Search

Large Language Models (LLMs) require frequent updates to correct errors and keep pace with continuously evolving knowledge in a timely and effective manner. Recent research in it model editing has highlighted the challenges in balancing generalization and locality, especially in the context of lifelong model editing. We discover that inserting knowledge directly into the model often causes conflicts and potentially disrupts other unrelated pre-trained knowledge. To address this problem, we introduce UniAdapt, a universal adapter for knowledge calibration. Inspired by the Mixture of Experts architecture and Retrieval-Augmented Generation, UniAdapt is designed with a vector-assisted router that is responsible for routing inputs to appropriate experts. The router maintains a vector store, including multiple shards, to construct routing vectors based on semantic similarity search results. UniAdapt is fully model-agnostic and designed for seamless plug-and-play integration. Experimental results show that UniAdapt outperforms existing lifelong model editors and achieves exceptional results in most metrics.

We consider the existence and $L^q$ gradient estimates for perturbed Stokes systems with divergence-free critical drift in a bounded Lipschitz domain in $\mathbb{R}^n$, $n \ge 3$. The first two results assume the drift is either in $L^n$ or sufficiently small in weak $L^n$. The third result assumes the drift is in weak $L^n$ without smallness, and obtain results for $q$ close to 2.

Conversational search offers an easier and faster alternative to conventional web search, while having downsides like lack of source verification. Research has examined performance disparities between these two systems in different settings. However, little work has considered the effects of variations within a given search task. We hypothesize that psychological distance - one''s perceived closeness to a target event - affects information needs in search tasks, and investigate the corresponding effects on user preferences between web and conversational search systems. We find that with greater psychological distances, users perceive conversational search as more credible, useful, enjoyable, and easy to use, and demonstrate increased preference for this system. We reveal qualitative reasons for these differences and provide design implications for search system designers., Comment: 28 pages

RAG (Retrieval-Augmented Generation) have recently gained significant attention for their enhanced ability to integrate external knowledge sources in open-domain question answering (QA) tasks. However, it remains unclear how these models address fairness concerns, particularly with respect to sensitive attributes such as gender, geographic location, and other demographic factors. First, as language models evolve to prioritize utility, like improving exact match accuracy, fairness may have been largely overlooked. Second, RAG methods are complex pipelines, making it hard to identify and address biases, as each component is optimized for different goals. In this paper, we aim to empirically evaluate fairness in several RAG methods. We propose a fairness evaluation framework tailored to RAG methods, using scenario-based questions and analyzing disparities across demographic attributes. The experimental results indicate that, despite recent advances in utility-driven optimization, fairness issues persist in both the retrieval and generation stages, highlighting the need for more targeted fairness interventions within RAG pipelines. We will release our dataset and code upon acceptance of the paper., Comment: Under review

Superoscillation (SO) wavefunctions, that locally oscillate much faster than its fastest Fourier component, in light waves have enhanced optical technologies beyond diffraction limits, but never been controlled into 2D periodic lattices. Here, we report the 2D superoscillation lattices (SOL) with controlled symmetries, where the local wavevector can be 700 times larger than the global maximal wavevector (k0) in a localized region 100 times smaller than the global minimal wavelength ({\lambda}0). We also demonstrate the superoscillation superlattices (SOSL) as twisted bilayer Moir\'e patterns of two SOL, akin to the magic angle tuning in advanced twistronics, we can continually tune the ondemand SO with local maximal wavevector in a range of 450k0 to 700k0 and with {\lambda}0/100 to{\lambda}0/1000. The twistronic SOSL will advance optical imaging and metrology into extreme higher dimensional superresolution., Comment: 6 pages, 4 figures

6D object pose estimation aims at determining an object's translation, rotation, and scale, typically from a single RGBD image. Recent advancements have expanded this estimation from instance-level to category-level, allowing models to generalize across unseen instances within the same category. However, this generalization is limited by the narrow range of categories covered by existing datasets, such as NOCS, which also tend to overlook common real-world challenges like occlusion. To tackle these challenges, we introduce Omni6D, a comprehensive RGBD dataset featuring a wide range of categories and varied backgrounds, elevating the task to a more realistic context. 1) The dataset comprises an extensive spectrum of 166 categories, 4688 instances adjusted to the canonical pose, and over 0.8 million captures, significantly broadening the scope for evaluation. 2) We introduce a symmetry-aware metric and conduct systematic benchmarks of existing algorithms on Omni6D, offering a thorough exploration of new challenges and insights. 3) Additionally, we propose an effective fine-tuning approach that adapts models from previous datasets to our extensive vocabulary setting. We believe this initiative will pave the way for new insights and substantial progress in both the industrial and academic fields, pushing forward the boundaries of general 6D pose estimation., Comment: ECCV 2024 (poster). Github page: https://github.com/3DTopia/Omni6D

Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA., Comment: Project page: https://zcmax.github.io/projects/LLaVA-3D/

Cinematographers adeptly capture the essence of the world, crafting compelling visual narratives through intricate camera movements. Witnessing the strides made by large language models in perceiving and interacting with the 3D world, this study explores their capability to control cameras with human language guidance. We introduce ChatCam, a system that navigates camera movements through conversations with users, mimicking a professional cinematographer's workflow. To achieve this, we propose CineGPT, a GPT-based autoregressive model for text-conditioned camera trajectory generation. We also develop an Anchor Determinator to ensure precise camera trajectory placement. ChatCam understands user requests and employs our proposed tools to generate trajectories, which can be used to render high-quality video footage on radiance field representations. Our experiments, including comparisons to state-of-the-art approaches and user studies, demonstrate our approach's ability to interpret and execute complex instructions for camera operation, showing promising applications in real-world production settings., Comment: Paper accepted to NeurIPS 2024

In the Standard Model (SM), the charged lepton-flavor violation (CLFV) processes are forbidden, so the observation of CLFV represents a clear signal of new physics that goes beyond the Standard Model. In this work, we focus on the CLFV processes $l_{j}^{-}\to l_{i}^{-}\gamma $ and $l_{j}^{-}\to l_{i}^{-}l_{i}^{-}l_{i}^{+}$ in LRSSM. Considering the constraints of the updated experimental datas, the numerical results show that the new contributions of $SU{{\left( 2 \right)}_{R}}$ gauge interaction and a large number of other new particles, such as ${{Z}^{'}}$ boson, double-charged Higgs-bosons in LRSSM can make significant contributions to the CLFV processes $l_{j}^{-}\to l_{i}^{-}\gamma $ and $l_{j}^{-}\to l_{i}^{-}l_{i}^{-}l_{i}^{+}$, which is much different from the ones predicted in other SUSY models. This work provide a theoretical base for finding the LFV phenomena in new physics., Comment: 24 pages,6 figures, 1 table

The myelinated axons are widely present in both central and peripheral nervous systems. Its unique compact spiraling structure poses significant challenges to understanding its biological functions and developmental mechanisms. Conventionally, myelin is considered as an insulating layer to achieve saltatory conduction for the enhancement of the neural signal speed, which serves as the foundation of neuroscience. However, this insulating hypothesis is inadequate to account for various experimental observations, especially the long unmyelinated tract observed in the cortex. We here show non-random distributions in three ultrastructural features of myelin: the non-random spiraling directions, the localization preferences of myelin outer tongues, and the radial components along boundaries between oppositely spiraled myelin sheaths. These phenomena are predicted by a novel concept of myelin biological function, which we propose as the signal synchronization function. Our findings demonstrate that cytoplasmic channels within myelin may act as coiled inductors, facilitating electromagnetic induction between adjacent myelin sheaths, and thereby promoting signal synchronization between axons. This, in turn, explains the non-random ultrastructural features observed. We believe these insights lay the foundation for a new understanding of myelin inductive function.

Discretely self-similar solutions to Oberbeck-Boussinesq system with Newtonian gravitational field for large discretely self-similar initial data are constructed in this note, extending the construction of Brandolese and Karch (arXiv:2311.01093) on self-similar solutions. It follows the approach of Bradshaw and Tsai (Ann.~Henri Poincar\'e 2017) and find an explicit a priori bound for the deviation from suitably revised profiles in similarity variables.

Societal risk emanating from how recommender algorithms disseminate content online is now well documented. Emergent regulation aims to mitigate this risk through ethical audits and enabling new research on the social impact of algorithms. However, there is currently a need for tools and methods that enable such evaluation. This paper presents ARTAI, an evaluation environment that enables large-scale assessments of recommender algorithms to identify harmful patterns in how content is distributed online and enables the implementation of new regulatory requirements for increased transparency in recommender systems., Comment: 3 pages, 1 figure, accepted at FAccTRec 2024 Workshop, RecSys 2024

