solutions of various logical consistencies, including implication, negation, transitivity, factuality consistency, and their composites. In addition, we review commonly used benchmark datasets and evaluation metrics, and discuss promising research directions, such as extensions to modal logic to account for uncertainty, and efficient algorithms satisfying multiple logical consistencies simultaneously.
Authors: Yoshua Bengio, Michael Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, S\"oren Mindermann, Adam Oberman, Jesse Richardson, Oliver Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, David Williams-King
Abstract: The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be, unchecked AI agency poses significant risks to public safety and security, ranging from misuse by malicious actors to a potentially irreversible loss of human control. We discuss how these risks arise from current AI training methods. Indeed, various scenarios and experiments have demonstrated the possibility of AI agents engaging in deception or pursuing goals that were not specified by human operators and that conflict with human interests, such as self-preservation. Following the precautionary principle, we see a strong need for safer, yet still useful, alternatives to the current agency-driven trajectory. Accordingly, we propose as a core building block for further advances the development of a non-agentic AI system that is trustworthy and safe by design, which we call Scientist AI. This system is designed to explain the world from observations, as opposed to taking actions in it to imitate or please humans. It comprises a world model that generates theories to explain data and a question-answering inference machine. Both components operate with an explicit notion of uncertainty to mitigate the risks of overconfident predictions. In light of these considerations, a Scientist AI could be used to assist human researchers in accelerating scientific progress, including in AI safety. In particular, our system can be employed as a guardrail against AI agents that might be created despite the risks involved. Ultimately, focusing on non-agentic AI may enable the benefits of AI innovation while avoiding the risks associated with the current trajectory. We hope these arguments will motivate researchers, developers, and policymakers to favor this safer path.
Authors: Vincent Hsiao, Mark Roberts, Laura M. Hiatt, George Konidaris, Dana Nau
Abstract: A major challenge for reinforcement learning is automatically generating curricula to reduce training time or improve performance in some target task. We introduce SEBNs (Skill-Environment Bayesian Networks) which model a probabilistic relationship between a set of skills, a set of goals that relate to the reward structure, and a set of environment features to predict policy performance on (possibly unseen) tasks. We develop an algorithm that uses the inferred estimates of agent success from SEBN to weigh the possible next tasks by expected improvement. We evaluate the benefit of the resulting curriculum on three environments: a discrete gridworld, continuous control, and simulated robotics. The results show that curricula constructed using SEBN frequently outperform other baselines.
Authors: Zhining Zhang, Chuanyang Jin, Mung Yao Jia, Tianmin Shu
Abstract: Theory of Mind (ToM), the ability to understand people's mental variables based on their behavior, is key to developing socially intelligent agents. Current approaches to Theory of Mind reasoning either rely on prompting Large Language Models (LLMs), which are prone to systematic errors, or use rigid, handcrafted Bayesian Theory of Mind (BToM) models, which are more robust but cannot generalize across different domains. In this work, we introduce AutoToM, an automated Bayesian Theory of Mind method for achieving open-ended machine Theory of Mind. AutoToM can operate in any domain, infer any mental variable, and conduct robust Theory of Mind reasoning of any order. Given a Theory of Mind inference problem, AutoToM first proposes an initial BToM model. It then conducts automated Bayesian inverse planning based on the proposed model, leveraging an LLM as the backend. Based on the uncertainty of the inference, it iteratively refines the model, by introducing additional mental variables and/or incorporating more timesteps in the context. Empirical evaluations across multiple Theory of Mind benchmarks demonstrate that AutoToM consistently achieves state-of-the-art performance, offering a scalable, robust, and interpretable approach to machine Theory of Mind.
Authors: Tiancheng Shen, Yuechen Zhang, Lu Qi, Jason Kuen, Xingyu Xie, Jianlong Wu, Zhe Lin, Jiaya Jia
Abstract: To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation. Common strategies, such as down-sampling, patch cropping, and cascade model, cannot address well the balance issue between accuracy and computation cost. Motivated by the fact that humans distinguish among objects continuously from coarse to precise levels, we propose the Continuous Refinement Model~(CRM) for the ultra high-resolution segmentation refinement task. CRM continuously aligns the feature map with the refinement target and aggregates features to reconstruct these images' details. Besides, our CRM shows its significant generalization ability to fill the resolution gap between low-resolution training images and ultra high-resolution testing ones. We present quantitative performance evaluation and visualization to show that our proposed method is fast and effective on image segmentation refinement. Code will be released at https://github.com/dvlab-research/Entity.
Authors: Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal, Michael Blumenstein
Abstract: Structural guidance in an image-to-image translation allows intricate control over the shapes of synthesized images. Generating high-quality realistic images from user-specified rough hand-drawn sketches is one such task that aims to impose a structural constraint on the conditional generation process. While the premise is intriguing for numerous use cases of content creation and academic research, the problem becomes fundamentally challenging due to substantial ambiguities in freehand sketches. Furthermore, balancing the trade-off between shape consistency and realistic generation contributes to additional complexity in the process. Existing approaches based on Generative Adversarial Networks (GANs) generally utilize conditional GANs or GAN inversions, often requiring application-specific data and optimization objectives. The recent introduction of Denoising Diffusion Probabilistic Models (DDPMs) achieves a generational leap for low-level visual attributes in general image synthesis. However, directly retraining a large-scale diffusion model on a domain-specific subtask is often extremely difficult due to demanding computation costs and insufficient data. In this paper, we introduce a technique for sketch-to-image translation by exploiting the feature generalization capabilities of a large-scale diffusion model without retraining. In particular, we use a learnable lightweight mapping network to achieve latent feature translation from source to target domain. Experimental results demonstrate that the proposed method outperforms the existing techniques in qualitative and quantitative benchmarks, allowing high-resolution realistic image synthesis from rough hand-drawn sketches.
Authors: Georgios Pavlidis
Abstract: The lack of explainability of Artificial Intelligence (AI) is one of the first obstacles that the industry and regulators must overcome to mitigate the risks associated with the technology. The need for eXplainable AI (XAI) is evident in fields where accountability, ethics and fairness are critical, such as healthcare, credit scoring, policing and the criminal justice system. At the EU level, the notion of explainability is one of the fundamental principles that underpin the AI Act, though the exact XAI techniques and requirements are still to be determined and tested in practice. This paper explores various approaches and techniques that promise to advance XAI, as well as the challenges of implementing the principle of explainability in AI governance and policies. Finally, the paper examines the integration of XAI into EU law, emphasising the issues of standard setting, oversight, and enforcement.
Authors: Julia Barnett, Kimon Kieslich, Natali Helberger, Nicholas Diakopoulos
Abstract: The potential for negative impacts of AI has rapidly become more pervasive around the world, and this has intensified a need for responsible AI governance. While many regulatory bodies endorse risk-based approaches and a multitude of risk mitigation practices are proposed by companies and academic scholars, these approaches are commonly expert-centered and thus lack the inclusion of a significant group of stakeholders. Ensuring that AI policies align with democratic expectations requires methods that prioritize the voices and needs of those impacted. In this work we develop a participative and forward-looking approach to inform policy-makers and academics that grounds the needs of lay stakeholders at the forefront and enriches the development of risk mitigation strategies. Our approach (1) maps potential mitigation and prevention strategies of negative AI impacts that assign responsibility to various stakeholders, (2) explores the importance and prioritization thereof in the eyes of laypeople, and (3) presents these insights in policy fact sheets, i.e., a digestible format for informing policy processes. We emphasize that this approach is not targeted towards replacing policy-makers; rather our aim is to present an informative method that enriches mitigation strategies and enables a more participatory approach to policy development.
Authors: Severin Field
Abstract: The development of artificial general intelligence (AGI) is likely to be one of humanity's most consequential technological advancements. Leading AI labs and scientists have called for the global prioritization of AI safety citing existential risks comparable to nuclear war. However, research on catastrophic risks and AI alignment is often met with skepticism, even by experts. Furthermore, online debate over the existential risk of AI has begun to turn tribal (e.g. name-calling such as "doomer" or "accelerationist"). Until now, no systematic study has explored the patterns of belief and the levels of familiarity with AI safety concepts among experts. I surveyed 111 AI experts on their familiarity with AI safety concepts, key objections to AI safety, and reactions to safety arguments. My findings reveal that AI experts cluster into two viewpoints -- an "AI as controllable tool" and an "AI as uncontrollable agent" perspective -- diverging in beliefs toward the importance of AI safety. While most experts (78%) agreed or strongly agreed that "technical AI researchers should be concerned about catastrophic risks", many were unfamiliar with specific AI safety concepts. For example, only 21% of surveyed experts had heard of "instrumental convergence," a fundamental concept in AI safety predicting that advanced AI systems will tend to pursue common sub-goals (such as self-preservation). The least concerned participants were the least familiar with concepts like this, suggesting that effective communication of AI safety should begin with establishing clear conceptual foundations in the field.
Authors: Jeremy Avigad
Abstract: This is an essay about the value of mathematical and symbolic reasoning in the age of AI.
Authors: Dong Chen, Zhengqing Hu, Peiguang Fan, Yueting Zhuang, Yafei Li, Qidong Liu, Xiaoheng Jiang, Mingliang Xu
Abstract: Vision anomaly detection, particularly in unsupervised settings, often struggles to distinguish between normal samples and anomalies due to the wide variability in anomalies. Recently, an increasing number of studies have focused on generating anomalies to help detectors learn more effective boundaries between normal samples and anomalies. However, as the generated anomalies are often derived from random factors, they frequently lack realism. Additionally, randomly generated anomalies typically offer limited support in constructing effective boundaries, as most differ substantially from normal samples and lie far from the boundary. To address these challenges, we propose Key Knowledge Augmentation (KKA), a method that extracts anomaly-related knowledge from large language models (LLMs). More specifically, KKA leverages the extensive prior knowledge of LLMs to generate meaningful anomalies based on normal samples. Then, KKA classifies the generated anomalies as easy anomalies and hard anomalies according to their similarity to normal samples. Easy anomalies exhibit significant differences from normal samples, whereas hard anomalies closely resemble normal samples. KKA iteratively updates the generated anomalies, and gradually increasing the proportion of hard anomalies to enable the detector to learn a more effective boundary. Experimental results show that the proposed method significantly improves the performance of various vision anomaly detectors while maintaining low generation costs. The code for CMG can be found at https://github.com/Anfeather/KKA.
Authors: Na Min An, Eunki Kim, Wan Ju Kang, Sangryul Kim, Hyunjung Shim, James Thorne
Abstract: Vision is a primary means of how humans perceive the environment, but Blind and Low-Vision (BLV) people need assistance understanding their surroundings, especially in unfamiliar environments. The emergence of semantic-based systems as assistance tools for BLV users has motivated many researchers to explore responses from Large Vision-Language Models (LVLMs). However, it has yet been studied preferences of BLV users on diverse types/styles of responses from LVLMs, specifically for navigational aid. To fill this gap, we first construct Eye4B dataset, consisting of human-validated 1.1k curated outdoor/indoor scenes with 5-10 relevant requests per scene. Then, we conduct an in-depth user study with eight BLV users to evaluate their preferences on six LVLMs from five perspectives: Afraidness, Nonactionability, Sufficiency, and Conciseness. Finally, we introduce Eye4B benchmark for evaluating alignment between widely used model-based image-text metrics and our collected BLV preferences. Our work can be set as a guideline for developing BLV-aware LVLMs towards a Barrier-Free AI system.
Authors: Weilin Ruan, Siru Zhong, Haomin Wen, Yuxuan Liang
Abstract: Diffusion models have recently emerged as powerful frameworks for generating high-quality images. While recent studies have explored their application to time series forecasting, these approaches face significant challenges in cross-modal modeling and transforming visual information effectively to capture temporal patterns. In this paper, we propose LDM4TS, a novel framework that leverages the powerful image reconstruction capabilities of latent diffusion models for vision-enhanced time series forecasting. Instead of introducing external visual data, we are the first to use complementary transformation techniques to convert time series into multi-view visual representations, allowing the model to exploit the rich feature extraction capabilities of the pre-trained vision encoder. Subsequently, these representations are reconstructed using a latent diffusion model with a cross-modal conditioning mechanism as well as a fusion module. Experimental results demonstrate that LDM4TS outperforms various specialized forecasting models for time series forecasting tasks.
Authors: Hanqi Yan, Xiangxiang Cui, Lu Yin, Paul Pu Liang, Yulan He, Yifei Wang
Abstract: In this paper, we leverage recent advancements in feature monosemanticity to extract interpretable features from deep multimodal models, offering a data-driven understanding of modality gaps. Specifically, we investigate CLIP (Contrastive Language-Image Pretraining), a prominent visual-language representation model trained on extensive image-text pairs. Building upon interpretability tools developed for single-modal models, we extend these methodologies to assess multi-modal interpretability of CLIP features. Additionally, we introduce the Modality Dominance Score (MDS) to attribute the interpretability of each feature to its respective modality. Next, we transform CLIP features into a more interpretable space, enabling us to categorize them into three distinct classes: vision features (single-modal), language features (single-modal), and visual-language features (cross-modal). Our findings reveal that this categorization aligns closely with human cognitive understandings of different modalities. We also demonstrate significant use cases of this modality-specific features including detecting gender bias, adversarial attack defense and text-to-image model editing. These results indicate that large-scale multimodal models, equipped with task-agnostic interpretability tools, offer valuable insights into key connections and distinctions between different modalities.
Authors: Zhiyu Zhu, Zhibo Jin, Jiayu Zhang, Nan Yang, Jiahao Huang, Jianlong Zhou, Fang Chen
Abstract: The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex associations between images and text. Despite these advancements, ensuring the interpretability of such models is paramount for their safe deployment in real-world applications, such as healthcare. While numerous interpretability methods have been developed for unimodal tasks, these approaches often fail to transfer effectively to multimodal contexts due to inherent differences in the representation structures. Bottleneck methods, well-established in information theory, have been applied to enhance CLIP's interpretability. However, they are often hindered by strong assumptions or intrinsic randomness. To overcome these challenges, we propose the Narrowing Information Bottleneck Theory, a novel framework that fundamentally redefines the traditional bottleneck approach. This theory is specifically designed to satisfy contemporary attribution axioms, providing a more robust and reliable solution for improving the interpretability of multimodal models. In our experiments, compared to state-of-the-art methods, our approach enhances image interpretability by an average of 9%, text interpretability by an average of 58.83%, and accelerates processing speed by 63.95%. Our code is publicly accessible at https://github.com/LMBTough/NIB.
Authors: Zhe Huang, Shuo Wang, Yongcai Wang, Lei Wang
Abstract: Collaborative 3D object detection holds significant importance in the field of autonomous driving, as it greatly enhances the perception capabilities of each individual agent by facilitating information exchange among multiple agents. However, in practice, due to pose estimation errors and time delays, the fusion of information across agents often results in feature representations with spatial and temporal noise, leading to detection errors. Diffusion models naturally have the ability to denoise noisy samples to the ideal data, which motivates us to explore the use of diffusion models to address the noise problem between multi-agent systems. In this work, we propose CoDiff, a novel robust collaborative perception framework that leverages the potential of diffusion models to generate more comprehensive and clearer feature representations. To the best of our knowledge, this is the first work to apply diffusion models to multi-agent collaborative perception. Specifically, we project high-dimensional feature map into the latent space of a powerful pre-trained autoencoder. Within this space, individual agent information serves as a condition to guide the diffusion model's sampling. This process denoises coarse feature maps and progressively refines the fused features. Experimental study on both simulated and real-world datasets demonstrates that the proposed framework CoDiff consistently outperforms existing relevant methods in terms of the collaborative object detection performance, and exhibits highly desired robustness when the pose and delay information of agents is with high-level noise.
Authors: Junhyeok Kim, Min Soo Kim, Jiwan Chung, Jungbin Cho, Jisoo Kim, Sungwoong Kim, Gyeongbo Sim, Youngjae Yu
Abstract: Predicting when to initiate speech in real-world environments remains a fundamental challenge for conversational agents. We introduce EgoSpeak, a novel framework for real-time speech initiation prediction in egocentric streaming video. By modeling the conversation from the speaker's first-person viewpoint, EgoSpeak is tailored for human-like interactions in which a conversational agent must continuously observe its environment and dynamically decide when to talk. Our approach bridges the gap between simplified experimental setups and complex natural conversations by integrating four key capabilities: (1) first-person perspective, (2) RGB processing, (3) online processing, and (4) untrimmed video processing. We also present YT-Conversation, a diverse collection of in-the-wild conversational videos from YouTube, as a resource for large-scale pretraining. Experiments on EasyCom and Ego4D demonstrate that EgoSpeak outperforms random and silence-based baselines in real time. Our results also highlight the importance of multimodal input and context length in effectively deciding when to speak.
Authors: Mingni Tang, Jiajia Li, Lu Yang, Zhiqiang Zhang, Jinghao Tian, Zuchao Li, Lefei Zhang, Ping Wang
Abstract: Symbolic music is represented in two distinct forms: two-dimensional, visually intuitive score images, and one-dimensional, standardized text annotation sequences. While large language models have shown extraordinary potential in music, current research has primarily focused on unimodal symbol sequence text. Existing general-domain visual language models still lack the ability of music notation understanding. Recognizing this gap, we propose NOTA, the first large-scale comprehensive multimodal music notation dataset. It consists of 1,019,237 records, from 3 regions of the world, and contains 3 tasks. Based on the dataset, we trained NotaGPT, a music notation visual large language model. Specifically, we involve a pre-alignment training phase for cross-modal alignment between the musical notes depicted in music score images and their textual representation in ABC notation. Subsequent training phases focus on foundational music information extraction, followed by training on music notation analysis. Experimental results demonstrate that our NotaGPT-7B achieves significant improvement on music understanding, showcasing the effectiveness of NOTA and the training pipeline. Our datasets are open-sourced at https://huggingface.co/datasets/MYTH-Lab/NOTA-dataset.
URLs: https://huggingface.co/datasets/MYTH-Lab/NOTA-dataset.
Authors: Jowaria Khan, Alexa Friedman, Sydney Evans, Runzi Wang, Kaley Beins, David Andrews, Elizabeth Bondi-Kelly
Abstract: Per and polyfluoroalkyl substances (PFAS), chemicals found in products like non-stick cookware, are unfortunately persistent environmental pollutants with severe health risks. Accurately mapping PFAS contamination is crucial for guiding targeted remediation efforts and protecting public and environmental health, yet detection across large regions remains challenging due to the cost of testing and the difficulty of simulating their spread. In this work, we introduce FOCUS, a geospatial deep learning framework with a label noise-aware loss function, to predict PFAS contamination in surface water over large regions. By integrating hydrological flow data, land cover information, and proximity to known PFAS sources, our approach leverages both spatial and environmental context to improve prediction accuracy. We evaluate the performance of our approach through extensive ablation studies and comparative analyses against baselines like sparse segmentation, as well as existing scientific methods, including Kriging and pollutant transport simulations. Results highlight our framework's potential for scalable PFAS monitoring.
Authors: Changhoon Kim, Yanjun Qi
Abstract: Text-to-Image (T2I) models have made remarkable progress in generating high-quality, diverse visual content from natural language prompts. However, their ability to reproduce copyrighted styles, sensitive imagery, and harmful content raises significant ethical and legal concerns. Concept erasure offers a proactive alternative to external filtering by modifying T2I models to prevent the generation of undesired content. In this survey, we provide a structured overview of concept erasure, categorizing existing methods based on their optimization strategies and the architectural components they modify. We categorize concept erasure methods into fine-tuning for parameter updates, closed-form solutions for efficient edits, and inference-time interventions for content restriction without weight modification. Additionally, we explore adversarial attacks that bypass erasure techniques and discuss emerging defenses. To support further research, we consolidate key datasets, evaluation metrics, and benchmarks for assessing erasure effectiveness and model robustness. This survey serves as a comprehensive resource, offering insights into the evolving landscape of concept erasure, its challenges, and future directions.
Authors: Lionel Wong, Ayman Ali, Raymond Xiong, Shannon Zeijang Shen, Yoon Kim, Monica Agrawal
Abstract: Patients have long sought health information online, and increasingly, they are turning to generative AI to answer their health-related queries. Given the high stakes of the medical domain, techniques like retrieval-augmented generation and citation grounding have been widely promoted as methods to reduce hallucinations and improve the accuracy of AI-generated responses and have been widely adopted into search engines. This paper argues that even when these methods produce literally accurate content drawn from source documents sans hallucinations, they can still be highly misleading. Patients may derive significantly different interpretations from AI-generated outputs than they would from reading the original source material, let alone consulting a knowledgeable clinician. Through a large-scale query analysis on topics including disputed diagnoses and procedure safety, we support our argument with quantitative and qualitative evidence of the suboptimal answers resulting from current systems. In particular, we highlight how these models tend to decontextualize facts, omit critical relevant sources, and reinforce patient misconceptions or biases. We propose a series of recommendations -- such as the incorporation of communication pragmatics and enhanced comprehension of source documents -- that could help mitigate these issues and extend beyond the medical domain.
Authors: Donghang Lyu, Chinmay Rao, Marius Staring, Matthias J. P. van Osch, Mariya Doneva, Hildo J. Lamb, Nicola Pezzotti
Abstract: Cardiac magnetic resonance imaging (CMR) is vital for diagnosing heart diseases, but long scan time remains a major drawback. To address this, accelerated imaging techniques have been introduced by undersampling k-space, which reduces the quality of the resulting images. Recent deep learning advancements aim to speed up scanning while preserving quality, but adapting to various sampling modes and undersampling factors remains challenging. Therefore, building a universal model is a promising direction. In this work, we introduce UPCMR, a universal unrolled model designed for CMR reconstruction. This model incorporates two kinds of learnable prompts, undersampling-specific prompt and spatial-specific prompt, and integrates them with a UNet structure in each block. Overall, by using the CMRxRecon2024 challenge dataset for training and validation, the UPCMR model highly enhances reconstructed image quality across all random sampling scenarios through an effective training strategy compared to some traditional methods, demonstrating strong adaptability potential for this task.
Authors: Georgios P. Georgiou
Abstract: One ongoing debate in linguistics is whether Artificial Intelligence (AI) can effectively mimic human performance in language-related tasks. While much research has focused on various linguistic abilities of AI, little attention has been given to how it defines neologisms formed through different word formation processes. This study addresses this gap by examining the degree of agreement between human and AI-generated responses in defining three types of Greek neologisms: blends, compounds, and derivatives. The study employed an online experiment in which human participants selected the most appropriate definitions for neologisms, while ChatGPT received identical prompts. The results revealed fair agreement between human and AI responses for blends and derivatives but no agreement for compounds. However, when considering the majority response among humans, agreement with AI was high for blends and derivatives. These findings highlight the complexity of human language and the challenges AI still faces in capturing its nuances. In particular, they suggest a need for integrating more advanced semantic networks and contextual learning mechanisms into AI models to improve their interpretation of complex word formations, especially compounds.
Authors: Boyu Chen, Zirui Guo, Zidan Yang, Yuluo Chen, Junze Chen, Zhenghao Liu, Chuan Shi, Cheng Yang
Abstract: Retrieval-augmented generation (RAG) improves the response quality of large language models (LLMs) by retrieving knowledge from external databases. Typical RAG approaches split the text database into chunks, organizing them in a flat structure for efficient searches. To better capture the inherent dependencies and structured relationships across the text database, researchers propose to organize textual information into an indexing graph, known asgraph-based RAG. However, we argue that the limitation of current graph-based RAG methods lies in the redundancy of the retrieved information, rather than its insufficiency. Moreover, previous methods use a flat structure to organize retrieved information within the prompts, leading to suboptimal performance. To overcome these limitations, we propose PathRAG, which retrieves key relational paths from the indexing graph, and converts these paths into textual form for prompting LLMs. Specifically, PathRAG effectively reduces redundant information with flow-based pruning, while guiding LLMs to generate more logical and coherent responses with path-based prompting. Experimental results show that PathRAG consistently outperforms state-of-the-art baselines across six datasets and five evaluation dimensions. The code is available at the following link: https://github.com/BUPT-GAMMA/PathRAG
Authors: Bhavik Agarwal, Ishan Joshi, Viktoria Rojkova
Abstract: In this paper, we address the challenge of enforcing strict schema adherence in large language model (LLM) generation by leveraging LLM reasoning capabilities. Building on the DeepSeek R1 reinforcement learning framework, our approach trains structured reasoning skills of a 1.5B parameter model through a novel pipeline that combines synthetic reasoning dataset construction with custom reward functions under Group Relative Policy Optimization (GRPO). Specifically, we first perform R1 reinforcement learning on a 20K sample unstructured-to-structured dataset, mirroring the original DeepSeek R1 methods, to establish core reasoning abilities. Subsequently, we performed supervised fine-tuning on a separate 10K reasoning sample dataset, focusing on refining schema adherence for downstream tasks. Despite the relatively modest training scope, requiring approximately 20 hours on an 8xH100 GPU cluster for GRPO training and 3 hours on 1xA100 for SFT, our model demonstrates robust performance in enforcing schema consistency. We compare our ThinkJSON approach against the original DeepSeek R1 (671B), distilled versions of DeepSeek R1 (Qwen-1.5B and Qwen-7B), and Gemini 2.0 Flash (70B), showcasing its effectiveness in real-world applications. Our results underscore the practical utility of a resource-efficient framework for schema-constrained text generation.
Authors: Srishti Yadav, Zhi Zhang, Daniel Hershcovich, Ekaterina Shutova
Abstract: Investigating value alignment in Large Language Models (LLMs) based on cultural context has become a critical area of research. However, similar biases have not been extensively explored in large vision-language models (VLMs). As the scale of multimodal models continues to grow, it becomes increasingly important to assess whether images can serve as reliable proxies for culture and how these values are embedded through the integration of both visual and textual data. In this paper, we conduct a thorough evaluation of multimodal model at different scales, focusing on their alignment with cultural values. Our findings reveal that, much like LLMs, VLMs exhibit sensitivity to cultural values, but their performance in aligning with these values is highly context-dependent. While VLMs show potential in improving value understanding through the use of images, this alignment varies significantly across contexts highlighting the complexities and underexplored challenges in the alignment of multimodal models.
Authors: Hajar Emami Gohari, Swanand Ravindra Kadhe, Syed Yousaf Shah. Constantin Adam, Abdulhamid Adebayo, Praneet Adusumilli, Farhan Ahmed, Nathalie Baracaldo Angel, Santosh Borse, Yuan-Chi Chang, Xuan-Hong Dang, Nirmit Desai, Ravital Eres, Ran Iwamoto, Alexei Karve, Yan Koyfman, Wei-Han Lee, Changchang Liu, Boris Lublinsky, Takuyo Ohko, Pablo Pesce, Maroun Touma, Shiqiang Wang, Shalisha Witherspoon, Herbert Woisetschlager, David Wood, Kun-Lung Wu, Issei Yoshida, Syed Zawad, Petros Zerfos, Yi Zhou, Bishwaranjan Bhattacharjee
Abstract: Data quantity and quality play a vital role in determining the performance of Large Language Models (LLMs). High-quality data, in particular, can significantly boost the LLM's ability to generalize on a wide range of downstream tasks. Large pre-training datasets for leading LLMs remain inaccessible to the public, whereas many open datasets are small in size (less than 5 trillion tokens), limiting their suitability for training large models. In this paper, we introduce GneissWeb, a large dataset yielding around 10 trillion tokens that caters to the data quality and quantity requirements of training LLMs. Our GneissWeb recipe that produced the dataset consists of sharded exact sub-string deduplication and a judiciously constructed ensemble of quality filters. GneissWeb achieves a favorable trade-off between data quality and quantity, producing models that outperform models trained on state-of-the-art open large datasets (5+ trillion tokens). We show that models trained using GneissWeb dataset outperform those trained on FineWeb-V1.1.0 by 2.73 percentage points in terms of average score computed on a set of 11 commonly used benchmarks (both zero-shot and few-shot) for pre-training dataset evaluation. When the evaluation set is extended to 20 benchmarks (both zero-shot and few-shot), models trained using GneissWeb still achieve a 1.75 percentage points advantage over those trained on FineWeb-V1.1.0.
Authors: Peter Carragher, Nikitha Rao, Abhinand Jha, R Raghav, Kathleen M. Carley
Abstract: The robustness of large language models (LLMs) against knowledge conflicts in unimodal question answering systems has been well studied. However, the effect of conflicts in information sources on vision language models (VLMs) in multimodal settings has not yet been explored. In this work, we propose \segsub, a framework that applies targeted perturbations to image sources to study and improve the robustness of VLMs against three different types of knowledge conflicts, namely parametric, source, and counterfactual conflicts. Contrary to prior findings that showed that LLMs are sensitive to parametric conflicts arising from textual perturbations, we find VLMs are largely robust to image perturbation. On the other hand, VLMs perform poorly on counterfactual examples (<30% accuracy) and fail to reason over source conflicts (<1% accuracy). We also find a link between hallucinations and image context, with GPT-4o prone to hallucination when presented with highly contextualized counterfactual examples. While challenges persist with source conflicts, finetuning models significantly improves reasoning over counterfactual samples. Our findings highlight the need for VLM training methodologies that enhance their reasoning capabilities, particularly in addressing complex knowledge conflicts between multimodal sources.
Authors: Cuong V. Nguyen, Hieu X. Nguyen, Dung D. Pham Minh, Cuong D. Do
Abstract: Electrocardiograms (ECGs) recorded on paper remain prevalent in clinical practice, yet their use presents challenges for automated analysis and digital storage. To address this issue, we introduce PTB-Image, a dataset comprising scanned paper ECGs with corresponding digital signals, enabling research on ECG digitization. We also provide VinDigitizer, a digitization baseline to convert paper-based ECGs into digital time-series signals. The method involves detecting signal rows, extracting waveforms from the background, and reconstructing numerical values from the digitized traces. We applied VinDigitizer to 549 scanned ECGs and evaluated its performance against the original PTB dataset (modified to match the printed signals). The results achieved a mean signal-to-noise ratio (SNR) of 0.01 dB, highlighting both the feasibility and challenges of ECG digitization, particularly in mitigating distortions from printing and scanning processes. By providing PTB-Image and baseline digitization methods, this work aims to facilitate advancements in ECG digitization, enhancing access to historical ECG data and supporting applications in telemedicine and automated cardiac diagnostics.
Authors: Shangyu Wu, Hongchao Du, Ying Xiong, Shuai Chen, Tei-wei Kuo, Nan Guan, Chun Jason Xue
Abstract: Large Language Models (LLMs) have achieved remarkable success in natural language processing tasks, but their massive size and computational demands hinder their deployment in resource-constrained environments. Existing structured pruning methods address this issue by removing redundant structures (e.g., elements, channels, layers) from the model. However, these methods employ a heuristic pruning strategy, which leads to suboptimal performance. Besides, they also ignore the data characteristics when pruning the model. To overcome these limitations, we propose EvoP, an evolutionary pruning framework for robust LLM inference. EvoP first presents a cluster-based calibration dataset sampling (CCDS) strategy for creating a more diverse calibration dataset. EvoP then introduces an evolutionary pruning pattern searching (EPPS) method to find the optimal pruning pattern. Compared to existing structured pruning techniques, EvoP achieves the best performance while maintaining the best efficiency. Experiments across different LLMs and different downstream tasks validate the effectiveness of the proposed EvoP, making it a practical and scalable solution for deploying LLMs in real-world applications.
Authors: Jann Railey Montalan, Jimson Paulo Layacan, David Demitri Africa, Richell Isaiah Flores, Michael T. Lopez II, Theresa Denise Magsajo, Anjanette Cayabyab, William Chandra Tjhi
Abstract: Recent advances in large language models (LLMs) have demonstrated remarkable capabilities on widely benchmarked high-resource languages; however, linguistic nuances of under-resourced languages remain unexplored. We introduce Batayan, a holistic Filipino benchmark designed to systematically evaluate LLMs across three key natural language processing (NLP) competencies: understanding, reasoning, and generation. Batayan consolidates eight tasks, covering both Tagalog and code-switched Taglish utterances. Our rigorous, native-speaker-driven annotation process ensures fluency and authenticity to the complex morphological and syntactic structures of Filipino, alleviating a pervasive translationese bias in existing Filipino corpora. We report empirical results on a variety of multilingual LLMs, highlighting significant performance gaps that signal the under-representation of Filipino in pretraining corpora, the unique hurdles in modeling Filipino's rich morphology and construction, and the importance of explicit Filipino language support and instruction tuning. Moreover, we discuss the practical challenges encountered in dataset construction and propose principled solutions for building culturally and linguistically-faithful resources in under-represented languages. We also provide a public benchmark and leaderboard as a clear foundation for iterative, community-driven progress in Filipino NLP.
Authors: Xiangjin Xie, Guangwei Xu, Lingyan Zhao, Ruijie Guo
Abstract: Although multi-agent collaborative Large Language Models (LLMs) have achieved significant breakthroughs in the Text-to-SQL task, their performance is still constrained by various factors. These factors include the incompleteness of the framework, failure to follow instructions, and model hallucination problems. To address these problems, we propose OpenSearch-SQL, which divides the Text-to-SQL task into four main modules: Preprocessing, Extraction, Generation, and Refinement, along with an Alignment module based on a consistency alignment mechanism. This architecture aligns the inputs and outputs of agents through the Alignment module, reducing failures in instruction following and hallucination. Additionally, we designed an intermediate language called SQL-Like and optimized the structured CoT based on SQL-Like. Meanwhile, we developed a dynamic few-shot strategy in the form of self-taught Query-CoT-SQL. These methods have significantly improved the performance of LLMs in the Text-to-SQL task. In terms of model selection, we directly applied the base LLMs without any post-training, thereby simplifying the task chain and enhancing the framework's portability. Experimental results show that OpenSearch-SQL achieves an execution accuracy(EX) of 69.3% on the BIRD development set, 72.28% on the test set, and a reward-based validity efficiency score (R-VES) of 69.36%, with all three metrics ranking first at the time of submission. These results demonstrate the comprehensive advantages of the proposed method in both effectiveness and efficiency.
Authors: Xinxin You, Xien Liu, Xue Yang, Ziyi Wang, Ji Wu
Abstract: The task of automatically coding the International Classification of Diseases (ICD) in the medical field has been well-established and has received much attention. Automatic coding of the ICD in the medical field has been successful in English but faces challenges when dealing with Chinese electronic medical records (EMRs). The first issue lies in the difficulty of extracting disease code-related information from Chinese EMRs, primarily due to the concise writing style and specific internal structure of the EMRs. The second problem is that previous methods have failed to leverage the disease-based multi-axial knowledge and lack of association with the corresponding clinical evidence. This paper introduces a novel framework called MKE-Coder: Multi-axial Knowledge with Evidence verification in ICD coding for Chinese EMRs. Initially, we identify candidate codes for the diagnosis and categorize each of them into knowledge under four coding axes.Subsequently, we retrieve corresponding clinical evidence from the comprehensive content of EMRs and filter credible evidence through a scoring model. Finally, to ensure the validity of the candidate code, we propose an inference module based on the masked language modeling strategy. This module verifies that all the axis knowledge associated with the candidate code is supported by evidence and provides recommendations accordingly. To evaluate the performance of our framework, we conduct experiments using a large-scale Chinese EMR dataset collected from various hospitals. The experimental results demonstrate that MKE-Coder exhibits significant superiority in the task of automatic ICD coding based on Chinese EMRs. In the practical evaluation of our method within simulated real coding scenarios, it has been demonstrated that our approach significantly aids coders in enhancing both their coding accuracy and speed.
