Search

Asian Americans as a group are overrepresented among STEM college graduates and have the highest average college enrollment rate of any racial or ethnic category. Thus, Asian Americans are typically excluded from educational interventions directed at improving STEM education for Students of Color because they are not considered to be underrepresented minorities. However, statistics obscure the individual needs of the more than 20 ethnic subgroups that fall under the umbrella term Asian Americans. Using a participatory action research approach, this paper documents the institutional and sociocultural factors that push out HMoob (or Hmong) American college students from STEM programs at one large, predominantly White university; and the coordinate processes of gatekeeping and transactional advising that either redirect those students toward non-STEM programs or force them out of the university completely.

This article clarifies historical and sociocultural factors that impact the role of STEM in the racialization of Asian Americans. Drawing on critical race and other theories of Asian American racialization, and a review of empirical research on the experiences of Asian American college students in STEM, we develop a conceptual framework called "STEM Asianization" that highlights the role of STEM ideology in the model minority racialization of Asian Americans. Consequences for Asian American students include (1) erasure of the intersectional experiences of minoritized Asian American students; (2) dehumanization of Asian Americans and establishment of a bamboo ceiling; (3) representation of Asian Americans as a perpetual foreigner/Yellow Peril during times of cultural and political crisis; and (4) representation of Asian Americans who cannot or do not conform to the STEM achievement narrative as a failed minority. We argue that STEM Asianization reproduces White supremacy by ideologically reinforcing the colorblind meritocracy of STEM institutions in the United States. [Additional funding provided by the Wisconsin Louis Stokes Alliance for Minority Participation.]

In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens. We conduct a thorough evaluation of Hunyuan-Large's superior performance across various benchmarks including language understanding and generation, logical reasoning, mathematical problem-solving, coding, long-context, and aggregated tasks, where it outperforms LLama3.1-70B and exhibits comparable performance when compared to the significantly larger LLama3.1-405B model. Key practice of Hunyuan-Large include large-scale synthetic data that is orders larger than in previous literature, a mixed expert routing strategy, a key-value cache compression technique, and an expert-specific learning rate strategy. Additionally, we also investigate the scaling laws and learning rate schedule of mixture of experts models, providing valuable insights and guidances for future model development and optimization. The code and checkpoints of Hunyuan-Large are released to facilitate future innovations and applications. Codes: https://github.com/Tencent/Hunyuan-Large Models: https://huggingface.co/tencent/Tencent-Hunyuan-Large, Comment: 17 pages, 4 Figures

The Chasing All Transients Constellation Hunters (CATCH) space mission is focused on exploring the dynamic universe via X-ray follow-up observations of various transients. The first pathfinder of the CATCH mission, CATCH-1, was launched on June 22, 2024, alongside the Space-based multiband astronomical Variable Objects Monitor (SVOM) mission. CATCH-1 is equipped with narrow-field optimized Micro Pore Optics (MPOs) featuring a large effective area and incorporates four Silicon Drift Detectors (SDDs) in its focal plane. This paper presents the system calibration results conducted before the satellite integration. Utilizing the data on the performance of the mirror and detectors obtained through the system calibration, combined with simulated data, the ground calibration database can be established. Measuring the relative positions of the mirror and detector system, which were adjusted during system calibration, allows for accurate installation of the entire satellite. Furthermore, the paper outlines the operational workflow of the ground network post-satellite launch.

Despite the remarkable success of Large Language Models (LLMs), evaluating their outputs' quality regarding preference remains a critical challenge. Existing works usually leverage a powerful LLM (e.g., GPT4) as the judge for comparing LLMs' output pairwisely, yet such model-based evaluator is vulnerable to conflicting preference, i.e., output A is better than B, B than C, but C than A, causing contradictory evaluation results. To improve model-based preference evaluation, we introduce GED (Preference Graph Ensemble and Denoise), a novel approach that leverages multiple model-based evaluators to construct preference graphs, and then ensemble and denoise these graphs for better, non-contradictory evaluation results. In particular, our method consists of two primary stages: aggregating evaluations into a unified graph and applying a denoising process to eliminate cyclic inconsistencies, ensuring a directed acyclic graph (DAG) structure. We provide theoretical guarantees for our framework, demonstrating its efficacy in recovering the ground truth preference structure. Extensive experiments across ten benchmark datasets show that GED outperforms baseline methods in model ranking, response selection, and model alignment tasks. Notably, GED combines weaker evaluators like Llama3-8B, Mistral-7B, and Qwen2-7B to surpass the performance of stronger evaluators like Qwen2-72B, highlighting its ability to enhance evaluation reliability and improve model performance.

As the field of Multimodal Large Language Models (MLLMs) continues to evolve, their potential to revolutionize artificial intelligence is particularly promising, especially in addressing mathematical reasoning tasks. Current mathematical benchmarks predominantly focus on evaluating MLLMs' problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection, for enhancing reasoning capability in complicated settings. To fill this gap, we formally formulate the new task: multimodal error detection, and introduce ErrorRadar, the first benchmark designed to assess MLLMs' capabilities in such a task. ErrorRadar evaluates two sub-tasks: error step identification and error categorization, providing a comprehensive framework for evaluating MLLMs' complex mathematical reasoning ability. It consists of 2,500 high-quality multimodal K-12 mathematical problems, collected from real-world student interactions in an educational organization, with rigorous annotation and rich metadata such as problem type and error category. Through extensive experiments, we evaluated both open-source and closed-source representative MLLMs, benchmarking their performance against educational expert evaluators. Results indicate significant challenges still remain, as GPT-4o with best performance is still around 10% behind human evaluation. The dataset will be available upon acceptance.

