Search

In the context of proxy modeling for process systems, traditional data-driven deep learning approaches frequently encounter significant challenges, such as substantial training costs induced by large amounts of data, and limited generalization capabilities. As a promising alternative, physics-aware models incorporate partial physics knowledge to ameliorate these challenges. Although demonstrating efficacy, they fall short in terms of exploration depth and universality. To address these shortcomings, we introduce a physics-aware proxy model (PAPM) that fully incorporates partial prior physics of process systems, which includes multiple input conditions and the general form of conservation relations, resulting in better out-of-sample generalization. Additionally, PAPM contains a holistic temporal-spatial stepping module for flexible adaptation across various process systems. Through systematic comparisons with state-of-the-art pure data-driven and physics-aware models across five two-dimensional benchmarks in nine generalization tasks, PAPM notably achieves an average performance improvement of 6.7%, while requiring fewer FLOPs, and just 1% of the parameters compared to the prior leading method. The code is available at https://github.com/pengwei07/PAPM., Comment: ICML 2024

Affective computing stands at the forefront of artificial intelligence (AI), seeking to imbue machines with the ability to comprehend and respond to human emotions. Central to this field is emotion recognition, which endeavors to identify and interpret human emotional states from different modalities, such as speech, facial images, text, and physiological signals. In recent years, important progress has been made in generative models, including Autoencoder, Generative Adversarial Network, Diffusion Model, and Large Language Model. These models, with their powerful data generation capabilities, emerge as pivotal tools in advancing emotion recognition. However, up to now, there remains a paucity of systematic efforts that review generative technology for emotion recognition. This survey aims to bridge the gaps in the existing literature by conducting a comprehensive analysis of over 320 research papers until June 2024. Specifically, this survey will firstly introduce the mathematical principles of different generative models and the commonly used datasets. Subsequently, through a taxonomy, it will provide an in-depth analysis of how generative techniques address emotion recognition based on different modalities in several aspects, including data augmentation, feature extraction, semi-supervised learning, cross-domain, etc. Finally, the review will outline future research directions, emphasizing the potential of generative models to advance the field of emotion recognition and enhance the emotional intelligence of AI systems., Comment: Under Review

Multi-Hop Question Answering (MHQA) tasks present a significant challenge for large language models (LLMs) due to the intensive knowledge required. Current solutions, like Retrieval-Augmented Generation, typically retrieve potential documents from an external corpus to read an answer. However, the performance of this retrieve-then-read paradigm is constrained by the retriever and the inevitable noise in the retrieved documents. To mitigate these challenges, we introduce a novel generate-then-ground (GenGround) framework, synergizing the parametric knowledge of LLMs and external documents to solve a multi-hop question. GenGround empowers LLMs to alternate two phases until the final answer is derived: (1) formulate a simpler, single-hop question and directly generate the answer; (2) ground the question-answer pair in retrieved documents, amending any wrong predictions in the answer. We also propose an instructional grounding distillation method to generalize our method into smaller models. Extensive experiments conducted on four datasets illustrate the superiority of our method., Comment: ACL 2024 (main conference)

Parameter-Efficient Fine-tuning (PEFT) facilitates the fine-tuning of Large Language Models (LLMs) under limited resources. However, the fine-tuning performance with PEFT on complex, knowledge-intensive tasks is limited due to the constrained model capacity, which originates from the limited number of additional trainable parameters. To overcome this limitation, we introduce a novel mechanism that fine-tunes LLMs with adapters of larger size yet memory-efficient. This is achieved by leveraging the inherent activation sparsity in the Feed-Forward Networks (FFNs) of LLMs and utilizing the larger capacity of Central Processing Unit (CPU) memory compared to Graphics Processing Unit (GPU). We store and update the parameters of larger adapters on the CPU. Moreover, we employ a Mixture of Experts (MoE)-like architecture to mitigate unnecessary CPU computations and reduce the communication volume between the GPU and CPU. This is particularly beneficial over the limited bandwidth of PCI Express (PCIe). Our method can achieve fine-tuning results comparable to those obtained with larger memory capacities, even when operating under more limited resources such as a 24GB memory single GPU setup, with acceptable loss in training efficiency. Our codes are available at https://github.com/CURRENTF/MEFT., Comment: ACL 24