This paper introduces CompressedMediQ, a novel hybrid quantum-classical machine learning pipeline specifically developed to address the computational challenges associated with high-dimensional multi-class neuroimaging data analysis. Standard neuroimaging datasets, such as large-scale MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Neuroimaging in Frontotemporal Dementia (NIFD), present significant hurdles due to their vast size and complexity. CompressedMediQ integrates classical high-performance computing (HPC) nodes for advanced MRI pre-processing and Convolutional Neural Network (CNN)-PCA-based feature extraction and reduction, addressing the limited-qubit availability for quantum data encoding in the NISQ (Noisy Intermediate-Scale Quantum) era. This is followed by Quantum Support Vector Machine (QSVM) classification. By utilizing quantum kernel methods, the pipeline optimizes feature mapping and classification, enhancing data separability and outperforming traditional neuroimaging analysis techniques. Experimental results highlight the pipeline's superior accuracy in dementia staging, validating the practical use of quantum machine learning in clinical diagnostics. Despite the limitations of NISQ devices, this proof-of-concept demonstrates the transformative potential of quantum-enhanced learning, paving the way for scalable and precise diagnostic tools in healthcare and signal processing.

Recently, a novel model named Kolmogorov-Arnold Networks (KAN) has been proposed with the potential to achieve the functionality of traditional deep neural networks (DNNs) using orders of magnitude fewer parameters by parameterized B-spline functions with trainable coefficients. However, the B-spline functions in KAN present new challenges for hardware acceleration. Evaluating the B-spline functions can be performed by using look-up tables (LUTs) to directly map the B-spline functions, thereby reducing computational resource requirements. However, this method still requires substantial circuit resources (LUTs, MUXs, decoders, etc.). For the first time, this paper employs an algorithm-hardware co-design methodology to accelerate KAN. The proposed algorithm-level techniques include Alignment-Symmetry and PowerGap KAN hardware aware quantization, KAN sparsity aware mapping strategy, and circuit-level techniques include N:1 Time Modulation Dynamic Voltage input generator with analog-CIM (ACIM) circuits. The impact of non-ideal effects, such as partial sum errors caused by the process variations, has been evaluated with the statistics measured from the TSMC 22nm RRAM-ACIM prototype chips. With the best searched hyperparameters of KAN and the optimized circuits implemented in 22 nm node, we can reduce hardware area by 41.78x, energy by 77.97x with 3.03% accuracy boost compared to the traditional DNN hardware., Comment: Accepted at ASP-DAC (Asia and South Pacific Design Automation Conference)

In this article, we develop nonparametric inference methods for comparing survival data across two samples, which are beneficial for clinical trials of novel cancer therapies where long-term survival is a critical outcome. These therapies, including immunotherapies or other advanced treatments, aim to establish durable effects. They often exhibit distinct survival patterns such as crossing or delayed separation and potentially leveling-off at the tails of survival curves, clearly violating the proportional hazards assumption and rendering the hazard ratio inappropriate for measuring treatment effects. The proposed methodology utilizes the mixture cure framework to separately analyze the cure rates of long-term survivors and the survival functions of susceptible individuals. We evaluate a nonparametric estimator for the susceptible survival function in the one-sample setting. Under sufficient follow-up, it is expressed as a location-scale-shift variant of the Kaplan-Meier (KM) estimator. It retains several desirable features of the KM estimator, including inverse-probability-censoring weighting, product-limit estimation, self-consistency, and nonparametric efficiency. In scenarios of insufficient follow-up, it can easily be adapted by incorporating a suitable cure rate estimator. In the two-sample setting, besides using the difference in cure rates to measure the long-term effect, we propose a graphical estimand to compare the relative treatment effects on susceptible subgroups. This process, inspired by Kendall's tau, compares the order of survival times among susceptible individuals. The proposed methods' large-sample properties are derived for further inference, and the finite-sample properties are examined through extensive simulation studies. The proposed methodology is applied to analyze the digitized data from the CheckMate 067 immunotherapy clinical trial.

The clustering of categorical data is a common and important task in computer science, offering profound implications across a spectrum of applications. Unlike purely numerical data, categorical data often lack inherent ordering as in nominal data, or have varying levels of order as in ordinal data, thus requiring specialized methodologies for efficient organization and analysis. This review provides a comprehensive synthesis of categorical data clustering in the past twenty-five years, starting from the introduction of K-modes. It elucidates the pivotal role of categorical data clustering in diverse fields such as health sciences, natural sciences, social sciences, education, engineering and economics. Practical comparisons are conducted for algorithms having public implementations, highlighting distinguishing clustering methodologies and revealing the performance of recent algorithms on several benchmark categorical datasets. Finally, challenges and opportunities in the field are discussed.