Recent studies in text-to-image customization show great success in generating personalized object variants given several images of a subject. While existing methods focus more on preserving the identity of the subject, they often fall short of controlling the spatial relationship between objects. In this work, we introduce GroundingBooth, a framework that achieves zero-shot instance-level spatial grounding on both foreground subjects and background objects in the text-to-image customization task. Our proposed text-image grounding module and masked cross-attention layer allow us to generate personalized images with both accurate layout alignment and identity preservation while maintaining text-image coherence. With such layout control, our model inherently enables the customization of multiple subjects at once. Our model is evaluated on both layout-guided image synthesis and reference-based customization tasks, showing strong results compared to existing methods. Our work is the first work to achieve a joint grounding on both subject-driven foreground generation and text-driven background generation.

Monocular visual odometry (MVO) is vital in autonomous navigation and robotics, providing a cost-effective and flexible motion tracking solution, but the inherent scale ambiguity in monocular setups often leads to cumulative errors over time. In this paper, we present BEV-ODOM, a novel MVO framework leveraging the Bird's Eye View (BEV) Representation to address scale drift. Unlike existing approaches, BEV-ODOM integrates a depth-based perspective-view (PV) to BEV encoder, a correlation feature extraction neck, and a CNN-MLP-based decoder, enabling it to estimate motion across three degrees of freedom without the need for depth supervision or complex optimization techniques. Our framework reduces scale drift in long-term sequences and achieves accurate motion estimation across various datasets, including NCLT, Oxford, and KITTI. The results indicate that BEV-ODOM outperforms current MVO methods, demonstrating reduced scale drift and higher accuracy.

Existing Image Quality Assessment (IQA) methods achieve remarkable success in analyzing quality for overall image, but few works explore quality analysis for Regions of Interest (ROIs). The quality analysis of ROIs can provide fine-grained guidance for image quality improvement and is crucial for scenarios focusing on region-level quality. This paper proposes a novel network, SEAGULL, which can SEe and Assess ROIs quality with GUidance from a Large vision-Language model. SEAGULL incorporates a vision-language model (VLM), masks generated by Segment Anything Model (SAM) to specify ROIs, and a meticulously designed Mask-based Feature Extractor (MFE) to extract global and local tokens for specified ROIs, enabling accurate fine-grained IQA for ROIs. Moreover, this paper constructs two ROI-based IQA datasets, SEAGULL-100w and SEAGULL-3k, for training and evaluating ROI-based IQA. SEAGULL-100w comprises about 100w synthetic distortion images with 33 million ROIs for pre-training to improve the model's ability of regional quality perception, and SEAGULL-3k contains about 3k authentic distortion ROIs to enhance the model's ability to perceive real world distortions. After pre-training on SEAGULL-100w and fine-tuning on SEAGULL-3k, SEAGULL shows remarkable performance on fine-grained ROI quality assessment. Code and datasets are publicly available at the https://github.com/chencn2020/Seagull.

This paper presents a confidence level-based distributionally information gap decision theory (CL-DIGDT) framework for the two-stage robust optimal operation of distribution networks, aiming at deriving an optimal operational scheme capable of addressing uncertainties related to renewable energy and load demands. Building on conventional IGDT, the proposed framework utilizes the confidence level to capture the asymmetric characteristics of uncertainties and maximize the risk-averse capability of the solution in a probabilistic manner. To account for the probabilistic consideration, the imprecise Dirichlet model is employed to construct the ambiguity sets of uncertainties, reducing reliance on precise probability distributions. Consequently, a two-stage robust optimal operation model for distribution networks using CL-DIGDT is developed. An iterative method is proposed to solve the model and determine the upper and lower bounds of the objective function. Case study demonstrates that the proposed approach yields a more robust and statistically optimized solution with required accuracy compared to existing method, contributing to a reduction in first-stage cost by 0.84%, second-stage average cost by 6.7%, and significantly increasing the reliability of the solution by 8%.

Due to power attenuation, improving transmission efficiency in the radio-frequency (RF) band remains a significant challenge, which hinders advancements in various fields of the Internet of Things (IoT), such as wireless power transfer (WPT) and wireless communication. Array design and retro-directive beamforming (RD-BF) techniques offer simple and effective ways to enhance transmission efficiency. However, when the target is an array or in the near field, the RD-BF system (RD-BFS) cannot radiate more energy to the target due to phase irregularities in the target region, resulting in challenges in achieving higher efficiency. To address this issue, we propose the RF-based resonant beam system (RF-RBS), which adaptively optimizes phase and power distribution between transmitting and receiving arrays by leveraging the resonance mechanism to achieve higher transmission efficiency. We analyze the system structure and develop an analytical model to evaluate power flow and resonance establishment. Numerical analysis demonstrates that the proposed RF-RBS achieves self-alignment without beam control and provides higher transmission efficiency compared to RD-BFS, with improvements of up to 16%. This self-alignment capability allows the system to effectively transfer power and information across varying distances and offsets. The numerical results indicate the capability to transmit watt-level power and achieve 21 bps/Hz of downlink spectral efficiency in indoor settings, highlighting the advantages of RF-RBS in information and power transfer for mobile applications.