We explore the bound neutrons decay into invisible particles (e.g., $n\rightarrow 3 \nu$ or $nn \rightarrow 2 \nu$) in the JUNO liquid scintillator detector. The invisible decay includes two decay modes: $ n \rightarrow { inv} $ and $ nn \rightarrow { inv} $. The invisible decays of $s$-shell neutrons in $^{12}{\rm C}$ will leave a highly excited residual nucleus. Subsequently, some de-excitation modes of the excited residual nuclei can produce a time- and space-correlated triple coincidence signal in the JUNO detector. Based on a full Monte Carlo simulation informed with the latest available data, we estimate all backgrounds, including inverse beta decay events of the reactor antineutrino $\bar{\nu}_e$, natural radioactivity, cosmogenic isotopes and neutral current interactions of atmospheric neutrinos. Pulse shape discrimination and multivariate analysis techniques are employed to further suppress backgrounds. With two years of exposure, JUNO is expected to give an order of magnitude improvement compared to the current best limits. After 10 years of data taking, the JUNO expected sensitivities at a 90% confidence level are $\tau/B( n \rightarrow { inv} ) > 5.0 \times 10^{31} \, {\rm yr}$ and $\tau/B( nn \rightarrow { inv} ) > 1.4 \times 10^{32} \, {\rm yr}$., Comment: 28 pages, 7 figures, 4 tables

We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token, and supports a context length of 128K tokens. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSeek 67B, DeepSeek-V2 achieves significantly stronger performance, and meanwhile saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts the maximum generation throughput to 5.76 times. We pretrain DeepSeek-V2 on a high-quality and multi-source corpus consisting of 8.1T tokens, and further perform Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to fully unlock its potential. Evaluation results show that, even with only 21B activated parameters, DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models.

As the nation transitions from responding to the height of the COVID-19 pandemic to navigating its ongoing impact on youth and their communities, K-12 students continue to experience mental health and wellbeing challenges. In the fall of 2021, Redwood City School District (RCSD) placed a full-time, district-employed mental health counselor in each of its twelve schools in order to bolster district capacity to support mental health and wellbeing. This study aims to identify strategic opportunities for understanding and advancing the counseling program's impact as it moves into its third year. With these goals in mind, this research brief will describe findings related to three questions: (1) What is the role of RCSD's school-based mental health counselors?; (2) What are early signals or "lead indicators" of the value or impact of the counseling program?; and (3) What considerations might further improve the program as it moves into Year 3? To answer these questions, the authors conducted 19 interviews with district administrators, site administrators, and mental health counselors; and 22 participant observations of meetings related to the counseling program and student services more broadly. While the research team employed qualitative data analysis software (Dedoose 9.0.90) to facilitate the coding of qualitative data, the analysis of coded data followed a more traditional, iterative approach, moving between deductive and inductive reasoning. This research brief summarizes key findings and offers considerations for leveraging the counseling program to strengthen a district-wide, coordinated system of support for mental health and wellbeing and developing a theory-based evaluation of impact during Year 3 of program implementation. [This work is generously funded by Stanford's Office of the Provost through the Office of Community Engagement.]

Phonon nonreciprocity, indicating different transport properties along opposite directions, has been observed in experiments under a magnetic field. We show that nonreciprocal acoustic phonons can also exist without a magnetic field nor net magnetization. We focus on PT symmetric antiferromagnets that break both time-reversal T and inversion symmetry P. We identify crucial contributions in phenomenological elastic theory, dubbed flexo-viscosity and flexo-torque, that induce phonon nonreciprocity without changing the phonon polarization. The microscopic origin of these contributions is the molecular Berry curvature, manifested as emergent nonlocal magnetic fields on phonons. The symmetry breaking originated from spin order is transferred to the phonon system through spin-orbit coupling, where the orbital degree of freedom affects the lattice dynamics directly. By electrically modifying the spin-orbit coupling, we show that both the phonon nonreciprocity and helicity can be controlled and enhanced. Importantly, the phonon nonreciprocity is an odd function of the N\'eel vector, serving as an indicator of the order parameter., Comment: 5 pages, 2 figures

Deep learning models have shown considerable vulnerability to adversarial attacks, particularly as attacker strategies become more sophisticated. While traditional adversarial training (AT) techniques offer some resilience, they often focus on defending against a single type of attack, e.g., the $\ell_\infty$-norm attack, which can fail for other types. This paper introduces a computationally efficient multilevel $\ell_p$ defense, called the Efficient Robust Mode Connectivity (EMRC) method, which aims to enhance a deep learning model's resilience against multiple $\ell_p$-norm attacks. Similar to analytical continuation approaches used in continuous optimization, the method blends two $p$-specific adversarially optimal models, the $\ell_1$- and $\ell_\infty$-norm AT solutions, to provide good adversarial robustness for a range of $p$. We present experiments demonstrating that our approach performs better on various attacks as compared to AT-$\ell_\infty$, E-AT, and MSD, for datasets/architectures including: CIFAR-10, CIFAR-100 / PreResNet110, WideResNet, ViT-Base.