In-context learning (ICL) of large language models has proven to be a surprisingly effective method of learning a new task from only a few demonstrative examples. In this paper, we study the efficacy of ICL from the viewpoint of statistical learning theory. We develop approximation and generalization error bounds for a transformer composed of a deep neural network and one linear attention layer, pretrained on nonparametric regression tasks sampled from general function spaces including the Besov space and piecewise $\gamma$-smooth class. We show that sufficiently trained transformers can achieve -- and even improve upon -- the minimax optimal estimation risk in context by encoding the most relevant basis representations during pretraining. Our analysis extends to high-dimensional or sequential data and distinguishes the \emph{pretraining} and \emph{in-context} generalization gaps. Furthermore, we establish information-theoretic lower bounds for meta-learners w.r.t. both the number of tasks and in-context examples. These findings shed light on the roles of task diversity and representation learning for ICL., Comment: NeurIPS 2024; 40 pages, 3 figures

A ubiquitous phenomenon observed throughout the primate hierarchical visual system is the sparsification of the neural representation of visual stimuli as a result of familiarization by repeated exposure, manifested as the sharpening of the population tuning curves and suppression of neural responses at the population level. In this work, we investigated the computational implications and circuit mechanisms underlying these neurophysiological observations in an early visual cortical circuit model. We found that such a recurrent neural circuit, shaped by BCM Hebbian learning, can also reproduce these phenomena. The resulting circuit became more robust against noises in encoding the familiar stimuli. Analysis of the geometry of the neural response manifold revealed that recurrent computation and familiar learning transform the response manifold and the neural dynamics, resulting in enhanced robustness against noise and better stimulus discrimination. This prediction is supported by preliminary physiological evidence. Familiarity training increases the alignment of the slow modes of network dynamics with the invariant features of the learned images. These findings revealed how these rapid plasticity mechanisms can improve contextual visual processing in even the early visual areas in the hierarchical visual system., Comment: 17 pages, 9 figures

Recent advances in text-guided 3D avatar generation have made substantial progress by distilling knowledge from diffusion models. Despite the plausible generated appearance, existing methods cannot achieve fine-grained disentanglement or high-fidelity modeling between inner body and outfit. In this paper, we propose Barbie, a novel framework for generating 3D avatars that can be dressed in diverse and high-quality Barbie-like garments and accessories. Instead of relying on a holistic model, Barbie achieves fine-grained disentanglement on avatars by semantic-aligned separated models for human body and outfits. These disentangled 3D representations are then optimized by different expert models to guarantee the domain-specific fidelity. To balance geometry diversity and reasonableness, we propose a series of losses for template-preserving and human-prior evolving. The final avatar is enhanced by unified texture refinement for superior texture consistency. Extensive experiments demonstrate that Barbie outperforms existing methods in both dressed human and outfit generation, supporting flexible apparel combination and animation. The code will be released for research purposes. Our project page is: https://xiaokunsun.github.io/Barbie.github.io/., Comment: 9 pages, 7 figures, Project page: https://xiaokunsun.github.io/Barbie.github.io/

Multimodal Large Language Models (MLLMs) are gaining increasing popularity in both academia and industry due to their remarkable performance in various applications such as visual question answering, visual perception, understanding, and reasoning. Over the past few years, significant efforts have been made to examine MLLMs from multiple perspectives. This paper presents a comprehensive review of 200 benchmarks and evaluations for MLLMs, focusing on (1)perception and understanding, (2)cognition and reasoning, (3)specific domains, (4)key capabilities, and (5)other modalities. Finally, we discuss the limitations of the current evaluation methods for MLLMs and explore promising future directions. Our key argument is that evaluation should be regarded as a crucial discipline to support the development of MLLMs better. For more details, please visit our GitHub repository: https://github.com/swordlidev/Evaluation-Multimodal-LLMs-Survey.