Authors: Rui Zhao, Qirui Yuan, Jinyu Li, Haofeng Hu, Yun Li, Chengyuan Zheng, Fei Gao
Abstract: End-to-end autonomous driving, which directly maps raw sensor inputs to low-level vehicle controls, is an important part of Embodied AI. Despite successes in applying Multimodal Large Language Models (MLLMs) for high-level traffic scene semantic understanding, it remains challenging to effectively translate these conceptual semantics understandings into low-level motion control commands and achieve generalization and consensus in cross-scene driving. We introduce Sce2DriveX, a human-like driving chain-of-thought (CoT) reasoning MLLM framework. Sce2DriveX utilizes multimodal joint learning from local scene videos and global BEV maps to deeply understand long-range spatiotemporal relationships and road topology, enhancing its comprehensive perception and reasoning capabilities in 3D dynamic/static scenes and achieving driving generalization across scenes. Building on this, it reconstructs the implicit cognitive chain inherent in human driving, covering scene understanding, meta-action reasoning, behavior interpretation analysis, motion planning and control, thereby further bridging the gap between autonomous driving and human thought processes. To elevate model performance, we have developed the first extensive Visual Question Answering (VQA) driving instruction dataset tailored for 3D spatial understanding and long-axis task reasoning. Extensive experiments demonstrate that Sce2DriveX achieves state-of-the-art performance from scene understanding to end-to-end driving, as well as robust generalization on the CARLA Bench2Drive benchmark.
Authors: Eliott Thomas, Mickael Coustaty, Aurelie Joseph, Elodie Carel, Vincent Poulain D'Andecy, Jean-Marc Ogier
Abstract: Extracting tables from documents is a critical task across various industries, especially on business documents like invoices and reports. Existing systems based on DEtection TRansformer (DETR) such as TAble TRansformer (TATR), offer solutions for Table Detection (TD) and Table Structure Recognition (TSR) but face challenges with diverse table formats and common errors like incorrect area detection and overlapping columns. This research introduces RAPTOR, a modular post-processing system designed to enhance state-of-the-art models for improved table extraction, particularly for product tables. RAPTOR addresses recurrent TD and TSR issues, improving both precision and structural predictions. For TD, we use DETR (trained on ICDAR 2019) and TATR (trained on PubTables-1M and FinTabNet), while TSR only relies on TATR. A Genetic Algorithm is incorporated to optimize RAPTOR's module parameters, using a private dataset of product tables to align with industrial needs. We evaluate our method on two private datasets of product tables, the public DOCILE dataset (which contains tables similar to our target product tables), and the ICDAR 2013 and ICDAR 2019 datasets. The results demonstrate that while our approach excels at product tables, it also maintains reasonable performance across diverse table formats. An ablation study further validates the contribution of each module in our system.
Authors: Hemant Kumar Aggarwal, Antony Jerald, Phaneendra K. Yalavarthy, Rajesh Langoju, Bipul Das
Abstract: In X-ray computed tomography (CT) imaging, the choice of reconstruction kernel is crucial as it significantly impacts the quality of clinical images. Different kernels influence spatial resolution, image noise, and contrast in various ways. Clinical applications involving lung imaging often require images reconstructed with both soft and sharp kernels. The reconstruction of images with different kernels requires raw sinogram data and storing images for all kernels increases processing time and storage requirements. The Display Field-of-View (DFOV) adds complexity to kernel synthesis, as data acquired at different DFOVs exhibit varying levels of sharpness and details. This work introduces an efficient, DFOV-agnostic solution for image-based kernel synthesis using model-based deep learning. The proposed method explicitly integrates CT kernel and DFOV characteristics into the forward model. Experimental results on clinical data, along with quantitative analysis of the estimated modulation transfer function using wire phantom data, clearly demonstrate the utility of the proposed method in real-time. Additionally, a comparative study with a direct learning network, that lacks forward model information, shows that the proposed method is more robust to DFOV variations.
Authors: Zihao Zeng, Xuyao Huang, Boxiu Li, Zhijie Deng
Abstract: This paper identifies the misinterpretation of the context can be a significant issue during the reasoning process of large language models, spanning from smaller models like Llama3.2-3B-Instruct to cutting-edge ones like DeepSeek-R1. For example, in the phrase "10 dollars per kilo," LLMs might not recognize that "per" means "for each," leading to calculation errors. We introduce a novel, post-training approach called **Stick to the Facts (SIFT)** to tackle this. SIFT leverages increasing inference-time compute to ground LLM reasoning in contexts. At the core of SIFT lies the *Sticker*, which is generated by the model itself to explicitly emphasize the key information within the context. Given the curated Sticker, SIFT generates two predictions -- one from the original query and one from the query augmented with the Sticker. If they differ, the Sticker is sequentially refined via *forward* optimization (to better align the extracted facts with the query) and *inverse* generation (to conform with the model's inherent tendencies) for more faithful reasoning outcomes. Studies across diverse models (from 3B to 100B+) and benchmarks (e.g., GSM8K, MATH-500) reveal consistent performance improvements. Notably, SIFT improves the pass@1 accuracy of DeepSeek-R1 on AIME2024 from 78.33% to **85.67**%, establishing a new state-of-the-art in the open-source community. The code is available at https://github.com/zhijie-group/SIFT.
Authors: Jose F Quesada
Abstract: While language technologies have advanced significantly, current approaches fail to address the complex sociocultural dimensions of linguistic preservation. AI Thinking proposes a meaning-centered framework that would transform technological development from creating tools FOR communities to co-creating solutions WITH them. This approach recognizes that meaningful solutions emerge through the interplay of cultural understanding, community agency, and technological innovation. The proposal articulates a holistic methodology and a five-layer technological ecosystem where communities maintain control over their linguistic and cultural knowledge representation. This systematic integration of community needs, cultural preservation, and advanced capabilities could revolutionize how we approach linguistic diversity preservation in the digital age.
Authors: Ibrahim Alabdulmohsin, Andreas Steiner
Abstract: Language exhibits a fractal structure in its information-theoretic complexity (i.e. bits per token), with self-similarity across scales and long-range dependence (LRD). In this work, we investigate whether large language models (LLMs) can replicate such fractal characteristics and identify conditions-such as temperature setting and prompting method-under which they may fail. Moreover, we find that the fractal parameters observed in natural language are contained within a narrow range, whereas those of LLMs' output vary widely, suggesting that fractal parameters might prove helpful in detecting a non-trivial portion of LLM-generated texts. Notably, these findings, and many others reported in this work, are robust to the choice of the architecture; e.g. Gemini 1.0 Pro, Mistral-7B and Gemma-2B. We also release a dataset comprising of over 240,000 articles generated by various LLMs (both pretrained and instruction-tuned) with different decoding temperatures and prompting methods, along with their corresponding human-generated texts. We hope that this work highlights the complex interplay between fractal properties, prompting, and statistical mimicry in LLMs, offering insights for generating, evaluating and detecting synthetic texts.
Authors: Zizhuo Zhang, Lijun Wu, Kaiyuan Gao, Jiangchao Yao, Tao Qin, Bo Han
Abstract: Molecular docking that predicts the bound structures of small molecules (ligands) to their protein targets, plays a vital role in drug discovery. However, existing docking methods often face limitations: they either overlook crucial structural changes by assuming protein rigidity or suffer from low computational efficiency due to their reliance on generative models for structure sampling. To address these challenges, we propose FABFlex, a fast and accurate regression-based multi-task learning model designed for realistic blind flexible docking scenarios, where proteins exhibit flexibility and binding pocket sites are unknown (blind). Specifically, FABFlex's architecture comprises three specialized modules working in concert: (1) A pocket prediction module that identifies potential binding sites, addressing the challenges inherent in blind docking scenarios. (2) A ligand docking module that predicts the bound (holo) structures of ligands from their unbound (apo) states. (3) A pocket docking module that forecasts the holo structures of protein pockets from their apo conformations. Notably, FABFlex incorporates an iterative update mechanism that serves as a conduit between the ligand and pocket docking modules, enabling continuous structural refinements. This approach effectively integrates the three subtasks of blind flexible docking-pocket identification, ligand conformation prediction, and protein flexibility modeling-into a unified, coherent framework. Extensive experiments on public benchmark datasets demonstrate that FABFlex not only achieves superior effectiveness in predicting accurate binding modes but also exhibits a significant speed advantage (208 $\times$) compared to existing state-of-the-art methods. Our code is released at https://github.com/tmlr-group/FABFlex.
Authors: Rim Slama, Wael Rabah, Hazem Wannous
Abstract: Online continuous action recognition has emerged as a critical research area due to its practical implications in real-world applications, such as human-computer interaction, healthcare, and robotics. Among various modalities, skeleton-based approaches have gained significant popularity, demonstrating their effectiveness in capturing 3D temporal data while ensuring robustness to environmental variations. However, most existing works focus on segment-based recognition, making them unsuitable for real-time, continuous recognition scenarios. In this paper, we propose a novel online recognition system designed for real-time skeleton sequence streaming. Our approach leverages a hybrid architecture combining Spatial Graph Convolutional Networks (S-GCN) for spatial feature extraction and a Transformer-based Graph Encoder (TGE) for capturing temporal dependencies across frames. Additionally, we introduce a continual learning mechanism to enhance model adaptability to evolving data distributions, ensuring robust recognition in dynamic environments. We evaluate our method on the SHREC'21 benchmark dataset, demonstrating its superior performance in online hand gesture recognition. Our approach not only achieves state-of-the-art accuracy but also significantly reduces false positive rates, making it a compelling solution for real-time applications. The proposed system can be seamlessly integrated into various domains, including human-robot collaboration and assistive technologies, where natural and intuitive interaction is crucial.
Authors: Thomas Froech, Olaf Wysocki, Yan Xia, Junyu Xie, Benedikt Schwab, Daniel Cremers, Thomas H. Kolbe
Abstract: High-detail semantic 3D building models are frequently utilized in robotics, geoinformatics, and computer vision. One key aspect of creating such models is employing 2D conflict maps that detect openings' locations in building facades. Yet, in reality, these maps are often incomplete due to obstacles encountered during laser scanning. To address this challenge, we introduce FacaDiffy, a novel method for inpainting unseen facade parts by completing conflict maps with a personalized Stable Diffusion model. Specifically, we first propose a deterministic ray analysis approach to derive 2D conflict maps from existing 3D building models and corresponding laser scanning point clouds. Furthermore, we facilitate the inpainting of unseen facade objects into these 2D conflict maps by leveraging the potential of personalizing a Stable Diffusion model. To complement the scarcity of real-world training data, we also develop a scalable pipeline to produce synthetic conflict maps using random city model generators and annotated facade images. Extensive experiments demonstrate that FacaDiffy achieves state-of-the-art performance in conflict map completion compared to various inpainting baselines and increases the detection rate by $22\%$ when applying the completed conflict maps for high-definition 3D semantic building reconstruction. The code is be publicly available in the corresponding GitHub repository: https://github.com/ThomasFroech/InpaintingofUnseenFacadeObjects
URLs: https://github.com/ThomasFroech/InpaintingofUnseenFacadeObjects
Authors: Masatoshi Uehara, Xingyu Su, Yulai Zhao, Xiner Li, Aviv Regev, Shuiwang Ji, Sergey Levine, Tommaso Biancalani
Abstract: To fully leverage the capabilities of diffusion models, we are often interested in optimizing downstream reward functions during inference. While numerous algorithms for reward-guided generation have been recently proposed due to their significance, current approaches predominantly focus on single-shot generation, transitioning from fully noised to denoised states. We propose a novel framework for inference-time reward optimization with diffusion models inspired by evolutionary algorithms. Our approach employs an iterative refinement process consisting of two steps in each iteration: noising and reward-guided denoising. This sequential refinement allows for the gradual correction of errors introduced during reward optimization. Besides, we provide a theoretical guarantee for our framework. Finally, we demonstrate its superior empirical performance in protein and cell-type-specific regulatory DNA design. The code is available at \href{https://github.com/masa-ue/ProDifEvo-Refinement}{https://github.com/masa-ue/ProDifEvo-Refinement}.
URLs: https://github.com/masa-ue/ProDifEvo-Refinement, https://github.com/masa-ue/ProDifEvo-Refinement
Authors: Ahmed Heakl, Abdullah Sohail, Mukul Ranjan, Rania Hossam, Ghazi Ahmed, Mohamed El-Geish, Omar Maher, Zhiqiang Shen, Fahad Khan, Salman Khan
Abstract: With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples across 9 major domains and 36 sub-domains, encompassing diverse document types including handwritten text, structured tables, and specialized coverage of 21 chart types for business intelligence. Our findings show that modern vision-language models (such as GPT-4, Gemini, and Qwen) outperform traditional OCR approaches (like EasyOCR, PaddleOCR, and Surya) by an average of 60% in Character Error Rate (CER). Furthermore, we highlight significant limitations of current Arabic OCR models, particularly in PDF-to-Markdown conversion, where the best model Gemini-2.0-Flash achieves only 65% accuracy. This underscores the challenges in accurately recognizing Arabic text, including issues with complex fonts, numeral recognition errors, word elongation, and table structure detection. This work establishes a rigorous evaluation framework that can drive improvements in Arabic document analysis methods and bridge the performance gap with English OCR technologies.
Authors: Krti Tallam
Abstract: The rapid advancement of artificial intelligence (AI) has significantly expanded the attack surface for AI-driven cybersecurity threats, necessitating adaptive defense strategies. This paper introduces CyberSentinel, a unified, single-agent system for emergent threat detection, designed to identify and mitigate novel security risks in real time. CyberSentinel integrates: (1) Brute-force attack detection through SSH log analysis, (2) Phishing threat assessment using domain blacklists and heuristic URL scoring, and (3) Emergent threat detection via machine learning-based anomaly detection. By continuously adapting to evolving adversarial tactics, CyberSentinel strengthens proactive cybersecurity defense, addressing critical vulnerabilities in AI security.
Authors: David Noever, Grant Rosario
Abstract: We present an open-source benchmark and evaluation framework for assessing emotional boundary handling in Large Language Models (LLMs). Using a dataset of 1156 prompts across six languages, we evaluated three leading LLMs (GPT-4o, Claude-3.5 Sonnet, and Mistral-large) on their ability to maintain appropriate emotional boundaries through pattern-matched response analysis. Our framework quantifies responses across seven key patterns: direct refusal, apology, explanation, deflection, acknowledgment, boundary setting, and emotional awareness. Results demonstrate significant variation in boundary-handling approaches, with Claude-3.5 achieving the highest overall score (8.69/10) and producing longer, more nuanced responses (86.51 words on average). We identified a substantial performance gap between English (average score 25.62) and non-English interactions (< 0.22), with English responses showing markedly higher refusal rates (43.20% vs. < 1% for non-English). Pattern analysis revealed model-specific strategies, such as Mistral's preference for deflection (4.2%) and consistently low empathy scores across all models (< 0.06). Limitations include potential oversimplification through pattern matching, lack of contextual understanding in response analysis, and binary classification of complex emotional responses. Future work should explore more nuanced scoring methods, expand language coverage, and investigate cultural variations in emotional boundary expectations. Our benchmark and methodology provide a foundation for systematic evaluation of LLM emotional intelligence and boundary-setting capabilities.
Authors: Manuel Knott, Ignacio Serna, Ethan Mann, Pietro Perona
Abstract: Measuring the accuracy of face recognition (FR) systems is essential for improving performance and ensuring responsible use. Accuracy is typically estimated using large annotated datasets, which are costly and difficult to obtain. We propose a novel method for 1:1 face verification that benchmarks FR systems quickly and without manual annotation, starting from approximate labels (e.g., from web search results). Unlike previous methods for training set label cleaning, ours leverages the embedding representation of the models being evaluated, achieving high accuracy in smaller-sized test datasets. Our approach reliably estimates FR accuracy and ranking, significantly reducing the time and cost of manual labeling. We also introduce the first public benchmark of five FR cloud services, revealing demographic biases, particularly lower accuracy for Asian women. Our rapid test method can democratize FR testing, promoting scrutiny and responsible use of the technology. Our method is provided as a publicly accessible tool at https://github.com/caltechvisionlab/frt-rapid-test
Authors: Lew Lefton, Kexin Rong, Chinar Dankhara, Lila Ghemri, Firdous Kausar, A. Hannibal Hamdallahi
Abstract: In this paper, we propose a Retrieval Augmented Generation (RAG) agent that maps natural language queries about research topics to precise, machine-interpretable semantic entities. Our approach combines RAG with Socratic dialogue to align a user's intuitive understanding of research topics with established Knowledge Organization Systems (KOSs). The proposed approach will effectively bridge "little semantics" (domain-specific KOS structures) with "big semantics" (broad bibliometric repositories), making complex academic taxonomies more accessible. Such agents have the potential for broad use. We illustrate with a sample application called CollabNext, which is a person-centric knowledge graph connecting people, organizations, and research topics. We further describe how the application design has an intentional focus on HBCUs and emerging researchers to raise visibility of people historically rendered invisible in the current science system.
Authors: Ji Yin, Oswin So, Eric Yang Yu, Chuchu Fan, Panagiotis Tsiotras
Abstract: A common problem when using model predictive control (MPC) in practice is the satisfaction of safety specifications beyond the prediction horizon. While theoretical works have shown that safety can be guaranteed by enforcing a suitable terminal set constraint or a sufficiently long prediction horizon, these techniques are difficult to apply and thus are rarely used by practitioners, especially in the case of general nonlinear dynamics. To solve this problem, we impose a tradeoff between exact recursive feasibility, computational tractability, and applicability to ''black-box'' dynamics by learning an approximate discrete-time control barrier function and incorporating it into a variational inference MPC (VIMPC), a sampling-based MPC paradigm. To handle the resulting state constraints, we further propose a new sampling strategy that greatly reduces the variance of the estimated optimal control, improving the sample efficiency, and enabling real-time planning on a CPU. The resulting Neural Shield-VIMPC (NS-VIMPC) controller yields substantial safety improvements compared to existing sampling-based MPC controllers, even under badly designed cost functions. We validate our approach in both simulation and real-world hardware experiments.
Authors: Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev, Elizaveta Goncharova, Polina Druzhinina, Ivan Oseledets, Andrey Kuznetsov
Abstract: We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these tokens -- especially stopwords, articles, and commas -- consistently degrades performance on MMLU and BABILong-4k, even if removing only irrelevant tokens. Our analysis also shows a strong correlation between contextualization and linearity, where linearity measures how closely the transformation from one layer's embeddings to the next can be approximated by a single linear mapping. These findings underscore the hidden importance of filler tokens in maintaining context. For further exploration, we present LLM-Microscope, an open-source toolkit that assesses token-level nonlinearity, evaluates contextual memory, visualizes intermediate layer contributions (via an adapted Logit Lens), and measures the intrinsic dimensionality of representations. This toolkit illuminates how seemingly trivial tokens can be critical for long-range understanding.
Authors: Mark Russinovich, Ahmed Salem
Abstract: Recent copyright agreements between AI companies and content creators have highlighted the need for precise control over language models' ability to reproduce copyrighted content. While existing approaches rely on either complete concept removal through unlearning or simple output filtering, we propose Obliviate, a novel post-training technique that selectively prevents verbatim reproduction of specific text while preserving semantic understanding. Obliviate operates by selecting tokens within memorized sequences and modifying the model's probability distribution to prevent exact reproduction while maintaining contextual understanding. We evaluate Obliviate on multiple large language models (LLaMA-3.1 8B, LLaMA-3.1-instruct 8B, Qwen-2.5-7B, and Yi-1.5 6B) across both synthetic memorization tasks and organic copyright content. Our results demonstrate that Obliviate achieves orders of magnitude reduction, e.g., 100x, in verbatim memorization while maintaining model performance within 1% of baseline on standard benchmarks (HellaSwag, MMLU, TruthfulQA, and Winogrande). This makes Obliviate particularly suitable for practical deployment scenarios where companies need to efficiently address copyright concerns in pretrained models without compromising their general capabilities.
Authors: Ruyi Ding, Tianhong Xu, Aidong Adam Ding, Yunsi Fei
Abstract: Wide deployment of machine learning models on edge devices has rendered the model intellectual property (IP) and data privacy vulnerable. We propose GNNVault, the first secure Graph Neural Network (GNN) deployment strategy based on Trusted Execution Environment (TEE). GNNVault follows the design of 'partition-before-training' and includes a private GNN rectifier to complement with a public backbone model. This way, both critical GNN model parameters and the private graph used during inference are protected within secure TEE compartments. Real-world implementations with Intel SGX demonstrate that GNNVault safeguards GNN inference against state-of-the-art link stealing attacks with negligible accuracy degradation (<2%).
Authors: Majid Farhadloo, Arun Sharma, Mingzhou Yang, Bharat Jayaprakash, William Northrop, Shashi Shekhar
Abstract: Traditional foundation models are pre-trained on broad datasets to reduce the training resources (e.g., time, energy, labeled samples) needed for fine-tuning a wide range of downstream tasks. However, traditional foundation models struggle with out-of-distribution prediction and can produce outputs that are unrealistic and physically infeasible. We propose the notation of physics-guided foundation models (PGFM), that is, foundation models integrated with broad or general domain (e.g., scientific) physical knowledge applicable to a wide range of downstream tasks.
Authors: Henry Hengyuan Zhao, Wenqi Pei, Yifei Tao, Haiyang Mei, Mike Zheng Shou
Abstract: Existing benchmarks do not test Large Multimodal Models (LMMs) on their interactive intelligence with human users which is vital for developing general-purpose AI assistants. We design InterFeedback, an interactive framework, which can be applied to any LMM and dataset to assess this ability autonomously. On top of this, we introduce InterFeedback-Bench which evaluates interactive intelligence using two representative datasets, MMMU-Pro and MathVerse, to test 10 different open-source LMMs. Additionally, we present InterFeedback-Human, a newly collected dataset of 120 cases designed for manually testing interactive performance in leading models such as OpenAI-o1 and Claude-3.5-Sonnet. Our evaluation results show that even state-of-the-art LMM (like OpenAI-o1) can correct their results through human feedback less than 50%. Our findings point to the need for methods that can enhance the LMMs' capability to interpret and benefit from feedback.
Authors: Yizhou Chen, Xiaoyue Wu, Yeheng Zong, Anran Li, Yuzhen Chen, Julie Wu, Bohao Zhang, Ram Vasudevan
Abstract: Autonomous wire harness assembly requires robots to manipulate complex branched cables with high precision and reliability. A key challenge in automating this process is predicting how these flexible and branched structures behave under manipulation. Without accurate predictions, it is difficult for robots to reliably plan or execute assembly operations. While existing research has made progress in modeling single-threaded Deformable Linear Objects (DLOs), extending these approaches to Branched Deformable Linear Objects (BDLOs) presents fundamental challenges. The junction points in BDLOs create complex force interactions and strain propagation patterns that cannot be adequately captured by simply connecting multiple single-DLO models. To address these challenges, this paper presents Differentiable discrete branched Elastic rods for modeling Furcated DLOs in real-Time (DEFT), a novel framework that combines a differentiable physics-based model with a learning framework to: 1) accurately model BDLO dynamics, including dynamic propagation at junction points and grasping in the middle of a BDLO, 2) achieve efficient computation for real-time inference, and 3) enable planning to demonstrate dexterous BDLO manipulation. A comprehensive series of real-world experiments demonstrates DEFT's efficacy in terms of accuracy, computational speed, and generalizability compared to state-of-the-art alternatives. Project page:https://roahmlab.github.io/DEFT/.
Authors: Yun-Wei Chu, Kai Zhang, Christopher Malon, Martin Renqiang Min
Abstract: Multimodal Large Language Models (MLLMs) have shown impressive performance in vision and text tasks. However, hallucination remains a major challenge, especially in fields like healthcare where details are critical. In this work, we show how MLLMs may be enhanced to support Visual RAG (V-RAG), a retrieval-augmented generation framework that incorporates both text and visual data from retrieved images. On the MIMIC-CXR chest X-ray report generation and Multicare medical image caption generation datasets, we show that Visual RAG improves the accuracy of entity probing, which asks whether a medical entities is grounded by an image. We show that the improvements extend both to frequent and rare entities, the latter of which may have less positive training data. Downstream, we apply V-RAG with entity probing to correct hallucinations and generate more clinically accurate X-ray reports, obtaining a higher RadGraph-F1 score.
Authors: Amlan Basu, Pranav Chaudhari, Gaetano Di Caterina
Abstract: Audio classification is paramount in a variety of applications including surveillance, healthcare monitoring, and environmental analysis. Traditional methods frequently depend on intricate signal processing algorithms and manually crafted features, which may fall short in fully capturing the complexities of audio patterns. Neuromorphic computing, inspired by the architecture and functioning of the human brain, presents a promising alternative for audio classification tasks. This survey provides an exhaustive examination of the current state-of-the-art in neuromorphic-based audio classification. It delves into the crucial components of neuromorphic systems, such as Spiking Neural Networks (SNNs), memristors, and neuromorphic hardware platforms, highlighting their advantages in audio classification. Furthermore, the survey explores various methodologies and strategies employed in neuromorphic audio classification, including event-based processing, spike-based learning, and bio-inspired feature extraction. It examines how these approaches address the limitations of traditional audio classification methods, particularly in terms of energy efficiency, real-time processing, and robustness to environmental noise. Additionally, the paper conducts a comparative analysis of different neuromorphic audio classification models and benchmarks, evaluating their performance metrics, computational efficiency, and scalability. By providing a comprehensive guide for researchers, engineers and practitioners, this survey aims to stimulate further innovation and advancements in the evolving field of neuromorphic audio classification.
Authors: Elliot Schumacher, Dhruv Naik, Anitha Kannan
Abstract: Large language models (LLMs) have demonstrated impressive capabilities in disease diagnosis. However, their effectiveness in identifying rarer diseases, which are inherently more challenging to diagnose, remains an open question. Rare disease performance is critical with the increasing use of LLMs in healthcare settings. This is especially true if a primary care physician needs to make a rarer prognosis from only a patient conversation so that they can take the appropriate next step. To that end, several clinical decision support systems are designed to support providers in rare disease identification. Yet their utility is limited due to their lack of knowledge of common disorders and difficulty of use. In this paper, we propose RareScale to combine the knowledge LLMs with expert systems. We use jointly use an expert system and LLM to simulate rare disease chats. This data is used to train a rare disease candidate predictor model. Candidates from this smaller model are then used as additional inputs to black-box LLM to make the final differential diagnosis. Thus, RareScale allows for a balance between rare and common diagnoses. We present results on over 575 rare diseases, beginning with Abdominal Actinomycosis and ending with Wilson's Disease. Our approach significantly improves the baseline performance of black-box LLMs by over 17% in Top-5 accuracy. We also find that our candidate generation performance is high (e.g. 88.8% on gpt-4o generated chats).
Authors: Sanghyun Yi, Qingfeng Liu, Mostafa El-Khamy
Abstract: Diffusion Transformers for video generation have gained significant research interest since the impressive performance of SORA. Efficient deployment of such generative-AI models on GPUs has been demonstrated with dynamic quantization. However, resource-constrained devices cannot support dynamic quantization, and need static quantization of the models for their efficient deployment on AI processors. In this paper, we propose a novel method for the post-training quantization of OpenSora\cite{opensora}, a Video Diffusion Transformer, without relying on dynamic quantization techniques. Our approach employs static quantization, achieving video quality comparable to FP16 and dynamically quantized ViDiT-Q methods, as measured by CLIP, and VQA metrics. In particular, we utilize per-step calibration data to adequately provide a post-training statically quantized model for each time step, incorporating channel-wise quantization for weights and tensor-wise quantization for activations. By further applying the smooth-quantization technique, we can obtain high-quality video outputs with the statically quantized models. Extensive experimental results demonstrate that static quantization can be a viable alternative to dynamic quantization for video diffusion transformers, offering a more efficient approach without sacrificing performance.
Authors: Lingjun Zhao, Mingyang Xie, Paola Cascante-Bonilla, Hal Daum\'e III, Kwonjoon Lee
Abstract: Large Vision-Language Models often generate hallucinated content that is not grounded in its visual inputs. While prior work focuses on mitigating hallucinations, we instead explore leveraging hallucination correction as a training objective to improve video-language alignment. We introduce HACA, a self-training framework learning to correct hallucinations in descriptions that do not align with the video content. By identifying and correcting inconsistencies, HACA enhances the model's ability to align video and textual representations for spatio-temporal reasoning. Our experimental results show consistent gains in video-caption binding and text-to-video retrieval tasks, demonstrating that hallucination correction-inspired tasks serve as an effective strategy for improving vision and language alignment.
Authors: Vaidehi Patil, Elias Stengel-Eskin, Mohit Bansal
Abstract: User specifications or legal frameworks often require information to be removed from pretrained models, including large language models (LLMs). This requires deleting or "forgetting" a set of data points from an already-trained model, which typically degrades its performance on other data points. Thus, a balance must be struck between removing information and keeping the model's other abilities intact, with a failure to balance this trade-off leading to poor deletion or an unusable model. To this end, we propose UPCORE (Utility-Preserving Coreset Selection), a method-agnostic data selection framework for mitigating collateral damage during unlearning. Finding that the model damage is correlated with the variance of the model's representations on the forget set, we selectively prune the forget set to remove outliers, thereby minimizing model degradation after unlearning. We evaluate UPCORE across three standard unlearning methods consistently achieving a superior balance between the competing objectives of deletion efficacy and model preservation. To better evaluate this trade-off, we introduce a new metric, measuring the area-under-the-curve (AUC) across standard metrics. We find that UPCORE improves both standard metrics and AUC, benefitting from positive transfer between the coreset and pruned points while reducing negative transfer from the forget set to points outside of it.
Authors: Masha Fedzechkina, Eleonora Gualdoni, Sinead Williamson, Katherine Metcalf, Skyler Seto, Barry-John Theobald
Abstract: Modern large language models (LLMs) achieve impressive performance on some tasks, while exhibiting distinctly non-human-like behaviors on others. This raises the question of how well the LLM's learned representations align with human representations. In this work, we introduce a novel approach to the study of representation alignment: we adopt a method from research on activation steering to identify neurons responsible for specific concepts (e.g., 'cat') and then analyze the corresponding activation patterns. Our findings reveal that LLM representations closely align with human representations inferred from behavioral data. Notably, this alignment surpasses that of word embeddings, which have been center stage in prior work on human and model alignment. Additionally, our approach enables a more granular view of how LLMs represent concepts. Specifically, we show that LLMs organize concepts in a way that reflects hierarchical relationships interpretable to humans (e.g., 'animal'-'dog').
Authors: Zewen Zhuo, Mohamad Najafi, Hazem Zein, Amine Nait-Ali
Abstract: This study introduces a specialized pipeline designed to classify the concentration state of an individual student during online learning sessions by training a custom-tailored machine learning model. Detailed protocols for acquiring and preprocessing EEG data are outlined, along with the extraction of fifty statistical features from five EEG signal bands: alpha, beta, theta, delta, and gamma. Following feature extraction, a thorough feature selection process was conducted to optimize the data inputs for a personalized analysis. The study also explores the benefits of hyperparameter fine-tuning to enhance the classification accuracy of the student's concentration state. EEG signals were captured from the student using a Muse headband (Gen 2), equipped with five electrodes (TP9, AF7, AF8, TP10, and a reference electrode NZ), during engagement with educational content on computer-based e-learning platforms. Employing a random forest model customized to the student's data, we achieved remarkable classification performance, with test accuracies of 97.6% in the computer-based learning setting and 98% in the virtual reality setting. These results underscore the effectiveness of our approach in delivering personalized insights into student concentration during online educational activities.
Authors: Zihao Sheng, Zilin Huang, Yansong Qu, Yue Leng, Sruthi Bhavanam, Sikai Chen
Abstract: Ensuring safety in autonomous driving systems remains a critical challenge, particularly in handling rare but potentially catastrophic safety-critical scenarios. While existing research has explored generating safety-critical scenarios for autonomous vehicle (AV) testing, there is limited work on effectively incorporating these scenarios into policy learning to enhance safety. Furthermore, developing training curricula that adapt to an AV's evolving behavioral patterns and performance bottlenecks remains largely unexplored. To address these challenges, we propose CurricuVLM, a novel framework that leverages Vision-Language Models (VLMs) to enable personalized curriculum learning for autonomous driving agents. Our approach uniquely exploits VLMs' multimodal understanding capabilities to analyze agent behavior, identify performance weaknesses, and dynamically generate tailored training scenarios for curriculum adaptation. Through comprehensive analysis of unsafe driving situations with narrative descriptions, CurricuVLM performs in-depth reasoning to evaluate the AV's capabilities and identify critical behavioral patterns. The framework then synthesizes customized training scenarios targeting these identified limitations, enabling effective and personalized curriculum learning. Extensive experiments on the Waymo Open Motion Dataset show that CurricuVLM outperforms state-of-the-art baselines across both regular and safety-critical scenarios, achieving superior performance in terms of navigation success, driving efficiency, and safety metrics. Further analysis reveals that CurricuVLM serves as a general approach that can be integrated with various RL algorithms to enhance autonomous driving systems. The code and demo video are available at: https://zihaosheng.github.io/CurricuVLM/.
Authors: Yen-Che Hsiao, Abhishek Dutta
Abstract: This study investigates the in-context learning capabilities of various decoder-only transformer-based language models with different model sizes and training data, including GPT2, SmolLM2, OpenELM, TinyLlama, Stable LM, and Gemma 2. We identify a critical parameter threshold (~1.6 billion), beyond which reasoning performance improves significantly in tasks such as commonsense reasoning in multiple-choice question answering and deductive reasoning. Specifically, models above this threshold achieve better success rates in chain-of-thought (CoT) prompting for deductive reasoning tasks, especially those requiring longer reasoning chains, such as proof by contradiction and disjunction elimination. To address limitations in sub-threshold models, we demonstrate that fine-tuning with task-specific exemplars substantially enhances reasoning performance, enabling accurate CoT generation even without additional exemplars in the prompt for tasks with shorter reasoning chains. Finally, our analysis of attention maps reveals that models capable of generating correct CoTs exhibit higher token-level attention scores on subsequent correct tokens and the correct parts of speech, providing interpretability insights into reasoning processes. These findings collectively advance understanding of reasoning capabilities in decoder-only transformer-based models. The code is available at: https://github.com/AnnonymousForPapers/CoT_Reasoning_Test.
URLs: https://github.com/AnnonymousForPapers/CoT_Reasoning_Test.
