Search

Theory of Mind (ToM) significantly impacts human collaboration and communication as a crucial capability to understand others. When AI agents with ToM capability collaborate with humans, Mutual Theory of Mind (MToM) arises in such human-AI teams (HATs). The MToM process, which involves interactive communication and ToM-based strategy adjustment, affects the team's performance and collaboration process. To explore the MToM process, we conducted a mixed-design experiment using a large language model-driven AI agent with ToM and communication modules in a real-time shared-workspace task. We find that the agent's ToM capability does not significantly impact team performance but enhances human understanding of the agent and the feeling of being understood. Most participants in our study believe verbal communication increases human burden, and the results show that bidirectional communication leads to lower HAT performance. We discuss the results' implications for designing AI agents that collaborate with humans in real-time shared workspace tasks., Comment: 34 pages, Preprint Under Review

The intermediate behavior near a quantum phase transition is crucial for understanding the quantum criticality of various competing phases and their separate origins, yet remains unexplored for the multiple Yu-Shiba-Rusinov (YSR) states. Here, we investigated the detailed spectroscopic change of the exchange coupling-dependent YSR states near a quantum phase transition. The initially developed one pair of YSR states, induced by the Fe vacancy in monolayer Fe(Te,Se) superconductor, are clearly resolved with high resolution showing an evolution into two pairs of YSR peaks yet with dichotomy in their spectral features. Interestingly, while the lower-energy YSR branch enters the quantum phase transition region, the higher-lying one remains rigidly away from the lower-energy counterpart with a constant energy difference. Spectral weight analysis of the higher-energy branch yields an exponential dependence on the exchange coupling, which can be well rationalized by taking the two pairs of YSR states as a result of field splitting by the magnetic anisotropy. Our results unveil the intermediate region of a quantum phase transition with a magnetic anisotropy-induced splitting of the YSR resonance, and highlight a prospect for developing functional electronics based on the flexibly controllable multiple quantum states., Comment: 8 pages, 3 figures

The rapid development of large language models (LLMs) has been witnessed in recent years. Based on the powerful LLMs, multi-modal LLMs (MLLMs) extend the modality from text to a broader spectrum of domains, attracting widespread attention due to the broader range of application scenarios. As LLMs and MLLMs rely on vast amounts of model parameters and data to achieve emergent capabilities, the importance of data is receiving increasingly widespread attention and recognition. Tracing and analyzing recent data-oriented works for MLLMs, we find that the development of models and data is not two separate paths but rather interconnected. On the one hand, vaster and higher-quality data contribute to better performance of MLLMs; on the other hand, MLLMs can facilitate the development of data. The co-development of multi-modal data and MLLMs requires a clear view of 1) at which development stages of MLLMs specific data-centric approaches can be employed to enhance certain MLLM capabilities, and 2) how MLLMs, utilizing those capabilities, can contribute to multi-modal data in specific roles. To promote the data-model co-development for MLLM community, we systematically review existing works related to MLLMs from the data-model co-development perspective. A regularly maintained project associated with this survey is accessible at https://github.com/modelscope/data-juicer/blob/main/docs/awesome_llm_data.md., Comment: Ongoing work. 21 pages. Related materials are continually maintained and available at https://github.com/modelscope/data-juicer/blob/main/docs/awesome_llm_data.md