As the academic landscape expands, the challenge of efficiently identifying potentially high-impact articles among the vast number of newly published works becomes critical. This paper introduces a promising approach, leveraging the capabilities of fine-tuned LLMs to predict the future impact of newborn articles solely based on titles and abstracts. Moving beyond traditional methods heavily reliant on external information, the proposed method discerns the shared semantic features of highly impactful papers from a large collection of title-abstract and potential impact pairs. These semantic features are further utilized to regress an improved metric, TNCSI_SP, which has been endowed with value, field, and time normalization properties. Additionally, a comprehensive dataset has been constructed and released for fine-tuning the LLM, containing over 12,000 entries with corresponding titles, abstracts, and TNCSI_SP. The quantitative results, with an NDCG@20 of 0.901, demonstrate that the proposed approach achieves state-of-the-art performance in predicting the impact of newborn articles when compared to competitive counterparts. Finally, we demonstrate a real-world application for predicting the impact of newborn journal articles to demonstrate its noteworthy practical value. Overall, our findings challenge existing paradigms and propose a shift towards a more content-focused prediction of academic impact, offering new insights for assessing newborn article impact., Comment: 7 pages for main sections, plus 3 additional pages for appendices. Code, dataset are released at https://sway.cloud.microsoft/KOH09sPR21Ubojbc

Machine-learned potentials (MLPs) trained on ab initio data combine the computational efficiency of classical interatomic potentials with the accuracy and generality of the first-principles method used in the creation of the respective training set. In this work, we implement and train a MLP to obtain an accurate description of the potential energy surface and property predictions for organic compounds, as both single molecules and in the condensed phase. We devise a dual descriptor, based on the atomic cluster expansion (ACE), that couples an information-rich short-range description with a coarser long-range description that captures weak intermolecular interactions. We employ uncertainty-guided active learning for the training set generation, creating a dataset that is comparatively small for the breadth of application and consists of alcohols, alkanes, and an adipate. Utilizing that MLP, we calculate densities of those systems of varying chain lengths as a function of temperature, obtaining a discrepancy of less than 4% compared with experiment. Vibrational frequencies calculated with the MLP have a root mean square error of less than 1 THz compared to DFT. The heat capacities of condensed systems are within 11% of experimental findings, which is strong evidence that the dual descriptor provides an accurate framework for the prediction of both short-range intramolecular and long-range intermolecular interactions.

Missing data in tabular dataset is a common issue as the performance of downstream tasks usually depends on the completeness of the training dataset. Previous missing data imputation methods focus on numeric and categorical columns, but we propose a novel end-to-end approach called Table Transformers for Imputing Textual Attributes (TTITA) based on the transformer to impute unstructured textual columns using other columns in the table. We conduct extensive experiments on three datasets, and our approach shows competitive performance outperforming baseline models such as recurrent neural networks and Llama2. The performance improvement is more significant when the target sequence has a longer length. Additionally, we incorporate multi-task learning to simultaneously impute for heterogeneous columns, boosting the performance for text imputation. We also qualitatively compare with ChatGPT for realistic applications.

Many head pose estimation (HPE) methods promise the ability to create full-range datasets, theoretically allowing the estimation of the rotation and positioning of the head from various angles. However, these methods are only accurate within a range of head angles; exceeding this specific range led to significant inaccuracies. This is dominantly explained by unclear specificity of the coordinate systems and Euler Angles used in the foundational rotation matrix calculations. Here, we addressed these limitations by presenting (1) methods that accurately infer the correct coordinate system and Euler angles in the correct axis-sequence, (2) novel formulae for 2D geometric augmentations of the rotation matrices under the (SPECIFIC) coordinate system, (3) derivations for the correct drawing routines for rotation matrices and poses, and (4) mathematical experimentation and verification that allow proper pitch-yaw coverage for full-range head pose dataset generation. Performing our augmentation techniques to existing head pose estimation methods demonstrated a significant improvement to the model performance. Code will be released upon paper acceptance., Comment: arXiv admin note: text overlap with arXiv:2403.18104

Continual graph learning (CGL) is an important and challenging task that aims to extend static GNNs to dynamic task flow scenarios. As one of the mainstream CGL methods, the experience replay (ER) method receives widespread attention due to its superior performance. However, existing ER methods focus on identifying samples by feature significance or topological relevance, which limits their utilization of comprehensive graph data. In addition, the topology-based ER methods only consider local topological information and add neighboring nodes to the buffer, which ignores the global topological information and increases memory overhead. To bridge these gaps, we propose a novel method called Feature-Topology Fusion-based Experience Replay (FTF-ER) to effectively mitigate the catastrophic forgetting issue with enhanced efficiency. Specifically, from an overall perspective to maximize the utilization of the entire graph data, we propose a highly complementary approach including both feature and global topological information, which can significantly improve the effectiveness of the sampled nodes. Moreover, to further utilize global topological information, we propose Hodge Potential Score (HPS) as a novel module to calculate the topological importance of nodes. HPS derives a global node ranking via Hodge decomposition on graphs, providing more accurate global topological information compared to neighbor sampling. By excluding neighbor sampling, HPS significantly reduces buffer storage costs for acquiring topological information and simultaneously decreases training time. Compared with state-of-the-art methods, FTF-ER achieves a significant improvement of 3.6% in AA and 7.1% in AF on the OGB-Arxiv dataset, demonstrating its superior performance in the class-incremental learning setting., Comment: Accepted by ACM Multimedia 2024