Authors: Vignesh Kothapalli, Hamed Firooz, Maziar Sanjabi
Abstract: We introduce CoT-ICL Lab, a framework and methodology to generate synthetic tokenized datasets and systematically study chain-of-thought (CoT) in-context learning (ICL) in language models. CoT-ICL Lab allows fine grained control over the complexity of in-context examples by decoupling (1) the causal structure involved in chain token generation from (2) the underlying token processing functions. We train decoder-only transformers (up to 700M parameters) on these datasets and show that CoT accelerates the accuracy transition to higher values across model sizes. In particular, we find that model depth is crucial for leveraging CoT with limited in-context examples, while more examples help shallow models match deeper model performance. Additionally, limiting the diversity of token processing functions throughout training improves causal structure learning via ICL. We also interpret these transitions by analyzing transformer embeddings and attention maps. Overall, CoT-ICL Lab serves as a simple yet powerful testbed for theoretical and empirical insights into ICL and CoT in language models.
Authors: Juntae Lee, Jihwan Bang, Seunghan Yang, Kyuhong Shim, Simyung Chang
Abstract: Retrieval-augmented generation (RAG) with large language models (LLMs) is especially valuable in specialized domains, where precision is critical. To more specialize the LLMs into a target domain, domain-specific RAG has recently been developed by allowing the LLM to access the target domain early via finetuning. The domain-specific RAG makes more sense in resource-constrained environments like edge devices, as they should perform a specific task (e.g. personalization) reliably using only small-scale LLMs. While the domain-specific RAG is well-aligned with edge devices in this respect, it often relies on widely-used reasoning techniques like chain-of-thought (CoT). The reasoning step is useful to understand the given external knowledge, and yet it is computationally expensive and difficult for small-scale LLMs to learn it. Tackling this, we propose the Chain of Rank (CoR) which shifts the focus from intricate lengthy reasoning to simple ranking of the reliability of input external documents. Then, CoR reduces computational complexity while maintaining high accuracy, making it particularly suited for resource-constrained environments. We attain the state-of-the-art (SOTA) results in benchmarks, and analyze its efficacy.
Authors: Nuoya Xiong, Aarti Singh
Abstract: Reinforcement Learning with Human Feedback (RLHF) is a widely used fine-tuning approach that aligns machine learning model, particularly Language Model (LM) with human preferences. There are typically multiple objectives driving the preference, hence humans find it easier to express per-objective comparisons rather than a global preference between two choices. %, e.g. compare two papers on their novelty, clarity, correctness, etc. Multi-Objective RLHF (MORLHF) aims to use per-objective preference feedback and achieve Pareto optimality among these objectives by aggregating them into a single unified objective for optimization. However, nearly all prior works rely on linear aggregation, which rules out policies that favor specific objectives such as the worst one. The only existing approach using non-linear aggregation is computationally expensive due to its reward-based nature and the need for retraining whenever the aggregation parameters change. In this work, we address this limitation by transforming the non-linear aggregation maximization problem into a series of sub-problems. Each sub-problem involves only linear aggregation, making it computationally efficient to solve. We further extend our framework to handle multi-group scenarios, where each group has distinct weights for the objectives. Our method enables achieving consensus or maximizing the aggregated objective across all groups. Theoretically, we demonstrate that our algorithmic framework achieves sublinear regret and can be easily adapted to a reward-free algorithm. Empirically, leveraging our theoretical insights, we propose a nearly training-free algorithm once the optimal policies for individual objectives are obtained.
Authors: Ebenezer Tarubinga, Jenifer Kalafatovich Espinoza
Abstract: Semi-supervised semantic segmentation (SSSS) aims to improve segmentation performance by utilising unlabeled data alongside limited labeled samples. Existing SSSS methods often face challenges such as coupling, where over-reliance on initial labeled data leads to suboptimal learning; confirmation bias, where incorrect predictions reinforce themselves repeatedly; and boundary blur caused by insufficient boundary-awareness and ambiguous edge information. To address these issues, we propose CW-BASS, a novel framework for SSSS. In order to mitigate the impact of incorrect predictions, we assign confidence weights to pseudo-labels. Additionally, we leverage boundary-delineation techniques, which, despite being extensively explored in weakly-supervised semantic segmentation (WSSS) remain under-explored in SSSS. Specifically, our approach: (1) reduces coupling through a confidence-weighted loss function that adjusts the influence of pseudo-labels based on their predicted confidence scores, (2) mitigates confirmation bias with a dynamic thresholding mechanism that learns to filter out pseudo-labels based on model performance, (3) resolves boundary blur with a boundary-aware module that enhances segmentation accuracy near object boundaries, and (4) reduces label noise with a confidence decay strategy that progressively refines pseudo-labels during training. Extensive experiments on the Pascal VOC 2012 and Cityscapes demonstrate that our method achieves state-of-the-art performance. Moreover, using only 1/8 or 12.5\% of labeled data, our method achieves a mIoU of 75.81 on Pascal VOC 2012, highlighting its effectiveness in limited-label settings.
Authors: Sarthak Mahajan, Nimmi Rangaswamy
Abstract: In recent years, widespread internet adoption and the growth in userbase of various social media platforms have led to an increase in the proliferation of extreme speech online. While traditional language models have demonstrated proficiency in distinguishing between neutral text and non-neutral text (i.e. extreme speech), categorizing the diverse types of extreme speech presents significant challenges. The task of extreme speech classification is particularly nuanced, as it requires a deep understanding of socio-cultural contexts to accurately interpret the intent of the language used by the speaker. Even human annotators often disagree on the appropriate classification of such content, emphasizing the complex and subjective nature of this task. The use of human moderators also presents a scaling issue, necessitating the need for automated systems for extreme speech classification. The recent launch of ChatGPT has drawn global attention to the potential applications of Large Language Models (LLMs) across a diverse variety of tasks. Trained on vast and diverse corpora, and demonstrating the ability to effectively capture and encode contextual information, LLMs emerge as highly promising tools for tackling this specific task of extreme speech classification. In this paper, we leverage the Indian subset of the extreme speech dataset from Maronikolakis et al. (2022) to develop an effective classification framework using LLMs. We evaluate open-source Llama models against closed-source OpenAI models, finding that while pre-trained LLMs show moderate efficacy, fine-tuning with domain-specific data significantly enhances performance, highlighting their adaptability to linguistic and contextual nuances. Although GPT-based models outperform Llama models in zero-shot settings, the performance gap disappears after fine-tuning.
Authors: Arpan Mahara, Naphtali Rishe
Abstract: The proliferation of generative models, such as Generative Adversarial Networks (GANs), Diffusion Models, and Variational Autoencoders (VAEs), has enabled the synthesis of high-quality multimedia data. However, these advancements have also raised significant concerns regarding adversarial attacks, unethical usage, and societal harm. Recognizing these challenges, researchers have increasingly focused on developing methodologies to detect synthesized data effectively, aiming to mitigate potential risks. Prior reviews have primarily focused on deepfake detection and often lack coverage of recent advancements in synthetic image detection, particularly methods leveraging multimodal frameworks for improved forensic analysis. To address this gap, the present survey provides a comprehensive review of state-of-the-art methods for detecting and classifying synthetic images generated by advanced generative AI models. This review systematically examines core detection methodologies, identifies commonalities among approaches, and categorizes them into meaningful taxonomies. Furthermore, given the crucial role of large-scale datasets in this field, we present an overview of publicly available datasets that facilitate further research and benchmarking in synthetic data detection.
Authors: Qi An, Chihua Ying, Yuqing Zhu, Yihao Xu, Manwei Zhang, Jianmin Wang
Abstract: Data discovery in data lakes with ever increasing datasets has long been recognized as a big challenge in the realm of data management, especially for semantic search of and hierarchical global catalog generation of tables. While large language models (LLMs) facilitate the processing of data semantics, challenges remain in architecting an end-to-end system that comprehensively exploits LLMs for the two semantics-related tasks. In this demo, we propose LEDD, an end-to-end system with an extensible architecture that leverages LLMs to provide hierarchical global catalogs with semantic meanings and semantic table search for data lakes. Specifically, LEDD can return semantically related tables based on natural-language specification. These features make LEDD an ideal foundation for downstream tasks such as model training and schema linking for text-to-SQL tasks. LEDD also provides a simple Python interface to facilitate the extension and the replacement of data discovery algorithms.
Authors: Zhang Xueliana, Fang Yingjieb, Liu Hang
Abstract: Objective To conduct biomechanical analysis on the starting technique of male short-distance speed skating athletes in China and determine the key factors affecting the effectiveness of the starting movement. Methods 13 high-level male short-distance speed skating athletes were selected as the test subjects, and kinematic data were collected using an artificial intelligence video capture and analysis system. The body posture features and their effects on the starting movement performance were analyzed in the three stages of starting preparation, starting, and sprinting. Results The post-stability angle, anterior knee angle of the front leg, posterior knee angle of the rear leg, and stride length showed moderate to high positive correlations with the starting speed during the starting preparation stage. The trunk angle showed a high negative correlation with the starting speed. The trunk angle (TO4, TD4, TO6, TD6), hip angle (TO1, TO4, TO6), and knee angle (TD1) showed moderate to high negative correlations with the effectiveness of the starting movement during the starting and sprinting stages. The knee angle (TD2), ice-contact angle (TD2, TD4, TD5, TD6), and propulsion angle (TO1, TO4, TO7) showed moderate positive correlations with the effectiveness of the starting movement. Conclusion Stride length, left knee angle, and post-stability angle are the key factors affecting the starting speed. The larger the post-stability angle and left knee angle and the longer the stride length, the faster the starting speed. During the starting and sprinting stages, the smaller the ice-contact angle and propulsion angle, the greater the trunk angle and hip angle changes, the more effective the starting movement.
Authors: Namrah Siddiqua, Kim Suneung
Abstract: Low-light image enhancement (LLIE) is a crucial task in computer vision aimed to enhance the visual fidelity of images captured under low-illumination conditions. Conventional methods frequently struggle to mitigate pervasive shortcomings such as noise, over-exposure, and color distortion thereby precipitating a pronounced degradation in image quality. To address these challenges, we propose LUMINA-Net an advanced deep learning framework designed specifically by integrating multi-stage illumination and reflectance modules. First, the illumination module intelligently adjusts brightness and contrast levels while meticulously preserving intricate textural details. Second, the reflectance module incorporates a noise reduction mechanism that leverages spatial attention and channel-wise feature refinement to mitigate noise contamination. Through a comprehensive suite of experiments conducted on LOL and SICE datasets using PSNR, SSIM and LPIPS metrics, surpassing state-of-the-art methodologies and showcasing its efficacy in low-light image enhancement.
Authors: Jianglin Lu, Yixuan Liu, Yitian Zhang, Yun Fu
Abstract: Graph-language models (GLMs) have demonstrated great potential in graph-based semi-supervised learning. A typical GLM consists of two key stages: graph generation and text embedding, which are usually implemented by inferring a latent graph and finetuning a language model (LM), respectively. However, the former often relies on artificial assumptions about the underlying edge distribution, while the latter requires extensive data annotations. To tackle these challenges, this paper introduces a novel GLM that integrates graph generation and text embedding within a unified framework. Specifically, for graph generation, we leverage an inherent characteristic of real edge distribution--the scale-free property--as a structural prior. We unexpectedly find that this natural property can be effectively approximated by a simple k-nearest neighbor (KNN) graph. For text embedding, we develop a graph-based pseudo-labeler that utilizes scale-free graphs to provide complementary supervision for improved LM finetuning. Extensive experiments on representative datasets validate our findings on the scale-free structural approximation of KNN graphs and demonstrate the effectiveness of integrating graph generation and text embedding with a real structural prior. Our code is available at https://github.com/Jianglin954/SFGL.
Authors: Zhaoxuan Wu, Zijian Zhou, Arun Verma, Alok Prakash, Daniela Rus, Bryan Kian Hsiang Low
Abstract: We propose TETRIS, a novel method that optimizes the total throughput of batch speculative decoding in multi-request settings. Unlike existing methods that optimize for a single request or a group of requests as a whole, TETRIS actively selects the most promising draft tokens (for every request in a batch) to be accepted when verified in parallel, resulting in fewer rejected tokens and hence less wasted computing resources. Such an effective resource utilization to achieve fast inference in large language models (LLMs) is especially important to service providers with limited inference capacity. Compared to baseline speculative decoding, TETRIS yields a consistently higher acceptance rate and more effective utilization of the limited inference capacity. We show theoretically and empirically that TETRIS outperforms baseline speculative decoding and existing methods that dynamically select draft tokens, leading to a more efficient batch inference in LLMs.
Authors: Young Beom Woo, Sun Eung Kim
Abstract: Recently, methods that integrate multiple personalized concepts into a single image have garnered significant attention in the field of text-to-image (T2I) generation. However, existing methods experience performance degradation in complex scenes with multiple objects due to distortions in non-personalized regions. To address this issue, we propose FlipConcept, a novel approach that seamlessly integrates multiple personalized concepts into a single image without requiring additional tuning. We introduce guided appearance attention to accurately mimic the appearance of a personalized concept as intended. Additionally, we introduce mask-guided noise mixing to protect non-personalized regions during editing. Lastly, we apply background dilution to minimize attribute leakage, which is the undesired blending of personalized concept attributes with other objects in the image. In our experiments, we demonstrate that the proposed method, despite not requiring tuning, outperforms existing models in both single and multiple personalized concept inference.
Authors: Aarash Feizi, Sai Rajeswar, Adriana Romero-Soriano, Reihaneh Rabbany, Spandana Gella, Valentina Zantedeschi, Jo\~ao Monteiro
Abstract: As large vision language models (VLMs) are increasingly used as automated evaluators, understanding their ability to effectively compare data pairs as instructed in the prompt becomes essential. To address this, we present PairBench, a low-cost framework that systematically evaluates VLMs as customizable similarity tools across various modalities and scenarios. Through PairBench, we introduce four metrics that represent key desiderata of similarity scores: alignment with human annotations, consistency for data pairs irrespective of their order, smoothness of similarity distributions, and controllability through prompting. Our analysis demonstrates that no model, whether closed- or open-source, is superior on all metrics; the optimal choice depends on an auto evaluator's desired behavior (e.g., a smooth vs. a sharp judge), highlighting risks of widespread adoption of VLMs as evaluators without thorough assessment. For instance, the majority of VLMs struggle with maintaining symmetric similarity scores regardless of order. Additionally, our results show that the performance of VLMs on the metrics in PairBench closely correlates with popular benchmarks, showcasing its predictive power in ranking models.
Authors: Sheila Schoepp, Masoud Jafaripour, Yingyue Cao, Tianpei Yang, Fatemeh Abdollahi, Shadan Golestan, Zahin Sufiyan, Osmar R. Zaiane, Matthew E. Taylor
Abstract: Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Meanwhile, Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged, exhibiting impressive capabilities in multimodal understanding and reasoning. These advances have led to a surge of research integrating LLMs and VLMs into RL. In this survey, we review representative works in which LLMs and VLMs are used to overcome key challenges in RL, such as lack of prior knowledge, long-horizon planning, and reward design. We present a taxonomy that categorizes these LLM/VLM-assisted RL approaches into three roles: agent, planner, and reward. We conclude by exploring open problems, including grounding, bias mitigation, improved representations, and action advice. By consolidating existing research and identifying future directions, this survey establishes a framework for integrating LLMs and VLMs into RL, advancing approaches that unify natural language and visual understanding with sequential decision-making.
Authors: Madhurima Chakraborty, Peter Pirkelbauer, Qing Yi
Abstract: FormalSpecCpp is a dataset designed to fill the gap in standardized benchmarks for verifying formal specifications in C++ programs. To the best of our knowledge, this is the first comprehensive collection of C++ programs with well-defined preconditions and postconditions. It provides a structured benchmark for evaluating specification inference tools and testing theaccuracy of generated specifications. Researchers and developers can use this dataset to benchmark specification inference tools,fine-tune Large Language Models (LLMs) for automated specification generation, and analyze the role of formal specifications in improving program verification and automated testing. By making this dataset publicly available, we aim to advance research in program verification, specification inference, and AI-assisted software development. The dataset and the code are available at https://github.com/MadhuNimmo/FormalSpecCpp.
Authors: Tingting Chen, Srinivas Anumasa, Beibei Lin, Vedant Shah, Anirudh Goyal, Dianbo Liu
Abstract: Given the remarkable performance of Large Language Models (LLMs), an important question arises: Can LLMs conduct human-like scientific research and discover new knowledge, and act as an AI scientist? Scientific discovery is an iterative process that demands efficient knowledge updating and encoding. It involves understanding the environment, identifying new hypotheses, and reasoning about actions; however, no standardized benchmark specifically designed for scientific discovery exists for LLM agents. In response to these limitations, we introduce a novel benchmark, \textit{Auto-Bench}, that encompasses necessary aspects to evaluate LLMs for scientific discovery in both natural and social sciences. Our benchmark is based on the principles of causal graph discovery. It challenges models to uncover hidden structures and make optimal decisions, which includes generating valid justifications. By engaging interactively with an oracle, the models iteratively refine their understanding of underlying interactions, the chemistry and social interactions, through strategic interventions. We evaluate state-of-the-art LLMs, including GPT-4, Gemini, Qwen, Claude, and Llama, and observe a significant performance drop as the problem complexity increases, which suggests an important gap between machine and human intelligence that future development of LLMs need to take into consideration.
Authors: Mengqiao Liu, Tevin Wang, Cassandra A. Cohen, Sarah Li, Chenyan Xiong
Abstract: Which large language model (LLM) is better? Every evaluation tells a story, but what do users really think about current LLMs? This paper presents CLUE, an LLM-powered interviewer that conducts in-the-moment user experience interviews, right after users interacted with LLMs, and automatically gathers insights about user opinions from massive interview logs. We conduct a study with thousands of users to understand user opinions on mainstream LLMs, recruiting users to first chat with a target LLM and then interviewed by CLUE. Our experiments demonstrate that CLUE captures interesting user opinions, for example, the bipolar views on the displayed reasoning process of DeepSeek-R1 and demands for information freshness and multi-modality. Our collected chat-and-interview logs will be released.
Authors: Likun Zhang, Sicheng Yang, Zhuo Wang, Haining Liang, Junxiao Shen
Abstract: In this paper, we present an end-to-end automated motion recognition (AutoMR) pipeline designed for multimodal datasets. The proposed framework seamlessly integrates data preprocessing, model training, hyperparameter tuning, and evaluation, enabling robust performance across diverse scenarios. Our approach addresses two primary challenges: 1) variability in sensor data formats and parameters across datasets, which traditionally requires task-specific machine learning implementations, and 2) the complexity and time consumption of hyperparameter tuning for optimal model performance. Our library features an all-in-one solution incorporating QuartzNet as the core model, automated hyperparameter tuning, and comprehensive metrics tracking. Extensive experiments demonstrate its effectiveness on 10 diverse datasets, achieving state-of-the-art performance. This work lays a solid foundation for deploying motion-capture solutions across varied real-world applications.
Authors: Hang Zhang, Yanxin Shen, Lun Wang, Chuanqi Shi, Shaoshuai Du, Yiyi Tao, Yixian Shen
Abstract: The advent of Large Language Models (LLMs) has revolutionized code completion, transforming it into a more intelligent and context-aware feature in modern integrated development environments. These advancements have significantly enhanced developers' ability to write efficient and error-free code. This study evaluates the performance of several chat-based LLMs, including Gemini 1.5 Flash, Gemini 1.5 Pro, GPT-4o, GPT-4o-mini, and GPT-4 Turbo, using the Syntax-Aware Fill-in-the-Middle (SAFIM) dataset. This benchmark is specifically designed to assess models' capabilities in syntax-sensitive code generation. Performance metrics, such as cosine similarity with ground-truth completions and latency, were employed to measure both accuracy and efficiency. The findings reveal substantial differences in the models' code completion abilities, offering valuable insights into their respective strengths and weaknesses. This work provides a comparative analysis that underscores the trade-offs between accuracy and speed, establishing a benchmark for future advancements in LLM-based code completion.
Authors: Hongxi Pu, Futian Jiang, Zihao Chen, Xingyue Song
Abstract: Music composition has long been recognized as a significant art form. However, existing digital audio workstations and music production software often present high entry barriers for users lacking formal musical training. To address this, we introduce ComposeOn, a music theory-based tool designed for users with limited musical knowledge. ComposeOn enables users to easily extend their melodic ideas into complete compositions and offers simple editing features. By integrating music theory, it explains music creation at beginner, intermediate, and advanced levels. Our user study (N=10) compared ComposeOn with the baseline method, Suno AI, demonstrating that ComposeOn provides a more accessible and enjoyable composing and learning experience for individuals with limited musical skills. ComposeOn bridges the gap between theory and practice, offering an innovative solution as both a composition aid and music education platform. The study also explores the differences between theory-based music creation and generative music, highlighting the former's advantages in personal expression and learning.
Authors: Jingheng Ye, Shang Qin, Yinghui Li, Hai-Tao Zheng, Shen Wang, Qingsong Wen
Abstract: Grammatical Error Correction (GEC) faces a critical challenge concerning explainability, notably when GEC systems are designed for language learners. Existing research predominantly focuses on explaining grammatical errors extracted in advance, thus neglecting the relationship between explanations and corrections. To address this gap, we introduce EXGEC, a unified explainable GEC framework that integrates explanation and correction tasks in a generative manner, advocating that these tasks mutually reinforce each other. Experiments have been conducted on EXPECT, a recent human-labeled dataset for explainable GEC, comprising around 20k samples. Moreover, we detect significant noise within EXPECT, potentially compromising model training and evaluation. Therefore, we introduce an alternative dataset named EXPECT-denoised, ensuring a more objective framework for training and evaluation. Results on various NLP models (BART, T5, and Llama3) show that EXGEC models surpass single-task baselines in both tasks, demonstrating the effectiveness of our approach.
Authors: Shunchang Liu, Zhuan Shi, Lingjuan Lyu, Yaochu Jin, Boi Faltings
Abstract: Assessing whether AI-generated images are substantially similar to copyrighted works is a crucial step in resolving copyright disputes. In this paper, we propose CopyJudge, an automated copyright infringement identification framework that leverages large vision-language models (LVLMs) to simulate practical court processes for determining substantial similarity between copyrighted images and those generated by text-to-image diffusion models. Specifically, we employ an abstraction-filtration-comparison test framework with multi-LVLM debate to assess the likelihood of infringement and provide detailed judgment rationales. Based on the judgments, we further introduce a general LVLM-based mitigation strategy that automatically optimizes infringing prompts by avoiding sensitive expressions while preserving the non-infringing content. Besides, our approach can be enhanced by exploring non-infringing noise vectors within the diffusion latent space via reinforcement learning, even without modifying the original prompts. Experimental results show that our identification method achieves comparable state-of-the-art performance, while offering superior generalization and interpretability across various forms of infringement, and that our mitigation method could more effectively mitigate memorization and IP infringement without losing non-infringing expressions.
Authors: Le Zhang, Quanling Zhao, Run Wang, Shirley Bian, Onat Gungor, Flavio Ponzina, Tajana Rosing
Abstract: Learning-based environmental sound recognition has emerged as a crucial method for ultra-low-power environmental monitoring in biological research and city-scale sensing systems. These systems usually operate under limited resources and are often powered by harvested energy in remote areas. Recent efforts in on-device sound recognition suffer from low accuracy due to resource constraints, whereas cloud offloading strategies are hindered by high communication costs. In this work, we introduce ORCA, a novel resource-efficient cloud-assisted environmental sound recognition system on batteryless devices operating over the Low-Power Wide-Area Networks (LPWANs), targeting wide-area audio sensing applications. We propose a cloud assistance strategy that remedies the low accuracy of on-device inference while minimizing the communication costs for cloud offloading. By leveraging a self-attention-based cloud sub-spectral feature selection method to facilitate efficient on-device inference, ORCA resolves three key challenges for resource-constrained cloud offloading over LPWANs: 1) high communication costs and low data rates, 2) dynamic wireless channel conditions, and 3) unreliable offloading. We implement ORCA on an energy-harvesting batteryless microcontroller and evaluate it in a real world urban sound testbed. Our results show that ORCA outperforms state-of-the-art methods by up to $80 \times$ in energy savings and $220 \times$ in latency reduction while maintaining comparable accuracy.
Authors: Sukrit Kumar, Drishti Goel, Thomas Zimmermann, Brian Houck, B. Ashok, Chetan Bansal
Abstract: Software developers balance a variety of different tasks in a workweek, yet the allocation of time often differs from what they consider ideal. Identifying and addressing these deviations is crucial for organizations aiming to enhance the productivity and well-being of the developers. In this paper, we present the findings from a survey of 484 software developers at Microsoft, which aims to identify the key differences between how developers would like to allocate their time during an ideal workweek versus their actual workweek. Our analysis reveals significant deviations between a developer's ideal workweek and their actual workweek, with a clear correlation: as the gap between these two workweeks widens, we observe a decline in both productivity and satisfaction. By examining these deviations in specific activities, we assess their direct impact on the developers' satisfaction and productivity. Additionally, given the growing adoption of AI tools in software engineering, both in the industry and academia, we identify specific tasks and areas that could be strong candidates for automation. In this paper, we make three key contributions: 1) We quantify the impact of workweek deviations on developer productivity and satisfaction 2) We identify individual tasks that disproportionately affect satisfaction and productivity 3) We provide actual data-driven insights to guide future AI automation efforts in software engineering, aligning them with the developers' requirements and ideal workflows for maximizing their productivity and satisfaction.
Authors: Yaohua Tang, Zhicheng Hu, Kun Cheng, Fan Mo, Qiheng Lv, Hua Wang, Zhi Chen
Abstract: The increasing context window size in large language models (LLMs) has improved their ability to handle complex, long-text tasks. However, as the conversation rounds continue, it is required to store a large amount of KV cache in GPU memory, which significantly affects the efficiency and even availability of the model serving systems. This paper analyzes dialogue data from real users and discovers that the LLM inference manifests a watershed layer, after which the distribution of round-level attention shows notable similarity. We propose Round Attention, a novel round-level attention mechanism that only recalls and computes the KV cache of the most relevant rounds. The experiments show that our method saves 55\% memory usage without compromising model performance.
Authors: Minbo Ma, Kai Tang, Huan Li, Fei Teng, Dalin Zhang, Tianrui Li
Abstract: Multivariate Time Series Forecasting (MTSF) has long been a key research focus. Traditionally, these studies assume a fixed number of variables, but in real-world applications, Cyber-Physical Systems often expand as new sensors are deployed, increasing variables in MTSF. In light of this, we introduce a novel task, Expanding-variate Time Series Forecasting (EVTSF). This task presents unique challenges, specifically (1) handling inconsistent data shapes caused by adding new variables, and (2) addressing imbalanced spatio-temporal learning, where expanding variables have limited observed data due to the necessity for timely operation. To address these challenges, we propose STEV, a flexible spatio-temporal forecasting framework. STEV includes a new Flat Scheme to tackle the inconsistent data shape issue, which extends the graph-based spatio-temporal modeling architecture into 1D space by flattening the 2D samples along the variable dimension, making the model variable-scale-agnostic while still preserving dynamic spatial correlations through a holistic graph. We introduce a novel Spatio-temporal Focal Learning strategy that incorporates a negative filter to resolve potential conflicts between contrastive learning and graph representation, and a focal contrastive loss as its core to guide the framework to focus on optimizing the expanding variables. We benchmark EVTSF performance using three real-world datasets and compare it against three potential solutions employing SOTA MTSF models tailored for EVSTF. Experimental results show that STEV significantly outperforms its competitors, particularly on expanding variables. Notably, STEV, with only 5% of observations from the expanding period, is on par with SOTA MTSF models trained with complete observations. Further exploration of various expanding strategies underscores the generalizability of STEV in real-world applications.
Authors: Hong Yankun, Li Xing, Zhen Hui-Ling, Yu Xianzhi, Liu Wulong, Yuan Mingxuan
Abstract: For the efficient inference of Large Language Models (LLMs), the effective compression of key-value (KV) cache is essential. Three main types of KV cache compression techniques, namely sparsity, channel compression, and quantization, have been identified. This study presents SVDq, a Singular Value Decomposition (SVD) - based mixed precision quantization method for K cache. Initially, K cache is transformed into latent channels using SVD basis representations. Since the values in latent channels decay rapidly and become negligible after only a few latent channels, our method then incorporates importance-aware quantization and compression for latent channels. This enables the effective allocation of higher precision to more significant channels. Theoretically, we prove that SVDq results in quantization errors (x0.1 or even lower) that are much lower than those of per-channel key quantization in the original space. Our findings based on RULER and LongBench benchmarks demonstrate that SVDq can achieve an equivalent key cache precision as low as 1.25-bit. When combined with key sparsity, it can reach a key compression ratio of up to 410x for attention computation, all while maintaining comparable model performance. Notably, our method is nearly lossless for LongBench datasets. This indicates that SVDq enables high-precision low-bit quantization, providing a more efficient solution for KV cache compression in LLMs.
Authors: Zhenghao Xi, Yuchao Shao, Yang Zheng, Xiang Liu, Yaqi Liu, Yitong Cai
Abstract: Traffic signs recognition (TSR) plays an essential role in assistant driving and intelligent transportation system. However, the noise of complex environment may lead to motion-blur or occlusion problems, which raise the tough challenge to real-time recognition with high accuracy and robust. In this article, we propose IECES-network which with improved encoders and Siamese net. The three-stage approach of our method includes Efficient-CNN based encoders, Siamese backbone and the fully-connected layers. We firstly use convolutional encoders to extract and encode the traffic sign features of augmented training samples and standard images. Then, we design the Siamese neural network with Efficient-CNN based encoder and contrastive loss function, which can be trained to improve the robustness of TSR problem when facing the samples of motion-blur and occlusion by computing the distance between inputs and templates. Additionally, the template branch of the proposed network can be stopped when executing the recognition tasks after training to raise the process speed of our real-time model, and alleviate the computational resource and parameter scale. Finally, we recombined the feature code and a fully-connected layer with SoftMax function to classify the codes of samples and recognize the category of traffic signs. The results of experiments on the Tsinghua-Tencent 100K dataset and the German Traffic Sign Recognition Benchmark dataset demonstrate the performance of the proposed IECESnetwork. Compared with other state-of-the-art methods, in the case of motion-blur and occluded environment, the proposed method achieves competitive performance precision-recall and accuracy metric average is 88.1%, 86.43% and 86.1% with a 2.9M lightweight scale, respectively. Moreover, processing time of our model is 0.1s per frame, of which the speed is increased by 1.5 times compared with existing methods.
Authors: Bin Feng, Shulan Ruan, Mingzheng Yang, Dongxuan Han, Huijie Liu, Kai Zhang, Qi Liu
Abstract: As more and more internet users post images online to express their daily emotions, image sentiment analysis has attracted increasing attention. Recently, researchers generally tend to design different neural networks to extract visual features from images for sentiment analysis. Despite the significant progress, metadata, the data (e.g., text descriptions and keyword tags) for describing the image, has not been sufficiently explored in this task. In this paper, we propose a novel Metadata Enhanced Transformer for sentiment analysis (SentiFormer) to fuse multiple metadata and the corresponding image into a unified framework. Specifically, we first obtain multiple metadata of the image and unify the representations of diverse data. To adaptively learn the appropriate weights for each metadata, we then design an adaptive relevance learning module to highlight more effective information while suppressing weaker ones. Moreover, we further develop a cross-modal fusion module to fuse the adaptively learned representations and make the final prediction. Extensive experiments on three publicly available datasets demonstrate the superiority and rationality of our proposed method.
Authors: Jinyu Zhang, Chao Li, Zhongying Zhao
Abstract: Graph-based Sequential Recommender systems (GSRs) have gained significant research attention due to their ability to simultaneously handle user-item interactions and sequential relationships between items. Current GSRs often utilize composite or in-depth structures for graph encoding (e.g., the Graph Transformer). Nevertheless, they have high computational complexity, hindering the deployment on resource-constrained edge devices. Moreover, the relative position encoding in Graph Transformer has difficulty in considering the complicated positional dependencies within sequence. To this end, we propose an External Attentive Graph convolutional network with Positional prompts for Sequential recommendation, namely EA-GPS. Specifically, we first introduce an external attentive graph convolutional network that linearly measures the global associations among nodes via two external memory units. Then, we present a positional prompt-based decoder that explicitly treats the absolute item positions as external prompts. By introducing length-adaptive sequential masking and a soft attention network, such a decoder facilitates the model to capture the long-term positional dependencies and contextual relationships within sequences. Extensive experimental results on five real-world datasets demonstrate that the proposed EA-GPS outperforms the state-of-the-art methods. Remarkably, it achieves the superior performance while maintaining a smaller parameter size and lower training overhead. The implementation of this work is publicly available at https://github.com/ZZY-GraphMiningLab/EA-GPS.
Authors: Pedram Zaree, Md Abdullah Al Mamun, Quazi Mishkatul Alam, Yue Dong, Ihsen Alouani, Nael Abu-Ghazaleh
Abstract: Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks to guide effective defenses and accurate assessment of model safety. In this paper, we present a new approach for generating highly effective Jailbreak attacks that manipulate the attention of the model to selectively strengthen or weaken attention among different parts of the prompt. By harnessing attention loss, we develop more effective jailbreak attacks, that are also transferrable. The attacks amplify the success rate of existing Jailbreak algorithms including GCG, AutoDAN, and ReNeLLM, while lowering their generation cost (for example, the amplified GCG attack achieves 91.2% ASR, vs. 67.9% for the original attack on Llama2-7B/AdvBench, using less than a third of the generation time).
Authors: Shoubin Chen, Zehao Wu, Kai Zhang, Chunyu Li, Baiyang Zhang, Fei Ma, Fei Richard Yu, Qingquan Li
Abstract: Embodied multimodal large models (EMLMs) have gained significant attention in recent years due to their potential to bridge the gap between perception, cognition, and action in complex, real-world environments. This comprehensive review explores the development of such models, including Large Language Models (LLMs), Large Vision Models (LVMs), and other models, while also examining other emerging architectures. We discuss the evolution of EMLMs, with a focus on embodied perception, navigation, interaction, and simulation. Furthermore, the review provides a detailed analysis of the datasets used for training and evaluating these models, highlighting the importance of diverse, high-quality data for effective learning. The paper also identifies key challenges faced by EMLMs, including issues of scalability, generalization, and real-time decision-making. Finally, we outline future directions, emphasizing the integration of multimodal sensing, reasoning, and action to advance the development of increasingly autonomous systems. By providing an in-depth analysis of state-of-the-art methods and identifying critical gaps, this paper aims to inspire future advancements in EMLMs and their applications across diverse domains.
Authors: Yi Zhang, Fan Wei, Jingyi Li, Yan Wang, Yanyan Yu, Jianli Chen, Zipo Cai, Xinyu Liu, Wei Wang, Peng Wang, Zhong Wang
Abstract: The use of children's drawings to examining their conceptual understanding has been proven to be an effective method, but there are two major problems with previous research: 1. The content of the drawings heavily relies on the task, and the ecological validity of the conclusions is low; 2. The interpretation of drawings relies too much on the subjective feelings of the researchers. To address this issue, this study uses the Large Language Model (LLM) to identify 1420 children's scientific drawings (covering 9 scientific themes/concepts), and uses the word2vec algorithm to calculate their semantic similarity. The study explores whether there are consistent drawing representations for children on the same theme, and attempts to establish a norm for children's scientific drawings, providing a baseline reference for follow-up children's drawing research. The results show that the representation of most drawings has consistency, manifested as most semantic similarity greater than 0.8. At the same time, it was found that the consistency of the representation is independent of the accuracy (of LLM's recognition), indicating the existence of consistency bias. In the subsequent exploration of influencing factors, we used Kendall rank correlation coefficient to investigate the effects of Sample Size, Abstract Degree, and Focus Points on drawings, and used word frequency statistics to explore whether children represented abstract themes/concepts by reproducing what was taught in class.