The success of deep neural networks has driven numerous research studies and applications from Euclidean to non-Euclidean data. However, there are increasing concerns about privacy leakage, as these networks rely on processing private data. Recently, a new type of privacy attack, the model inversion attacks (MIAs), aims to extract sensitive features of private data for training by abusing access to a well-trained model. The effectiveness of MIAs has been demonstrated in various domains, including images, texts, and graphs. These attacks highlight the vulnerability of neural networks and raise awareness about the risk of privacy leakage within the research community. Despite the significance, there is a lack of systematic studies that provide a comprehensive overview and deeper insights into MIAs across different domains. This survey aims to summarize up-to-date MIA methods in both attacks and defenses, highlighting their contributions and limitations, underlying modeling principles, optimization challenges, and future directions. We hope this survey bridges the gap in the literature and facilitates future research in this critical area. Besides, we are maintaining a repository to keep track of relevant research at https://github.com/AndrewZhou924/Awesome-model-inversion-attack., Comment: 40 pages, 17 figures

This article propose a whole-body impedance coordinative control framework for a wheel-legged humanoid robot to achieve adaptability on complex terrains while maintaining robot upper body stability. The framework contains a bi-level control strategy. The outer level is a variable damping impedance controller, which optimizes the damping parameters to ensure the stability of the upper body while holding an object. The inner level employs Whole-Body Control (WBC) optimization that integrates real-time terrain estimation based on wheel-foot position and force data. It generates motor torques while accounting for dynamic constraints, joint limits,friction cones, real-time terrain updates, and a model-free friction compensation strategy. The proposed whole-body coordinative control method has been tested on a recently developed quadruped humanoid robot. The results demonstrate that the proposed algorithm effectively controls the robot, maintaining upper body stability to successfully complete a water-carrying task while adapting to varying terrains.

We consider a real-time state reconstruction system for industrial metaverse. The time-varying physical process states in real space are captured by multiple sensors via wireless links, and then reconstructed in virtual space. In this paper, we use the spatial-temporal correlation of the sensor data of interest to infer the real-time data of the target sensor to reduce the mean squared error (MSE) of reconstruction for industrial metaverse under short-packet transmission (SPT). Both synchronous and asynchronous transmission modes for multiple sensors are considered. It is proved that the average MSE of reconstruction and average block error probability (BLEP) have a positive correlation under inference with synchronous transmission scheme, and they have a negative correlation in some conditions under inference with asynchronous transmission scheme. Also, it is proved that the average MSE of reconstruction with inference can be significantly lower than that without inference, even under weak mean squared spatial correlation (MSSC). In addition, closed-form MSSC thresholds are derived for the superiority regions of the inference with synchronous transmission and inference with asynchronous transmission schemes, respectively. Adaptations of blocklength and time shift of asynchronous transmission are conducted to minimize the average MSE of reconstruction. Simulation results show that the two schemes significantly outperform the no inference case, with an average MSE reduction of more than 50%.

The construction of attack technique knowledge graphs aims to transform various types of attack knowledge into structured representations for more effective attack procedure modeling. Existing methods typically rely on textual data, such as Cyber Threat Intelligence (CTI) reports, which are often coarse-grained and unstructured, resulting in incomplete and inaccurate knowledge graphs. To address these issues, we expand attack knowledge sources by incorporating audit logs and static code analysis alongside CTI reports, providing finer-grained data for constructing attack technique knowledge graphs. We propose MultiKG, a fully automated framework that integrates multiple threat knowledge sources. MultiKG processes data from CTI reports, dynamic logs, and static code separately, then merges them into a unified attack knowledge graph. Through system design and the utilization of the Large Language Model (LLM), MultiKG automates the analysis, construction, and merging of attack graphs across these sources, producing a fine-grained, multi-source attack knowledge graph. We implemented MultiKG and evaluated it using 1,015 real attack techniques and 9,006 attack intelligence entries from CTI reports. Results show that MultiKG effectively extracts attack knowledge graphs from diverse sources and aggregates them into accurate, comprehensive representations. Through case studies, we demonstrate that our approach directly benefits security tasks such as attack reconstruction and detection., Comment: 21 pages, 15 figures, 8 tables

The rapid development of generative AI technologies, including large language models (LLMs), has brought transformative changes to various fields. However, deploying such advanced models on mobile and edge devices remains challenging due to their high computational, memory, communication, and energy requirements. To address these challenges, we propose a model-centric framework for democratizing generative AI deployment on mobile and edge networks. First, we comprehensively review key compact model strategies, such as quantization, model pruning, and knowledge distillation, and present key performance metrics to optimize generative AI for mobile deployment. Next, we provide a focused review of mobile and edge networks, emphasizing the specific challenges and requirements of these environments. We further conduct a case study demonstrating the effectiveness of these strategies by deploying LLMs on real mobile edge devices. Experimental results highlight the practicality of democratized LLMs, with significant improvements in generalization accuracy, hallucination rate, accessibility, and resource consumption. Finally, we discuss potential research directions to further advance the deployment of generative AI in resource-constrained environments., Comment: 9 pages, 5 figures