Recently, code-oriented large language models (Code LLMs) have been widely and successfully used to simplify and facilitate code programming. With these tools, developers can easily generate desired complete functional codes based on incomplete code and natural language prompts. However, a few pioneering works revealed that these Code LLMs are also vulnerable, e.g., against backdoor and adversarial attacks. The former could induce LLMs to respond to triggers to insert malicious code snippets by poisoning the training data or model parameters, while the latter can craft malicious adversarial input codes to reduce the quality of generated codes. However, both attack methods have underlying limitations: backdoor attacks rely on controlling the model training process, while adversarial attacks struggle with fulfilling specific malicious purposes. To inherit the advantages of both backdoor and adversarial attacks, this paper proposes a new attack paradigm, i.e., target-specific and adversarial prompt injection (TAPI), against Code LLMs. TAPI generates unreadable comments containing information about malicious instructions and hides them as triggers in the external source code. When users exploit Code LLMs to complete codes containing the trigger, the models will generate attacker-specified malicious code snippets at specific locations. We evaluate our TAPI attack on four representative LLMs under three representative malicious objectives and seven cases. The results show that our method is highly threatening (achieving an attack success rate of up to 89.3\%) and stealthy (saving an average of 53.1\% of tokens in the trigger design). In particular, we successfully attack some famous deployed code completion integrated applications, including CodeGeex and Github Copilot. This further confirms the realistic threat of our attack.

Intelligent maritime, as an essential component of smart ocean construction, deeply integrates advanced artificial intelligence technology and data analysis methods, which covers multiple aspects such as smart vessels, route optimization, safe navigation, aiming to enhance the efficiency of ocean resource utilization and the intelligence of transportation networks. However, the complex and dynamic maritime environment, along with diverse and heterogeneous large-scale data sources, present challenges for real-time decision-making in intelligent maritime. In this paper, We propose KUNPENG, the first-ever embodied large model for intelligent maritime in the smart ocean construction, which consists of six systems. The model perceives multi-source heterogeneous data for the cognition of environmental interaction and make autonomous decision strategies, which are used for intelligent vessels to perform navigation behaviors under safety and emergency guarantees and continuously optimize power to achieve embodied intelligence in maritime. In comprehensive maritime task evaluations, KUNPENG has demonstrated excellent performance., Comment: 9 pages, 3 figures

The rapid growth of biomedical knowledge has outpaced our ability to efficiently extract insights and generate novel hypotheses. Large language models (LLMs) have emerged as a promising tool to revolutionize knowledge interaction and potentially accelerate biomedical discovery. In this paper, we present a comprehensive evaluation of LLMs as biomedical hypothesis generators. We construct a dataset of background-hypothesis pairs from biomedical literature, carefully partitioned into training, seen, and unseen test sets based on publication date to mitigate data contamination. Using this dataset, we assess the hypothesis generation capabilities of top-tier instructed models in zero-shot, few-shot, and fine-tuning settings. To enhance the exploration of uncertainty, a crucial aspect of scientific discovery, we incorporate tool use and multi-agent interactions in our evaluation framework. Furthermore, we propose four novel metrics grounded in extensive literature review to evaluate the quality of generated hypotheses, considering both LLM-based and human assessments. Our experiments yield two key findings: 1) LLMs can generate novel and validated hypotheses, even when tested on literature unseen during training, and 2) Increasing uncertainty through multi-agent interactions and tool use can facilitate diverse candidate generation and improve zero-shot hypothesis generation performance. However, we also observe that the integration of additional knowledge through few-shot learning and tool use may not always lead to performance gains, highlighting the need for careful consideration of the type and scope of external knowledge incorporated. These findings underscore the potential of LLMs as powerful aids in biomedical hypothesis generation and provide valuable insights to guide further research in this area., Comment: Accepted to COLM 2024. This is an extended version of the paper at arXiv:2311.05965

Screen content (SC) differs from natural scene (NS) with unique characteristics such as noise-free, repetitive patterns, and high contrast. Aiming at addressing the inadequacies of current learned image compression (LIC) methods for SC, we propose an improved two-stage octave convolutional residual blocks (IToRB) for high and low-frequency feature extraction and a cascaded two-stage multi-scale residual blocks (CTMSRB) for improved multi-scale learning and nonlinearity in SC. Additionally, we employ a window-based attention module (WAM) to capture pixel correlations, especially for high contrast regions in the image. We also construct a diverse SC image compression dataset (SDU-SCICD2K) for training, including text, charts, graphics, animation, movie, game and mixture of SC images and NS images. Experimental results show our method, more suited for SC than NS data, outperforms existing LIC methods in rate-distortion performance on SC images. The code is publicly available at https://github.com/SunshineSki/OMR Net.git., Comment: 7 figures, 2 tables