Authors: Mahmoud Elkhodr, Ergun Gide
Abstract: The rapid advancement of Generative Artificial Intelligence (GenAI) has introduced new opportunities for transforming higher education, particularly in fields that require analytical reasoning and regulatory compliance, such as cybersecurity management. This study presents a structured framework for integrating GenAI tools into cybersecurity education, demonstrating their role in fostering critical thinking, real-world problem-solving, and regulatory awareness. The implementation strategy followed a two-stage approach, embedding GenAI within tutorial exercises and assessment tasks. Tutorials enabled students to generate, critique, and refine AI-assisted cybersecurity policies, while assessments required them to apply AI-generated outputs to real-world scenarios, ensuring alignment with industry standards and regulatory requirements. Findings indicate that AI-assisted learning significantly enhanced students' ability to evaluate security policies, refine risk assessments, and bridge theoretical knowledge with practical application. Student reflections and instructor observations revealed improvements in analytical engagement, yet challenges emerged regarding AI over-reliance, variability in AI literacy, and the contextual limitations of AI-generated content. Through structured intervention and research-driven refinement, students were able to recognize AI strengths as a generative tool while acknowledging its need for human oversight. This study further highlights the broader implications of AI adoption in cybersecurity education, emphasizing the necessity of balancing automation with expert judgment to cultivate industry-ready professionals. Future research should explore the long-term impact of AI-driven learning on cybersecurity competency, as well as the potential for adaptive AI-assisted assessments to further personalize and enhance educational outcomes.
Authors: Xuyang Wu, Jinming Nian, Zhiqiang Tao, Yi Fang
Abstract: In the recent development of AI reasoning, large language models (LLMs) are trained to automatically generate chain-of-thought reasoning steps, which have demonstrated compelling performance on math and coding tasks. However, when bias is mixed within the reasoning process to form strong logical arguments, it could cause even more harmful results and further induce hallucinations. In this paper, we have evaluated the 8B and 32B variants of DeepSeek-R1 against their instruction tuned counterparts on the BBQ dataset, and investigated the bias that is elicited out and being amplified through reasoning steps. To the best of our knowledge, this empirical study is the first to assess bias issues in LLM reasoning.
Authors: Kang Bongsu, Kim Jundong, Yun Tae-Rim, Bae Hyojin, Kim Chang-Eop
Abstract: This study quantitively examines which features of AI-generated text lead humans to perceive subjective consciousness in large language model (LLM)-based AI systems. Drawing on 99 passages from conversations with Claude 3 Opus and focusing on eight features -- metacognitive self-reflection, logical reasoning, empathy, emotionality, knowledge, fluency, unexpectedness, and subjective expressiveness -- we conducted a survey with 123 participants. Using regression and clustering analyses, we investigated how these features influence participants' perceptions of AI consciousness. The results reveal that metacognitive self-reflection and the AI's expression of its own emotions significantly increased perceived consciousness, while a heavy emphasis on knowledge reduced it. Participants clustered into seven subgroups, each showing distinct feature-weighting patterns. Additionally, higher prior knowledge of LLMs and more frequent usage of LLM-based chatbots were associated with greater overall likelihood assessments of AI consciousness. This study underscores the multidimensional and individualized nature of perceived AI consciousness and provides a foundation for better understanding the psychosocial implications of human-AI interaction.
Authors: Hasan Berkay Abdioglu, Rana Gursoy, Yagmur Isik, Ibrahim Cem Balci, Taha Unal, Kerem Bayer, Mustafa Ismail Inal, Nehir Serin, Muhammed Furkan Kosar, Gokhan Bora Esmer, Huseyin Uvet
Abstract: This study investigates the application of Super-Resolution techniques in holographic microscopy to enhance quantitative phase imaging. An off-axis Mach-Zehnder interferometric setup was employed to capture interferograms. The study evaluates two Super-Resolution models, RCAN and Real-ESRGAN, for their effectiveness in reconstructing high-resolution interferograms from a microparticle-based dataset. The models were assessed using two primary approaches: image-based analysis for structural detail enhancement and morphological evaluation for maintaining sample integrity and phase map accuracy. The results demonstrate that RCAN achieves superior numerical precision, making it ideal for applications requiring highly accurate phase map reconstruction, while Real-ESRGAN enhances visual quality and structural coherence, making it suitable for visualization-focused applications. This study highlights the potential of Super-Resolution models in overcoming diffraction-imposed resolution limitations in holographic microscopy, opening the way for improved imaging techniques in biomedical diagnostics, materials science, and other high-precision fields.
Authors: Narges Semiromizadeh, Omid Nejati Manzari, Shahriar B. Shokouhi, Sattar Mirzakuchaki
Abstract: Vehicle make and model recognition (VMMR) is a crucial component of the Intelligent Transport System, garnering significant attention in recent years. VMMR has been widely utilized for detecting suspicious vehicles, monitoring urban traffic, and autonomous driving systems. The complexity of VMMR arises from the subtle visual distinctions among vehicle models and the wide variety of classes produced by manufacturers. Convolutional Neural Networks (CNNs), a prominent type of deep learning model, have been extensively employed in various computer vision tasks, including VMMR, yielding remarkable results. As VMMR is a fine-grained classification problem, it primarily faces inter-class similarity and intra-class variation challenges. In this study, we implement an attention module to address these challenges and enhance the model's focus on critical areas containing distinguishing features. This module, which does not increase the parameters of the original model, generates three-dimensional (3-D) attention weights to refine the feature map. Our proposed model integrates the attention module into two different locations within the middle section of a convolutional model, where the feature maps from these sections offer sufficient information about the input frames without being overly detailed or overly coarse. The performance of our proposed model, along with state-of-the-art (SOTA) convolutional and transformer-based models, was evaluated using the Stanford Cars dataset. Our proposed model achieved the highest accuracy, 90.69\%, among the compared models.
Authors: Rasmus Aavang, Giovanni Rizzi, Rasmus B{\o}ggild, Alexandre Iolov, Mike Zhang, Johannes Bjerva
Abstract: The U.S. Securities and Exchange Commission (SEC) requires that public companies file financial reports tagging numbers with the machine readable inline eXtensible Business Reporting Language (iXBRL) standard. However, the highly complex and highly granular taxonomy defined by iXBRL limits label transferability across domains. In this paper, we introduce the Hierarchical Financial Key Performance Indicator (HiFi-KPI) dataset, designed to facilitate numerical KPI extraction at specified levels of granularity from unstructured financial text. Our approach organizes a 218,126-label hierarchy using a taxonomy based grouping method, investigating which taxonomy layer provides the most meaningful structure. HiFi-KPI comprises ~1.8M paragraphs and ~5M entities, each linked to a label in the iXBRL-specific calculation and presentation taxonomies. We provide baselines using encoder-based approaches and structured extraction using Large Language Models (LLMs). To simplify LLM inference and evaluation, we additionally release HiFi-KPI Lite, a manually curated subset with four expert-mapped labels. We publicly release all artifacts
Authors: Yi-Ling Chung, Aurora Cobo, Pablo Serna
Abstract: Robust automatic fact-checking systems have the potential to combat online misinformation at scale. However, most existing research primarily focuses on English. In this paper, we introduce MultiSynFact, the first large-scale multilingual fact-checking dataset containing 2.2M claim-source pairs designed to support Spanish, German, English, and other low-resource languages. Our dataset generation pipeline leverages Large Language Models (LLMs), integrating external knowledge from Wikipedia and incorporating rigorous claim validation steps to ensure data quality. We evaluate the effectiveness of MultiSynFact across multiple models and experimental settings. Additionally, we open-source a user-friendly framework to facilitate further research in multilingual fact-checking and dataset generation.
Authors: Sanghee Park, Geewook Kim
Abstract: This paper presents the Korean National Educational Test Benchmark (KoNET), a new benchmark designed to evaluate Multimodal Generative AI Systems using Korean national educational tests. KoNET comprises four exams: the Korean Elementary General Educational Development Test (KoEGED), Middle (KoMGED), High (KoHGED), and College Scholastic Ability Test (KoCSAT). These exams are renowned for their rigorous standards and diverse questions, facilitating a comprehensive analysis of AI performance across different educational levels. By focusing on Korean, KoNET provides insights into model performance in less-explored languages. We assess a range of models - open-source, open-access, and closed APIs - by examining difficulties, subject diversity, and human error rates. The code and dataset builder will be made fully open-sourced at https://github.com/naver-ai/KoNET.
Authors: Georgii Kolokolnikov, Marie-Lena Schmalhofer, Lennart Well, Said Farschtschi, Victor-Felix Mautner, Inka Ristow, Rene Werner
Abstract: Neurofibromatosis Type 1 is a genetic disorder characterized by the development of neurofibromas (NFs), which exhibit significant variability in size, morphology, and anatomical location. Accurate and automated segmentation of these tumors in whole-body magnetic resonance imaging (WB-MRI) is crucial to assess tumor burden and monitor disease progression. In this study, we present and analyze a fully automated pipeline for NF segmentation in fat-suppressed T2-weighted WB-MRI, consisting of three stages: anatomy segmentation, NF segmentation, and tumor candidate classification. In the first stage, we use the MRSegmentator model to generate an anatomy segmentation mask, extended with a high-risk zone for NFs. This mask is concatenated with the input image as anatomical context information for NF segmentation. The second stage employs an ensemble of 3D anisotropic anatomy-informed U-Nets to produce an NF segmentation confidence mask. In the final stage, tumor candidates are extracted from the confidence mask and classified based on radiomic features, distinguishing tumors from non-tumor regions and reducing false positives. We evaluate the proposed pipeline on three test sets representing different conditions: in-domain data (test set 1), varying imaging protocols and field strength (test set 2), and low tumor burden cases (test set 3). Experimental results show a 68% improvement in per-scan Dice Similarity Coefficient (DSC), a 21% increase in per-tumor DSC, and a two-fold improvement in F1 score for tumor detection in high tumor burden cases by integrating anatomy information. The method is integrated into the 3D Slicer platform for practical clinical use, with the code publicly accessible.
Authors: Leyla Naz Candogan, Yongtao Wu, Elias Abad Rocamora, Grigorios G. Chrysos, Volkan Cevher
Abstract: Defending aligned Large Language Models (LLMs) against jailbreaking attacks is a challenging problem, with existing approaches requiring multiple requests or even queries to auxiliary LLMs, making them computationally heavy. Instead, we focus on detecting jailbreaking input in a single forward pass. Our method, called Single Pass Detection SPD, leverages the information carried by the logits to predict whether the output sentence will be harmful. This allows us to defend in just one forward pass. SPD can not only detect attacks effectively on open-source models, but also minimizes the misclassification of harmless inputs. Furthermore, we show that SPD remains effective even without complete logit access in GPT-3.5 and GPT-4. We believe that our proposed method offers a promising approach to efficiently safeguard LLMs against adversarial attacks.
Authors: Raghav Singhal, Kaustubh Ponkshe, Rohit Vartak, Lav R. Varshney, Praneeth Vepakomma
Abstract: Low-Rank Adaptation (LoRA) has become ubiquitous for efficiently fine-tuning foundation models. However, federated fine-tuning using LoRA is challenging due to suboptimal updates arising from traditional federated averaging of individual adapters. Existing solutions either incur prohibitively high communication cost that scales linearly with the number of clients or suffer from performance degradation due to limited expressivity. We introduce Federated Silver Bullet (Fed-SB), a novel approach for federated fine-tuning of LLMs using LoRA-SB, a recently proposed low-rank adaptation method. LoRA-SB optimally aligns the optimization trajectory with the ideal low-rank full fine-tuning projection by learning a small square matrix (R) between adapters B and A, keeping other components fixed. Direct averaging of R guarantees exact updates, substantially reducing communication cost, which remains independent of the number of clients, and enables scalability. Fed-SB achieves state-of-the-art performance across commonsense reasoning, arithmetic reasoning, and language inference tasks while reducing communication costs by up to 230x. In private settings, Fed-SB further improves performance by (1) reducing trainable parameters, thereby lowering the noise required for differential privacy and (2) avoiding noise amplification introduced by other methods. Overall, Fed-SB establishes a new Pareto frontier in the tradeoff between communication and performance, offering an efficient and scalable solution for both private and non-private federated fine-tuning. Our code is publicly available at https://github.com/CERT-Lab/fed-sb.
Authors: Weilan Wang, Yu Mao, Dongdong Tang, Hongchao Du, Nan Guan, Chun Jason Xue
Abstract: Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a framework to compress LLM after quantization further, achieving about 2.2x compression ratio. A compression-aware quantization is first proposed to enhance model weight compressibility by re-scaling the model parameters before quantization, followed by a pruning method to improve further. Upon this, we notice that decompression can be a bottleneck during practical scenarios. We then give a detailed analysis of the trade-off between memory usage and latency brought by the proposed method. A speed-adaptive method is proposed to overcome it. The experimental results show inference with the compressed model can achieve a 40% reduction in memory size with negligible loss in accuracy and inference speed.
Authors: Paul Koch, Marian Schl\"uter, J\"org Kr\"uger
Abstract: We present MVIP, a novel dataset for multi-modal and multi-view application-oriented industrial part recognition. Here we are the first to combine a calibrated RGBD multi-view dataset with additional object context such as physical properties, natural language, and super-classes. The current portfolio of available datasets offers a wide range of representations to design and benchmark related methods. In contrast to existing classification challenges, industrial recognition applications offer controlled multi-modal environments but at the same time have different problems than traditional 2D/3D classification challenges. Frequently, industrial applications must deal with a small amount or increased number of training data, visually similar parts, and varying object sizes, while requiring a robust near 100% top 5 accuracy under cost and time constraints. Current methods tackle such challenges individually, but direct adoption of these methods within industrial applications is complex and requires further research. Our main goal with MVIP is to study and push transferability of various state-of-the-art methods within related downstream tasks towards an efficient deployment of industrial classifiers. Additionally, we intend to push with MVIP research regarding several modality fusion topics, (automated) synthetic data generation, and complex data sampling -- combined in a single application-oriented benchmark.
Authors: Jinda Liu, Yi Chang, Yuan Wu
Abstract: Fine-tuning large language models (LLMs) is prohibitively expensive in terms of computational and memory costs. Low-rank Adaptation (LoRA), as one of the most popular parameter-efficient fine-tuning (PEFT) methods, offers a cost-effective alternative by approximating the model changes $\Delta W \in \mathbb{R}^{m \times n}$ through the product of down-projection matrix $A \in \mathbb{R}^{m \times r}$ and head matrix $B \in \mathbb{R}^{r \times n}$, where $r \ll \min(m, n)$. In real-world scenarios, LLMs are fine-tuned on data from multiple domains to perform tasks across various fields, embodying multi-task learning (MTL). LoRA often underperforms in such complex scenarios. To enhance LoRA's capability in multi-task learning, we propose R-LoRA, which incorporates Multi-Head Randomization. Multi-Head Randomization diversifies the head matrices through Multi-Head Random Initialization and Multi-Head Dropout, enabling more efficient learning of task-specific features while maintaining shared knowledge representation. Extensive experiments demonstrate that R-LoRA is better at capturing task-specific knowledge, thereby improving performance in multi-task scenarios. The code is available at https://github.com/jinda-liu/R-LoRA.
Authors: Wenxuan Wang, Kai Wu, Yujian Betterest Li, Dan Wang, Xiaoyu Zhang, Jing Liu
Abstract: Foundation models for time series analysis (TSA) have attracted significant attention. However, challenges such as data scarcity and data imbalance continue to hinder their development. To address this, we consider modeling complex systems through symbolic expressions that serve as semantic descriptors of time series. Building on this concept, we introduce a series-symbol (S2) dual-modulity data generation mechanism, enabling the unrestricted creation of high-quality time series data paired with corresponding symbolic representations. Leveraging the S2 dataset, we develop SymTime, a pre-trained foundation model for TSA. SymTime demonstrates competitive performance across five major TSA tasks when fine-tuned with downstream task, rivaling foundation models pre-trained on real-world datasets. This approach underscores the potential of dual-modality data generation and pretraining mechanisms in overcoming data scarcity and enhancing task performance.
Authors: Yintao He, Haiyu Mao, Christina Giannoula, Mohammad Sadrosadati, Juan G\'omez-Luna, Huawei Li, Xiaowei Li, Ying Wang, Onur Mutlu
Abstract: Large language models (LLMs) are widely used for natural language understanding and text generation. An LLM model relies on a time-consuming step called LLM decoding to generate output tokens. Several prior works focus on improving the performance of LLM decoding using parallelism techniques, such as batching and speculative decoding. State-of-the-art LLM decoding has both compute-bound and memory-bound kernels. Some prior works statically identify and map these different kernels to a heterogeneous architecture consisting of both processing-in-memory (PIM) units and computation-centric accelerators. We observe that characteristics of LLM decoding kernels (e.g., whether or not a kernel is memory-bound) can change dynamically due to parameter changes to meet user and/or system demands, making (1) static kernel mapping to PIM units and computation-centric accelerators suboptimal, and (2) one-size-fits-all approach of designing PIM units inefficient due to a large degree of heterogeneity even in memory-bound kernels. In this paper, we aim to accelerate LLM decoding while considering the dynamically changing characteristics of the kernels involved. We propose PAPI (PArallel Decoding with PIM), a PIM-enabled heterogeneous architecture that exploits dynamic scheduling of compute-bound or memory-bound kernels to suitable hardware units. PAPI has two key mechanisms: (1) online kernel characterization to dynamically schedule kernels to the most suitable hardware units at runtime and (2) a PIM-enabled heterogeneous computing system that harmoniously orchestrates both computation-centric processing units and hybrid PIM units with different computing capabilities. Our experimental results on three broadly-used LLMs show that PAPI achieves 1.8$\times$ and 11.1$\times$ speedups over a state-of-the-art heterogeneous LLM accelerator and a state-of-the-art PIM-only LLM accelerator, respectively.
Authors: Xinghan Pan
Abstract: This paper presents an enhanced RWKV-based language generation model designed to improve long-sequence text processing. We propose an adaptive token shift and gating mechanism to better capture long-range dependencies in text generation. Through a series of experiments, we compare the baseline RWKV model with the enhanced model, evaluating performance in terms of forward propagation time, text generation quality, and automatic evaluation metrics such as perplexity, BLEU, and ROUGE. Experimental results show that the enhanced model significantly improves generation quality, especially in BLEU and ROUGE scores, and demonstrates stronger context-capturing ability in long-text generation tasks.
Authors: Martina Miliani, Serenna Auriemma, Alessandro Bondielli, Emmanuele Chersoni, Lucia Passaro, Irene Sucameli, Alessandro Lenci
Abstract: Large Language Models (LLMs) are increasingly used in tasks requiring interpretive and inferential accuracy. In this paper, we introduce ExpliCa, a new dataset for evaluating LLMs in explicit causal reasoning. ExpliCa uniquely integrates both causal and temporal relations presented in different linguistic orders and explicitly expressed by linguistic connectives. The dataset is enriched with crowdsourced human acceptability ratings. We tested LLMs on ExpliCa through prompting and perplexity-based metrics. We assessed seven commercial and open-source LLMs, revealing that even top models struggle to reach 0.80 accuracy. Interestingly, models tend to confound temporal relations with causal ones, and their performance is also strongly influenced by the linguistic order of the events. Finally, perplexity-based scores and prompting performance are differently affected by model size.
Authors: Jiangyong Yu, Changyong Shu, Dawei Yang, Zichen Yu, Xing Hu, Yan Chen
Abstract: PETR-based methods have dominated benchmarks in 3D perception and are increasingly becoming a key component in modern autonomous driving systems. However, their quantization performance significantly degrades when INT8 inference is required, with a degradation of 58.2% in mAP and 36.9% in NDS on the NuScenes dataset. To address this issue, we propose a quantization-aware position embedding transformation for multi-view 3D object detection, termed Q-PETR. Q-PETR offers a quantizationfriendly and deployment-friendly architecture while preserving the original performance of PETR. It substantially narrows the accuracy gap between INT8 and FP32 inference for PETR-series methods. Without bells and whistles, our approach reduces the mAP and NDS drop to within 1% under standard 8-bit per-tensor post-training quantization. Furthermore, our method exceeds the performance of the original PETR in terms of floating-point precision. Extensive experiments across a variety of PETR-series models demonstrate its broad generalization.
Authors: Haidong Wang, Pengfei Xiao, Ao Liu, Jianhua Zhang, Qia Shan
Abstract: Drawing inspiration from neurosciences, artificial neural networks (ANNs) have evolved from shallow architectures to highly complex, deep structures, yielding exceptional performance in auditory recognition tasks. However, traditional ANNs often struggle to align with brain regions due to their excessive depth and lack of biologically realistic features, like recurrent connection. To address this, a brain-like auditory network (BAN) is introduced, which incorporates four neuroanatomically mapped areas and recurrent connection, guided by a novel metric called the brain-like auditory score (BAS). BAS serves as a benchmark for evaluating the similarity between BAN and human auditory recognition pathway. We further propose that specific areas in the cerebral cortex, mainly the middle and medial superior temporal (T2/T3) areas, correspond to the designed network structure, drawing parallels with the brain's auditory perception pathway. Our findings suggest that the neuroanatomical similarity in the cortex and auditory classification abilities of the ANN are well-aligned. In addition to delivering excellent performance on a music genre classification task, the BAN demonstrates a high BAS score. In conclusion, this study presents BAN as a recurrent, brain-inspired ANN, representing the first model that mirrors the cortical pathway of auditory recognition.
Authors: Shashank Kirtania
Abstract: Large Language Models (LLMs) have shown promise in proving formal theorems using proof assistants like Lean. However, current state of the art language models struggles to predict next step in proofs leading practitioners to use different sampling techniques to improve LLMs capabilities. We observe that the LLM is capable of predicting the correct tactic; however, it faces challenges in ranking it appropriately within the set of candidate tactics, affecting the overall selection process. To overcome this hurdle, we use activation steering to guide LLMs responses to improve the generations at the time of inference. Our results suggest that activation steering offers a promising lightweight alternative to specialized fine-tuning for enhancing theorem proving capabilities in LLMs, particularly valuable in resource-constrained environments.
Authors: Yue Sun, Yeqiang Qian, Chunxiang Wang, Ming Yang
Abstract: Safety and reliability are crucial for the public acceptance of autonomous driving. To ensure accurate and reliable environmental perception, intelligent vehicles must exhibit accuracy and robustness in various environments. Millimeter-wave radar, known for its high penetration capability, can operate effectively in adverse weather conditions such as rain, snow, and fog. Traditional 3D millimeter-wave radars can only provide range, Doppler, and azimuth information for objects. Although the recent emergence of 4D millimeter-wave radars has added elevation resolution, the radar point clouds remain sparse due to Constant False Alarm Rate (CFAR) operations. In contrast, cameras offer rich semantic details but are sensitive to lighting and weather conditions. Hence, this paper leverages these two highly complementary and cost-effective sensors, 4D millimeter-wave radar and camera. By integrating 4D radar spectra with depth-aware camera images and employing attention mechanisms, we fuse texture-rich images with depth-rich radar data in the Bird's Eye View (BEV) perspective, enhancing 3D object detection. Additionally, we propose using GAN-based networks to generate depth images from radar spectra in the absence of depth sensors, further improving detection accuracy.
Authors: Wenyu Zhang, Jie Luo, Xinming Zhang, Yuan Fang
Abstract: With the explosive growth of multimodal content online, pre-trained visual-language models have shown great potential for multimodal recommendation. However, while these models achieve decent performance when applied in a frozen manner, surprisingly, due to significant domain gaps (e.g., feature distribution discrepancy and task objective misalignment) between pre-training and personalized recommendation, adopting a joint training approach instead leads to performance worse than baseline. Existing approaches either rely on simple feature extraction or require computationally expensive full model fine-tuning, struggling to balance effectiveness and efficiency. To tackle these challenges, we propose \textbf{P}arameter-efficient \textbf{T}uning for \textbf{M}ultimodal \textbf{Rec}ommendation (\textbf{PTMRec}), a novel framework that bridges the domain gap between pre-trained models and recommendation systems through a knowledge-guided dual-stage parameter-efficient training strategy. This framework not only eliminates the need for costly additional pre-training but also flexibly accommodates various parameter-efficient tuning methods.
Authors: Pengcheng Huang, Zhenghao Liu, Yukun Yan, Xiaoyuan Yi, Hao Chen, Zhiyuan Liu, Maosong Sun, Tong Xiao, Ge Yu, Chenyan Xiong
Abstract: Knowledge-Augmented Generation (KAG) has shown great promise in updating the internal memory of Large Language Models (LLMs) by integrating external knowledge. However, KAG inevitably faces knowledge conflicts when the internal memory contradicts external information. Current approaches to mitigating these conflicts mainly focus on improving external knowledge utilization. However, these methods have shown only limited effectiveness in mitigating the knowledge conflict problem, as internal knowledge continues to influence the generation process of LLMs. In this paper, we propose a ParametrIc Pruning-based Knowledge-Augmented Generation (PIP-KAG) approach, which prunes internal knowledge of LLMs and incorporates a plug-and-play adaptation module to help LLMs better leverage external sources. Additionally, we construct the CoConflictQA benchmark based on the hallucination of LLMs to better evaluate contextual faithfulness during answering questions. Experimental results on CoConflictQA demonstrate that PIP-KAG significantly reduces knowledge conflicts and improves context fidelity. Notably, PIP-KAG reduces LLM's parameters by 13%, enhancing parameter efficiency in LLMs within the KAG framework. All codes are available at https://github.com/OpenBMB/PIP-KAG.
Authors: Tim R\"adsch, Leon Mayer, Simon Pavicic, A. Emre Kavur, Marcel Knopp, Bar{\i}\c{s} \"Ozt\"urk, Klaus Maier-Hein, Paul F. Jaeger, Fabian Isensee, Annika Reinke, Lena Maier-Hein
Abstract: Reliable evaluation of AI models is critical for scientific progress and practical application. While existing VLM benchmarks provide general insights into model capabilities, their heterogeneous designs and limited focus on a few imaging domains pose significant challenges for both cross-domain performance comparison and targeted domain-specific evaluation. To address this, we propose three key contributions: (1) a framework for the resource-efficient creation of domain-specific VLM benchmarks enabled by task augmentation for creating multiple diverse tasks from a single existing task, (2) the release of new VLM benchmarks for seven domains, created according to the same homogeneous protocol and including 162,946 thoroughly human-validated answers, and (3) an extensive benchmarking of 22 state-of-the-art VLMs on a total of 37,171 tasks, revealing performance variances across domains and tasks, thereby supporting the need for tailored VLM benchmarks. Adoption of our methodology will pave the way for the resource-efficient domain-specific selection of models and guide future research efforts toward addressing core open questions.
Authors: Ina Dormuth, Sven Franke, Marlies Hafer, Tim Katzke, Alexander Marx, Emmanuel M\"uller, Daniel Neider, Markus Pauly, J\'er\^ome Rutinowski
Abstract: In this study, we examine the reliability of AI-based Voting Advice Applications (VAAs) and large language models (LLMs) in providing objective political information. Our analysis is based upon a comparison with party responses to 38 statements of the Wahl-O-Mat, a well-established German online tool that helps inform voters by comparing their views with political party positions. For the LLMs, we identify significant biases. They exhibit a strong alignment (over 75% on average) with left-wing parties and a substantially lower alignment with center-right (smaller 50%) and right-wing parties (around 30%). Furthermore, for the VAAs, intended to objectively inform voters, we found substantial deviations from the parties' stated positions in Wahl-O-Mat: While one VAA deviated in 25% of cases, another VAA showed deviations in more than 50% of cases. For the latter, we even observed that simple prompt injections led to severe hallucinations, including false claims such as non-existent connections between political parties and right-wing extremist ties.
Authors: Sudhendu Ahir, Parthe Pandit
Abstract: Recent applications of kernel methods in machine learning have seen a renewed interest in the Laplacian kernel, due to its stability to the bandwidth hyperparameter in comparison to the Gaussian kernel, as well as its expressivity being equivalent to that of the neural tangent kernel of deep fully connected networks. However, unlike the Gaussian kernel, the Laplacian kernel is not separable. This poses challenges for techniques to approximate it, especially via the random Fourier features (RFF) methodology and its variants. In this work, we provide random features for the Laplacian kernel and its two generalizations: Mat\'{e}rn kernel and the Exponential power kernel. We provide efficiently implementable schemes to sample weight matrices so that random features approximate these kernels. These weight matrices have a weakly coupled heavy-tailed randomness. Via numerical experiments on real datasets we demonstrate the efficacy of these random feature maps.
Authors: Reyhane Askari-Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano
Abstract: Inspired by the principle of deliberate practice in human learning, we propose Deliberate Practice for Synthetic Data Generation (DP), a novel framework that improves sample efficiency through dynamic synthetic data generation. Prior work has shown that scaling synthetic data is inherently challenging, as naively adding new data leads to diminishing returns. To address this, pruning has been identified as a key mechanism for improving scaling, enabling models to focus on the most informative synthetic samples. Rather than generating a large dataset and pruning it afterward, DP efficiently approximates the direct generation of informative samples. We theoretically show how training on challenging, informative examples improves scaling laws and empirically validate that DP achieves better scaling performance with significantly fewer training samples and iterations. On ImageNet-100, DP generates 3.4x fewer samples and requires six times fewer iterations, while on ImageNet-1k, it generates 8x fewer samples with a 30 percent reduction in iterations, all while achieving superior performance compared to prior work.
Authors: Jintian Zhang, Yuqi Zhu, Mengshu Sun, Yujie Luo, Shuofei Qiao, Lun Du, Da Zheng, Huajun Chen, Ningyu Zhang
Abstract: Large language models (LLMs) have shown remarkable performance in complex reasoning tasks, but their efficiency is hindered by the substantial memory and computational costs associated with generating lengthy tokens. In this paper, we propose LightThinker, a novel method that enables LLMs to dynamically compress intermediate thoughts during reasoning. Inspired by human cognitive processes, LightThinker compresses verbose thought steps into compact representations and discards the original reasoning chains, thereby significantly reducing the number of tokens stored in the context window. This is achieved by training the model on when and how to perform compression through data construction, mapping hidden states to condensed gist tokens, and creating specialized attention masks. Additionally, we introduce the Dependency (Dep) metric to quantify the degree of compression by measuring the reliance on historical tokens during generation. Extensive experiments on four datasets and two models show that LightThinker reduces peak memory usage and inference time, while maintaining competitive accuracy. Our work provides a new direction for improving the efficiency of LLMs in complex reasoning tasks without sacrificing performance. Code will be released at https://github.com/zjunlp/LightThinker.
Authors: Wenhao Zhu, Pinzhen Chen, Hanxu Hu, Shujian Huang, Fei Yuan, Jiajun Chen, Alexandra Birch
Abstract: Long-context modelling for large language models (LLMs) has been a key area of recent research because many real world use cases require reasoning over longer inputs such as documents. The focus of research into modelling long context has been on how to model position and there has been little investigation into other important aspects of language modelling such as instruction tuning. Long context training examples are challenging and expensive to create and use. In this paper, we investigate how to design instruction data for the post-training phase of a long context pre-trained model: how much and what type of context is needed for optimal and efficient post-training. Our controlled study reveals that models instruction-tuned on short contexts can effectively generalize to longer ones, while also identifying other critical factors such as instruction difficulty and context composition. Based on these findings, we propose context synthesis, a novel data synthesis framework that leverages off-the-shelf LLMs to generate extended background contexts for high-quality instruction-answer pairs. Experiment results on the document-level benchmark (LongBench) demonstrate that our proposed approach outperforms previous instruction synthesis approaches and comes close to the performance of human-annotated long-context instruction data. The project will be available at: https://github.com/NJUNLP/context-synthesis.
Authors: Xinhang Liu, Chi-Keung Tang, Yu-Wing Tai
Abstract: Constructing photorealistic virtual worlds has applications across various fields, but it often requires the extensive labor of highly trained professionals to operate conventional 3D modeling software. To democratize this process, we introduce WorldCraft, a system where large language model (LLM) agents leverage procedural generation to create indoor and outdoor scenes populated with objects, allowing users to control individual object attributes and the scene layout using intuitive natural language commands. In our framework, a coordinator agent manages the overall process and works with two specialized LLM agents to complete the scene creation: ForgeIt, which integrates an ever-growing manual through auto-verification to enable precise customization of individual objects, and ArrangeIt, which formulates hierarchical optimization problems to achieve a layout that balances ergonomic and aesthetic considerations. Additionally, our pipeline incorporates a trajectory control agent, allowing users to animate the scene and operate the camera through natural language interactions. Our system is also compatible with off-the-shelf deep 3D generators to enrich scene assets. Through evaluations and comparisons with state-of-the-art methods, we demonstrate the versatility of WorldCraft, ranging from single-object customization to intricate, large-scale interior and exterior scene designs. This system empowers non-professionals to bring their creative visions to life.
Authors: Yoonjin Chung, Pilsun Eu, Junwon Lee, Keunwoo Choi, Juhan Nam, Ben Sangbae Chon
Abstract: Although being widely adopted for evaluating generated audio signals, the Fr\'echet Audio Distance (FAD) suffers from significant limitations, including reliance on Gaussian assumptions, sensitivity to sample size, and high computational complexity. As an alternative, we introduce the Kernel Audio Distance (KAD), a novel, distribution-free, unbiased, and computationally efficient metric based on Maximum Mean Discrepancy (MMD). Through analysis and empirical validation, we demonstrate KAD's advantages: (1) faster convergence with smaller sample sizes, enabling reliable evaluation with limited data; (2) lower computational cost, with scalable GPU acceleration; and (3) stronger alignment with human perceptual judgments. By leveraging advanced embeddings and characteristic kernels, KAD captures nuanced differences between real and generated audio. Open-sourced in the kadtk toolkit, KAD provides an efficient, reliable, and perceptually aligned benchmark for evaluating generative audio models.
Authors: Lisa Schut, Yarin Gal, Sebastian Farquhar
Abstract: Large language models (LLMs) have multilingual capabilities and can solve tasks across various languages. However, we show that current LLMs make key decisions in a representation space closest to English, regardless of their input and output languages. Exploring the internal representations with a logit lens for sentences in French, German, Dutch, and Mandarin, we show that the LLM first emits representations close to English for semantically-loaded words before translating them into the target language. We further show that activation steering in these LLMs is more effective when the steering vectors are computed in English rather than in the language of the inputs and outputs. This suggests that multilingual LLMs perform key reasoning steps in a representation that is heavily shaped by English in a way that is not transparent to system users.