Although connections between flaring blazars and some IceCube neutrinos have been established, the dominant sources for the bulk extragalactic neutrino emissions are still unclear and one widely suggested candidate is a population of radio galaxies. Because of their relatively low $\gamma$-ray radiation luminosities ($L_\gamma$), it is rather challenging to confirm such a hypothesis with the neutrino/GeV flare association. Here we report on the search for GeV $\gamma$-ray counterpart of the neutrino IC-180213A and show that the nearby ($z$ = 0.03) broad line radio galaxy 3C 120 is the unique co-spatial GeV $\gamma$-ray source in a half-year epoch around the neutrino detection. Particularly, an intense $\gamma$-ray flare, the second strongest one among the entire 16-year period, is temporally coincident with the detection of IC-180213A. Accompanying optical flare is observed, too. We also find that the IC-180213A/3C 120 association well follows the $L_\gamma$-$D_{L}^{2}$ correlation for the (candidate) neutrino sources including NGC 1068 and some blazars. These facts are strongly in favor of 3C 120 as a high energy neutrino emitter and provide the first piece of evidence for the radio galaxy origin of some PeV neutrinos., Comment: 17 pages,4 figures, 1 table

Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics. We introduce Spider 2.0, an evaluation framework comprising 632 real-world text-to-SQL workflow problems derived from enterprise-level database use cases. The databases in Spider 2.0 are sourced from real data applications, often containing over 1,000 columns and stored in local or cloud database systems such as BigQuery and Snowflake. We show that solving problems in Spider 2.0 frequently requires understanding and searching through database metadata, dialect documentation, and even project-level codebases. This challenge calls for models to interact with complex SQL workflow environments, process extremely long contexts, perform intricate reasoning, and generate multiple SQL queries with diverse operations, often exceeding 100 lines, which goes far beyond traditional text-to-SQL challenges. Our evaluations indicate that based on o1-preview, our code agent framework successfully solves only 17.0% of the tasks, compared with 91.2% on Spider 1.0 and 73.0% on BIRD. Our results on Spider 2.0 show that while language models have demonstrated remarkable performance in code generation -- especially in prior text-to-SQL benchmarks -- they require significant improvement in order to achieve adequate performance for real-world enterprise usage. Progress on Spider 2.0 represents crucial steps towards developing intelligent, autonomous, code agents for real-world enterprise settings. Our code, baseline models, and data are available at https://spider2-sql.github.io.

The increasing popularity of deep learning models has created new opportunities for developing AI-based recommender systems. Designing recommender systems using deep neural networks requires careful architecture design, and further optimization demands extensive co-design efforts on jointly optimizing model architecture and hardware. Design automation, such as Automated Machine Learning (AutoML), is necessary to fully exploit the potential of recommender model design, including model choices and model-hardware co-design strategies. We introduce a novel paradigm that utilizes weight sharing to explore abundant solution spaces. Our paradigm creates a large supernet to search for optimal architectures and co-design strategies to address the challenges of data multi-modality and heterogeneity in the recommendation domain. From a model perspective, the supernet includes a variety of operators, dense connectivity, and dimension search options. From a co-design perspective, it encompasses versatile Processing-In-Memory (PIM) configurations to produce hardware-efficient models. Our solution space's scale, heterogeneity, and complexity pose several challenges, which we address by proposing various techniques for training and evaluating the supernet. Our crafted models show promising results on three Click-Through Rates (CTR) prediction benchmarks, outperforming both manually designed and AutoML-crafted models with state-of-the-art performance when focusing solely on architecture search. From a co-design perspective, we achieve 2x FLOPs efficiency, 1.8x energy efficiency, and 1.5x performance improvements in recommender models., Comment: Accepted in ACM Transactions on Recommender Systems. arXiv admin note: substantial text overlap with arXiv:2207.07187

Traditional decision tree algorithms are explainable but struggle with non-linear, high-dimensional data, limiting its applicability in complex decision-making. Neural networks excel at capturing complex patterns but sacrifice explainability in the process. In this work, we present GPTree, a novel framework combining explainability of decision trees with the advanced reasoning capabilities of LLMs. GPTree eliminates the need for feature engineering and prompt chaining, requiring only a task-specific prompt and leveraging a tree-based structure to dynamically split samples. We also introduce an expert-in-the-loop feedback mechanism to further enhance performance by enabling human intervention to refine and rebuild decision paths, emphasizing the harmony between human expertise and machine intelligence. Our decision tree achieved a 7.8% precision rate for identifying "unicorn" startups at the inception stage of a startup, surpassing gpt-4o with few-shot learning as well as the best human decision-makers (3.1% to 5.6%).