The integration of Artificial Intelligence (AI) into education has transformative potential, providing tailored learning experiences and creative instructional approaches. However, the inherent biases in AI algorithms hinder this improvement by unintentionally perpetuating prejudice against specific demographics, especially in human-centered applications like education. This survey delves deeply into the developing topic of algorithmic fairness in educational contexts, providing a comprehensive evaluation of the diverse literature on fairness, bias, and ethics in AI-driven educational applications. It identifies the common forms of biases, such as data-related, algorithmic, and user-interaction, that fundamentally undermine the accomplishment of fairness in AI teaching aids. By outlining existing techniques for mitigating these biases, ranging from varied data gathering to algorithmic fairness interventions, the survey emphasizes the critical role of ethical considerations and legal frameworks in shaping a more equitable educational environment. Furthermore, it guides readers through the complexities of fairness measurements, methods, and datasets, shedding light on the way to bias reduction. Despite these gains, this survey highlights long-standing issues, such as achieving a balance between fairness and accuracy, as well as the need for diverse datasets. Overcoming these challenges and ensuring the ethical and fair use of AI's promise in education call for a collaborative, interdisciplinary approach.

Reinforcement Learning (RL) is a continuously growing field that has the potential to revolutionize many areas of artificial intelligence. However, despite its promise, RL research is often hindered by the lack of standardization in environment and algorithm implementations. This makes it difficult for researchers to compare and build upon each other's work, slowing down progress in the field. Gymnasium is an open-source library that provides a standard API for RL environments, aiming to tackle this issue. Gymnasium's main feature is a set of abstractions that allow for wide interoperability between environments and training algorithms, making it easier for researchers to develop and test RL algorithms. In addition, Gymnasium provides a collection of easy-to-use environments, tools for easily customizing environments, and tools to ensure the reproducibility and robustness of RL research. Through this unified framework, Gymnasium significantly streamlines the process of developing and testing RL algorithms, enabling researchers to focus more on innovation and less on implementation details. By providing a standardized platform for RL research, Gymnasium helps to drive forward the field of reinforcement learning and unlock its full potential. Gymnasium is available online at https://github.com/Farama-Foundation/Gymnasium

Elected officials have privileged roles in public communication. In contrast to national politicians, whose posting content is more likely to be closely scrutinized by a robust ecosystem of nationally focused media outlets, sub-national politicians are more likely to openly disseminate harmful content with limited media scrutiny. In this paper, we analyze the factors that explain the online visibility of over 6.5K unique state legislators in the US and how their visibility might be impacted by posting low-credibility or uncivil content. We conducted a study of posting on Twitter and Facebook (FB) during 2020-21 to analyze how legislators engage with users on these platforms. The results indicate that distributing content with low-credibility information attracts greater attention from users on FB and Twitter for Republicans. Conversely, posting content that is considered uncivil on Twitter receives less attention. A noticeable scarcity of posts containing uncivil content was observed on FB, which may be attributed to the different communication patterns of legislators on these platforms. In most cases, the effect is more pronounced among the most ideologically extreme legislators. Our research explores the influence exerted by state legislators on online political conversations, with Twitter and FB serving as case studies. Furthermore, it sheds light on the differences in the conduct of political actors on these platforms. This study contributes to a better understanding of the role that political figures play in shaping online political discourse., Comment: Accepted for publication in the International AAAI Conference on Web and Social Media (ICWSM) 2025

Graph-level anomaly detection is significant in diverse domains. To improve detection performance, counterfactual graphs have been exploited to benefit the generalization capacity by learning causal relations. Most existing studies directly introduce perturbations (e.g., flipping edges) to generate counterfactual graphs, which are prone to alter the semantics of generated examples and make them off the data manifold, resulting in sub-optimal performance. To address these issues, we propose a novel approach, Motif-consistent Counterfactuals with Adversarial Refinement (MotifCAR), for graph-level anomaly detection. The model combines the motif of one graph, the core subgraph containing the identification (category) information, and the contextual subgraph (non-motif) of another graph to produce a raw counterfactual graph. However, the produced raw graph might be distorted and cannot satisfy the important counterfactual properties: Realism, Validity, Proximity and Sparsity. Towards that, we present a Generative Adversarial Network (GAN)-based graph optimizer to refine the raw counterfactual graphs. It adopts the discriminator to guide the generator to generate graphs close to realistic data, i.e., meet the property Realism. Further, we design the motif consistency to force the motif of the generated graphs to be consistent with the realistic graphs, meeting the property Validity. Also, we devise the contextual loss and connection loss to control the contextual subgraph and the newly added links to meet the properties Proximity and Sparsity. As a result, the model can generate high-quality counterfactual graphs. Experiments demonstrate the superiority of MotifCAR., Comment: Accepted by KDD 2024