Authors: Tianle Li, Chenyang Zhang, Xingwu Chen, Yuan Cao, Difan Zou
Abstract: Transformer-based Large Language Models (LLMs) have demonstrated powerful in-context learning capabilities. However, their predictions can be disrupted by factually correct context, a phenomenon known as context hijacking, revealing a significant robustness issue. To understand this phenomenon theoretically, we explore an in-context linear classification problem based on recent advances in linear transformers. In our setup, context tokens are designed as factually correct query-answer pairs, where the queries are similar to the final query but have opposite labels. Then, we develop a general theoretical analysis on the robustness of the linear transformers, which is formulated as a function of the model depth, training context lengths, and number of hijacking context tokens. A key finding is that a well-trained deeper transformer can achieve higher robustness, which aligns with empirical observations. We show that this improvement arises because deeper layers enable more fine-grained optimization steps, effectively mitigating interference from context hijacking. This is also well supported by our numerical experiments. Our findings provide theoretical insights into the benefits of deeper architectures and contribute to enhancing the understanding of transformer architectures.
Authors: Jixiu Zhai, Tianchi Lu, Haitian Zhong, Ziyang Xu, Yuhuan Liu, Xueying Wang, Dan Huang
Abstract: Protein post-translational modifications (PTMs) and bioactive peptides (BPs) play critical roles in various biological processes and have significant therapeutic potential. However, identifying PTM sites and bioactive peptides through experimental methods is often labor-intensive, costly, and time-consuming. As a result, computational tools, particularly those based on deep learning, have become effective solutions for predicting PTM sites and peptide bioactivity. Despite progress in this field, existing methods still struggle with the complexity of protein sequences and the challenge of requiring high-quality predictions across diverse datasets. To address these issues, we propose a deep learning framework that integrates pretrained protein language models with a neural network combining transformer and CNN for peptide classification. By leveraging the ability of pretrained models to capture complex relationships within protein sequences, combined with the predictive power of parallel networks, our approach improves feature extraction while enhancing prediction accuracy. This framework was applied to multiple tasks involving PTM site and bioactive peptide prediction, utilizing large-scale datasets to enhance the model's robustness. In the comparison across 33 tasks, the model achieved state-of-the-art (SOTA) performance in 25 of them, surpassing existing methods and demonstrating its versatility across different datasets. Our results suggest that this approach provides a scalable and effective solution for large-scale peptide discovery and PTM analysis, paving the way for more efficient peptide classification and functional annotation.
Authors: Xueran Han, Yuhan Liu, Mingzhe Li, Wei Liu, Sen Hu, Rui Yan, Zhiqiang Xu, Xiuying Chen
Abstract: Great novels create immersive worlds with rich character arcs, well-structured plots, and nuanced writing styles. However, current novel generation methods often rely on brief, simplistic story outlines and generate details using plain, generic language. To bridge this gap, we introduce the task of Pastiche Novel Generation, which requires the generated novels to imitate the distinctive features of the original work, including understanding character profiles, predicting plausible plot developments, and writing concrete details using vivid, expressive language. To achieve this, we propose WriterAgent, a novel generation system designed to master the core aspects of literary pastiche. WriterAgent is trained through a curriculum learning paradigm, progressing from low-level stylistic mastery to high-level narrative coherence. Its key tasks include language style learning, character modeling, plot planning, and stylish writing, ensuring comprehensive narrative control. To support this, WriterAgent leverages the WriterLoRA framework, an extension of LoRA with hierarchical and cumulative task-specific modules, each specializing in a different narrative aspect. We evaluate WriterAgent on multilingual classics like Harry Potter and Dream of the Red Chamber, demonstrating its superiority over baselines in capturing the target author's settings, character dynamics, and writing style to produce coherent, faithful narratives.
Authors: Qi Le, Enmao Diao, Ziyan Wang, Xinran Wang, Jie Ding, Li Yang, Ali Anwar
Abstract: We introduce Probe Pruning (PP), a novel framework for online, dynamic, structured pruning of Large Language Models (LLMs) applied in a batch-wise manner. PP leverages the insight that not all samples and tokens contribute equally to the model's output, and probing a small portion of each batch effectively identifies crucial weights, enabling tailored dynamic pruning for different batches. It comprises three main stages: probing, history-informed pruning, and full inference. In the probing stage, PP selects a small yet crucial set of hidden states, based on residual importance, to run a few model layers ahead. During the history-informed pruning stage, PP strategically integrates the probing states with historical states. Subsequently, it structurally prunes weights based on the integrated states and the PP importance score, a metric developed specifically to assess the importance of each weight channel in maintaining performance. In the final stage, full inference is conducted on the remaining weights. A major advantage of PP is its compatibility with existing models, as it operates without requiring additional neural network modules or fine-tuning. Comprehensive evaluations of PP on LLaMA-2/3 and OPT models reveal that even minimal probing-using just 1.5% of FLOPs-can substantially enhance the efficiency of structured pruning of LLMs. For instance, when evaluated on LLaMA-2-7B with WikiText2, PP achieves a 2.56 times lower ratio of performance degradation per unit of runtime reduction compared to the state-of-the-art method at a 40% pruning ratio. Our code is available at https://github.com/Qi-Le1/Probe_Pruning.
Authors: Ngoc Luyen Le, Gildas Tagny Ngomp\'e
Abstract: In this article, we present the BTransformer18 model, a deep learning architecture designed for multi-label relation extraction in French texts. Our approach combines the contextual representation capabilities of pre-trained language models from the BERT family - such as BERT, RoBERTa, and their French counterparts CamemBERT and FlauBERT - with the power of Transformer encoders to capture long-term dependencies between tokens. Experiments conducted on the dataset from the TextMine'25 challenge show that our model achieves superior performance, particularly when using CamemBERT-Large, with a macro F1 score of 0.654, surpassing the results obtained with FlauBERT-Large. These results demonstrate the effectiveness of our approach for the automatic extraction of complex relations in intelligence reports.
Authors: Feng Xia, Zhifei Hu
Abstract: In recent years recommendation systems typically employ the edge information provided by knowledge graphs combined with the advantages of high-order connectivity of graph networks in the recommendation field. However, this method is limited by the sparsity of labels, cannot learn the graph structure well, and a large number of noisy entities in the knowledge graph will affect the accuracy of the recommendation results. In order to alleviate the above problems, we propose a dynamic knowledge-selecting and evaluating method guided by collaborative signals to distill information in the knowledge graph. Specifically, we use a Chain Route Evaluator to evaluate the contributions of different neighborhoods for the recommendation task and employ a Knowledge Selector strategy to filter the less informative knowledge before evaluating. We conduct baseline model comparison and experimental ablation evaluations on three public datasets. The experiments demonstrate that our proposed model outperforms current state-of-the-art baseline models, and each modules effectiveness in our model is demonstrated through ablation experiments.
Authors: Marthe Ballon, Andres Algaba, Vincent Ginis
Abstract: Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and test-time compute scaling. However, many open questions remain regarding the interplay between reasoning token usage and accuracy gains. In particular, when comparing models across generations, it is unclear whether improved performance results from longer reasoning chains or more efficient reasoning. We systematically analyze chain-of-thought length across o1-mini and o3-mini variants on the Omni-MATH benchmark, finding that o3-mini (m) achieves superior accuracy without requiring longer reasoning chains than o1-mini. Moreover, we show that accuracy generally declines as reasoning chains grow across all models and compute settings, even when controlling for difficulty of the questions. This accuracy drop is significantly smaller in more proficient models, suggesting that new generations of reasoning models use test-time compute more effectively. Finally, we highlight that while o3-mini (h) achieves a marginal accuracy gain over o3-mini (m), it does so by allocating substantially more reasoning tokens across all problems, even the ones that o3-mini (m) can already solve. These findings provide new insights into the relationship between model capability and reasoning length, with implications for efficiency, scaling, and evaluation methodologies.
Authors: Vasilii Feofanov, Songkang Wen, Marius Alonso, Romain Ilbert, Hongbo Guo, Malik Tiomoko, Lujia Pan, Jianfeng Zhang, Ievgen Redko
Abstract: In recent years, there has been increasing interest in developing foundation models for time series data that can generalize across diverse downstream tasks. While numerous forecasting-oriented foundation models have been introduced, there is a notable scarcity of models tailored for time series classification. To address this gap, we present Mantis, a new open-source foundation model for time series classification based on the Vision Transformer (ViT) architecture that has been pre-trained using a contrastive learning approach. Our experimental results show that Mantis outperforms existing foundation models both when the backbone is frozen and when fine-tuned, while achieving the lowest calibration error. In addition, we propose several adapters to handle the multivariate setting, reducing memory requirements and modeling channel interdependence.
Authors: Anirudh Sundar, Sinead Williamson, Katherine Metcalf, Barry-John Theobald, Skyler Seto, Masha Fedzechkina
Abstract: Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is computationally expensive, and sizable language data, which often may not be available. A data-efficient alternative to fine-tuning is model interventions -- a method for manipulating model activations to steer generation into the desired direction. We analyze the effect of a popular intervention (finding experts) on the alignment of cross-lingual representations in mLLMs. We identify the neurons to manipulate for a given language and introspect the embedding space of mLLMs pre- and post-manipulation. We show that modifying the mLLM's activations changes its embedding space such that cross-lingual alignment is enhanced. Further, we show that the changes to the embedding space translate into improved downstream performance on retrieval tasks, with up to 2x improvements in top-1 accuracy on cross-lingual retrieval.
Authors: Luka Grbcic, Juliane M\"uller, Wibe Albert de Jong
Abstract: Inverse design in science and engineering involves determining optimal design parameters that achieve desired performance outcomes, a process often hindered by the complexity and high dimensionality of design spaces, leading to significant computational costs. To tackle this challenge, we propose a novel hybrid approach that combines active learning with Tandem Neural Networks to enhance the efficiency and effectiveness of solving inverse design problems. Active learning allows to selectively sample the most informative data points, reducing the required dataset size without compromising accuracy. We investigate this approach using three benchmark problems: airfoil inverse design, photonic surface inverse design, and scalar boundary condition reconstruction in diffusion partial differential equations. We demonstrate that integrating active learning with Tandem Neural Networks outperforms standard approaches across the benchmark suite, achieving better accuracy with fewer training samples.
Authors: Natasha Astudillo, Fernando Koch
Abstract: The increasing demand for energy-efficient solutions in large-scale infrastructure, particularly data centers, requires advanced control strategies to optimize environmental management systems. We propose a multi-agent architecture for distributed control of air-cooled chiller systems in data centers. Our vision employs autonomous agents to monitor and regulate local operational parameters and optimize system-wide efficiency. We demonstrate how this approach improves the responsiveness, operational robustness, and energy efficiency of the system, contributing to the broader goal of sustainable infrastructure management.
Authors: Shoumik Saha, Soheil Feizi
Abstract: The growing use of large language models (LLMs) for text generation has led to widespread concerns about AI-generated content detection. However, an overlooked challenge is AI-polished text, where human-written content undergoes subtle refinements using AI tools. This raises a critical question: should minimally polished text be classified as AI-generated? Misclassification can lead to false plagiarism accusations and misleading claims about AI prevalence in online content. In this study, we systematically evaluate eleven state-of-the-art AI-text detectors using our AI-Polished-Text Evaluation (APT-Eval) dataset, which contains $11.7K$ samples refined at varying AI-involvement levels. Our findings reveal that detectors frequently misclassify even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models. These limitations highlight the urgent need for more nuanced detection methodologies.
Authors: Florent Bartoccioni, Elias Ramzi, Victor Besnier, Shashanka Venkataramanan, Tuan-Hung Vu, Yihong Xu, Loick Chambon, Spyros Gidaris, Serkan Odabas, David Hurych, Renaud Marlet, Alexandre Boulch, Mickael Chen, \'Eloi Zablocki, Andrei Bursuc, Eduardo Valle, Matthieu Cord
Abstract: We explore the potential of large-scale generative video models for autonomous driving, introducing an open-source auto-regressive video model (VaViM) and its companion video-action model (VaVAM) to investigate how video pre-training transfers to real-world driving. VaViM is a simple auto-regressive video model that predicts frames using spatio-temporal token sequences. We show that it captures the semantics and dynamics of driving scenes. VaVAM, the video-action model, leverages the learned representations of VaViM to generate driving trajectories through imitation learning. Together, the models form a complete perception-to-action pipeline. We evaluate our models in open- and closed-loop driving scenarios, revealing that video-based pre-training holds promise for autonomous driving. Key insights include the semantic richness of the learned representations, the benefits of scaling for video synthesis, and the complex relationship between model size, data, and safety metrics in closed-loop evaluations. We release code and model weights at https://github.com/valeoai/VideoActionModel
Authors: Zongkai Zhao, Guozeng Xu, Xiuhua Li, Kaiwen Wei, Jiang Zhong
Abstract: Locate-then-Edit Knowledge Editing (LEKE) is a key technique for updating large language models (LLMs) without full retraining. However, existing methods assume a single-user setting and become inefficient in real-world multi-client scenarios, where decentralized organizations (e.g., hospitals, financial institutions) independently update overlapping knowledge, leading to redundant mediator knowledge vector (MKV) computations and privacy concerns. To address these challenges, we introduce Federated Locate-then-Edit Knowledge Editing (FLEKE), a novel task that enables multiple clients to collaboratively perform LEKE while preserving privacy and reducing computational overhead. To achieve this, we propose FedEdit, a two-stage framework that optimizes MKV selection and reuse. In the first stage, clients locally apply LEKE and upload the computed MKVs. In the second stage, rather than relying solely on server-based MKV sharing, FLEKE allows clients retrieve relevant MKVs based on cosine similarity, enabling knowledge re-edit and minimizing redundant computations. Experimental results on two benchmark datasets demonstrate that FedEdit retains over 96% of the performance of non-federated LEKE while significantly outperforming a FedAvg-based baseline by approximately twofold. Besides, we find that MEMIT performs more consistently than PMET in the FLEKE task with our FedEdit framework. Our code is available at https://github.com/zongkaiz/FLEKE.
Authors: Yue Yang, Linfeng Zhao, Mingyu Ding, Gedas Bertasius, Daniel Szafir
Abstract: Robotics has long sought to develop visual-servoing robots capable of completing previously unseen long-horizon tasks. Hierarchical approaches offer a pathway for achieving this goal by executing skill combinations arranged by a task planner, with each visuomotor skill pre-trained using a specific imitation learning (IL) algorithm. However, even in simple long-horizon tasks like skill chaining, hierarchical approaches often struggle due to a problem we identify as Observation Space Shift (OSS), where the sequential execution of preceding skills causes shifts in the observation space, disrupting the performance of subsequent individually trained skill policies. To validate OSS and evaluate its impact on long-horizon tasks, we introduce BOSS (a Benchmark for Observation Space Shift). BOSS comprises three distinct challenges: "Single Predicate Shift", "Accumulated Predicate Shift", and "Skill Chaining", each designed to assess a different aspect of OSS's negative effect. We evaluated several recent popular IL algorithms on BOSS, including three Behavioral Cloning methods and the Visual Language Action model OpenVLA. Even on the simplest challenge, we observed average performance drops of 67%, 35%, 34%, and 54%, respectively, when comparing skill performance with and without OSS. Additionally, we investigate a potential solution to OSS that scales up the training data for each skill with a larger and more visually diverse set of demonstrations, with our results showing it is not sufficient to resolve OSS. The project page is: https://boss-benchmark.github.io/
Authors: Yilun Xu, Weili Nie, Arash Vahdat
Abstract: Sampling from diffusion models involves a slow iterative process that hinders their practical deployment, especially for interactive applications. To accelerate generation speed, recent approaches distill a multi-step diffusion model into a single-step student generator via variational score distillation, which matches the distribution of samples generated by the student to the teacher's distribution. However, these approaches use the reverse Kullback-Leibler (KL) divergence for distribution matching which is known to be mode seeking. In this paper, we generalize the distribution matching approach using a novel $f$-divergence minimization framework, termed $f$-distill, that covers different divergences with different trade-offs in terms of mode coverage and training variance. We derive the gradient of the $f$-divergence between the teacher and student distributions and show that it is expressed as the product of their score differences and a weighting function determined by their density ratio. This weighting function naturally emphasizes samples with higher density in the teacher distribution, when using a less mode-seeking divergence. We observe that the popular variational score distillation approach using the reverse-KL divergence is a special case within our framework. Empirically, we demonstrate that alternative $f$-divergences, such as forward-KL and Jensen-Shannon divergences, outperform the current best variational score distillation methods across image generation tasks. In particular, when using Jensen-Shannon divergence, $f$-distill achieves current state-of-the-art one-step generation performance on ImageNet64 and zero-shot text-to-image generation on MS-COCO. Project page: https://research.nvidia.com/labs/genair/f-distill
Authors: Sowmya S. Sundaram, Benjamin Solomon, Avani Khatri, Anisha Laumas, Purvesh Khatri, Mark A. Musen
Abstract: Metadata play a crucial role in ensuring the findability, accessibility, interoperability, and reusability of datasets. This paper investigates the potential of large language models (LLMs), specifically GPT-4, to improve adherence to metadata standards. We conducted experiments on 200 random data records describing human samples relating to lung cancer from the NCBI BioSample repository, evaluating GPT-4's ability to suggest edits for adherence to metadata standards. We computed the adherence accuracy of field name-field value pairs through a peer review process, and we observed a marginal average improvement in adherence to the standard data dictionary from 79% to 80% (p<0.5). We then prompted GPT-4 with domain information in the form of the textual descriptions of CEDAR templates and recorded a significant improvement to 97% from 79% (p<0.01). These results indicate that, while LLMs may not be able to correct legacy metadata to ensure satisfactory adherence to standards when unaided, they do show promise for use in automated metadata curation when integrated with a structured knowledge base
Authors: Fangxu Yu, Lai Jiang, Haoqiang Kang, Shibo Hao, Lianhui Qin
Abstract: The ability to generate diverse solutions to a given problem is a hallmark of human creativity. This divergent reasoning is also crucial for machines, enhancing their robustness and enabling them to assist humans in many applications such as scientific discovery. However, existing approaches to multi-step reasoning with large language models (LLMs) have mostly focused only on reasoning accuracy, without further discovering more diverse valid solutions. For example, supervised fine-tuning can improve LLM reasoning quality, but requires extensive supervised data to capture the full range of possible solutions. Reward-maximization reinforcement learning aims to find limited highest-reward solutions while neglecting the solution diversity. To fill this gap, we propose Flow of Reasoning (FoR), an efficient diversity-seeking LLM finetuning method aimed at improving reasoning quality and diversity with minimal data. FoR formulates multi-step LLM reasoning as a Markovian flow on a DAG-structured reasoning graph. This formulation allows us to incorporate and adapt principled GFlowNet approaches, for finetuning LLMs to sample divergent paths with probabilities proportional to the (unnormalized) reward of target problems. Extensive experiments show that, with limited training examples (e.g., 15 examples), FoR enables the discovery of diverse, creative, high-quality solutions, greatly outperforming a wide range of existing inference and training methods across six challenging reasoning tasks, including BlocksWorld (embodied reasoning), Game24 (math puzzle solving), Rubik's Cube (spatial reasoning), 1D-ARC (abstraction reasoning), GSM8k (math reasoning), and ProntoQA (logical reasoning). Code is available at https://github.com/Yu-Fangxu/FoR.
Authors: Gianmarco Mengaldo
Abstract: The scientific method is the cornerstone of human progress across all branches of the natural and applied sciences, from understanding the human body to explaining how the universe works. The scientific method is based on identifying systematic rules or principles that describe the phenomenon of interest in a reproducible way that can be validated through experimental evidence. In the era of generative artificial intelligence, there are discussions on how AI systems may discover new knowledge. We argue that human complex reasoning for scientific discovery remains of vital importance, at least before the advent of artificial general intelligence. Yet, AI can be leveraged for scientific discovery via explainable AI. More specifically, knowing the `principles' the AI systems used to make decisions can be a point of contact with domain experts and scientists, that can lead to divergent or convergent views on a given scientific problem. Divergent views may spark further scientific investigations leading to interpretability-guided explanations (IGEs), and possibly to new scientific knowledge. We define this field as Explainable AI for Science, where domain experts -- potentially assisted by generative AI -- formulate scientific hypotheses and explanations based on the interpretability of a predictive AI system.
Authors: Rubing Chen, Xulu Zhang, Jiaxin Wu, Wenqi Fan, Xiao-Yong Wei, Qing Li
Abstract: This paper addresses the need for improved precision in existing knowledge-enhanced question-answering frameworks, specifically Retrieval-Augmented Generation (RAG) methods that primarily focus on enhancing recall. We propose a multi-layer knowledge pyramid approach within the RAG framework to achieve a better balance between precision and recall. The knowledge pyramid consists of three layers: Ontologies, Knowledge Graphs (KGs), and chunk-based raw text. We employ cross-layer augmentation techniques for comprehensive knowledge coverage and dynamic updates of the Ontology schema and instances. To ensure compactness, we utilize cross-layer filtering methods for knowledge condensation in KGs. Our approach, named PolyRAG, follows a waterfall model for retrieval, starting from the top of the pyramid and progressing down until a confident answer is obtained. We introduce two benchmarks for domain-specific knowledge retrieval, one in the academic domain and the other in the financial domain. The effectiveness of the methods has been validated through comprehensive experiments by outperforming 19 SOTA methods. An encouraging observation is that the proposed method has augmented the GPT-4, providing 395% F1 gain by improving its performance from 0.1636 to 0.8109.
Authors: Xi Jiang, Jian Li, Hanqiu Deng, Yong Liu, Bin-Bin Gao, Yifeng Zhou, Jialin Li, Chengjie Wang, Feng Zheng
Abstract: In the field of industrial inspection, Multimodal Large Language Models (MLLMs) have a high potential to renew the paradigms in practical applications due to their robust language capabilities and generalization abilities. However, despite their impressive problem-solving skills in many domains, MLLMs' ability in industrial anomaly detection has not been systematically studied. To bridge this gap, we present MMAD, the first-ever full-spectrum MLLMs benchmark in industrial Anomaly Detection. We defined seven key subtasks of MLLMs in industrial inspection and designed a novel pipeline to generate the MMAD dataset with 39,672 questions for 8,366 industrial images. With MMAD, we have conducted a comprehensive, quantitative evaluation of various state-of-the-art MLLMs. The commercial models performed the best, with the average accuracy of GPT-4o models reaching 74.9%. However, this result falls far short of industrial requirements. Our analysis reveals that current MLLMs still have significant room for improvement in answering questions related to industrial anomalies and defects. We further explore two training-free performance enhancement strategies to help models improve in industrial scenarios, highlighting their promising potential for future research.
Authors: Inbal Avraham, Reuth Mirsky
Abstract: Shared control problems involve a robot learning to collaborate with a human. When learning a shared control policy, short communication between the agents can often significantly reduce running times and improve the system's accuracy. We extend the shared control problem to include the ability to directly query a cooperating agent. We consider two types of potential responses to a query, namely oracles: one that can provide the learner with the best action they should take, even when that action might be myopically wrong, and one with a bounded knowledge limited to its part of the system. Given this additional information channel, this work further presents three heuristics for choosing when to query: reinforcement learning-based, utility-based, and entropy-based. These heuristics aim to reduce a system's overall learning cost. Empirical results on two environments show the benefits of querying to learn a better control policy and the tradeoffs between the proposed heuristics.
Authors: M Anuprabha, Krishna Gurugubelli, V Kesavaraj, Anil Kumar Vuppala
Abstract: Automatic detection and severity assessment of dysarthria are crucial for delivering targeted therapeutic interventions to patients. While most existing research focuses primarily on speech modality, this study introduces a novel approach that leverages both speech and text modalities. By employing cross-attention mechanism, our method learns the acoustic and linguistic similarities between speech and text representations. This approach assesses specifically the pronunciation deviations across different severity levels, thereby enhancing the accuracy of dysarthric detection and severity assessment. All the experiments have been performed using UA-Speech dysarthric database. Improved accuracies of 99.53% and 93.20% in detection, and 98.12% and 51.97% for severity assessment have been achieved when speaker-dependent and speaker-independent, unseen and seen words settings are used. These findings suggest that by integrating text information, which provides a reference linguistic knowledge, a more robust framework has been developed for dysarthric detection and assessment, thereby potentially leading to more effective diagnoses.
Authors: Hao Zheng, Xinyan Guan, Hao Kong, Jia Zheng, Weixiang Zhou, Hongyu Lin, Yaojie Lu, Ben He, Xianpei Han, Le Sun
Abstract: Automatically generating presentations from documents is a challenging task that requires accommodating content quality, visual appeal, and structural coherence. Existing methods primarily focus on improving and evaluating the content quality in isolation, overlooking visual appeal and structural coherence, which limits their practical applicability. To address these limitations, we propose PPTAgent, which comprehensively improves presentation generation through a two-stage, edit-based approach inspired by human workflows. PPTAgent first analyzes reference presentations to extract slide-level functional types and content schemas, then drafts an outline and iteratively generates editing actions based on selected reference slides to create new slides. To comprehensively evaluate the quality of generated presentations, we further introduce PPTEval, an evaluation framework that assesses presentations across three dimensions: Content, Design, and Coherence. Results demonstrate that PPTAgent significantly outperforms existing automatic presentation generation methods across all three dimensions.
Authors: Brian Hyeongseok Kim, Chao Wang
Abstract: We propose a clinical decision support system (CDSS) for mental health diagnosis that combines the strengths of large language models (LLMs) and constraint logic programming (CLP). Having a CDSS is important because of the high complexity of diagnostic manuals used by mental health professionals and the danger of diagnostic errors. Our CDSS is a software tool that uses an LLM to translate diagnostic manuals to a logic program and solves the program using an off-the-shelf CLP engine to query a patient's diagnosis based on the encoded rules and provided data. By giving domain experts the opportunity to inspect the LLM-generated logic program, and making modifications when needed, our CDSS ensures that the diagnosis is not only accurate but also interpretable. We experimentally compare it with two baseline approaches of using LLMs: diagnosing patients using the LLM-only approach, and using the LLM-generated logic program but without expert inspection. The results show that, while LLMs are extremely useful in generating candidate logic programs, these programs still require expert inspection and modification to guarantee faithfulness to the official diagnostic manuals. Additionally, ethical concerns arise from the direct use of patient data in LLMs, underscoring the need for a safer hybrid approach like our proposed method.
Authors: Kai Yan, Zhan Ling, Kang Liu, Yifan Yang, Ting-Han Fan, Lingfeng Shen, Zhengyin Du, Jiecao Chen
Abstract: Inductive Reasoning (IR), the ability to summarize rules from examples and apply on new ones, has long been viewed as a primal ability for general intelligence and widely studied by cognitive science and AI researchers. Many benchmarks have been proposed to measure such ability for Large Language Models (LLMs); however, they focus on few-shot (usually $<$10) setting and lack evaluation for aggregating many pieces of information from long contexts. On the other hand, the ever-growing context length of LLMs have brought forth the novel paradigm of many-shot In-Context Learning (ICL), which addresses new tasks with hundreds to thousands of examples without expensive and inefficient fine-tuning. However, many-shot evaluations are mostly focused on classification (a very limited aspect of IR), and popular long-context LLM tasks such as Needle-In-A-Haystack (NIAH) seldom require complicated intelligence for integrating many pieces of information. To fix the issues from both worlds, we propose MIR-Bench, the first many-shot in-context inductive reasoning benchmark that asks LLM to induce output via input-output examples from underlying functions with diverse data format. Based on MIR-Bench, we study many novel problems for inductive reasoning and many-shot ICL, including robustness against erroneous shots and the effect of Chain-of-Thought (CoT), and acquired insightful findings.
Authors: Hongliang Lu, Zhonglin Xie, Yaoyu Wu, Can Ren, Yuxuan Chen, Zaiwen Wen
Abstract: Despite the rapid development of large language models (LLMs), a fundamental challenge persists: the lack of high-quality optimization modeling datasets hampers LLMs' robust modeling of practical optimization problems from natural language descriptions (NL). This data scarcity also contributes to the generalization difficulties experienced by learning-based methods. To address these challenges, we propose a scalable framework for synthesizing a high-quality dataset, named OptMATH. Starting from curated seed data with mathematical formulations (MF), this framework automatically generates problem data (PD) with controllable complexity. Then, a back-translation step is employed to obtain NL. To verify the correspondence between the NL and the PD, a forward modeling step followed by rejection sampling is used. The accepted pairs constitute the training part of OptMATH. Then a collection of rejected pairs is identified and further filtered. This collection serves as a new benchmark for optimization modeling, containing difficult instances whose lengths are much longer than these of NL4OPT and MAMO. Through extensive experiments, we demonstrate that models of various sizes (0.5B-32B parameters) trained on OptMATH achieve superior results on multiple modeling benchmarks, thereby validating the effectiveness and scalability of our approach. Our dataset is publicly available at https://github.com/AuroraLHL/OptMATH.
Authors: Kaikai Zhao, Zhaoxiang Liu, Xuejiao Lei, Ning Wang, Jiaojiao Zhao, Zipeng Wang, Zhenhong Long, Peijun Yang, Minjie Hua, Chaoyang Ma, Wen Liu, Kai Wang, Shiguo Lian
Abstract: DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks. However, detailed evaluations from the perspective of real-world applications are lacking, making it challenging for users to select the most suitable DeepSeek models for their specific needs. To address this gap, we evaluate the DeepSeek-V3, DeepSeek-R1, DeepSeek-R1-Distill-Qwen series, and DeepSeek-R1-Distill-Llama series on the improved version A-Eval (A-Eval-2.0), an application-driven benchmark. By comparing original instruction-tuned models with their distilled counterparts, we analyze how reasoning enhancements impact performance across diverse practical tasks. Our results show that reasoning-enhanced models, while generally powerful, do not universally outperform across all tasks, with performance gains varying significantly across tasks and models. To further assist users in model selection, we quantify the capability boundary of DeepSeek models through performance tier classifications and intuitive line charts. Specific examples provide actionable insights to help users select and deploy the most cost-effective DeepSeek models, ensuring optimal performance and resource efficiency in real-world applications. It should be noted that, despite our efforts to establish a comprehensive, objective, and authoritative evaluation benchmark, the selection of test samples, characteristics of data distribution, and the setting of evaluation criteria may inevitably introduce certain biases into the evaluation results. We will continuously optimize the evaluation benchmarks and periodically update this paper to provide more comprehensive and accurate evaluation results. Please refer to the latest version of the paper for the most recent results and conclusions.
Authors: Johan Boye, Birger Moell
Abstract: This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems. Unlike prior studies that focus solely on answer correctness, we rigorously analyze both final answers and solution steps to identify reasoning failures. Evaluating eight state-of-the-art models - including Mixtral, Llama, Gemini, GPT-4o, and OpenAI's o1 variants - we find that while newer models (e.g., o3-mini, deepseek-r1) achieve higher accuracy, all models exhibit errors in spatial reasoning, strategic planning, and arithmetic, sometimes producing correct answers through flawed logic. Common failure modes include unwarranted assumptions, over-reliance on numerical patterns, and difficulty translating physical intuition into mathematical steps. Manual analysis reveals that models struggle with problems requiring multi-step deduction or real-world knowledge, despite possessing broad mathematical knowledge. Our results underscore the importance of evaluating reasoning processes, not just answers, and caution against overestimating LLMs' problem-solving proficiency. The study highlights persistent gaps in LLMs' generalization abilities, emphasizing the need for targeted improvements in structured reasoning and constraint handling.
Authors: Shuo Wang, Renhao Li, Xi Chen, Yulin Yuan, Derek F. Wong, Min Yang
Abstract: With the different roles that AI is expected to play in human life, imbuing large language models (LLMs) with different personalities has attracted increasing research interests. While the "personification" enhances human experiences of interactivity and adaptability of LLMs, it gives rise to critical concerns about content safety, particularly regarding bias, sentiment and toxicity of LLM generation. This study explores how assigning different personality traits to LLMs affects the toxicity and biases of their outputs. Leveraging the widely accepted HEXACO personality framework developed in social psychology, we design experimentally sound prompts to test three LLMs' performance on three toxic and bias benchmarks. The findings demonstrate the sensitivity of all three models to HEXACO personality traits and, more importantly, a consistent variation in the biases, negative sentiment and toxicity of their output. In particular, adjusting the levels of several personality traits can effectively reduce bias and toxicity in model performance, similar to humans' correlations between personality traits and toxic behaviors. The findings highlight the additional need to examine content safety besides the efficiency of training or fine-tuning methods for LLM personification. They also suggest a potential for the adjustment of personalities to be a simple and low-cost method to conduct controlled text generation.
Authors: Animesh Nighojkar, Bekhzodbek Moydinboyev, My Duong, John Licato
Abstract: In computational cognitive modeling, capturing the full spectrum of human judgment and decision-making processes, beyond just optimal behaviors, is a significant challenge. This study explores whether Large Language Models (LLMs) can emulate the breadth of human reasoning by predicting both intuitive, fast System 1 and deliberate, slow System 2 processes. We investigate the potential of AI to mimic diverse reasoning behaviors across a human population, addressing what we call the "full reasoning spectrum problem". We designed reasoning tasks using a novel generalization of the Natural Language Inference (NLI) format to evaluate LLMs' ability to replicate human reasoning. The questions were crafted to elicit both System 1 and System 2 responses. Human responses were collected through crowd-sourcing and the entire distribution was modeled, rather than just the majority of the answers. We used personality-based prompting inspired by the Big Five personality model to elicit AI responses reflecting specific personality traits, capturing the diversity of human reasoning, and exploring how personality traits influence LLM outputs. Combined with genetic algorithms to optimize the weighting of these prompts, this method was tested alongside traditional machine learning models. The results show that LLMs can mimic human response distributions, with open-source models like Llama and Mistral outperforming proprietary GPT models. Personality-based prompting, especially when optimized with genetic algorithms, significantly enhanced LLMs' ability to predict human response distributions, suggesting that capturing suboptimal, naturalistic reasoning may require modeling techniques incorporating diverse reasoning styles and psychological profiles. The study concludes that personality-based prompting combined with genetic algorithms is promising for enhancing AI's 'human-ness' in reasoning.