Large Language Models (LLMs) deployed on edge devices, known as edge LLMs, need to continuously fine-tune their model parameters from user-generated data under limited resource constraints. However, most existing learning methods are not applicable for edge LLMs because of their reliance on high resources and low learning capacity. Prompt tuning (PT) has recently emerged as an effective fine-tuning method for edge LLMs by only modifying a small portion of LLM parameters, but it suffers from user domain shifts, resulting in repetitive training and losing resource efficiency. Conventional techniques to address domain shift issues often involve complex neural networks and sophisticated training, which are incompatible for PT for edge LLMs. Therefore, an open research question is how to address domain shift issues for edge LLMs with limited resources. In this paper, we propose a prompt tuning framework for edge LLMs, exploiting the benefits offered by non-volatile computing-in-memory (NVCiM) architectures. We introduce a novel NVCiM-assisted PT framework, where we narrow down the core operations to matrix-matrix multiplication, which can then be accelerated by performing in-situ computation on NVCiM. To the best of our knowledge, this is the first work employing NVCiM to improve the edge LLM PT performance., Comment: Accepted by DATE 2025

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the \emph{structure constraint} with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at \href{https://github.com/WangJingyao07/NeuronML}{https://github.com/WangJingyao07/NeuronML}.

We introduce BLIP3-KALE, a dataset of 218 million image-text pairs that bridges the gap between descriptive synthetic captions and factual web-scale alt-text. KALE augments synthetic dense image captions with web-scale alt-text to generate factually grounded image captions. Our two-stage approach leverages large vision-language models and language models to create knowledge-augmented captions, which are then used to train a specialized VLM for scaling up the dataset. We train vision-language models on KALE and demonstrate improvements on vision-language tasks. Our experiments show the utility of KALE for training more capable and knowledgeable multimodal models. We release the KALE dataset at https://huggingface.co/datasets/Salesforce/blip3-kale

Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prompt optimization. During inference, they may further retrieve several semantically-related exemplars and concatenate them to the optimized prompts to improve the performance. However, those works only utilize the feedback at the current step, ignoring historical and unseleccted feedbacks which are potentially beneficial. Moreover, the selection of exemplars only considers the general semantic relationship and may not be optimal in terms of task performance and matching with the optimized prompt. In this work, we propose an Exemplar-Guided Reflection with Memory mechanism (ERM) to realize more efficient and accurate prompt optimization. Specifically, we design an exemplar-guided reflection mechanism where the feedback generation is additionally guided by the generated exemplars. We further build two kinds of memory to fully utilize the historical feedback information and support more effective exemplar retrieval. Empirical evaluations show our method surpasses previous state-of-the-arts with less optimization steps, i.e., improving F1 score by 10.1 on LIAR dataset, and reducing half of the optimization steps on ProTeGi.

Instruction-guided image editing methods have demonstrated significant potential by training diffusion models on automatically synthesized or manually annotated image editing pairs. However, these methods remain far from practical, real-life applications. We identify three primary challenges contributing to this gap. Firstly, existing models have limited editing skills due to the biased synthesis process. Secondly, these methods are trained with datasets with a high volume of noise and artifacts. This is due to the application of simple filtering methods like CLIP-score. Thirdly, all these datasets are restricted to a single low resolution and fixed aspect ratio, limiting the versatility to handle real-world use cases. In this paper, we present \omniedit, which is an omnipotent editor to handle seven different image editing tasks with any aspect ratio seamlessly. Our contribution is in four folds: (1) \omniedit is trained by utilizing the supervision from seven different specialist models to ensure task coverage. (2) we utilize importance sampling based on the scores provided by large multimodal models (like GPT-4o) instead of CLIP-score to improve the data quality. (3) we propose a new editing architecture called EditNet to greatly boost the editing success rate, (4) we provide images with different aspect ratios to ensure that our model can handle any image in the wild. We have curated a test set containing images of different aspect ratios, accompanied by diverse instructions to cover different tasks. Both automatic evaluation and human evaluations demonstrate that \omniedit can significantly outperform all the existing models. Our code, dataset and model will be available at \url{https://tiger-ai-lab.github.io/OmniEdit/}, Comment: 21 pages

In this paper, we study an optimal stopping problem in the presence of model uncertainty and regime switching. The max-min formulation for robust control and the dynamic programming approach are adopted to establish a general theoretical framework for such kind of problem. First, based on the dynamic programming principle, the value function of the optimal stopping problem is characterized as the unique viscosity solution to the associated Hamilton-Jacobi-Bellman equation. Then, the so-called smooth-fit principle for optimal stopping problems is proved in the current context, and a verification theorem consisting of a set of sufficient conditions for robust optimality is established. Moreover, when the Markov chain has a large state space and exhibits a two-time-scale structure, a singular perturbation approach is utilized to reduce the complexity involved and obtain an asymptotically optimal solution. Finally, an example of choosing the best time to sell a stock is provided, in which numerical experiments are reported to illustrate the implications of model uncertainty and regime switching.

Data is the new oil of the 21st century. The growing trend of trading data for greater welfare has led to the emergence of data markets. A data market is any mechanism whereby the exchange of data products including datasets and data derivatives takes place as a result of data buyers and data sellers being in contact with one another, either directly or through mediating agents. It serves as a coordinating mechanism by which several functions, including the pricing and the distribution of data as the most important ones, interact to make the value of data fully exploited and enhanced. In this article, we present a comprehensive survey of this important and emerging direction from the aspects of data search, data productization, data transaction, data pricing, revenue allocation as well as privacy, security, and trust issues. We also investigate the government policies and industry status of data markets across different countries and different domains. Finally, we identify the unresolved challenges and discuss possible future directions for the development of data markets.