Recent works have been exploring the scaling laws in the field of Embodied AI. Given the prohibitive costs of collecting real-world data, we believe the Simulation-to-Real (Sim2Real) paradigm is a crucial step for scaling the learning of embodied models. This paper introduces project GRUtopia, the first simulated interactive 3D society designed for various robots. It features several advancements: (a) The scene dataset, GRScenes, includes 100k interactive, finely annotated scenes, which can be freely combined into city-scale environments. In contrast to previous works mainly focusing on home, GRScenes covers 89 diverse scene categories, bridging the gap of service-oriented environments where general robots would be initially deployed. (b) GRResidents, a Large Language Model (LLM) driven Non-Player Character (NPC) system that is responsible for social interaction, task generation, and task assignment, thus simulating social scenarios for embodied AI applications. (c) The benchmark, GRBench, supports various robots but focuses on legged robots as primary agents and poses moderately challenging tasks involving Object Loco-Navigation, Social Loco-Navigation, and Loco-Manipulation. We hope that this work can alleviate the scarcity of high-quality data in this field and provide a more comprehensive assessment of Embodied AI research. The project is available at https://github.com/OpenRobotLab/GRUtopia.

Embedding Feynman integrals in Grassmannians, we express Feynman integrals as linear combinations of generalized hypergeometric functions. Here we present general methods to obtain Gauss relations among those generalized hypergeometric functions. The hypergeometric expressions of Feynman integral are analytically continued from some connected component to another by the Gauss inverse relations, then continued to the whole domain of definition by the Gauss-Kummer relations. The Laurant series of the Feynman integral around the time-space dimension $D=4$ is obtained by the Gauss adjacent relations where the coefficients of powers of $D-4$ are given as some finite linear combinations of hypergeometric functions with integer parameters. As an example, we illustrate how to use the method to obtain the analytic expression of the Feynman integral of one-loop self energy in its whole domain of definition., Comment: 75 pages, including text of 22 pages + 1 figure +appendices of 52 pages

Object-oriented embodied navigation aims to locate specific objects, defined by category or depicted in images. Existing methods often struggle to generalize to open vocabulary goals without extensive training data. While recent advances in Vision-Language Models (VLMs) offer a promising solution by extending object recognition beyond predefined categories, efficient goal-oriented exploration becomes more challenging in an open vocabulary setting. We introduce OVExp, a learning-based framework that integrates VLMs for Open-Vocabulary Exploration. OVExp constructs scene representations by encoding observations with VLMs and projecting them onto top-down maps for goal-conditioned exploration. Goals are encoded in the same VLM feature space, and a lightweight transformer-based decoder predicts target locations while maintaining versatile representation abilities. To address the impracticality of fusing dense pixel embeddings with full 3D scene reconstruction for training, we propose constructing maps using low-cost semantic categories and transforming them into CLIP's embedding space via the text encoder. The simple but effective design of OVExp significantly reduces computational costs and demonstrates strong generalization abilities to various navigation settings. Experiments on established benchmarks show OVExp outperforms previous zero-shot methods, can generalize to diverse scenes, and handle different goal modalities.

In this paper, we present a series of applications of the pointwise estimates of the (unrestricted) Green tensor of the nonstationary Stokes system in the half space, established in our previous work [CMP 2023]. First, we show the $L^1$-$L^q$ estimates for the Stokes flow with possibly non-solenoidal $L^1$ initial data, generalizing the results of Giga-Matsui-Shimizu [Math. Z. 1999] and Desch-Hieber-Pr\"uss [J. Evol. Equ. 2001]. Second, we construct mild solutions of the Navier-Stokes equations in the half space with mixed-type pointwise decay or with pointwise decay alongside boundary vanishing. Finally, we explore various coupled fluid systems in the half space including viscous resistive magnetohydrodynamics equations, a coupled system for the flow and the magnetic field of MHD type, and the nematic liquid crystal flow. For each of these systems, we construct mild solutions in $L^q$, pointwise decay, and uniformly local $L^q$ spaces.