Authors: Shu Wu, Zekun Li, Yunyue Su, Zeyu Cui, Xiaoyu Zhang, Liang Wang
Abstract: Factorization machine (FM) is a prevalent approach to modeling pairwise (second-order) feature interactions when dealing with high-dimensional sparse data. However, on the one hand, FM fails to capture higher-order feature interactions suffering from combinatorial expansion. On the other hand, taking into account interactions between every pair of features may introduce noise and degrade prediction accuracy. To solve the problems, we propose a novel approach, Graph Factorization Machine (GraphFM), by naturally representing features in the graph structure. In particular, we design a mechanism to select the beneficial feature interactions and formulate them as edges between features. Then the proposed model, which integrates the interaction function of FM into the feature aggregation strategy of Graph Neural Network (GNN), can model arbitrary-order feature interactions on the graph-structured features by stacking layers. Experimental results on several real-world datasets have demonstrated the rationality and effectiveness of our proposed approach. The code and data are available at https://github.com/CRIPAC-DIG/GraphCTR}{https://github.com/CRIPAC-DIG/GraphCTR
URLs: https://github.com/CRIPAC-DIG/GraphCTR, https://github.com/CRIPAC-DIG/GraphCTR
Authors: Wei Ye, Zexi Huang, Yunqi Hong, Ambuj Singh
Abstract: Graph Convolutional Networks (GCN) is a pioneering model for graph-based semi-supervised learning. However, GCN does not perform well on sparsely-labeled graphs. Its two-layer version cannot effectively propagate the label information to the whole graph structure (i.e., the under-smoothing problem) while its deep version over-smoothens and is hard to train (i.e., the over-smoothing problem). To solve these two issues, we propose a new graph neural network called GND-Nets (for Graph Neural Diffusion Networks) that exploits the local and global neighborhood information of a vertex in a single layer. Exploiting the shallow network mitigates the over-smoothing problem while exploiting the local and global neighborhood information mitigates the under-smoothing problem. The utilization of the local and global neighborhood information of a vertex is achieved by a new graph diffusion method called neural diffusions, which integrate neural networks into the conventional linear and nonlinear graph diffusions. The adoption of neural networks makes neural diffusions adaptable to different datasets. Extensive experiments on various sparsely-labeled graphs verify the effectiveness and efficiency of GND-Nets compared to state-of-the-art approaches.
Authors: Tingting Yuan, Hwei-Ming Chung, Xiaoming Fu
Abstract: Cooperative intelligence (CI) is expected to become an integral element in next-generation networks because it can aggregate the capabilities and intelligence of multiple devices. Multi-agent reinforcement learning (MARL) is a popular approach for achieving CI in communication problems by enabling effective collaboration among agents to address sequential problems. However, ensuring privacy protection for MARL is a challenging task because of the presence of heterogeneous agents that learn interdependently via sharing information. Implementing privacy protection techniques such as data encryption and federated learning to MARL introduces the notable overheads (e.g., computation and bandwidth). To overcome these challenges, we propose PP-MARL, an efficient privacy-preserving learning scheme for MARL. PP-MARL leverages homomorphic encryption (HE) and differential privacy (DP) to protect privacy, while introducing split learning to decrease overheads via reducing the volume of shared messages, and then improve efficiency. We apply and evaluate PP-MARL in two communication-related use cases. Simulation results reveal that PP-MARL can achieve efficient and reliable collaboration with 1.1-6 times better privacy protection and lower overheads (e.g., 84-91% reduction in bandwidth) than state-of-the-art approaches.
Authors: Haozheng Luo, Tianyi Wu, Colin Feiyu Han, Zhijun Yan
Abstract: In this work, we build recent advances in distributional reinforcement learning to give a state-of-art distributional variant of the model based on the IQN. We achieve this by using the GAN model's generator and discriminator function with the quantile regression to approximate the full quantile value for the state-action return distribution. We demonstrate improved performance on our baseline dataset - 57 Atari 2600 games in the ALE. Also, we use our algorithm to show the state-of-art training performance of risk-sensitive policies in Atari games with the policy optimization and evaluation.
Authors: Yingda Yin, Jiangran Lyu, Yang Wang, Haoran Liu, He Wang, Baoquan Chen
Abstract: Estimating the 3DoF rotation from a single RGB image is an important yet challenging problem. As a popular approach, probabilistic rotation modeling additionally carries prediction uncertainty information, compared to single-prediction rotation regression. For modeling probabilistic distribution over SO(3), it is natural to use Gaussian-like Bingham distribution and matrix Fisher, however they are shown to be sensitive to outlier predictions, e.g. $180^\circ$ error and thus are unlikely to converge with optimal performance. In this paper, we draw inspiration from multivariate Laplace distribution and propose a novel rotation Laplace distribution on SO(3). Our rotation Laplace distribution is robust to the disturbance of outliers and enforces much gradient to the low-error region that it can improve. In addition, we show that our method also exhibits robustness to small noises and thus tolerates imperfect annotations. With this benefit, we demonstrate its advantages in semi-supervised rotation regression, where the pseudo labels are noisy. To further capture the multi-modal rotation solution space for symmetric objects, we extend our distribution to rotation Laplace mixture model and demonstrate its effectiveness. Our extensive experiments show that our proposed distribution and the mixture model achieve state-of-the-art performance in all the rotation regression experiments over both probabilistic and non-probabilistic baselines.
Authors: YongKyung Oh, Dong-Young Lim, Sungil Kim
Abstract: Real-world 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 analysis, 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: Tianlong Li, Zhenghua Wang, Wenhao Liu, Muling Wu, Shihan Dou, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
Abstract: The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has been limited research into the underlying mechanisms that make LLMs vulnerable to such attacks. In this study, we suggest that the self-safeguarding capability of LLMs is linked to specific activity patterns within their representation space. Although these patterns have little impact on the semantic content of the generated text, they play a crucial role in shaping LLM behavior under jailbreaking attacks. Our findings demonstrate that these patterns can be detected with just a few pairs of contrastive queries. Extensive experimentation shows that the robustness of LLMs against jailbreaking can be manipulated by weakening or strengthening these patterns. Further visual analysis provides additional evidence for our conclusions, providing new insights into the jailbreaking phenomenon. These findings highlight the importance of addressing the potential misuse of open-source LLMs within the community.
Authors: Yizhou Xu, Liu Ziyin
Abstract: Understanding the dynamics of neural networks in different width regimes is crucial for improving their training and performance. We present an exact solution for the learning dynamics of a one-hidden-layer linear network, with one-dimensional data, across any finite width, uniquely exhibiting both kernel and feature learning phases. This study marks a technical advancement by enabling the analysis of the training trajectory from any initialization and a detailed phase diagram under varying common hyperparameters such as width, layer-wise learning rates, and scales of output and initialization. We identify three novel prototype mechanisms specific to the feature learning regime: (1) learning by alignment, (2) learning by disalignment, and (3) learning by rescaling, which contrast starkly with the dynamics observed in the kernel regime. Our theoretical findings are substantiated with empirical evidence showing that these mechanisms also manifest in deep nonlinear networks handling real-world tasks, enhancing our understanding of neural network training dynamics and guiding the design of more effective learning strategies.
Authors: Kun-Peng Ning, Shuo Yang, Yu-Yang Liu, Jia-Yu Yao, Zhen-Hui Liu, Yong-Hong Tian, Yibing Song, Li Yuan
Abstract: Existing large language models (LLMs) evaluation methods typically focus on testing the performance on some closed-environment and domain-specific benchmarks with human annotations. In this paper, we explore a novel unsupervised evaluation direction, utilizing peer-review mechanisms to measure LLMs automatically. In this setting, both open-source and closed-source LLMs lie in the same environment, capable of answering unlabeled questions and evaluating each other, where each LLM's response score is jointly determined by other anonymous ones. To obtain the ability hierarchy among these models, we assign each LLM a learnable capability parameter to adjust the final ranking. We formalize it as a constrained optimization problem, intending to maximize the consistency of each LLM's capabilities and scores. The key assumption behind is that high-level LLM can evaluate others' answers more accurately than low-level ones, while higher-level LLM can also achieve higher response scores. Moreover, we propose three metrics called PEN, CIN, and LIS to evaluate the gap in aligning human rankings. We perform experiments on multiple datasets with these metrics, validating the effectiveness of the proposed approach.
Authors: Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter, Johannes Brandstetter
Abstract: We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations within MIM models generally reside in intermediate layers. Accordingly, MIM-Refiner leverages multiple contrastive heads that are connected to different intermediate layers. In each head, a modified nearest neighbor objective constructs semantic clusters that capture semantic information which improves performance on downstream tasks, including off-the-shelf and fine-tuning settings. The refinement process is short and simple - yet highly effective. Within a few epochs, we refine the features of MIM models from subpar to state-of-the-art, off-the-shelf features. Refining a ViT-H, pre-trained with data2vec 2.0 on ImageNet-1K, sets a new state-of-the-art in linear probing (84.7%) and low-shot classification among models that are pre-trained on ImageNet-1K. MIM-Refiner efficiently combines the advantages of MIM and ID objectives and compares favorably against previous state-of-the-art SSL models on a variety of benchmarks such as low-shot classification, long-tailed classification, clustering and semantic segmentation.
Authors: Koyena Pal, David Bau, Ren\'ee J. Miller
Abstract: Given a set of deep learning models, it can be hard to find models appropriate to a task, understand the models, and characterize how models are different one from another. Currently, practitioners rely on manually-written documentation to understand and choose models. However, not all models have complete and reliable documentation. As the number of models increases, the challenges of finding, differentiating, and understanding models become increasingly crucial. Inspired from research on data lakes, we introduce the concept of model lakes. We formalize key model lake tasks, including model attribution, versioning, search, and benchmarking, and discuss fundamental research challenges in the management of large models. We also explore what data management techniques can be brought to bear on the study of large model management.
Authors: Yunpeng Luo, Junlong Du, Ke Yan, Shouhong Ding
Abstract: The evolution of Diffusion Models has dramatically improved image generation quality, making it increasingly difficult to differentiate between real and generated images. This development, while impressive, also raises significant privacy and security concerns. In response to this, we propose a novel Latent REconstruction error guided feature REfinement method (LaRE^2) for detecting the diffusion-generated images. We come up with the Latent Reconstruction Error (LaRE), the first reconstruction-error based feature in the latent space for generated image detection. LaRE surpasses existing methods in terms of feature extraction efficiency while preserving crucial cues required to differentiate between the real and the fake. To exploit LaRE, we propose an Error-Guided feature REfinement module (EGRE), which can refine the image feature guided by LaRE to enhance the discriminativeness of the feature. Our EGRE utilizes an align-then-refine mechanism, which effectively refines the image feature for generated-image detection from both spatial and channel perspectives. Extensive experiments on the large-scale GenImage benchmark demonstrate the superiority of our LaRE^2, which surpasses the best SoTA method by up to 11.9%/12.1% average ACC/AP across 8 different image generators. LaRE also surpasses existing methods in terms of feature extraction cost, delivering an impressive speed enhancement of 8 times. Code is available.
Authors: Hirokazu Ishida, Naoki Hiraoka, Kei Okada, Masayuki Inaba
Abstract: Library-based methods are known to be very effective for fast motion planning by adapting an experience retrieved from a precomputed library. This article presents CoverLib, a principled approach for constructing and utilizing such a library. CoverLib iteratively adds an experience-classifier-pair to the library, where each classifier corresponds to an adaptable region of the experience within the problem space. This iterative process is an active procedure, as it selects the next experience based on its ability to effectively cover the uncovered region. During the query phase, these classifiers are utilized to select an experience that is expected to be adaptable for a given problem. Experimental results demonstrate that CoverLib effectively mitigates the trade-off between plannability and speed observed in global (e.g. sampling-based) and local (e.g. optimization-based) methods. As a result, it achieves both fast planning and high success rates over the problem domain. Moreover, due to its adaptation-algorithm-agnostic nature, CoverLib seamlessly integrates with various adaptation methods, including nonlinear programming-based and sampling-based algorithms.
Authors: Nikhil Churamani, Saksham Checker, Fethiye Irmak Dogan, Hao-Tien Lewis Chiang, Hatice Gunes
Abstract: It is critical for robots to explore Federated Learning (FL) settings where several robots, deployed in parallel, can learn independently while also sharing their learning with each other. This collaborative learning in real-world environments requires social robots to adapt dynamically to changing and unpredictable situations and varying task settings. Our work contributes to addressing these challenges by exploring a simulated living room environment where robots need to learn the social appropriateness of their actions. First, we propose Federated Root (FedRoot) averaging, a novel weight aggregation strategy which disentangles feature learning across clients from individual task-based learning. Second, to adapt to challenging environments, we extend FedRoot to Federated Latent Generative Replay (FedLGR), a novel Federated Continual Learning (FCL) strategy that uses FedRoot-based weight aggregation and embeds each client with a generator model for pseudo-rehearsal of learnt feature embeddings to mitigate forgetting in a resource-efficient manner. Our results show that FedRoot-based methods offer competitive performance while also resulting in a sizeable reduction in resource consumption (up to 86% for CPU usage and up to 72% for GPU usage). Additionally, our results demonstrate that FedRoot-based FCL methods outperform other methods while also offering an efficient solution (up to 84% CPU and 92% GPU usage reduction), with FedLGR providing the best results across evaluations.
Authors: Raeid Saqur, Anastasis Kratsios, Florian Krach, Yannick Limmer, Jacob-Junqi Tian, John Willes, Blanka Horvath, Frank Rudzicz
Abstract: We propose MoE-F - a formalized mechanism for combining $N$ pre-trained Large Language Models (LLMs) for online time-series prediction by adaptively forecasting the best weighting of LLM predictions at every time step. Our mechanism leverages the conditional information in each expert's running performance to forecast the best combination of LLMs for predicting the time series in its next step. Diverging from static (learned) Mixture of Experts (MoE) methods, our approach employs time-adaptive stochastic filtering techniques to combine experts. By framing the expert selection problem as a finite state-space, continuous-time Hidden Markov model (HMM), we can leverage the Wohman-Shiryaev filter. Our approach first constructs N parallel filters corresponding to each of the $N$ individual LLMs. Each filter proposes its best combination of LLMs, given the information that they have access to. Subsequently, the N filter outputs are optimally aggregated to maximize their robust predictive power, and this update is computed efficiently via a closed-form expression, generating our ensemble predictor. Our contributions are: **(I)** the MoE-F plug-and-play filtering harness algorithm, **(II)** theoretical optimality guarantees of the proposed filtering-based gating algorithm (via optimality guarantees for its parallel Bayesian filtering and its robust aggregation steps), and **(III)** empirical evaluation and ablative results using state-of-the-art foundational and MoE LLMs on a real-world __Financial Market Movement__ task where MoE-F attains a remarkable 17\% absolute and 48.5\% relative F1 measure improvement over the next best performing individual LLM expert predicting short-horizon market movement based on streaming news. Further, we provide empirical evidence of substantial performance gains in applying MoE-F over specialized models in the long-horizon time-series forecasting domain.
Authors: Benedikt Alkin, Maximilian Beck, Korbinian P\"oppel, Sepp Hochreiter, Johannes Brandstetter
Abstract: Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has been extended to a scalable and performant architecture - the xLSTM - which overcomes long-standing LSTM limitations via exponential gating and parallelizable matrix memory structure. In this report, we introduce Vision-LSTM (ViL), an adaption of the xLSTM building blocks to computer vision. ViL comprises a stack of xLSTM blocks where odd blocks process the sequence of patch tokens from top to bottom while even blocks go from bottom to top. Experiments show that ViL holds promise to be further deployed as new generic backbone for computer vision architectures.
Authors: Mehrdad Khatir, Sanchit Kabara, Chandan K. Reddy
Abstract: This paper shifts focus to the often-overlooked input embeddings - the initial representations fed into transformer blocks. Using fuzzy graph, k-nearest neighbor (k-NN), and community detection, we analyze embeddings from diverse LLMs, finding significant categorical community structure aligned with predefined concepts and categories aligned with humans. We observe these groupings exhibit within-cluster organization (such as hierarchies, topological ordering, etc.), hypothesizing a fundamental structure that precedes contextual processing. To further investigate the conceptual nature of these groupings, we explore cross-model alignments across different LLM categories within their input embeddings, observing a medium to high degree of alignment. Furthermore, provide evidence that manipulating these groupings can play a functional role in mitigating ethnicity bias in LLM tasks.
Authors: Lidia Garrucho, Kaisar Kushibar, Claire-Anne Reidel, Smriti Joshi, Richard Osuala, Apostolia Tsirikoglou, Maciej Bobowicz, Javier del Riego, Alessandro Catanese, Katarzyna Gwo\'zdziewicz, Maria-Laura Cosaka, Pasant M. Abo-Elhoda, Sara W. Tantawy, Shorouq S. Sakrana, Norhan O. Shawky-Abdelfatah, Amr Muhammad Abdo-Salem, Androniki Kozana, Eugen Divjak, Gordana Ivanac, Katerina Nikiforaki, Michail E. Klontzas, Rosa Garc\'ia-Dosd\'a, Meltem Gulsun-Akpinar, O\u{g}uz Lafc{\i}, Ritse Mann, Carlos Mart\'in-Isla, Fred Prior, Kostas Marias, Martijn P. A. Starmans, Fredrik Strand, Oliver D\'iaz, Laura Igual, Karim Lekadir
Abstract: Artificial Intelligence (AI) research in breast cancer Magnetic Resonance Imaging (MRI) faces challenges due to limited expert-labeled segmentations. To address this, we present a multicenter dataset of 1506 pre-treatment T1-weighted dynamic contrast-enhanced MRI cases, including expert annotations of primary tumors and non-mass-enhanced regions. The dataset integrates imaging data from four collections in The Cancer Imaging Archive (TCIA), where only 163 cases with expert segmentations were initially available. To facilitate the annotation process, a deep learning model was trained to produce preliminary segmentations for the remaining cases. These were subsequently corrected and verified by 16 breast cancer experts (averaging 9 years of experience), creating a fully annotated dataset. Additionally, the dataset includes 49 harmonized clinical and demographic variables, as well as pre-trained weights for a baseline nnU-Net model trained on the annotated data. This resource addresses a critical gap in publicly available breast cancer datasets, enabling the development, validation, and benchmarking of advanced deep learning models, thus driving progress in breast cancer diagnostics, treatment response prediction, and personalized care.
Authors: Riya Sawhney, Samrat Yadav, Indrajit Bhattacharya, Mausam
Abstract: Real-world applications of KBQA require models to handle unanswerable questions with a limited volume of in-domain labeled training data. We propose the novel task of few-shot transfer for KBQA with unanswerable questions and contribute two new datasets for performance evaluation. We present FUn-FuSIC - a novel solution for our task that extends FuSIC KBQA, the state-of-the-art few-shot transfer model for answerable-only KBQA. We first note that FuSIC-KBQA's iterative repair makes a strong assumption that all questions are unanswerable. As a remedy, we propose Feedback for Unanswerability (FUn), which uses iterative repair using feedback from a suite of strong and weak verifiers, and an adaptation of self consistency for unanswerabilty to better assess the answerability of a question. Our experiments show that FUn-FuSIC significantly outperforms suitable adaptations of multiple LLM based and supervised SoTA models on our task, while establishing a new SoTA for answerable few-shot transfer as well.
Authors: Amalie Brogaard Pauli, Isabelle Augenstein, Ira Assent
Abstract: We are exposed to much information trying to influence us, such as teaser messages, debates, politically framed news, and propaganda - all of which use persuasive language. With the recent interest in Large Language Models (LLMs), we study the ability of LLMs to produce persuasive text. As opposed to prior work which focuses on particular domains or types of persuasion, we conduct a general study across various domains to measure and benchmark to what degree LLMs produce persuasive language - both when explicitly instructed to rewrite text to be more or less persuasive and when only instructed to paraphrase. We construct the new dataset Persuasive-Pairs of pairs of a short text and its rewrite by an LLM to amplify or diminish persuasive language. We multi-annotate the pairs on a relative scale for persuasive language: a valuable resource in itself, and for training a regression model to score and benchmark persuasive language, including for new LLMs across domains. In our analysis, we find that different 'personas' in LLaMA3's system prompt change persuasive language substantially, even when only instructed to paraphrase.
Authors: Yan Chen, Tao Li
Abstract: We study the distributed optimization problem over a graphon with a continuum of nodes, which is regarded as the limit of the distributed networked optimization as the number of nodes goes to infinity. Each node has a private local cost function. The global cost function, which all nodes cooperatively minimize, is the integral of the local cost functions on the node set. We propose stochastic gradient descent and gradient tracking algorithms over the graphon. We establish a general lemma for the upper bound estimation related to a class of time-varying differential inequalities with negative linear terms, based upon which, we prove that for both kinds of algorithms, the second moments of the nodes' states are uniformly bounded. Especially, for the stochastic gradient tracking algorithm, we transform the convergence analysis into the asymptotic property of coupled nonlinear differential inequalities with time-varying coefficients and develop a decoupling method. For both kinds of algorithms, we show that by choosing the time-varying algorithm gains properly, all nodes' states achieve $\mathcal{L}^{\infty}$-consensus for a connected graphon. Furthermore, if the local cost functions are strongly convex, then all nodes' states converge to the minimizer of the global cost function and the auxiliary states in the stochastic gradient tracking algorithm converge to the gradient value of the global cost function at the minimizer uniformly in mean square.
Authors: Alex Kim, Maximilian Muhn, Valeri Nikolaev
Abstract: We investigate whether large language models (LLMs) can successfully perform financial statement analysis in a way similar to a professional human analyst. We provide standardized and anonymous financial statements to GPT4 and instruct the model to analyze them to determine the direction of firms' future earnings. Even without narrative or industry-specific information, the LLM outperforms financial analysts in its ability to predict earnings changes directionally. The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle. Furthermore, we find that the prediction accuracy of the LLM is on par with a narrowly trained state-of-the-art ML model. LLM prediction does not stem from its training memory. Instead, we find that the LLM generates useful narrative insights about a company's future performance. Lastly, our trading strategies based on GPT's predictions yield a higher Sharpe ratio and alphas than strategies based on other models. Our results suggest that LLMs may take a central role in analysis and decision-making.
Authors: Yuan Tian, Tianyi Zhang
Abstract: Recent advances in large language models (LLMs) have transformed software development by automatically generating code from natural language. Yet challenges remain in generating fully correct code that aligns with user intent. Our study reveals that LLMs tend to pay less attention to user prompts as more code tokens are generated. We hypothesize that this attention dilution issue is an important reason for code generation errors. To mitigate this issue, we propose Selective Prompt Anchoring (SPA) to guide code LLMs to pay more attention to user intent when generating code. We evaluate SPA using six base LLMs across six benchmarks. Our results demonstrate that SPA enhances Pass@1 by up to 12.9%, consistently outperforming SOTA code generation methods in all settings. Our code is available at https://github.com/magic-YuanTian/Selective-Prompt-Anchoring.
URLs: https://github.com/magic-YuanTian/Selective-Prompt-Anchoring.
Authors: Chenglong Wang, Bongshin Lee, Steven Drucker, Dan Marshall, Jianfeng Gao
Abstract: Data analysts often need to iterate between data transformations and chart designs to create rich visualizations for exploratory data analysis. Although many AI-powered systems have been introduced to reduce the effort of visualization authoring, existing systems are not well suited for iterative authoring. They typically require analysts to provide, in a single turn, a text-only prompt that fully describe a complex visualization. We introduce Data Formulator 2 (DF2 for short), an AI-powered visualization system designed to overcome this limitation. DF2 blends graphical user interfaces and natural language inputs to enable users to convey their intent more effectively, while delegating data transformation to AI. Furthermore, to support efficient iteration, DF2 lets users navigate their iteration history and reuse previous designs, eliminating the need to start from scratch each time. A user study with eight participants demonstrated that DF2 allowed participants to develop their own iteration styles to complete challenging data exploration sessions.
Authors: Markus Knauer, Alin Albu-Sch\"affer, Freek Stulp, Jo\~ao Silv\'erio
Abstract: The problem of generalization in learning from demonstration (LfD) has received considerable attention over the years, particularly within the context of movement primitives, where a number of approaches have emerged. Recently, two important approaches have gained recognition. While one leverages via-points to adapt skills locally by modulating demonstrated trajectories, another relies on so-called task-parameterized models that encode movements with respect to different coordinate systems, using a product of probabilities for generalization. While the former are well-suited to precise, local modulations, the latter aim at generalizing over large regions of the workspace and often involve multiple objects. Addressing the quality of generalization by leveraging both approaches simultaneously has received little attention. In this work, we propose an interactive imitation learning framework that simultaneously leverages local and global modulations of trajectory distributions. Building on the kernelized movement primitives (KMP) framework, we introduce novel mechanisms for skill modulation from direct human corrective feedback. Our approach particularly exploits the concept of via-points to incrementally and interactively 1) improve the model accuracy locally, 2) add new objects to the task during execution and 3) extend the skill into regions where demonstrations were not provided. We evaluate our method on a bearing ring-loading task using a torque-controlled, 7-DoF, DLR SARA robot.
Authors: Jiahao Nick Li, Zhuohao Jerry Zhang, Jiaju Ma
Abstract: People often capture memories through photos, screenshots, and videos. While existing AI-based tools enable querying this data using natural language, they only support retrieving individual pieces of information like certain objects in photos, and struggle with answering more complex queries that involve interpreting interconnected memories like sequential events. We conducted a one-month diary study to collect realistic user queries and generated a taxonomy of necessary contextual information for integrating with captured memories. We then introduce OmniQuery, a novel system that is able to answer complex personal memory-related questions that require extracting and inferring contextual information. OmniQuery augments individual captured memories through integrating scattered contextual information from multiple interconnected memories. Given a question, OmniQuery retrieves relevant augmented memories and uses a large language model (LLM) to generate answers with references. In human evaluations, we show the effectiveness of OmniQuery with an accuracy of 71.5%, outperforming a conventional RAG system by winning or tying for 74.5% of the time.
Authors: Suhyeon Yoo, Khai N. Truong, Young-Ho Kim
Abstract: d/Deaf and hearing song-signers have become prevalent across video-sharing platforms, but translating songs into sign language remains cumbersome and inaccessible. Our formative study revealed the challenges song-signers face, including semantic, syntactic, expressive, and rhythmic considerations in translations. We present ELMI, an accessible song-signing tool that assists in translating lyrics into sign language. ELMI enables users to edit glosses line-by-line, with real-time synced lyric and music video snippets. Users can also chat with a large language model-driven AI to discuss meaning, glossing, emoting, and timing. Through an exploratory study with 13 song-signers, we examined how ELMI facilitates their workflows and how song-signers leverage and receive an LLM-driven chat for translation. Participants successfully adopted ELMI to song-signing, with active discussions throughout. They also reported improved confidence and independence in their translations, finding ELMI encouraging, constructive, and informative. We discuss research and design implications for accessible and culturally sensitive song-signing translation tools.
Authors: Diego Marcos, Robert van de Vlasakker, Ioannis N. Athanasiadis, Pierre Bonnet, Herv\'e Goeau, Alexis Joly, W. Daniel Kissling, C\'esar Leblanc, Andr\'e S. J. van Proosdij, Konstantinos P. Panousis
Abstract: Plant morphological traits, their observable characteristics, are fundamental to understand the role played by each species within their ecosystem. However, compiling trait information for even a moderate number of species is a demanding task that may take experts years to accomplish. At the same time, massive amounts of information about species descriptions is available online in the form of text, although the lack of structure makes this source of data impossible to use at scale. To overcome this, we propose to leverage recent advances in large language models (LLMs) and devise a mechanism for gathering and processing information on plant traits in the form of unstructured textual descriptions, without manual curation. We evaluate our approach by automatically replicating three manually created species-trait matrices. Our method managed to find values for over half of all species-trait pairs, with an F1-score of over 75%. Our results suggest that large-scale creation of structured trait databases from unstructured online text is currently feasible thanks to the information extraction capabilities of LLMs, being limited by the availability of textual descriptions covering all the traits of interest.
Authors: Nathaniel Berger, Miriam Exel, Matthias Huck, Stefan Riezler
Abstract: Preference Optimization (PO) techniques are currently one of the state of the art techniques for fine-tuning large language models (LLMs) on pairwise preference feedback from human annotators. However, in machine translation, this sort of feedback can be difficult to solicit. Additionally, Kreutzer et al. (2018) have shown that, for machine translation, pairwise preferences are less reliable than other forms of human feedback, such as 5-point ratings. We examine post-edits to see if they can be a source of reliable human preferences by construction. In PO, a human annotator is shown sequences $s_1$ and $s_2$ and asked for a preference judgment, %$s_1 > s_2$; while for post-editing, editors create $s_1$ and know that it should be better than $s_2$. We attempt to use these implicit preferences for PO and show that it helps the model move towards post-edit-like hypotheses and away from machine translation-like hypotheses. Furthermore, we show that best results are obtained by pre-training the model with supervised fine-tuning (SFT) on post-edits in order to promote post-edit-like hypotheses to the top output ranks.
Authors: Stephanie Brandl, Oliver Eberle
Abstract: Instruction-tuned LLMs are able to provide an explanation about their output to users by generating self-explanations. These do not require gradient computations or the application of possibly complex XAI methods. In this paper, we analyse whether this ability results in a good explanation. We evaluate self-explanations in the form of input rationales with respect to their plausibility to humans as well as their faithfulness to models. We study two text classification tasks: sentiment classification and forced labour detection, i.e., identifying pre-defined risk indicators of forced labour. In addition to English, we include Danish and Italian translations of the sentiment classification task and compare self-explanations to human annotations for all samples. To allow for direct comparisons, we also compute post-hoc feature attribution, i.e., layer-wise relevance propagation (LRP) and analyse 4 LLMs. We show that self-explanations align more closely with human annotations compared to LRP, while maintaining a comparable level of faithfulness. This finding suggests that self-explanations indeed provide good explanations for text classification.
Authors: Yuhan Fu, Ruobing Xie, Jiazhen Liu, Bangxiang Lan, Xingwu Sun, Zhanhui Kang, Xirong Li
Abstract: Hallucinations in multimodal large language models (MLLMs) hinder their practical applications. To address this, we propose a Magnifier Prompt (MagPrompt), a simple yet effective method to tackle hallucinations in MLLMs via extremely simple instructions. MagPrompt is based on the following two key principles, which guide the design of various effective prompts, demonstrating robustness: (1) MLLMs should focus more on the image. (2) When there are conflicts between the image and the model's inner knowledge, MLLMs should prioritize the image. MagPrompt is training-free and can be applied to open-source and closed-source models, such as GPT-4o and Gemini-pro. It performs well across many datasets and its effectiveness is comparable or even better than more complex methods like VCD. Furthermore, our prompt design principles and experimental analyses provide valuable insights into multimodal hallucination.
Authors: Taiyi Wang, Zhihao Wu, Jianheng Liu, Jianye Hao, Jun Wang, Kun Shao
Abstract: On-device control agents, especially on mobile devices, are responsible for operating mobile devices to fulfill users' requests, enabling seamless and intuitive interactions. Integrating Multimodal Large Language Models (MLLMs) into these agents enhances their ability to understand and execute complex commands, thereby improving user experience. However, fine-tuning MLLMs for on-device control presents significant challenges due to limited data availability and inefficient online training processes. This paper introduces DistRL, a novel framework designed to enhance the efficiency of online RL fine-tuning for mobile device control agents. DistRL employs centralized training and decentralized data acquisition to ensure efficient fine-tuning in the context of dynamic online interactions. Additionally, the framework is backed by our tailor-made RL algorithm, which effectively balances exploration with the prioritized utilization of collected data to ensure stable and robust training. Our experiments show that, on average, DistRL delivers a 3X improvement in training efficiency and enables training data collection 2.4X faster than the leading synchronous multi-machine methods. Notably, after training, DistRL achieves a 20% relative improvement in success rate compared to state-of-the-art methods on general Android tasks from an open benchmark, significantly outperforming existing approaches while maintaining the same training time. These results validate DistRL as a scalable and efficient solution, offering substantial improvements in both training efficiency and agent performance for real-world, in-the-wild device control tasks.
Authors: Isamu Isozaki, Manil Shrestha, Rick Console, Edward Kim
Abstract: Hacking poses a significant threat to cybersecurity, inflicting billions of dollars in damages annually. To mitigate these risks, ethical hacking, or penetration testing, is employed to identify vulnerabilities in systems and networks. Recent advancements in large language models (LLMs) have shown potential across various domains, including cybersecurity. However, there is currently no comprehensive, open, automated, end-to-end penetration testing benchmark to drive progress and evaluate the capabilities of these models in security contexts. This paper introduces a novel open benchmark for LLM-based automated penetration testing, addressing this critical gap. We first evaluate the performance of LLMs, including GPT-4o and LLama 3.1-405B, using the state-of-the-art PentestGPT tool. Our findings reveal that while LLama 3.1 demonstrates an edge over GPT-4o, both models currently fall short of performing end-to-end penetration testing even with some minimal human assistance. Next, we advance the state-of-the-art and present ablation studies that provide insights into improving the PentestGPT tool. Our research illuminates the challenges LLMs face in each aspect of Pentesting, e.g. enumeration, exploitation, and privilege escalation. This work contributes to the growing body of knowledge on AI-assisted cybersecurity and lays the foundation for future research in automated penetration testing using large language models.
Authors: Liyu Zhang, Haochi Wu, Xu Wan, Quan Kong, Ruilong Deng, Mingyang Sun
Abstract: Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to mitigate the effects of out-of-distribution (OOD) data, which significantly limits their efficiency in exploiting online samples. To address this deficiency, we introduce a new paradigm for O2O RL called State-Action-Conditional Offline \Model Guidance (SAMG). It freezes the pre-trained offline critic to provide compact offline understanding for each state-action sample, thus eliminating the need for retraining on offline data. The frozen offline critic is incorporated with the online target critic weighted by a state-action-adaptive coefficient. This coefficient aims to capture the offline degree of samples at the state-action level, and is updated adaptively during training. In practice, SAMG could be easily integrated with Q-function-based algorithms. Theoretical analysis shows good optimality and lower estimation error. Empirically, SAMG outperforms state-of-the-art O2O RL algorithms on the D4RL benchmark.
Authors: Suchir Salhan, Richard Diehl Martinez, Z\'ebulon Goriely, Paula Buttery
Abstract: Curriculum Learning has been a popular strategy to improve the cognitive plausibility of Small-Scale Language Models (SSLMs) in the BabyLM Challenge. However, it has not led to considerable improvements over non-curriculum models. We assess whether theoretical linguistic acquisition theories can be used to specify more fine-grained curriculum learning strategies, creating age-ordered corpora of Child-Directed Speech for four typologically distant language families to implement SSLMs and acquisition-inspired curricula cross-lingually. Comparing the success of three objective curricula (Growing, Inwards and MMM) that precisely replicate the predictions of acquisition theories on a standard SSLM architecture, we find fine-grained acquisition-inspired curricula can outperform non-curriculum baselines and performance benefits of curricula strategies in SSLMs can be derived by specifying fine-grained language-specific curricula that precisely replicate language acquisition theories.
Authors: Alireza Mohamadi, Hosna Ghahramani, Seyyed Amir Asghari, Mehdi Aminian
Abstract: The increasing integration of the Internet of Medical Things (IoMT) into healthcare systems has significantly enhanced patient care but has also introduced critical cybersecurity challenges. This paper presents a novel approach based on Convolutional Neural Networks (CNNs) for detecting cyberattacks within IoMT environments. Unlike previous studies that predominantly utilized traditional machine learning (ML) models or simpler Deep Neural Networks (DNNs), the proposed model leverages the capabilities of CNNs to effectively analyze the temporal characteristics of network traffic data. Trained and evaluated on the CICIoMT2024 dataset, which comprises 18 distinct types of cyberattacks across a range of IoMT devices, the proposed CNN model demonstrates superior performance compared to previous state-of-the-art methods, achieving a perfect accuracy of 99% in binary, categorical, and multiclass classification tasks. This performance surpasses that of conventional ML models such as Logistic Regression, AdaBoost, DNNs, and Random Forests. These findings highlight the potential of CNNs to substantially improve IoMT cybersecurity, thereby ensuring the protection and integrity of connected healthcare systems.