Urban Air Mobility (UAM), powered by flying cars, is poised to revolutionize urban transportation by expanding vehicle travel from the ground to the air. This advancement promises to alleviate congestion and enable faster commutes. However, the fast travel speeds mean vehicles will encounter vastly different environments during a single journey. As a result, onboard learning systems need access to extensive environmental data, leading to high costs in data collection and training. These demands conflict with the limited in-vehicle computing and battery resources. Fortunately, learning model sharing offers a solution. Well-trained local Deep Learning (DL) models can be shared with other vehicles, reducing the need for redundant data collection and training. However, this sharing process relies heavily on efficient vehicular communications in UAM. To address these challenges, this paper leverages the multi-hop Reconfigurable Intelligent Surface (RIS) technology to improve DL model sharing between distant flying cars. We also employ knowledge distillation to reduce the size of the shared DL models and enable efficient integration of non-identical models at the receiver. Our approach enhances model sharing and onboard learning performance for cars entering new environments. Simulation results show that our scheme improves the total reward by 85% compared to benchmark methods., Comment: 13pages, 17 figures

Autoregressive modeling has been a huge success in the field of natural language processing (NLP). Recently, autoregressive models have emerged as a significant area of focus in computer vision, where they excel in producing high-quality visual content. Autoregressive models in NLP typically operate on subword tokens. However, the representation strategy in computer vision can vary in different levels, \textit{i.e.}, pixel-level, token-level, or scale-level, reflecting the diverse and hierarchical nature of visual data compared to the sequential structure of language. This survey comprehensively examines the literature on autoregressive models applied to vision. To improve readability for researchers from diverse research backgrounds, we start with preliminary sequence representation and modeling in vision. Next, we divide the fundamental frameworks of visual autoregressive models into three general sub-categories, including pixel-based, token-based, and scale-based models based on the strategy of representation. We then explore the interconnections between autoregressive models and other generative models. Furthermore, we present a multi-faceted categorization of autoregressive models in computer vision, including image generation, video generation, 3D generation, and multi-modal generation. We also elaborate on their applications in diverse domains, including emerging domains such as embodied AI and 3D medical AI, with about 250 related references. Finally, we highlight the current challenges to autoregressive models in vision with suggestions about potential research directions. We have also set up a Github repository to organize the papers included in this survey at: \url{https://github.com/ChaofanTao/Autoregressive-Models-in-Vision-Survey}.

Although large language models (LLMs) have been assessed for general medical knowledge using medical licensing exams, their ability to effectively support clinical decision-making tasks, such as selecting and using medical calculators, remains uncertain. Here, we evaluate the capability of both medical trainees and LLMs to recommend medical calculators in response to various multiple-choice clinical scenarios such as risk stratification, prognosis, and disease diagnosis. We assessed eight LLMs, including open-source, proprietary, and domain-specific models, with 1,009 question-answer pairs across 35 clinical calculators and measured human performance on a subset of 100 questions. While the highest-performing LLM, GPT-4o, provided an answer accuracy of 74.3% (CI: 71.5-76.9%), human annotators, on average, outperformed LLMs with an accuracy of 79.5% (CI: 73.5-85.0%). With error analysis showing that the highest-performing LLMs continue to make mistakes in comprehension (56.6%) and calculator knowledge (8.1%), our findings emphasize that humans continue to surpass LLMs on complex clinical tasks such as calculator recommendation.

Clarifying the physical origin of valley polarization and exploring promising ferrovalley materials are conducive to the application of valley degrees of freedom in the field of information storage. Here, we explore two novel altermagnetic semiconductors (monolayers Nb2Se2O and Nb2SeTeO) with N\'eel temperature above room temperature based on first-principles calculations. It reveals that uniaxial strain induces valley polarization without spin-orbital coupling (SOC) in altermagnets owing to the piezovalley effect, while uniaxial compressive strain transforms the intrinsic ferrovalley semiconductor into a semimetal, half metal and metal. Moreover, moderate biaxial strain renders Janus monolayer Nb2SeTeO to robust Dirac-like band dispersion. The SOC and intrinsic in-plane magnetocrystalline anisotropy energy induce Dirac-like altermagnets to generate apparent valley polarization through magnetovalley coupling. In terms of SOC perturbation, we elucidate the physical mechanism behind in-plane-magnetization induced valley polarization and demonstrate the magnitude of valley polarization is positively correlated with the square of SOC strength and negatively correlated with the bandgap. The present work reveals the physical origin of valley polarization in altermagnets and expands the application of ferrovalley at room temperature in valleytronics., Comment: 14 pages, 6 figures

The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its success, a critical challenge persists: long tokens, rich in semantic information, have fewer occurrences in tokenized datasets compared to short tokens, which can result in imbalanced learning issue across different tokens. To address that, we propose LBPE, which prioritizes long tokens during the encoding process. LBPE generates tokens according to their reverse ranks of token length rather than their ranks in the vocabulary, granting longer tokens higher priority during the encoding process. Consequently, LBPE smooths the frequency differences between short and long tokens, and thus mitigates the learning imbalance. Extensive experiments across diverse language modeling tasks demonstrate that LBPE consistently outperforms the original BPE, well demonstrating its effectiveness., Comment: arXiv admin note: text overlap with arXiv:2404.17808