Multi-modal recommendation greatly enhances the performance of recommender systems by modeling the auxiliary information from multi-modality contents. Most existing multi-modal recommendation models primarily exploit multimedia information propagation processes to enrich item representations and directly utilize modal-specific embedding vectors independently obtained from upstream pre-trained models. However, this might be inappropriate since the abundant task-specific semantics remain unexplored, and the cross-modality semantic gap hinders the recommendation performance. Inspired by the recent progress of the cross-modal alignment model CLIP, in this paper, we propose a novel \textbf{CLIP} \textbf{E}nhanced \textbf{R}ecommender (\textbf{CLIPER}) framework to bridge the semantic gap between modalities and extract fine-grained multi-view semantic information. Specifically, we introduce a multi-view modality-alignment approach for representation extraction and measure the semantic similarity between modalities. Furthermore, we integrate the multi-view multimedia representations into downstream recommendation models. Extensive experiments conducted on three public datasets demonstrate the consistent superiority of our model over state-of-the-art multi-modal recommendation models.

Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and minimal training data. However, existing works typically rely on optimizing unified prompt inputs, often struggling with fine-grained classification tasks due to insufficient discriminative attributes. To tackle this, we consider a new framework based on a dual context of both domain-shared and class-specific contexts, where the latter is generated by Large Language Models (LLMs) such as GPTs. Such dual prompt methods enhance the model's feature representation by joining implicit and explicit factors encoded in LLM knowledge. Moreover, we formulate the Unbalanced Optimal Transport (UOT) theory to quantify the relationships between constructed prompts and visual tokens. Through partial matching, UOT can properly align discrete sets of visual tokens and prompt embeddings under different mass distributions, which is particularly valuable for handling irrelevant or noisy elements, ensuring that the preservation of mass does not restrict transport solutions. Furthermore, UOT's characteristics integrate seamlessly with image augmentation, expanding the training sample pool while maintaining a reasonable distance between perturbed images and prompt inputs. Extensive experiments across few-shot classification and adapter settings substantiate the superiority of our model over current state-of-the-art baselines., Comment: Version 1

A method to reverse engineering of a fly brain using the {\it FlyCircuit} database is presented. This method was designed based on the assumption that similar neurons could serve identical functions. We thus cluster the neurons based on the similarity between neurons. The procedures are to partition the neurons in the database into groups, and then assemble the groups into potential modules. Some of the modules correspond to known neuropils, including Medulla were obtained. The same clustering algorithm was applied to analyze Medulla's structure. Another possible application of the clustering result is to study the brain-wide neuron connectome by looking at the connectivity between groups of neurons.

Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset. The previous popular video datasets, e.g. WebVid-10M and Panda-70M, are either with low quality or too large for most research institutions. Therefore, it is challenging but crucial to collect a precise high-quality text-video pairs for T2V generation. 2) Ignoring to fully utilize textual information. Recent T2V methods have focused on vision transformers, using a simple cross attention module for video generation, which falls short of thoroughly extracting semantic information from text prompt. To address these issues, we introduce OpenVid-1M, a precise high-quality dataset with expressive captions. This open-scenario dataset contains over 1 million text-video pairs, facilitating research on T2V generation. Furthermore, we curate 433K 1080p videos from OpenVid-1M to create OpenVidHD-0.4M, advancing high-definition video generation. Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens. Extensive experiments and ablation studies verify the superiority of OpenVid-1M over previous datasets and the effectiveness of our MVDiT., Comment: 15 pages, 9 figures

Although great progress has been made in 3D visual grounding, current models still rely on explicit textual descriptions for grounding and lack the ability to reason human intentions from implicit instructions. We propose a new task called 3D reasoning grounding and introduce a new benchmark ScanReason which provides over 10K question-answer-location pairs from five reasoning types that require the synerization of reasoning and grounding. We further design our approach, ReGround3D, composed of the visual-centric reasoning module empowered by Multi-modal Large Language Model (MLLM) and the 3D grounding module to obtain accurate object locations by looking back to the enhanced geometry and fine-grained details from the 3D scenes. A chain-of-grounding mechanism is proposed to further boost the performance with interleaved reasoning and grounding steps during inference. Extensive experiments on the proposed benchmark validate the effectiveness of our proposed approach., Comment: Accepted by ECCV 2024. A comprehensive and hierarchical 3D reasoning grounding benchmark in the era of foundation models. Project page: https://zcmax.github.io/projects/ScanReason