Authors: Christopher Richardson, Roshan Sharma, Neeraj Gaur, Parisa Haghani, Anirudh Sundar, Bhuvana Ramabhadran
Abstract: Zero-shot domain adaptation for dialogue state tracking (DST) remains a challenging problem in task-oriented dialogue (TOD) systems, where models must generalize to target domains unseen at training time. Current large language model approaches for zero-shot domain adaptation rely on prompting to introduce knowledge pertaining to the target domains. However, their efficacy strongly depends on prompt engineering, as well as the zero-shot ability of the underlying language model. In this work, we devise a novel data augmentation approach, Schema Augmentation, that improves the zero-shot domain adaptation of language models through fine-tuning. Schema Augmentation is a simple but effective technique that enhances generalization by introducing variations of slot names within the schema provided in the prompt. Experiments on MultiWOZ and SpokenWOZ showed that the proposed approach resulted in a substantial improvement over the baseline, in some experiments achieving over a twofold accuracy gain over unseen domains while maintaining equal or superior performance over all domains.
Authors: Yiwen Ding, Zhiheng Xi, Wei He, Zhuoyuan Li, Yitao Zhai, Xiaowei Shi, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang
Abstract: Self-improvement methods enable large language models (LLMs) to generate solutions themselves and iteratively train on filtered, high-quality rationales. This process proves effective and reduces the reliance on human supervision in LLMs' reasoning, but the performance soon plateaus. We delve into the process and find that models tend to over-sample on easy queries and under-sample on queries they have yet to master. As iterations proceed, this imbalance in sampling is exacerbated, leading to a long-tail distribution where solutions to difficult queries almost diminish. This phenomenon limits the performance gain of self-improving models. A straightforward solution is brute-force sampling to balance the distribution, which significantly raises computational costs. In this paper, we introduce Guided Self-Improvement (GSI), a strategy aimed at improving the efficiency of sampling challenging heavy-tailed data. It leverages Socratic-style guidance signals to help LLM reasoning with complex queries, reducing the exploration effort and minimizing computational overhead. Experiments on four models across diverse mathematical tasks show that GSI strikes a balance between performance and efficiency, while also being effective on held-out tasks.
Authors: Hyukhun Koh, Minha Jhang, Dohyung Kim, Sangmook Lee, Kyomin Jung
Abstract: Although auto-regressive models excel in natural language processing, they often struggle to generate diverse text and provide limited controllability. Non-auto-regressive methods could be an alternative but often produce degenerate outputs and exhibit shortcomings in conditional generation. To address these challenges, we propose Diffusion-EAGS, a novel framework that integrates conditional masked language models into diffusion language models through the theoretical lens of a conditional Markov Random Field. In doing so, we propose entropy-adaptive Gibbs sampling and entropy-based noise scheduling to counterbalance each model's shortcomings. Experimental results show that Diffusion-EAGS outperforms baselines and achieves the best quality-diversity tradeoff, demonstrating its effectiveness in non-autoregressive text generation.
Authors: Yifei Jin, Ali Maatouk, Sarunas Girdzijauskas, Shugong Xu, Leandros Tassiulas, Rex Ying
Abstract: Wireless ray-tracing (RT) is emerging as a key tool for three-dimensional (3D) wireless channel modeling, driven by advances in graphical rendering. Current approaches struggle to accurately model beyond 5G (B5G) network signaling, which often operates at higher frequencies and is more susceptible to environmental conditions and changes. Existing online learning solutions require real-time environmental supervision during training, which is both costly and incompatible with GPU-based processing. In response, we propose a novel approach that redefines ray trajectory generation as a sequential decision-making problem, leveraging generative models to jointly learn the optical, physical, and signal properties within each designated environment. Our work introduces the Scene-Aware Neural Decision Wireless Channel Raytracing Hierarchy (SANDWICH), an innovative offline, fully differentiable approach that can be trained entirely on GPUs. SANDWICH offers superior performance compared to existing online learning methods, outperforms the baseline by 4e^-2 radian in RT accuracy, and only fades 0.5 dB away from toplined channel gain estimation.
Authors: Aladin Djuhera, Vlad C. Andrei, Mohsen Pourghasemian, Haris Gacanin, Holger Boche, Walid Saad
Abstract: Multi-task large language models (MTLLMs) are important for many applications at the wireless edge, where users demand specialized models to handle multiple tasks efficiently. However, training MTLLMs is complex and exhaustive, particularly when tasks are subject to change. Recently, the concept of model fusion via task vectors has emerged as an efficient approach for combining fine-tuning parameters to produce an MTLLM. In this paper, the problem of enabling edge users to collaboratively craft such MTLMs via tasks vectors is studied, under the assumption of worst-case adversarial attacks. To this end, first the influence of adversarial noise to multi-task model fusion is investigated and a relationship between the so-called weight disentanglement error and the mean squared error (MSE) is derived. Using hypothesis testing, it is directly shown that the MSE increases interference between task vectors, thereby rendering model fusion ineffective. Then, a novel resilient MTLLM fusion (R-MTLLMF) is proposed, which leverages insights about the LLM architecture and fine-tuning process to safeguard task vector aggregation under adversarial noise by realigning the MTLLM. The proposed R-MTLLMF is then compared for both worst-case and ideal transmission scenarios to study the impact of the wireless channel. Extensive model fusion experiments with vision LLMs demonstrate R-MTLLMF's effectiveness, achieving close-to-baseline performance across eight different tasks in ideal noise scenarios and significantly outperforming unprotected model fusion in worst-case scenarios. The results further advocate for additional physical layer protection for a holistic approach to resilience, from both a wireless and LLM perspective.
Authors: Taneesh Gupta, Rahul Madhavan, Xuchao Zhang, Chetan Bansal, Saravan Rajmohan
Abstract: Direct Preference Optimization (DPO) has proven effective in aligning large language models with human preferences but is often constrained to pairwise comparisons -- overlooking additional positive and negative responses that are commonly available in real-world settings. We propose Simultaneous Weighted Preference Optimization (SWEPO), which incorporates multiple responses per query and prioritizes those that deviate most from the average reward. This deviation-based weighting focuses training on the most informative outliers, akin to a built-in curriculum. Theoretically, we prove that such multi-preference sampling lowers alignment bias, bounding the expected deviation from the true acceptable-response distribution at a rate of $\mathcal{O}(\tfrac{1}{\sqrt{k}})$. Empirically, SWEPO outperforms state-of-the-art baselines on the Ultra-Feedback dataset and demonstrates substantial improvements over DPO and InfoNCA, yielding boosts of up to $\sim 4$% on length-controlled win-rate on AlpacaEval.
Authors: Ryota Nonomura, Hiroki Mori
Abstract: Multi-agent systems utilizing large language models (LLMs) have shown great promise in achieving natural dialogue. However, smooth dialogue control and autonomous decision making among agents still remain challenges. In this study, we focus on conversational norms such as adjacency pairs and turn-taking found in conversation analysis and propose a new framework called "Murder Mystery Agents" that applies these norms to AI agents' dialogue control. As an evaluation target, we employed the "Murder Mystery" game, a reasoning-type table-top role-playing game that requires complex social reasoning and information manipulation. In this game, players need to unravel the truth of the case based on fragmentary information through cooperation and bargaining. The proposed framework integrates next speaker selection based on adjacency pairs and a self-selection mechanism that takes agents' internal states into account to achieve more natural and strategic dialogue. To verify the effectiveness of this new approach, we analyzed utterances that led to dialogue breakdowns and conducted automatic evaluation using LLMs, as well as human evaluation using evaluation criteria developed for the Murder Mystery game. Experimental results showed that the implementation of the next speaker selection mechanism significantly reduced dialogue breakdowns and improved the ability of agents to share information and perform logical reasoning. The results of this study demonstrate that the systematics of turn-taking in human conversation are also effective in controlling dialogue among AI agents, and provide design guidelines for more advanced multi-agent dialogue systems.
Authors: Pusen Dong, Tianchen Zhu, Yue Qiu, Haoyi Zhou, Jianxin Li
Abstract: Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints. Giving constraints in natural language form has great potential for practical scenarios due to its flexible transfer capability and accessibility. Previous safe RL methods with natural language constraints typically need to design cost functions manually for each constraint, which requires domain expertise and lacks flexibility. In this paper, we harness the dual role of text in this task, using it not only to provide constraint but also as a training signal. We introduce the Trajectory-level Textual Constraints Translator (TTCT) to replace the manually designed cost function. Our empirical results demonstrate that TTCT effectively comprehends textual constraint and trajectory, and the policies trained by TTCT can achieve a lower violation rate than the standard cost function. Extra studies are conducted to demonstrate that the TTCT has zero-shot transfer capability to adapt to constraint-shift environments.
Authors: Xiaoran Xu, Jiangang Yang, Wenhui Shi, Siyuan Ding, Luqing Luo, Jian Liu
Abstract: Single-Domain Generalized Object Detection~(S-DGOD) aims to train on a single source domain for robust performance across a variety of unseen target domains by taking advantage of an object detector. Existing S-DGOD approaches often rely on data augmentation strategies, including a composition of visual transformations, to enhance the detector's generalization ability. However, the absence of real-world prior knowledge hinders data augmentation from contributing to the diversity of training data distributions. To address this issue, we propose PhysAug, a novel physical model-based non-ideal imaging condition data augmentation method, to enhance the adaptability of the S-DGOD tasks. Drawing upon the principles of atmospheric optics, we develop a universal perturbation model that serves as the foundation for our proposed PhysAug. Given that visual perturbations typically arise from the interaction of light with atmospheric particles, the image frequency spectrum is harnessed to simulate real-world variations during training. This approach fosters the detector to learn domain-invariant representations, thereby enhancing its ability to generalize across various settings. Without altering the network architecture or loss function, our approach significantly outperforms the state-of-the-art across various S-DGOD datasets. In particular, it achieves a substantial improvement of $7.3\%$ and $7.2\%$ over the baseline on DWD and Cityscape-C, highlighting its enhanced generalizability in real-world settings.
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 often require to maintain optimizer states throughout training, which can result in memory requirements several times greater than the model footprint. This overhead imposes constraints on scalability and computational efficiency. Stochastic Gradient Descent (SGD), in contrast, is a stateless optimizer, as it does not track state variables during training. Consequently, it achieves optimal memory efficiency. However, its capability in LLM training is limited (Zhao et al., 2024b). In this work, we show that pre-processing SGD in a stateless manner can achieve the same performance as the Adam optimizer for LLM training, while drastically reducing the memory cost. Specifically, we propose to pre-process the instantaneous stochastic gradients using normalization and whitening. We show that normalization stabilizes gradient distributions, and whitening counteracts the local curvature of the loss landscape. This results in SWAN (SGD with Whitening And Normalization), a stochastic optimizer that eliminates the need to store any optimizer states. 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 comparable or even better performance than Adam: when pre-training the LLaMA model with 350M and 1.3B parameters, SWAN achieves a 2x speedup by reaching the same evaluation perplexity using half as many tokens.
Authors: Zijie Chen, Zhanchao Zhou, Yu Lu, Renjun Xu, Lili Pan, Zhenzhong Lan
Abstract: Solving NP-hard problems traditionally relies on heuristics, yet manually designing effective heuristics for complex problems remains a significant challenge. While recent advancements like FunSearch have shown that large language models (LLMs) can be integrated into evolutionary algorithms (EAs) for heuristic design, their potential is hindered by limitations in balancing exploitation and exploration. We introduce Quality-Uncertainty Balanced Evolution (QUBE), a novel approach that enhances LLM+EA methods by redefining the priority criterion within the FunSearch framework. QUBE employs the Quality-Uncertainty Trade-off Criterion (QUTC), based on our proposed Uncertainty-Inclusive Quality metric, to evaluate and guide the evolutionary process. Through extensive experiments on challenging NP-complete problems, QUBE demonstrates significant performance improvements over FunSearch and baseline methods. Our code are available at https://github.com/zzjchen/QUBE_code.
Authors: KuanChao Chu, Yi-Pei Chen, Hideki Nakayama
Abstract: Controlling diversity in LLM-agent world simulations is essential for maintaining stability in structured tasks while enabling variation where creativity is needed. However, we observe that dialogue diversity declines significantly over long-term simulation. To investigate the role of prompt design in conversational diversity, we modularized the utterance generation prompt and found that reducing the given information leads to more diverse outputs. Based on this insight, we propose Adaptive Prompt Pruning (APP), a novel method that allows users to control diversity through a single parameter, lambda. APP dynamically prunes the utterance generation prompt based on their attention weights and is compatible with traditional diversity control techniques. We demonstrate that APP effectively controls output diversity through extensive experiments, and propose a method to balance the control trade-offs. Additionally, we provide an in-depth analysis to offer insights into optimizing diversity control in multi-agent simulation.
Authors: Mayi Xu, Yunfeng Ning, Yongqi Li, Jianhao Chen, Jintao Wen, Yao Xiao, Shen Zhou, Birong Pan, Zepeng Bao, Xin Miao, Hankun Kang, Ke Sun, Tieyun Qian
Abstract: Reasoning is fundamental to human intelligence, and critical for problem-solving, decision-making, and critical thinking. Reasoning refers to drawing new conclusions based on existing knowledge, which can support various applications like clinical diagnosis, basic education, and financial analysis. Though a good number of surveys have been proposed for reviewing reasoning-related methods, none of them has systematically investigated these methods from the viewpoint of their dependent knowledge base. Both the scenarios to which the knowledge bases are applied and their storage formats are significantly different. Hence, investigating reasoning methods from the knowledge base perspective helps us better understand the challenges and future directions. To fill this gap, this paper first classifies the knowledge base into symbolic and parametric ones. The former explicitly stores information in human-readable symbols, and the latter implicitly encodes knowledge within parameters. Then, we provide a comprehensive overview of reasoning methods using symbolic knowledge bases, parametric knowledge bases, and both of them. Finally, we identify the future direction toward enhancing reasoning capabilities to bridge the gap between human and machine intelligence.
Authors: Christian Rahe, Walid Maalej
Abstract: Programming students have a widespread access to powerful Generative AI tools like ChatGPT. While this can help understand the learning material and assist with exercises, educators are voicing more and more concerns about an overreliance on generated outputs and lack of critical thinking skills. It is thus important to understand how students actually use generative AI and what impact this could have on their learning behavior. To this end, we conducted a study including an exploratory experiment with 37 programming students, giving them monitored access to ChatGPT while solving a code authoring exercise. The task was not directly solvable by ChatGPT and required code comprehension and reasoning. While only 23 of the students actually opted to use the chatbot, the majority of those eventually prompted it to simply generate a full solution. We observed two prevalent usage strategies: to seek knowledge about general concepts and to directly generate solutions. Instead of using the bot to comprehend the code and their own mistakes, students often got trapped in a vicious cycle of submitting wrong generated code and then asking the bot for a fix. Those who self-reported using generative AI regularly were more likely to prompt the bot to generate a solution. Our findings indicate that concerns about potential decrease in programmers' agency and productivity with Generative AI are justified. We discuss how researchers and educators can respond to the potential risk of students uncritically over-relying on Generative AI. We also discuss potential modifications to our study design for large-scale replications.
Authors: Santhosh Thottingal
Abstract: This paper introduces an approach to question answering over knowledge bases like Wikipedia and Wikidata by performing "question-to-question" matching and retrieval from a dense vector embedding store. Instead of embedding document content, we generate a comprehensive set of questions for each logical content unit using an instruction-tuned LLM. These questions are vector-embedded and stored, mapping to the corresponding content. Vector embedding of user queries are then matched against this question vector store. The highest similarity score leads to direct retrieval of the associated article content, eliminating the need for answer generation. Our method achieves high cosine similarity ( > 0.9 ) for relevant question pairs, enabling highly precise retrieval. This approach offers several advantages including computational efficiency, rapid response times, and increased scalability. We demonstrate its effectiveness on Wikipedia and Wikidata, including multimedia content through structured fact retrieval from Wikidata, opening up new pathways for multimodal question answering.
Authors: Long Phan (Michael Pokorny), Alice Gatti (Michael Pokorny), Ziwen Han (Michael Pokorny), Nathaniel Li (Michael Pokorny), Josephina Hu (Michael Pokorny), Hugh Zhang (Michael Pokorny), Chen Bo Calvin Zhang (Michael Pokorny), Mohamed Shaaban (Michael Pokorny), John Ling (Michael Pokorny), Sean Shi (Michael Pokorny), Michael Choi (Michael Pokorny), Anish Agrawal (Michael Pokorny), Arnav Chopra (Michael Pokorny), Adam Khoja (Michael Pokorny), Ryan Kim (Michael Pokorny), Richard Ren (Michael Pokorny), Jason Hausenloy (Michael Pokorny), Oliver Zhang (Michael Pokorny), Mantas Mazeika (Michael Pokorny), Tung Nguyen (Michael Pokorny), Daron Anderson (Michael Pokorny), Imad Ali Shah (Michael Pokorny), Mikhail Doroshenko (Michael Pokorny), Alun Cennyth Stokes (Michael Pokorny), Mobeen Mahmood (Michael Pokorny), Jaeho Lee (Michael Pokorny), Oleksandr Pokutnyi (Michael Pokorny), Oleg Iskra (Michael Pokorny), Jessica P. Wang (Michael Pokorny), Robert Gerbicz (Michael Pokorny), John-Clark Levin (Michael Pokorny), Serguei Popov (Michael Pokorny), Fiona Feng (Michael Pokorny), Steven Y. Feng (Michael Pokorny), Haoran Zhao (Michael Pokorny), Michael Yu (Michael Pokorny), Varun Gangal (Michael Pokorny), Chelsea Zou (Michael Pokorny), Zihan Wang (Michael Pokorny), Mstyslav Kazakov (Michael Pokorny), Geoff Galgon (Michael Pokorny), Johannes Schmitt (Michael Pokorny), Alvaro Sanchez (Michael Pokorny), Yongki Lee (Michael Pokorny), Will Yeadon (Michael Pokorny), Scott Sauers (Michael Pokorny), Marc Roth (Michael Pokorny), Chidozie Agu (Michael Pokorny), S{\o}ren Riis (Michael Pokorny), Fabian Giska (Michael Pokorny), Saiteja Utpala (Michael Pokorny), Antrell Cheatom (Michael Pokorny), Zachary Giboney (Michael Pokorny), Gashaw M. Goshu (Michael Pokorny), Sarah-Jane Crowson (Michael Pokorny), Mohinder Maheshbhai Naiya (Michael Pokorny), Noah Burns (Michael Pokorny), Lennart Finke (Michael Pokorny), Zerui Cheng (Michael Pokorny), Hyunwoo Park (Michael Pokorny), Francesco Fournier-Facio (Michael Pokorny), Jennifer Zampese (Michael Pokorny), John B. Wydallis (Michael Pokorny), Ryan G. Hoerr (Michael Pokorny), Mark Nandor (Michael Pokorny), Tim Gehrunger (Michael Pokorny), Jiaqi Cai (Michael Pokorny), Ben McCarty (Michael Pokorny), Jungbae Nam (Michael Pokorny), Edwin Taylor (Michael Pokorny), Jun Jin (Michael Pokorny), Gautier Abou Loume (Michael Pokorny), Hangrui Cao (Michael Pokorny), Alexis C Garretson (Michael Pokorny), Damien Sileo (Michael Pokorny), Qiuyu Ren (Michael Pokorny), Doru Cojoc (Michael Pokorny), Pavel Arkhipov (Michael Pokorny), Usman Qazi (Michael Pokorny), Aras Bacho (Michael Pokorny), Lianghui Li (Michael Pokorny), Sumeet Motwani (Michael Pokorny), Christian Schroeder de Witt (Michael Pokorny), Alexei Kopylov (Michael Pokorny), Johannes Veith (Michael Pokorny), Eric Singer (Michael Pokorny), Paolo Rissone (Michael Pokorny), Jaehyeok Jin (Michael Pokorny), Jack Wei Lun Shi (Michael Pokorny), Chris G. Willcocks (Michael Pokorny), Ameya Prabhu (Michael Pokorny), Longke Tang (Michael Pokorny), Kevin Zhou (Michael Pokorny), Emily de Oliveira Santos (Michael Pokorny), Andrey Pupasov Maksimov (Michael Pokorny), Edward Vendrow (Michael Pokorny), Kengo Zenitani (Michael Pokorny), Joshua Robinson (Michael Pokorny), Aleksandar Mikov (Michael Pokorny), Julien Guillod (Michael Pokorny), Yuqi Li (Michael Pokorny), Ben Pageler (Michael Pokorny), Joshua Vendrow (Michael Pokorny), Vladyslav Kuchkin (Michael Pokorny), Pierre Marion (Michael Pokorny), Denis Efremov (Michael Pokorny), Jayson Lynch (Michael Pokorny), Kaiqu Liang (Michael Pokorny), Andrew Gritsevskiy (Michael Pokorny), Dakotah Martinez (Michael Pokorny), Nick Crispino (Michael Pokorny), Dimitri Zvonkine (Michael Pokorny), Natanael Wildner Fraga (Michael Pokorny), Saeed Soori (Michael Pokorny), Ori Press (Michael Pokorny), Henry Tang (Michael Pokorny), Julian Salazar (Michael Pokorny), Sean R. Green (Michael Pokorny), Lina Br\"ussel (Michael Pokorny), Moon Twayana (Michael Pokorny), Aymeric Dieuleveut (Michael Pokorny), T. Ryan Rogers (Michael Pokorny), Wenjin Zhang (Michael Pokorny), Ross Finocchio (Michael Pokorny), Bikun Li (Michael Pokorny), Jinzhou Yang (Michael Pokorny), Arun Rao (Michael Pokorny), Gabriel Loiseau (Michael Pokorny), Mikhail Kalinin (Michael Pokorny), Marco Lukas (Michael Pokorny), Ciprian Manolescu (Michael Pokorny), Nate Stambaugh (Michael Pokorny), Subrata Mishra (Michael Pokorny), Ariel Ghislain Kemogne Kamdoum (Michael Pokorny), Tad Hogg (Michael Pokorny), Alvin Jin (Michael Pokorny), Carlo Bosio (Michael Pokorny), Gongbo Sun (Michael Pokorny), Brian P Coppola (Michael Pokorny), Haline Heidinger (Michael Pokorny), Rafael Sayous (Michael Pokorny), Stefan Ivanov (Michael Pokorny), Joseph M Cavanagh (Michael Pokorny), Jiawei Shen (Michael Pokorny), Joseph Marvin Imperial (Michael Pokorny), Philippe Schwaller (Michael Pokorny), Shaipranesh Senthilkuma (Michael Pokorny), Andres M Bran (Michael Pokorny), Andres Algaba (Michael Pokorny), Brecht Verbeken (Michael Pokorny), Kelsey Van den Houte (Michael Pokorny), Lynn Van Der Sypt (Michael Pokorny), David Noever (Michael Pokorny), Lisa Schut (Michael Pokorny), Ilia Sucholutsky (Michael Pokorny), Evgenii Zheltonozhskii (Michael Pokorny), Qiaochu Yuan (Michael Pokorny), Derek Lim (Michael Pokorny), Richard Stanley (Michael Pokorny), Shankar Sivarajan (Michael Pokorny), Tong Yang (Michael Pokorny), John Maar (Michael Pokorny), Julian Wykowski (Michael Pokorny), Mart\'i Oller (Michael Pokorny), Jennifer Sandlin (Michael Pokorny), Anmol Sahu (Michael Pokorny), Cesare Giulio Ardito (Michael Pokorny), Yuzheng Hu (Michael Pokorny), Felipe Meneguitti Dias (Michael Pokorny), Tobias Kreiman (Michael Pokorny), Kaivalya Rawal (Michael Pokorny), Tobias Garcia Vilchis (Michael Pokorny), Yuexuan Zu (Michael Pokorny), Martin Lackner (Michael Pokorny), James Koppel (Michael Pokorny), Jeremy Nguyen (Michael Pokorny), Daniil S. Antonenko (Michael Pokorny), Steffi Chern (Michael Pokorny), Bingchen Zhao (Michael Pokorny), Pierrot Arsene (Michael Pokorny), Sergey Ivanov (Michael Pokorny), Rafa{\l} Po\'swiata (Michael Pokorny), Chenguang Wang (Michael Pokorny), Daofeng Li (Michael Pokorny), Donato Crisostomi (Michael Pokorny), Ali Dehghan (Michael Pokorny), Andrea Achilleos (Michael Pokorny), John Arnold Ambay (Michael Pokorny), Benjamin Myklebust (Michael Pokorny), Archan Sen (Michael Pokorny), David Perrella (Michael Pokorny), Nurdin Kaparov (Michael Pokorny), Mark H Inlow (Michael Pokorny), Allen Zang (Michael Pokorny), Kalyan Ramakrishnan (Michael Pokorny), Daniil Orel (Michael Pokorny), Vladislav Poritski (Michael Pokorny), Shalev Ben-David (Michael Pokorny), Zachary Berger (Michael Pokorny), Parker Whitfill (Michael Pokorny), Michael Foster (Michael Pokorny), Daniel Munro (Michael Pokorny), Linh Ho (Michael Pokorny), Dan Bar Hava (Michael Pokorny), Aleksey Kuchkin (Michael Pokorny), Robert Lauff (Michael Pokorny), David Holmes (Michael Pokorny), Frank Sommerhage (Michael Pokorny), Anji Zhang (Michael Pokorny), Richard Moat (Michael Pokorny), Keith Schneider (Michael Pokorny), Daniel Pyda (Michael Pokorny), Zakayo Kazibwe (Michael Pokorny), Mukhwinder Singh (Michael Pokorny), Don Clarke (Michael Pokorny), Dae Hyun Kim (Michael Pokorny), Sara Fish (Michael Pokorny), Veit Elser (Michael Pokorny), Victor Efren Guadarrama Vilchis (Michael Pokorny), Immo Klose (Michael Pokorny), Christoph Demian (Michael Pokorny), Ujjwala Anantheswaran (Michael Pokorny), Adam Zweiger (Michael Pokorny), Guglielmo Albani (Michael Pokorny), Jeffery Li (Michael Pokorny), Nicolas Daans (Michael Pokorny), Maksim Radionov (Michael Pokorny), V\'aclav Rozho\v{n} (Michael Pokorny), Vincent Ginis (Michael Pokorny), Ziqiao Ma (Michael Pokorny), Christian Stump (Michael Pokorny), Jacob Platnick (Michael Pokorny), Volodymyr Nevirkovets (Michael Pokorny), Luke Basler (Michael Pokorny), Marco Piccardo (Michael Pokorny), Niv Cohen (Michael Pokorny), Virendra Singh (Michael Pokorny), Josef Tkadlec (Michael Pokorny), Paul Rosu (Michael Pokorny), Alan Goldfarb (Michael Pokorny), Piotr Padlewski (Michael Pokorny), Stanislaw Barzowski (Michael Pokorny), Kyle Montgomery (Michael Pokorny), Aline Menezes (Michael Pokorny), Arkil Patel (Michael Pokorny), Zixuan Wang (Michael Pokorny), Jamie Tucker-Foltz (Michael Pokorny), Jack Stade (Michael Pokorny), Declan Grabb (Michael Pokorny), Tom Goertzen (Michael Pokorny), Fereshteh Kazemi (Michael Pokorny), Jeremiah Milbauer (Michael Pokorny), Abhishek Shukla (Michael Pokorny), Hossam Elgnainy (Michael Pokorny), Yan Carlos Leyva Labrador (Michael Pokorny), Hao He (Michael Pokorny), Ling Zhang (Michael Pokorny), Alan Givr\'e (Michael Pokorny), Hew Wolff (Michael Pokorny), G\"ozdenur Demir (Michael Pokorny), Muhammad Fayez Aziz (Michael Pokorny), Younesse Kaddar (Michael Pokorny), Ivar \"Angquist (Michael Pokorny), Yanxu Chen (Michael Pokorny), Elliott Thornley (Michael Pokorny), Robin Zhang (Michael Pokorny), Jiayi Pan (Michael Pokorny), Antonio Terpin (Michael Pokorny), Niklas Muennighoff (Michael Pokorny), Hailey Schoelkopf (Michael Pokorny), Eric Zheng (Michael Pokorny), Avishy Carmi (Michael Pokorny), Jainam Shah (Michael Pokorny), Ethan D. L. Brown (Michael Pokorny), Kelin Zhu (Michael Pokorny), Max Bartolo (Michael Pokorny), Richard Wheeler (Michael Pokorny), Andrew Ho (Michael Pokorny), Shaul Barkan (Michael Pokorny), Jiaqi Wang (Michael Pokorny), Martin Stehberger (Michael Pokorny), Egor Kretov (Michael Pokorny), Peter Bradshaw (Michael Pokorny), JP Heimonen (Michael Pokorny), Kaustubh Sridhar (Michael Pokorny), Zaki Hossain (Michael Pokorny), Ido Akov (Michael Pokorny), Yury Makarychev (Michael Pokorny), Joanna Tam (Michael Pokorny), Hieu Hoang (Michael Pokorny), David M. Cunningham (Michael Pokorny), Vladimir Goryachev (Michael Pokorny), Demosthenes Patramanis (Michael Pokorny), Michael Krause (Michael Pokorny), Andrew Redenti (Michael Pokorny), David Aldous (Michael Pokorny), Jesyin Lai (Michael Pokorny), Shannon Coleman (Michael Pokorny), Jiangnan Xu (Michael Pokorny), Sangwon Lee (Michael Pokorny), Ilias Magoulas (Michael Pokorny), Sandy Zhao (Michael Pokorny), Ning Tang (Michael Pokorny), Michael K. Cohen (Michael Pokorny), Micah Carroll (Michael Pokorny), Orr Paradise (Michael Pokorny), Jan Hendrik Kirchner (Michael Pokorny), Stefan Steinerberger (Michael Pokorny), Maksym Ovchynnikov (Michael Pokorny), Jason O. Matos (Michael Pokorny), Adithya Shenoy (Michael Pokorny), Michael Wang (Michael Pokorny), Yuzhou Nie (Michael Pokorny), Paolo Giordano (Michael Pokorny), Philipp Petersen (Michael Pokorny), Anna Sztyber-Betley (Michael Pokorny), Paolo Faraboschi (Michael Pokorny), Robin Riblet (Michael Pokorny), Jonathan Crozier (Michael Pokorny), Shiv Halasyamani (Michael Pokorny), Antonella Pinto (Michael Pokorny), Shreyas Verma (Michael Pokorny), Prashant Joshi (Michael Pokorny), Eli Meril (Michael Pokorny), Zheng-Xin Yong (Michael Pokorny), Allison Tee (Michael Pokorny), J\'er\'emy Andr\'eoletti (Michael Pokorny), Orion Weller (Michael Pokorny), Raghav Singhal (Michael Pokorny), Gang Zhang (Michael Pokorny), Alexander Ivanov (Michael Pokorny), Seri Khoury (Michael Pokorny), Nils Gustafsson (Michael Pokorny), Hamid Mostaghimi (Michael Pokorny), Kunvar Thaman (Michael Pokorny), Qijia Chen (Michael Pokorny), Tran Quoc Kh\'anh (Michael Pokorny), Jacob Loader (Michael Pokorny), Stefano Cavalleri (Michael Pokorny), Hannah Szlyk (Michael Pokorny), Zachary Brown (Michael Pokorny), Himanshu Narayan (Michael Pokorny), Jonathan Roberts (Michael Pokorny), William Alley (Michael Pokorny), Kunyang Sun (Michael Pokorny), Ryan Stendall (Michael Pokorny), Max Lamparth (Michael Pokorny), Anka Reuel (Michael Pokorny), Ting Wang (Michael Pokorny), Hanmeng Xu (Michael Pokorny), Pablo Hern\'andez-C\'amara (Michael Pokorny), Freddie Martin (Michael Pokorny), Thomas Preu (Michael Pokorny), Tomek Korbak (Michael Pokorny), Marcus Abramovitch (Michael Pokorny), Dominic Williamson (Michael Pokorny), Ida Bosio (Michael Pokorny), Ziye Chen (Michael Pokorny), Bir\'o B\'alint (Michael Pokorny), Eve J. Y. Lo (Michael Pokorny), Maria In\^es S. Nunes (Michael Pokorny), Yibo Jiang (Michael Pokorny), M Saiful Bari (Michael Pokorny), Peyman Kassani (Michael Pokorny), Zihao Wang (Michael Pokorny), Behzad Ansarinejad (Michael Pokorny), Yewen Sun (Michael Pokorny), Stephane Durand (Michael Pokorny), Guillaume Douville (Michael Pokorny), Daniel Tordera (Michael Pokorny), George Balabanian (Michael Pokorny), Earth Anderson (Michael Pokorny), Lynna Kvistad (Michael Pokorny), Alejandro Jos\'e Moyano (Michael Pokorny), Hsiaoyun Milliron (Michael Pokorny), Ahmad Sakor (Michael Pokorny), Murat Eron (Michael Pokorny), Isaac C. McAlister (Michael Pokorny), Andrew Favre D. O. (Michael Pokorny), Shailesh Shah (Michael Pokorny), Xiaoxiang Zhou (Michael Pokorny), Firuz Kamalov (Michael Pokorny), Ronald Clark (Michael Pokorny), Sherwin Abdoli (Michael Pokorny), Tim Santens (Michael Pokorny), Harrison K Wang (Michael Pokorny), Evan Chen (Michael Pokorny), Alessandro Tomasiello (Michael Pokorny), G. Bruno De Luca (Michael Pokorny), Shi-Zhuo Looi (Michael Pokorny), Vinh-Kha Le (Michael Pokorny), Noam Kolt (Michael Pokorny), Niels M\"undler (Michael Pokorny), Avi Semler (Michael Pokorny), Emma Rodman (Michael Pokorny), Jacob Drori (Michael Pokorny), Carl J Fossum (Michael Pokorny), Luk Gloor (Michael Pokorny), Milind Jagota (Michael Pokorny), Ronak Pradeep (Michael Pokorny), Honglu Fan (Michael Pokorny), Tej Shah (Michael Pokorny), Jonathan Eicher (Michael Pokorny), Michael Chen (Michael Pokorny), Kushal Thaman (Michael Pokorny), William Merrill (Michael Pokorny), Moritz Firsching (Michael Pokorny), Carter Harris (Michael Pokorny), Stefan Ciob\^ac\u{a} (Michael Pokorny), Jason Gross (Michael Pokorny), Rohan Pandey (Michael Pokorny), Ilya Gusev (Michael Pokorny), Adam Jones (Michael Pokorny), Shashank Agnihotri (Michael Pokorny), Pavel Zhelnov (Michael Pokorny), Siranut Usawasutsakorn (Michael Pokorny), Mohammadreza Mofayezi (Michael Pokorny), Alexander Piperski (Michael Pokorny), Marc Carauleanu (Michael Pokorny), David K. Zhang (Michael Pokorny), Kostiantyn Dobarskyi (Michael Pokorny), Dylan Ler (Michael Pokorny), Roman Leventov (Michael Pokorny), Ignat Soroko (Michael Pokorny), Thorben Jansen (Michael Pokorny), Scott Creighton (Michael Pokorny), Pascal Lauer (Michael Pokorny), Joshua Duersch (Michael Pokorny), Vage Taamazyan (Michael Pokorny), Dario Bezzi (Michael Pokorny), Wiktor Morak (Michael Pokorny), Wenjie Ma (Michael Pokorny), William Held (Michael Pokorny), Tran {\DJ}uc Huy (Michael Pokorny), Ruicheng Xian (Michael Pokorny), Armel Randy Zebaze (Michael Pokorny), Mohanad Mohamed (Michael Pokorny), Julian Noah Leser (Michael Pokorny), Michelle X Yuan (Michael Pokorny), Laila Yacar (Michael Pokorny), Johannes Lengler (Michael Pokorny), Katarzyna Olszewska (Michael Pokorny), Hossein Shahrtash (Michael Pokorny), Edson Oliveira (Michael Pokorny), Joseph W. Jackson (Michael Pokorny), Daniel Espinosa Gonzalez (Michael Pokorny), Andy Zou (Michael Pokorny), Muthu Chidambaram (Michael Pokorny), Timothy Manik (Michael Pokorny), Hector Haffenden (Michael Pokorny), Dashiell Stander (Michael Pokorny), Ali Dasouqi (Michael Pokorny), Alexander Shen (Michael Pokorny), Emilien Duc (Michael Pokorny), Bita Golshani (Michael Pokorny), David Stap (Michael Pokorny), Mikalai Uzhou (Michael Pokorny), Alina Borisovna Zhidkovskaya (Michael Pokorny), Lukas Lewark (Michael Pokorny), Miguel Orbegozo Rodriguez (Michael Pokorny), M\'aty\'as Vincze (Michael Pokorny), Dustin Wehr (Michael Pokorny), Colin Tang (Michael Pokorny), Shaun Phillips (Michael Pokorny), Fortuna Samuele (Michael Pokorny), Jiang Muzhen (Michael Pokorny), Fredrik Ekstr\"om (Michael Pokorny), Angela Hammon (Michael Pokorny), Oam Patel (Michael Pokorny), Faraz Farhidi (Michael Pokorny), George Medley (Michael Pokorny), Forough Mohammadzadeh (Michael Pokorny), Madellene Pe\~naflor (Michael Pokorny), Haile Kassahun (Michael Pokorny), Alena