Narrow-gap rare-earth Zintl phases frequently exhibit fascinating physical phenomena due to their various crystal structures, complex magnetic properties, and tunable transport behaviors. Here we report the synthesis, magnetic, thermodynamic, and transport properties of a Eu-containing Zintl arsenide, Eu$_{11}$Zn$_6$As$_{12}$, which consists of infinite chains of Eu cations and anionic frameworks constructed from corner-sharing ZnAs$_4$ tetrahedra. Eu$_{11}$Zn$_6$As$_{12}$ exhibits complicated magnetic behavior owing to intricate exchange interactions mediated by the discrete anionic fragments. Two long-range magnetic transitions at 22 K ($T_\mathrm{N}$) and 9 K ($T^*$), as well as exceptionally strong ferromagnetic fluctuations around 29 K ($T_\mathrm{F}$), are indicated by the susceptibility, heat capacity and resistivity measurements. Besides, Eu$_{11}$Zn$_6$As$_{12}$ displays metallic behavior, attributable to the hole carriers doped by slight Eu vacancies or the mixed valence of Eu$^{2+}$ and Eu$^{3+}$. A prominent resistivity peak occurs around $T_\mathrm{N}$, which is rapidly suppressed by the applied field, leading to a prominent negative magnetoresistance effect. A resistivity hysteresis is observed below 5 K, caused by a small net ferromagnetic component. Our study presents the distinct magnetic and transport properties of Eu$_{11}$Zn$_6$As$_{12}$, and further experiments are required to elucidate the origin of these novel behaviors. Moreover, our findings demonstrate that Eu-based Zintl phases are a fertile ground to study the interplay between magnetism and charge transport.

This paper proposes ProEdit - a simple yet effective framework for high-quality 3D scene editing guided by diffusion distillation in a novel progressive manner. Inspired by the crucial observation that multi-view inconsistency in scene editing is rooted in the diffusion model's large feasible output space (FOS), our framework controls the size of FOS and reduces inconsistency by decomposing the overall editing task into several subtasks, which are then executed progressively on the scene. Within this framework, we design a difficulty-aware subtask decomposition scheduler and an adaptive 3D Gaussian splatting (3DGS) training strategy, ensuring high quality and efficiency in performing each subtask. Extensive evaluation shows that our ProEdit achieves state-of-the-art results in various scenes and challenging editing tasks, all through a simple framework without any expensive or sophisticated add-ons like distillation losses, components, or training procedures. Notably, ProEdit also provides a new way to control, preview, and select the "aggressivity" of editing operation during the editing process., Comment: NeurIPS 2024. Project Page: https://immortalco.github.io/ProEdit/

Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion models as a standalone component for perception tasks, employing them either solely for off-the-shelf data augmentation or as mere feature extractors. In contrast to these isolated and thus sub-optimal efforts, we introduce a unified, versatile, diffusion-based framework, Diff-2-in-1, that can simultaneously handle both multi-modal data generation and dense visual perception, through a unique exploitation of the diffusion-denoising process. Within this framework, we further enhance discriminative visual perception via multi-modal generation, by utilizing the denoising network to create multi-modal data that mirror the distribution of the original training set. Importantly, Diff-2-in-1 optimizes the utilization of the created diverse and faithful data by leveraging a novel self-improving learning mechanism. Comprehensive experimental evaluations validate the effectiveness of our framework, showcasing consistent performance improvements across various discriminative backbones and high-quality multi-modal data generation characterized by both realism and usefulness., Comment: 26 pages, 14 figures

Machine-learned potentials (MLPs) have been extensively used to obtain the lattice thermal conductivity via atomistic simulations. However, the impact of force errors in various MLPs on thermal transport has not been widely recognized and remains to be fully understood. Here, we employ MLP-driven molecular dynamics (MD) and anharmonic lattice dynamics (LD) to systematically investigate how the calculated thermal conductivity varies with the force errors, using boron arsenide as a prototypical material. We consistently observe an underestimation of thermal conductivity in MD simulations with three different MLPs including the neuroevolution potential, deep potential, and moment tensor potential. We provide a robust extrapolation scheme based on controlled force noises via the Langevin thermostat to correct this underestimation. The corrected results achieve a good agreement with previous experimental measurement from 200 K to 600 K. In contrast, the thermal conductivity values from LD calculations with MLPs readily align with the experimental data, which is attributed to the much smaller effects of the force errors on the force-constant calculations.

Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional execution-based feedback, these models can act as agents with capabilities to self-refine and improve generated code autonomously. However, on challenging coding tasks with extremely large search space, current agentic approaches still struggle with multi-stage planning, generating, and debugging. To address this problem, we propose CodeTree, a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. Specifically, we adopted a unified tree structure to explicitly explore different coding strategies, generate corresponding coding solutions, and subsequently refine the solutions. In each stage, critical decision-making (ranking, termination, expanding) of the exploration process is guided by both the environmental execution-based feedback and LLM-agent-generated feedback. We comprehensively evaluated CodeTree on 7 code generation benchmarks and demonstrated the significant performance gains of CodeTree against strong baselines. Using GPT-4o as the base model, we consistently achieved top results of 95.1 on HumanEval, 98.7 on MBPP, and 43.0 on CodeContests. On the challenging SWEBench benchmark, our approach led to significant performance gains.