Channel and spatial attentions have respectively brought significant improvements in extracting feature dependencies and spatial structure relations for various downstream vision tasks. While their combination is more beneficial for leveraging their individual strengths, the synergy between channel and spatial attentions has not been fully explored, lacking in fully harness the synergistic potential of multi-semantic information for feature guidance and mitigation of semantic disparities. Our study attempts to reveal the synergistic relationship between spatial and channel attention at multiple semantic levels, proposing a novel Spatial and Channel Synergistic Attention module (SCSA). Our SCSA consists of two parts: the Shareable Multi-Semantic Spatial Attention (SMSA) and the Progressive Channel-wise Self-Attention (PCSA). SMSA integrates multi-semantic information and utilizes a progressive compression strategy to inject discriminative spatial priors into PCSA's channel self-attention, effectively guiding channel recalibration. Additionally, the robust feature interactions based on the self-attention mechanism in PCSA further mitigate the disparities in multi-semantic information among different sub-features within SMSA. We conduct extensive experiments on seven benchmark datasets, including classification on ImageNet-1K, object detection on MSCOCO 2017, segmentation on ADE20K, and four other complex scene detection datasets. Our results demonstrate that our proposed SCSA not only surpasses the current state-of-the-art attention but also exhibits enhanced generalization capabilities across various task scenarios. The code and models are available at: https://github.com/HZAI-ZJNU/SCSA.

Typical BCS superconductors are microscopically homogeneous in real space governed by the coherent Cooper pairs with high phase stiffness of superfluid density, which is characterized by a coherence length. However, a periodic oscillation of superconducting order parameter may develop driven by breaking the time-reversal or translational invariance. To date, such modulated orders were specific to each material systems, with a periodicity much larger than the lattice constant. Here we report the direct observation of a uniform lattice-scale pair density wave (PDW) in single-layer FeSe/SrTiO3 films, enforced by peculiar interfacial structure of crystal symmetries breaking. Our spectroscopic imaging scanning tunneling microscopy unravels a spatial modulation of Cooper-pairing gap within a single unit-cell, depending on inequivalent atomic sites. Prominent periodic variation of superfluid density is visualized via Josephson current by a superconducting tip, indicating a real-space oscillation of phase stiffness. Such a lattice-scale superconducting modulation, which coexists with a larger length scale of PDW order, indicates the lattice-scale variation of both pairing strength and phase stiffness. Our findings provide new insights into the intertwined density-wave orders of quasiparticle character in correlated electronic systems, and provoke future studies on the unconventional pairing interaction and phase stiffness in the two-dimensional limit., Comment: 15 pages, 4 figures

Low-dose computed tomography (LDCT) plays a vital role in clinical applications by mitigating radiation risks. Nevertheless, reducing radiation doses significantly degrades image quality. Concurrently, common deep learning methods demand extensive data, posing concerns about privacy, cost, and time constraints. Consequently, we propose a few-shot low-dose CT reconstruction method using Partitioned Hankel-based Diffusion (PHD) models. During the prior learning stage, the projection data is first transformed into multiple partitioned Hankel matrices. Structured tensors are then extracted from these matrices to facilitate prior learning through multiple diffusion models. In the iterative reconstruction stage, an iterative stochastic differential equation solver is employed along with data consistency constraints to update the acquired projection data. Furthermore, penalized weighted least-squares and total variation techniques are introduced to enhance the resulting image quality. The results approximate those of normal-dose counterparts, validating PHD model as an effective and practical model for reducing artifacts and noise while preserving image quality.

Exclusion is an important and universal linguistic skill that humans use to express what they do not want. However, in information retrieval community, there is little research on exclusionary retrieval, where users express what they do not want in their queries. In this work, we investigate the scenario of exclusionary retrieval in document retrieval for the first time. We present ExcluIR, a set of resources for exclusionary retrieval, consisting of an evaluation benchmark and a training set for helping retrieval models to comprehend exclusionary queries. The evaluation benchmark includes 3,452 high-quality exclusionary queries, each of which has been manually annotated. The training set contains 70,293 exclusionary queries, each paired with a positive document and a negative document. We conduct detailed experiments and analyses, obtaining three main observations: (1) Existing retrieval models with different architectures struggle to effectively comprehend exclusionary queries; (2) Although integrating our training data can improve the performance of retrieval models on exclusionary retrieval, there still exists a gap compared to human performance; (3) Generative retrieval models have a natural advantage in handling exclusionary queries. To facilitate future research on exclusionary retrieval, we share the benchmark and evaluation scripts on \url{https://github.com/zwh-sdu/ExcluIR}.

Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts. Our code will be publicly available.

With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications. However, the complexities in coordinating agents' cooperation and LLMs' erratic performance pose notable challenges in developing robust and efficient multi-agent applications. To tackle these challenges, we propose AgentScope, a developer-centric multi-agent platform with message exchange as its core communication mechanism. The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment. Towards robust and flexible multi-agent application, AgentScope provides both built-in and customizable fault tolerance mechanisms. At the same time, it is also armed with system-level support for managing and utilizing multi-modal data, tools, and external knowledge. Additionally, we design an actor-based distribution framework, enabling easy conversion between local and distributed deployments and automatic parallel optimization without extra effort. With these features, AgentScope empowers developers to build applications that fully realize the potential of intelligent agents. We have released AgentScope at https://github.com/modelscope/agentscope, and hope AgentScope invites wider participation and innovation in this fast-moving field., Comment: We have released code on https://github.com/modelscope/agentscope

Among the research topics in multi-agent learning, mixed-motive cooperation is one of the most prominent challenges, primarily due to the mismatch between individual and collective goals. The cutting-edge research is focused on incorporating domain knowledge into rewards and introducing additional mechanisms to incentivize cooperation. However, these approaches often face shortcomings such as the effort on manual design and the absence of theoretical groundings. To close this gap, we model the mixed-motive game as a differentiable game for the ease of illuminating the learning dynamics towards cooperation. More detailed, we introduce a novel optimization method named \textbf{\textit{A}}ltruistic \textbf{\textit{G}}radient \textbf{\textit{A}}djustment (\textbf{\textit{AgA}}) that employs gradient adjustments to progressively align individual and collective objectives. Furthermore, we theoretically prove that AgA effectively attracts gradients to stable fixed points of the collective objective while considering individual interests, and we validate these claims with empirical evidence. We evaluate the effectiveness of our algorithm AgA through benchmark environments for testing mixed-motive collaboration with small-scale agents such as the two-player public good game and the sequential social dilemma games, Cleanup and Harvest, as well as our self-developed large-scale environment in the game StarCraft II., Comment: 19 pages

Segmentation is a critical step in analyzing the developing human fetal brain. There have been vast improvements in automatic segmentation methods in the past several years, and the Fetal Brain Tissue Annotation (FeTA) Challenge 2021 helped to establish an excellent standard of fetal brain segmentation. However, FeTA 2021 was a single center study, and the generalizability of algorithms across different imaging centers remains unsolved, limiting real-world clinical applicability. The multi-center FeTA Challenge 2022 focuses on advancing the generalizability of fetal brain segmentation algorithms for magnetic resonance imaging (MRI). In FeTA 2022, the training dataset contained images and corresponding manually annotated multi-class labels from two imaging centers, and the testing data contained images from these two imaging centers as well as two additional unseen centers. The data from different centers varied in many aspects, including scanners used, imaging parameters, and fetal brain super-resolution algorithms applied. 16 teams participated in the challenge, and 17 algorithms were evaluated. Here, a detailed overview and analysis of the challenge results are provided, focusing on the generalizability of the submissions. Both in- and out of domain, the white matter and ventricles were segmented with the highest accuracy, while the most challenging structure remains the cerebral cortex due to anatomical complexity. The FeTA Challenge 2022 was able to successfully evaluate and advance generalizability of multi-class fetal brain tissue segmentation algorithms for MRI and it continues to benchmark new algorithms. The resulting new methods contribute to improving the analysis of brain development in utero., Comment: Results from FeTA Challenge 2022, held at MICCAI; Manuscript submitted. Supplementary Info (including submission methods descriptions) available here: https://zenodo.org/records/10628648

Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality variation. However, these methods often lead to a higher computational overhead and may introduce interfering information when generating the corresponding images or features. To address this issue, it is critical to leverage pedestrian-attentive features and learn modality-complete and -consistent representation. In this paper, a novel Transferring Modality-Aware Pedestrian Attentive Learning (TMPA) model is proposed, focusing on the pedestrian regions to efficiently compensate for missing modality-specific features. Specifically, we propose a region-based data augmentation module PedMix to enhance pedestrian region coherence by mixing the corresponding regions from different modalities. A lightweight hybrid compensation module, i.e., the Modality Feature Transfer (MFT), is devised to integrate cross attention and convolution networks to fully explore the discriminative modality-complete features with minimal computational overhead. Extensive experiments conducted on the benchmark SYSU-MM01 and RegDB datasets demonstrated the effectiveness of our proposed TMPA model.

Zero-shot coordination (ZSC) is a new cooperative multi-agent reinforcement learning (MARL) challenge that aims to train an ego agent to work with diverse, unseen partners during deployment. The significant difference between the deployment-time partners' distribution and the training partners' distribution determined by the training algorithm makes ZSC a unique out-of-distribution (OOD) generalization challenge. The potential distribution gap between evaluation and deployment-time partners leads to inadequate evaluation, which is exacerbated by the lack of appropriate evaluation metrics. In this paper, we present ZSC-Eval, the first evaluation toolkit and benchmark for ZSC algorithms. ZSC-Eval consists of: 1) Generation of evaluation partner candidates through behavior-preferring rewards to approximate deployment-time partners' distribution; 2) Selection of evaluation partners by Best-Response Diversity (BR-Div); 3) Measurement of generalization performance with various evaluation partners via the Best-Response Proximity (BR-Prox) metric. We use ZSC-Eval to benchmark ZSC algorithms in Overcooked and Google Research Football environments and get novel empirical findings. We also conduct a human experiment of current ZSC algorithms to verify the ZSC-Eval's consistency with human evaluation. ZSC-Eval is now available at https://github.com/sjtu-marl/ZSC-Eval., Comment: Accepted in NeurIPS 2024 Dataset and Benchmark Track

Securing coordination between AI agent and teammates (human players or AI agents) in contexts involving unfamiliar humans continues to pose a significant challenge in Zero-Shot Coordination. The issue of cooperative incompatibility becomes particularly prominent when an AI agent is unsuccessful in synchronizing with certain previously unknown partners. Traditional algorithms have aimed to collaborate with partners by optimizing fixed objectives within a population, fostering diversity in strategies and behaviors. However, these techniques may lead to learning loss and an inability to cooperate with specific strategies within the population, a phenomenon named cooperative incompatibility in learning. In order to solve cooperative incompatibility in learning and effectively address the problem in the context of ZSC, we introduce the Cooperative Open-ended LEarning (COLE) framework, which formulates open-ended objectives in cooperative games with two players using perspectives of graph theory to evaluate and pinpoint the cooperative capacity of each strategy. We present two practical algorithms, specifically \algo and \algoR, which incorporate insights from game theory and graph theory. We also show that COLE could effectively overcome the cooperative incompatibility from theoretical and empirical analysis. Subsequently, we created an online Overcooked human-AI experiment platform, the COLE platform, which enables easy customization of questionnaires, model weights, and other aspects. Utilizing the COLE platform, we enlist 130 participants for human experiments. Our findings reveal a preference for our approach over state-of-the-art methods using a variety of subjective metrics. Moreover, objective experimental outcomes in the Overcooked game environment indicate that our method surpasses existing ones when coordinating with previously unencountered AI agents and the human proxy model., Comment: 46 pages. arXiv admin note: substantial text overlap with arXiv:2302.04831