Friedrich (Michael Pokorny), Claire Sparrow (Michael Pokorny), Rayner Hernandez Perez (Michael Pokorny), Taom Sakal (Michael Pokorny), Omkar Dhamane (Michael Pokorny), Ali Khajegili Mirabadi (Michael Pokorny), Eric Hallman (Michael Pokorny), Kenchi Okutsu (Michael Pokorny), Mike Battaglia (Michael Pokorny), Mohammad Maghsoudimehrabani (Michael Pokorny), Alon Amit (Michael Pokorny), Dave Hulbert (Michael Pokorny), Roberto Pereira (Michael Pokorny), Simon Weber (Michael Pokorny), Handoko (Michael Pokorny), Anton Peristyy (Michael Pokorny), Stephen Malina (Michael Pokorny), Samuel Albanie (Michael Pokorny), Will Cai (Michael Pokorny), Mustafa Mehkary (Michael Pokorny), Rami Aly (Michael Pokorny), Frank Reidegeld (Michael Pokorny), Anna-Katharina Dick (Michael Pokorny), Cary Friday (Michael Pokorny), Jasdeep Sidhu (Michael Pokorny), Hassan Shapourian (Michael Pokorny), Wanyoung Kim (Michael Pokorny), Mariana Costa (Michael Pokorny), Hubeyb Gurdogan (Michael Pokorny), Brian Weber (Michael Pokorny), Harsh Kumar (Michael Pokorny), Tong Jiang (Michael Pokorny), Arunim Agarwal (Michael Pokorny), Chiara Ceconello (Michael Pokorny), Warren S. Vaz (Michael Pokorny), Chao Zhuang (Michael Pokorny), Haon Park (Michael Pokorny), Andrew R. Tawfeek (Michael Pokorny), Daattavya Aggarwal (Michael Pokorny), Michael Kirchhof (Michael Pokorny), Linjie Dai (Michael Pokorny), Evan Kim (Michael Pokorny), Johan Ferret (Michael Pokorny), Yuzhou Wang (Michael Pokorny), Minghao Yan (Michael Pokorny), Krzysztof Burdzy (Michael Pokorny), Lixin Zhang (Michael Pokorny), Antonio Franca (Michael Pokorny), Diana T. Pham (Michael Pokorny), Kang Yong Loh (Michael Pokorny), Joshua Robinson (Michael Pokorny), Abram Jackson (Michael Pokorny), Shreen Gul (Michael Pokorny), Gunjan Chhablani (Michael Pokorny), Zhehang Du (Michael Pokorny), Adrian Cosma (Michael Pokorny), Jesus Colino (Michael Pokorny), Colin White (Michael Pokorny), Jacob Votava (Michael Pokorny), Vladimir Vinnikov (Michael Pokorny), Ethan Delaney (Michael Pokorny), Petr Spelda (Michael Pokorny), Vit Stritecky (Michael Pokorny), Syed M. Shahid (Michael Pokorny), Jean-Christophe Mourrat (Michael Pokorny), Lavr Vetoshkin (Michael Pokorny), Koen Sponselee (Michael Pokorny), Renas Bacho (Michael Pokorny), Florencia de la Rosa (Michael Pokorny), Xiuyu Li (Michael Pokorny), Guillaume Malod (Michael Pokorny), Leon Lang (Michael Pokorny), Julien Laurendeau (Michael Pokorny), Dmitry Kazakov (Michael Pokorny), Fatimah Adesanya (Michael Pokorny), Julien Portier (Michael Pokorny), Lawrence Hollom (Michael Pokorny), Victor Souza (Michael Pokorny), Yuchen Anna Zhou (Michael Pokorny), Julien Degorre (Michael Pokorny), Yi\u{g}it Yal{\i}n (Michael Pokorny), Gbenga Daniel Obikoya (Michael Pokorny), Luca Arnaboldi (Michael Pokorny), Rai (Michael Pokorny), Filippo Bigi (Quinn), M. C. Bosc\'a (Quinn), Oleg Shumar (Quinn), Kaniuar Bacho (Quinn), Pierre Clavier (Quinn), Gabriel Recchia (Quinn), Mara Popescu (Quinn), Nikita Shulga (Quinn), Ngefor Mildred Tanwie (Quinn), Denis Peskoff (Quinn), Thomas C. H. Lux (Quinn), Ben Rank (Quinn), Colin Ni (Quinn), Matthew Brooks (Quinn), Alesia Yakimchyk (Quinn), Huanxu (Quinn), Liu (Tony), Olle H\"aggstr\"om (Tony), Emil Verkama (Tony), Hans Gundlach (Tony), Leonor Brito-Santana (Tony), Brian Amaro (Tony), Vivek Vajipey (Tony), Rynaa Grover (Tony), Yiyang Fan (Tony), Gabriel Poesia Reis e Silva (Tony), Linwei Xin (Tony), Yosi Kratish (Tony), Jakub {\L}ucki (Tony), Wen-Ding Li (Tony), Sivakanth Gopi (Tony), Andrea Caciolai (Tony), Justin Xu (Tony), Kevin Joseph Scaria (Tony), Freddie Vargus (Tony), Farzad Habibi (Tony), Long (Tony), Lian, Emanuele Rodol\`a, Jules Robins, Vincent Cheng, Tony Fruhauff, Brad Raynor, Hao Qi, Xi Jiang, Ben Segev, Jingxuan Fan, Sarah Martinson, Erik Y. Wang, Kaylie Hausknecht, Michael P. Brenner, Mao Mao, Xinyu Zhang, David Avagian, Eshawn Jessica Scipio, Alon Ragoler, Justin Tan, Blake Sims, Rebeka Plecnik, Aaron Kirtland, Omer Faruk Bodur, D. P. Shinde, Zahra Adoul, Mohamed Zekry, Ali Karakoc, Tania C. B. Santos, Samir Shamseldeen, Loukmane Karim, Anna Liakhovitskaia, Nate Resman, Nicholas Farina, Juan Carlos Gonzalez, Gabe Maayan, Sarah Hoback, Rodrigo De Oliveira Pena, Glen Sherman, Elizabeth Kelley, Hodjat Mariji, Rasoul Pouriamanesh, Wentao Wu, Sandra Mendoza, Ismail Alarab, Joshua Cole, Danyelle Ferreira, Bryan Johnson, Mohammad Safdari, Liangti Dai, Siriphan Arthornthurasuk, Alexey Pronin, Jing Fan, Angel Ramirez-Trinidad, Ashley Cartwright, Daphiny Pottmaier, Omid Taheri, David Outevsky, Stanley Stepanic, Samuel Perry, Luke Askew, Ra\'ul Adri\'an Huerta Rodr\'iguez, Ali M. R. Minissi, Sam Ali, Ricardo Lorena, Krishnamurthy Iyer, Arshad Anil Fasiludeen, Sk Md Salauddin, Murat Islam, Juan Gonzalez, Josh Ducey, Maja Somrak, Vasilios Mavroudis, Eric Vergo, Juehang Qin, Benj\'amin Borb\'as, Eric Chu, Jack Lindsey, Anil Radhakrishnan, Antoine Jallon, I. M. J. McInnis, Pawan Kumar, Laxman Prasad Goswami, Daniel Bugas, Nasser Heydari, Ferenc Jeanplong, Archimedes Apronti, Abdallah Galal, Ng Ze-An, Ankit Singh, Joan of Arc Xavier, Kanu Priya Agarwal, Mohammed Berkani, Benedito Alves de Oliveira Junior, Dmitry Malishev, Nicolas Remy, Taylor D. Hartman, Tim Tarver, Stephen Mensah, Javier Gimenez, Roselynn Grace Montecillo, Russell Campbell, Asankhaya Sharma, Khalida Meer, Xavier Alapont, Deepakkumar Patil, Rajat Maheshwari, Abdelkader Dendane, Priti Shukla, Sergei Bogdanov, S\"oren M\"oller, Muhammad Rehan Siddiqi, Prajvi Saxena, Himanshu Gupta, Innocent Enyekwe, Ragavendran P V, Zienab EL-Wasif, Aleksandr Maksapetyan, Vivien Rossbach, Chris Harjadi, Mohsen Bahaloohoreh, Song Bian, John Lai, Justine Leon Uro, Greg Bateman, Mohamed Sayed, Ahmed Menshawy, Darling Duclosel, Yashaswini Jain, Ashley Aaron, Murat Tiryakioglu, Sheeshram Siddh, Keith Krenek, Alex Hoover, Joseph McGowan, Tejal Patwardhan, Summer Yue, Alexandr Wang, Dan Hendrycks
Abstract: Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,700 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.
URLs: https://lastexam.ai.
Authors: Anoushkrit Goel, Simroop Singh, Ankita Joshi, Ranjeet Ranjan Jha, Chirag Ahuja, Aditya Nigam, Arnav Bhavsar
Abstract: White matter bundle segmentation is crucial for studying brain structural connectivity, neurosurgical planning, and neurological disorders. White Matter Segmentation remains challenging due to structural similarity in streamlines, subject variability, symmetry in 2 hemispheres, etc. To address these challenges, we propose TractoGPT, a GPT-based architecture trained on streamline, cluster, and fusion data representations separately. TractoGPT is a fully-automatic method that generalizes across datasets and retains shape information of the white matter bundles. Experiments also show that TractoGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores. We use TractoInferno and 105HCP datasets and validate generalization across dataset.
Authors: Xinyu Liu, Zixuan Xie, Shangtong Zhang
Abstract: $Q$-learning is one of the most fundamental reinforcement learning algorithms. It is widely believed that $Q$-learning with linear function approximation (i.e., linear $Q$-learning) suffers from possible divergence until the recent work Meyn (2024) which establishes the ultimate almost sure boundedness of the iterates of linear $Q$-learning. Building on this success, this paper further establishes the first $L^2$ convergence rate of linear $Q$-learning iterates (to a bounded set). Similar to Meyn (2024), we do not make any modification to the original linear $Q$-learning algorithm, do not make any Bellman completeness assumption, and do not make any near-optimality assumption on the behavior policy. All we need is an $\epsilon$-softmax behavior policy with an adaptive temperature. The key to our analysis is the general result of stochastic approximations under Markovian noise with fast-changing transition functions. As a side product, we also use this general result to establish the $L^2$ convergence rate of tabular $Q$-learning with an $\epsilon$-softmax behavior policy, for which we rely on a novel pseudo-contraction property of the weighted Bellman optimality operator.
Authors: Jia Li, Wenjie Zhao, Ziru Huang, Yunhui Guo, Yapeng Tian
Abstract: Unlike traditional visual segmentation, audio-visual segmentation (AVS) requires the model not only to identify and segment objects but also to determine whether they are sound sources. Recent AVS approaches, leveraging transformer architectures and powerful foundation models like SAM, have achieved impressive performance on standard benchmarks. Yet, an important question remains: Do these models genuinely integrate audio-visual cues to segment sounding objects? In this paper, we systematically investigate this issue in the context of robust AVS. Our study reveals a fundamental bias in current methods: they tend to generate segmentation masks based predominantly on visual salience, irrespective of the audio context. This bias results in unreliable predictions when sounds are absent or irrelevant. To address this challenge, we introduce AVSBench-Robust, a comprehensive benchmark incorporating diverse negative audio scenarios including silence, ambient noise, and off-screen sounds. We also propose a simple yet effective approach combining balanced training with negative samples and classifier-guided similarity learning. Our extensive experiments show that state-of-theart AVS methods consistently fail under negative audio conditions, demonstrating the prevalence of visual bias. In contrast, our approach achieves remarkable improvements in both standard metrics and robustness measures, maintaining near-perfect false positive rates while preserving highquality segmentation performance.
Authors: Naor Cohen, Roy Orfaig, Ben-Zion Bobrovsky
Abstract: Efforts to connect LiDAR data with text, such as LidarCLIP, have primarily focused on embedding 3D point clouds into CLIP text-image space. However, these approaches rely on 3D point clouds, which present challenges in encoding efficiency and neural network processing. With the advent of advanced LiDAR sensors like Ouster OS1, which, in addition to 3D point clouds, produce fixed resolution depth, signal, and ambient panoramic 2D images, new opportunities emerge for LiDAR based tasks. In this work, we propose an alternative approach to connect LiDAR data with text by leveraging 2D imagery generated by the OS1 sensor instead of 3D point clouds. Using the Florence 2 large model in a zero-shot setting, we perform image captioning and object detection. Our experiments demonstrate that Florence 2 generates more informative captions and achieves superior performance in object detection tasks compared to existing methods like CLIP. By combining advanced LiDAR sensor data with a large pre-trained model, our approach provides a robust and accurate solution for challenging detection scenarios, including real-time applications requiring high accuracy and robustness.
Authors: Kaizhen Zhu, Mokai Pan, Yuexin Ma, Yanwei Fu, Jingyi Yu, Jingya Wang, Ye Shi
Abstract: Recent advances in diffusion bridge models leverage Doob's $h$-transform to establish fixed endpoints between distributions, demonstrating promising results in image translation and restoration tasks. However, these approaches frequently produce blurred or excessively smoothed image details and lack a comprehensive theoretical foundation to explain these shortcomings. To address these limitations, we propose UniDB, a unified framework for diffusion bridges based on Stochastic Optimal Control (SOC). UniDB formulates the problem through an SOC-based optimization and derives a closed-form solution for the optimal controller, thereby unifying and generalizing existing diffusion bridge models. We demonstrate that existing diffusion bridges employing Doob's $h$-transform constitute a special case of our framework, emerging when the terminal penalty coefficient in the SOC cost function tends to infinity. By incorporating a tunable terminal penalty coefficient, UniDB achieves an optimal balance between control costs and terminal penalties, substantially improving detail preservation and output quality. Notably, UniDB seamlessly integrates with existing diffusion bridge models, requiring only minimal code modifications. Extensive experiments across diverse image restoration tasks validate the superiority and adaptability of the proposed framework. Our code is available at https://github.com/UniDB-SOC/UniDB/.
Authors: Ang Li, Yichuan Mo, Mingjie Li, Yifei Wang, Yisen Wang
Abstract: Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise decision-making demands more than raw language proficiency--LLMs must reason, i.e., think logically, draw from past experiences, and synthesize information to reach conclusions and take action. To enhance reasoning abilities, approaches such as prompting and fine-tuning have been widely explored. While these methods have led to clear improvements in reasoning, their impact on LLM safety remains less understood. In this work, we investigate the interplay between reasoning and safety in LLMs. We highlight the latent safety risks that arise as reasoning capabilities improve, shedding light on previously overlooked vulnerabilities. At the same time, we explore how reasoning itself can be leveraged to enhance safety, uncovering potential mitigation strategies. By examining both the risks and opportunities in reasoning-driven LLM safety, our study provides valuable insights for developing models that are not only more capable but also more trustworthy in real-world deployments.
Authors: Tianwei Lin, Wenqiao Zhang, Sijing Li, Yuqian Yuan, Binhe Yu, Haoyuan Li, Wanggui He, Hao Jiang, Mengze Li, Xiaohui Song, Siliang Tang, Jun Xiao, Hui Lin, Yueting Zhuang, Beng Chin Ooi
Abstract: We present HealthGPT, a powerful Medical Large Vision-Language Model (Med-LVLM) that integrates medical visual comprehension and generation capabilities within a unified autoregressive paradigm. Our bootstrapping philosophy is to progressively adapt heterogeneous comprehension and generation knowledge to pre-trained large language models (LLMs). This is achieved through a novel heterogeneous low-rank adaptation (H-LoRA) technique, which is complemented by a tailored hierarchical visual perception approach and a three-stage learning strategy. To effectively learn the HealthGPT, we devise a comprehensive medical domain-specific comprehension and generation dataset called VL-Health. Experimental results demonstrate exceptional performance and scalability of HealthGPT in medical visual unified tasks. Our project can be accessed at https://github.com/DCDmllm/HealthGPT.
Authors: Minyang Chen, Chenchen Feng, and Ran Cheng
Abstract: As a cornerstone in the Evolutionary Computation (EC) domain, Differential Evolution (DE) is known for its simplicity and effectiveness in handling challenging black-box optimization problems. While the advantages of DE are well-recognized, achieving peak performance heavily depends on its hyperparameters such as the mutation factor, crossover probability, and the selection of specific DE strategies. Traditional approaches to this hyperparameter dilemma have leaned towards parameter tuning or adaptive mechanisms. However, identifying the optimal settings tailored for specific problems remains a persistent challenge. In response, we introduce MetaDE, an approach that evolves DE's intrinsic hyperparameters and strategies using DE itself at a meta-level. A pivotal aspect of MetaDE is a specialized parameterization technique, which endows it with the capability to dynamically modify DE's parameters and strategies throughout the evolutionary process. To augment computational efficiency, MetaDE incorporates a design that leverages parallel processing through a GPU-accelerated computing framework. Within such a framework, DE is not just a solver but also an optimizer for its own configurations, thus streamlining the process of hyperparameter optimization and problem-solving into a cohesive and automated workflow. Extensive evaluations on the CEC2022 benchmark suite demonstrate MetaDE's promising performance. Moreover, when applied to robot control via evolutionary reinforcement learning, MetaDE also demonstrates promising performance. The source code of MetaDE is publicly accessible at: https://github.com/EMI-Group/metade.
Authors: Shahriar Kabir Nahin, Rabindra Nath Nandi, Sagor Sarker, Quazi Sarwar Muhtaseem, Md Kowsher, Apu Chandraw Shill, Md Ibrahim, Mehadi Hasan Menon, Tareq Al Muntasir, Firoj Alam
Abstract: In this paper, we present TituLLMs, the first large pretrained Bangla LLMs, available in 1b and 3b parameter sizes. Due to computational constraints during both training and inference, we focused on smaller models. To train TituLLMs, we collected a pretraining dataset of approximately ~37 billion tokens. We extended the Llama-3.2 tokenizer to incorporate language- and culture-specific knowledge, which also enables faster training and inference. There was a lack of benchmarking datasets to benchmark LLMs for Bangla. To address this gap, we developed five benchmarking datasets. We benchmarked various LLMs, including TituLLMs, and demonstrated that TituLLMs outperforms its initial multilingual versions. However, this is not always the case, highlighting the complexities of language adaptation. Our work lays the groundwork for adapting existing multilingual open models to other low-resource languages. To facilitate broader adoption and further research, we have made the TituLLMs models and benchmarking datasets publicly available (https://huggingface.co/collections/hishab/titulm-llama-family-6718d31fc1b83529276f490a).
URLs: https://huggingface.co/collections/hishab/titulm-llama-family-6718d31fc1b83529276f490a).
Authors: Yuncheng Hua, Lizhen Qu, Zhuang Li, Hao Xue, Flora D. Salim, Gholamreza Haffari
Abstract: Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting aspects of LLM alignment--factuality and safety. We packaged the restyled examples as prompts to trigger few-shot learning, improving LLM alignment. Compared to the best baseline approach, with an average score of 5.00 as the maximum, our method achieves a maximum 0.10 increase on the Alpaca task (from 4.50 to 4.60), a 0.22 enhancement on the Just-eval benchmark (from 4.34 to 4.56), and a maximum improvement of 0.32 (from 3.53 to 3.85) on the MT-Bench dataset. We release the code and data at https://github.com/AnonymousCode-ComputerScience/RIDE.
URLs: https://github.com/AnonymousCode-ComputerScience/RIDE.
Authors: Florian Sestak, Artur Toshev, Andreas F\"urst, G\"unter Klambauer, Andreas Mayr, Johannes Brandstetter
Abstract: Generative models are spearheading recent progress in deep learning, showing strong promise for trajectory sampling in dynamical systems as well. However, while latent space modeling paradigms have transformed image and video generation, similar approaches are more difficult for most dynamical systems. Such systems -- from chemical molecule structures to collective human behavior -- are described by interactions of entities, making them inherently linked to connectivity patterns and the traceability of entities over time. Our approach, LaM-SLidE (Latent Space Modeling of Spatial Dynamical Systems via Linked Entities), combines the advantages of graph neural networks, i.e., the traceability of entities across time-steps, with the efficiency and scalability of recent advances in image and video generation, where pre-trained encoder and decoder are frozen to enable generative modeling in the latent space. The core idea of LaM-SLidE is to introduce identifier representations (IDs) to allow for retrieval of entity properties, e.g., entity coordinates, from latent system representations and thus enables traceability. Experimentally, across different domains, we show that LaM-SLidE performs favorably in terms of speed, accuracy, and generalizability. Code is available at https://github.com/ml-jku/LaM-SLidE .
Authors: Mingyang Sun, Pengxiang Ding, Weinan Zhang, Donglin Wang
Abstract: Diffusion policies have shown promise in learning complex behaviors from demonstrations, particularly for tasks requiring precise control and long-term planning. However, they face challenges in robustness when encountering distribution shifts. This paper explores improving diffusion-based imitation learning models through online interactions with the environment. We propose OTPR (Optimal Transport-guided score-based diffusion Policy for Reinforcement learning fine-tuning), a novel method that integrates diffusion policies with RL using optimal transport theory. OTPR leverages the Q-function as a transport cost and views the policy as an optimal transport map, enabling efficient and stable fine-tuning. Moreover, we introduce masked optimal transport to guide state-action matching using expert keypoints and a compatibility-based resampling strategy to enhance training stability. Experiments on three simulation tasks demonstrate OTPR's superior performance and robustness compared to existing methods, especially in complex and sparse-reward environments. In sum, OTPR provides an effective framework for combining IL and RL, achieving versatile and reliable policy learning. The code will be released at https://github.com/Sunmmyy/OTPR.git.
Authors: Jian Wang, Yinpei Dai, Yichi Zhang, Ziqiao Ma, Wenjie Li, Joyce Chai
Abstract: Intelligent tutoring agents powered by large language models (LLMs) have been increasingly explored to deliver personalized guidance in areas such as language learning and science education. However, their capabilities in guiding users to solve complex real-world tasks remain underexplored. To address this limitation, in this work, we focus on coding tutoring, a challenging problem that requires tutors to proactively guide students toward completing predefined coding tasks. We propose a novel agent workflow, Trace-and-Verify (TRAVER), which combines knowledge tracing to estimate a student's knowledge state and turn-by-turn verification to ensure effective guidance toward task completion. We introduce DICT, an automatic evaluation protocol that assesses tutor agents holistically using controlled student simulation and code generation tests. Extensive experiments reveal the challenges of coding tutoring and demonstrate that TRAVER achieves a significantly higher success rate. Although we use code tutoring as an example in this paper, our results and findings can be extended beyond coding, providing valuable insights into advancing tutoring agents for a variety of tasks.
Authors: Yifei Xu, Tusher Chakraborty, Emre K{\i}c{\i}man, Bibek Aryal, Eduardo Rodrigues, Srinagesh Sharma, Roberto Estevao, Maria Angels de Luis Balaguer, Jessica Wolk, Rafael Padilha, Leonardo Nunes, Shobana Balakrishnan, Songwu Lu, Ranveer Chandra
Abstract: Fine-tuning large language models (LLMs) to align with user preferences is challenging due to the high cost of quality human annotations in Reinforcement Learning from Human Feedback (RLHF) and the generalizability limitations of AI Feedback. To address these challenges, we propose RLTHF, a human-AI hybrid framework that combines LLM-based initial alignment with selective human annotations to achieve full-human annotation alignment with minimal effort. RLTHF identifies hard-to-annotate samples mislabeled by LLMs using a reward model's reward distribution and iteratively enhances alignment by integrating strategic human corrections while leveraging LLM's correctly labeled samples. Evaluations on HH-RLHF and TL;DR datasets show that RLTHF reaches full-human annotation-level alignment with only 6-7% of the human annotation effort. Furthermore, models trained on RLTHF's curated datasets for downstream tasks outperform those trained on fully human-annotated datasets, underscoring the effectiveness of RLTHF's strategic data curation.
Authors: Haun Leung, ZiNan Wang
Abstract: It is popular lately to train large language models to be used as chat assistants, but in the conversation between the user and the chat assistant, there are prompts, require multi-turns between the chat assistant and the user. However, there are a number of issues with the multi-turns conversation: The response of the chat assistant is prone to errors and can't help users achieve their goals, and as the number of conversation turns increases, the probability of errors will also increase; It is difficult for chat assistant to generate responses with different processes based on actual needs for the same prompt; Chat assistant require the use of tools, but the current approach is not elegant and efficient, and the number of tool calls is limited. The main reason for these issues is that large language models don't have the thinking ability as a human, lack the reasoning ability and planning ability, and lack the ability to execute plans. To solve these issues, we propose a thinking method based on a built-in chain of thought: In the multi-turns conversation, for each user prompt, the large language model thinks based on elements such as chat history, thinking context, action calls, memory and knowledge, makes detailed reasoning and planning, and actions according to the plan. We also explored how the large language model enhances thinking ability through this thinking method: Collect training datasets according to the thinking method and fine tune the large language model through supervised learning; Train a consistency reward model and use it as a reward function to fine tune the large language model using reinforcement learning, and the reinforced large language model outputs according to this way of thinking. Our experimental results show that the reasoning ability and planning ability of the large language model are enhanced, and the issues in the multi-turns conversation are solved.
Authors: Peiwen Yuan, Chuyi Tan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Boyuan Pan, Yao Hu, Kan Li
Abstract: Despite the rapid progress of large language models (LLMs), their length-controllable text generation (LCTG) ability remains below expectations, posing a major limitation for practical applications. Existing methods mainly focus on end-to-end training to reinforce adherence to length constraints. However, the lack of decomposition and targeted enhancement of LCTG sub-abilities restricts further progress. To bridge this gap, we conduct a bottom-up decomposition of LCTG sub-abilities with human patterns as reference and perform a detailed error analysis. On this basis, we propose MarkerGen, a simple-yet-effective plug-and-play approach that:(1) mitigates LLM fundamental deficiencies via external tool integration;(2) conducts explicit length modeling with dynamically inserted markers;(3) employs a three-stage generation scheme to better align length constraints while maintaining content quality. Comprehensive experiments demonstrate that MarkerGen significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability.
Authors: Sein Kim, Hongseok Kang, Kibum Kim, Jiwan Kim, Donghyun Kim, Minchul Yang, Kwangjin Oh, Julian McAuley, Chanyoung Park
Abstract: Large Language Models (LLMs) have recently emerged as promising tools for recommendation thanks to their advanced textual understanding ability and context-awareness. Despite the current practice of training and evaluating LLM-based recommendation (LLM4Rec) models under a sequential recommendation scenario, we found that whether these models understand the sequential information inherent in users' item interaction sequences has been largely overlooked. In this paper, we first demonstrate through a series of experiments that existing LLM4Rec models do not fully capture sequential information both during training and inference. Then, we propose a simple yet effective LLM-based sequential recommender, called LLM-SRec, a method that enhances the integration of sequential information into LLMs by distilling the user representations extracted from a pre-trained CF-SRec model into LLMs. Our extensive experiments show that LLM-SRec enhances LLMs' ability to understand users' item interaction sequences, ultimately leading to improved recommendation performance. Furthermore, unlike existing LLM4Rec models that require fine-tuning of LLMs, LLM-SRec achieves state-of-the-art performance by training only a few lightweight MLPs, highlighting its practicality in real-world applications. Our code is available at https://github.com/Sein-Kim/LLM-SRec.
Authors: Philipp Wissmann, Daniel Hein, Steffen Udluft, Thomas Runkler
Abstract: This paper investigates the instability of Q-learning in continuous environments, a challenge frequently encountered by practitioners. Traditionally, this instability is attributed to bootstrapping and regression model errors. Using a representative reinforcement learning benchmark, we systematically examine the effects of bootstrapping and model inaccuracies by incrementally eliminating these potential error sources. Our findings reveal that even in relatively simple benchmarks, the fundamental task of Q-learning - iteratively learning a Q-function from policy-specific target values - can be inherently ill-posed and prone to failure. These insights cast doubt on the reliability of Q-learning as a universal solution for reinforcement learning problems.
Authors: Velibor Bojkovi\'c, Xiaofeng Wu, Bin Gu
Abstract: Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a promising approach to mitigate the increasing energy demands of large-scale neural models. However, fully harnessing the capabilities of SNNs remains challenging due to their discrete signal processing and temporal dynamics. ANN-SNN conversion has emerged as a practical approach, enabling SNNs to achieve competitive performance on complex machine learning tasks. In this work, we identify a phenomenon in the ANN-SNN conversion framework, termed temporal misalignment, in which random spike rearrangement across SNN layers leads to performance improvements. Based on this observation, we introduce biologically plausible two-phase probabilistic (TPP) spiking neurons, further enhancing the conversion process. We demonstrate the advantages of our proposed method both theoretically and empirically through comprehensive experiments on CIFAR-10/100, CIFAR10-DVS, and ImageNet across a variety of architectures, achieving state-of-the-art results.
Authors: Maryam Rahimi, Yadollah Yaghoobzadeh, Mohammad Reza Daliri
Abstract: Recent advances in artificial intelligence have given rise to large language models (LLMs) that not only achieve human-like performance but also share computational principles with the brain's language processing mechanisms. While previous research has primarily focused on aligning LLMs' internal representations with neural activity, we introduce a novel approach that leverages explainable AI (XAI) methods to forge deeper connections between the two domains. Using attribution methods, we quantified how preceding words contribute to an LLM's next-word predictions and employed these explanations to predict fMRI recordings from participants listening to the same narratives. Our findings demonstrate that attribution methods robustly predict brain activity across the language network, surpassing traditional internal representations in early language areas. This alignment is hierarchical: early-layer explanations correspond to the initial stages of language processing in the brain, while later layers align with more advanced stages. Moreover, the layers more influential on LLM next-word prediction$\unicode{x2014}$those with higher attribution scores$\unicode{x2014}$exhibited stronger alignment with neural activity. This work establishes a bidirectional bridge between AI and neuroscience. First, we demonstrate that attribution methods offer a powerful lens for investigating the neural mechanisms of language comprehension, revealing how meaning emerges from preceding context. Second, we propose using brain alignment as a metric to evaluate the validity of attribution methods, providing a framework for assessing their biological plausibility.
Authors: Thomas Vakili, Aron Henriksson, Hercules Dalianis
Abstract: Many sensitive domains -- such as the clinical domain -- lack widely available datasets due to privacy risks. The increasing generative capabilities of large language models (LLMs) have made synthetic datasets a viable path forward. In this study, we domain-adapt LLMs to the clinical domain and generate synthetic clinical texts that are machine-annotated with tags for personally identifiable information using capable encoder-based NER models. The synthetic corpora are then used to train synthetic NER models. The results show that training NER models using synthetic corpora incurs only a small drop in predictive performance. The limits of this process are investigated in a systematic ablation study -- using both Swedish and Spanish data. Our analysis shows that smaller datasets can be sufficient for domain-adapting LLMs for data synthesis. Instead, the effectiveness of this process is almost entirely contingent on the performance of the machine-annotating NER models trained using the original data.
Authors: Yuxuan Yang, Dalin Zhang, Yuxuan Liang, Hua Lu, Gang Chen, Huan Li
Abstract: Time Series Forecasting (TSF) is a crucial task in various domains, yet existing TSF models rely heavily on high-quality data and insufficiently exploit all available data. This paper explores a novel self-supervised approach to re-label time series datasets by inherently constructing candidate datasets. During the optimization of a simple reconstruction network, intermediates are used as pseudo labels in a self-supervised paradigm, improving generalization for any predictor. We introduce the Self-Correction with Adaptive Mask (SCAM), which discards overfitted components and selectively replaces them with pseudo labels generated from reconstructions. Additionally, we incorporate Spectral Norm Regularization (SNR) to further suppress overfitting from a loss landscape perspective. Our experiments on eleven real-world datasets demonstrate that SCAM consistently improves the performance of various backbone models. This work offers a new perspective on constructing datasets and enhancing the generalization of TSF models through self-supervised learning.
Authors: Lijun Sun, Yijun Yang, Qiqi Duan, Yuhui Shi, Chao Lyu, Yu-Cheng Chang, Chin-Teng Lin, Yang Shen
Abstract: Multi-agent coordination studies the underlying mechanism enabling the trending spread of diverse multi-agent systems (MAS) and has received increasing attention, driven by the expansion of emerging applications and rapid AI advances. This survey outlines the current state of coordination research across applications through a unified understanding that answers four fundamental coordination questions: (1) what is coordination; (2) why coordination; (3) who to coordinate with; and (4) how to coordinate. Our purpose is to explore existing ideas and expertise in coordination and their connections across diverse applications, while identifying and highlighting emerging and promising research directions. First, general coordination problems that are essential to varied applications are identified and analyzed. Second, a number of MAS applications are surveyed, ranging from widely studied domains, e.g., search and rescue, warehouse automation and logistics, and transportation systems, to emerging fields including humanoid and anthropomorphic robots, satellite systems, and large language models (LLMs). Finally, open challenges about the scalability, heterogeneity, and learning mechanisms of MAS are analyzed and discussed. In particular, we identify the hybridization of hierarchical and decentralized coordination, human-MAS coordination, and LLM-based MAS as promising future directions.