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time, optimizing reasoning capabilities during training remains challenging. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution and optimizes it via variational approaches. LaTRO enables LLMs to concurrently improve both their reasoning process and ability to evaluate reasoning quality, without requiring external feedback or reward models. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures. On GSM8K, LaTRO improves zero-shot accuracy by an average of 12.5% over base models and 9.6% over supervised fine-tuning across Phi-3.5-mini, Mistral-7B, and Llama-3.1-8B. Our findings suggest that pre-trained LLMs possess latent reasoning capabilities that can be unlocked and enhanced through our proposed optimization approach in a self-improvement manner. The code of LaTRO is available at \url{https://github.com/SalesforceAIResearch/LaTRO}.

With the extensive use of machine learning technologies, data providers encounter increasing privacy risks. Recent legislation, such as GDPR, obligates organizations to remove requested data and its influence from a trained model. Machine unlearning is an emerging technique designed to enable machine learning models to erase users' private information. Although several efficient machine unlearning schemes have been proposed, these methods still have limitations. First, removing the contributions of partial data may lead to model performance degradation. Second, discrepancies between the original and generated unlearned models can be exploited by attackers to obtain target sample's information, resulting in additional privacy leakage risks. To address above challenges, we proposed a game-theoretic machine unlearning algorithm that simulates the competitive relationship between unlearning performance and privacy protection. This algorithm comprises unlearning and privacy modules. The unlearning module possesses a loss function composed of model distance and classification error, which is used to derive the optimal strategy. The privacy module aims to make it difficult for an attacker to infer membership information from the unlearned data, thereby reducing the privacy leakage risk during the unlearning process. Additionally, the experimental results on real-world datasets demonstrate that this game-theoretic unlearning algorithm's effectiveness and its ability to generate an unlearned model with a performance similar to that of the retrained one while mitigating extra privacy leakage risks.

The outstanding capabilities of large language models (LLMs) render them a crucial component in various autonomous agent systems. While traditional methods depend on the inherent knowledge of LLMs without fine-tuning, more recent approaches have shifted toward the reinforcement learning strategy to further enhance agents' ability to solve complex interactive tasks with environments and tools. However, previous approaches are constrained by the sparse reward issue, where existing datasets solely provide a final scalar reward for each multi-step reasoning chain, potentially leading to ineffectiveness and inefficiency in policy learning. In this paper, we introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. Inheriting the spirit of novice-to-expert theory, we first compare the actions of the expert and the agent to automatically generate intermediate rewards for fine-grained optimization. Additionally, we propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment. Further theoretical analysis demonstrates that the action distribution of the agent can converge toward the expert action distribution over multiple training cycles. Experimental results across various datasets indicate that StepAgent outperforms existing baseline methods.

With the development of artificial intelligence, its contribution to science is evolving from simulating a complex problem to automating entire research processes and producing novel discoveries. Achieving this advancement requires both specialized general models grounded in real-world scientific data and iterative, exploratory frameworks that mirror human scientific methodologies. In this paper, we present PROTEUS, a fully automated system for scientific discovery from raw proteomics data. PROTEUS uses large language models (LLMs) to perform hierarchical planning, execute specialized bioinformatics tools, and iteratively refine analysis workflows to generate high-quality scientific hypotheses. The system takes proteomics datasets as input and produces a comprehensive set of research objectives, analysis results, and novel biological hypotheses without human intervention. We evaluated PROTEUS on 12 proteomics datasets collected from various biological samples (e.g. immune cells, tumors) and different sample types (single-cell and bulk), generating 191 scientific hypotheses. These were assessed using both automatic LLM-based scoring on 5 metrics and detailed reviews from human experts. Results demonstrate that PROTEUS consistently produces reliable, logically coherent results that align well with existing literature while also proposing novel, evaluable hypotheses. The system's flexible architecture facilitates seamless integration of diverse analysis tools and adaptation to different proteomics data types. By automating complex proteomics analysis workflows and hypothesis generation, PROTEUS has the potential to considerably accelerate the pace of scientific discovery in proteomics research, enabling researchers to efficiently explore large-scale datasets and uncover biological insights.

The dynamical Casimir effect (DCE) describes the energy conversion from a mechanical motion to the electromagnetic fields. When the mechanical oscillator is in a mechanically excited state, the free evolution due to the DCE produces radiation in the vacuum, in analogy with the spontaneous emission from an excited atom. In this manuscript, we investigate such a spontaneous radiation process by employing the quantum trajectory approach. When the dissipation rate of the system is very low, there can be a reversible energy exchange between the mirror in the excited state and the vacuum field, and this reversible exchange is called vacuum Casimir-Rabi oscillations. Multiple quantum trajectory simulations of this process show that the number of trajectories responsible for the generation of radiation can reach a significant value when the mechanical dissipation rate is less than the photon dissipation rate. We also find that two-photon (two/three-phonon) bundle emission occurs in photon (phonon) emission. In comparison to pure two-photon and three-phonon free dissipation, the probability of two-photon bundle emission and two-phonon bundle emission are observed to be marginally elevated as a consequence of the presence of the DCE. This pattern may assist in developing a deeper comprehension of the physical characteristics of photon and phonon emission in the DCE., Comment: 9 pages, 9 figures, comments are welcome