Trapped-ion has shown great advantages in building quantum computers. While high fidelity entangling-gate has been realized for few ions, how to maintain the high fidelity for large scale trapped-ions still remains an open problem.Here, we present an analysis on arbitrary scale ion chain and focus on motional-related errors, reported as one of the leading error sources in state-of-the-art experiments. We theoretically analyze two-qubit entangling-gate infidelity in a large ion crystal. To verify our result, we develop an efficient numerical simulation algorithm that avoids exponential increases of the Hilbert space dimension. For the motional heating error, We derive a much tighter bound of gate infidelity than previously estimated $O(N\Gamma\tau)$, and we give an intuitive understanding from the trajectories in the phase space of motional modes. Our discoveries may inspire the scheme of pulse design against incoherent errors and shed light on the way toward constructing scalable quantum computers with large ion crystals., Comment: 17 pages, 7 figures

This paper investigates the covert communication in an air-to-ground (A2G) system, where a UAV (Alice) can adopt the omnidirectional microwave (OM) or directional mmWave (DM) transmission mode to transmit covert data to a ground user (Bob) while suffering from the detection of an adversary (Willie). For both the OM and DM modes, we first conduct theoretical analysis to reveal the inherent relationship between the transmit rate/transmit power and basic covert performance metrics in terms of detection error probability (DEP), effective covert rate (ECR), and covert Shannon capacity (CSC). To facilitate the transmission mode selection at Alice, we then explore the optimization of transmit rate and transmit power for ECR/CSC maximization under the OM and DM modes, and further propose a hybrid OM/DM transmission mode which allows the UAV to adaptively select between the OM and DM modes to achieve the maximum ECR and CSC at a given location of UAV. Finally, extensive numerical results are provided to illustrate the covert performances of the concerned A2G system under different transmission modes, and demonstrate that the hybrid OM/DM transmission mode outperforms the pure OM or DM mode in terms of covert performance.

A low-cost, accurate device to measure and record knee range of motion (ROM) is of the essential need to improve confidence in at-home rehabilitation. It is to reduce hospital stay duration and overall medical cost after Total Knee Arthroplasty (TKA) procedures. The shift in Medicare funding from pay-as-you-go to the Bundled Payments for Care Improvement (BPCI) has created a push towards at-home care over extended hospital stays. It has heavily affected TKA patients, who typically undergo physical therapy at the clinic after the procedure to ensure full recovery of ROM. In this paper, we use accelerometers to create a ROM sensor that can be integrated into the post-operative surgical dressing, so that the cost of the sensors can be included in the bundled payments. In this paper, we demonstrate the efficacy of our method in comparison to the baseline computer vision method. Our results suggest that calculating angular displacement from accelerometer sensors demonstrates accurate ROM recordings under both stationary and walking conditions. The device would keep track of angle measurements and alert the patient when certain angle thresholds have been crossed, allowing patients to recover safely at home instead of going to multiple physical therapy sessions. The affordability of our sensor makes it more accessible to patients in need., Comment: 8 pages, 16 figures, 1 table, submitted to BSN conference 2022

Electrocardiogram (ECG) is a simple non-invasive measure to identify heart-related issues such as irregular heartbeats known as arrhythmias. While artificial intelligence and machine learning is being utilized in a wide range of healthcare related applications and datasets, many arrhythmia classifiers using deep learning methods have been proposed in recent years. However, sizes of the available datasets from which to build and assess machine learning models is often very small and the lack of well-annotated public ECG datasets is evident. In this paper, we propose a deep transfer learning framework that is aimed to perform classification on a small size training dataset. The proposed method is to fine-tune a general-purpose image classifier ResNet-18 with MIT-BIH arrhythmia dataset in accordance with the AAMI EC57 standard. This paper further investigates many existing deep learning models that have failed to avoid data leakage against AAMI recommendations. We compare how different data split methods impact the model performance. This comparison study implies that future work in arrhythmia classification should follow the AAMI EC57 standard when using any including MIT-BIH arrhythmia dataset., Comment: 14 pages, 5 figures, 4 tables, submitted to The 4th International Conference on Computing and Data Science (CONF-CDS 2022)