When the task of locating manipulation regions in partially-fake audio (PFA) involves cross-domain datasets, the performance of deep learning models drops significantly due to the shift between the source and target domains. To address this issue, existing approaches often employ data augmentation before training. However, they overlook the characteristics in target domain that are absent in source domain. Inspired by the mixture-of-experts model, we propose an unsupervised method named Samples mining with Diversity and Entropy (SDE). Our method first learns from a collection of diverse experts that achieve great performance from different perspectives in the source domain, but with ambiguity on target samples. We leverage these diverse experts to select the most informative samples by calculating their entropy. Furthermore, we introduced a label generation method tailored for these selected samples that are incorporated in the training process in source domain integrating the target domain information. We applied our method to a cross-domain partially fake audio detection dataset, ADD2023Track2. By introducing 10% of unknown samples from the target domain, we achieved an F1 score of 43.84%, which represents a relative increase of 77.2% compared to the second-best method.

Memory management across discrete CPU and GPU physical memory is traditionally achieved through explicit GPU allocations and data copy or unified virtual memory. The Grace Hopper Superchip, for the first time, supports an integrated CPU-GPU system page table, hardware-level addressing of system allocated memory, and cache-coherent NVLink-C2C interconnect, bringing an alternative solution for enabling a Unified Memory system. In this work, we provide the first in-depth study of the system memory management on the Grace Hopper Superchip, in both in-memory and memory oversubscription scenarios. We provide a suite of six representative applications, including the Qiskit quantum computing simulator, using system memory and managed memory. Using our memory utilization profiler and hardware counters, we quantify and characterize the impact of the integrated CPU-GPU system page table on GPU applications. Our study focuses on first-touch policy, page table entry initialization, page sizes, and page migration. We identify practical optimization strategies for different access patterns. Our results show that as a new solution for unified memory, the system-allocated memory can benefit most use cases with minimal porting efforts., Comment: Accepted to ICPP '24 (The 53rd International Conference on Parallel Processing)

Open-vocabulary detection is a challenging task due to the requirement of detecting objects based on class names, including those not encountered during training. Existing methods have shown strong zero-shot detection capabilities through pre-training on diverse large-scale datasets. However, these approaches still face two primary challenges: (i) how to universally integrate diverse data sources for end-to-end training, and (ii) how to effectively leverage the language-aware capability for region-level cross-modality understanding. To address these challenges, we propose a novel unified open-vocabulary detection method called OV-DINO, which pre-trains on diverse large-scale datasets with language-aware selective fusion in a unified framework. Specifically, we introduce a Unified Data Integration (UniDI) pipeline to enable end-to-end training and eliminate noise from pseudo-label generation by unifying different data sources into detection-centric data. In addition, we propose a Language-Aware Selective Fusion (LASF) module to enable the language-aware ability of the model through a language-aware query selection and fusion process. We evaluate the performance of the proposed OV-DINO on popular open-vocabulary detection benchmark datasets, achieving state-of-the-art results with an AP of 50.6\% on the COCO dataset and 40.0\% on the LVIS dataset in a zero-shot manner, demonstrating its strong generalization ability. Furthermore, the fine-tuned OV-DINO on COCO achieves 58.4\% AP, outperforming many existing methods with the same backbone. The code for OV-DINO will be available at \href{https://github.com/wanghao9610/OV-DINO}{https://github.com/wanghao9610/OV-DINO}., Comment: Technical Report

The $e^+e^-\rightarrow D_s^+D_{s1}(2536)^-$ and $e^+e^-\rightarrow D_s^+D^*_{s2}(2573)^-$ processes are studied using data samples collected with the BESIII detector at center-of-mass energies from 4.530 to 4.946~GeV. The absolute branching fractions of $D_{s1}(2536)^- \rightarrow \bar{D}^{*0}K^-$ and $D_{s2}^*(2573)^- \rightarrow \bar{D}^0K^-$ are measured for the first time to be $(35.9\pm 4.8\pm 3.5)\%$ and $(37.4\pm 3.1\pm 4.6)\%$, respectively. The measurements are in tension with predictions based on the assumption that the $D_{s1}(2536)$ and $D_{s2}^*(2573)$ are dominated by a bare $c\bar{s}$ component. The $e^+e^-\rightarrow D_s^+D_{s1}(2536)^-$ and $e^+e^-\rightarrow D_s^+D^*_{s2}(2573)^-$ cross sections are measured, and a resonant structure at around 4.6~GeV with a width of 50~MeV is observed for the first time with a statistical significance of $15\sigma$ in the $e^+e^-\rightarrow D_s^+D^*_{s2}(2573)^-$ process. It could be the $Y(4626)$ found by the Belle collaboration in the $D_s^+D_{s1}(2536)^{-}$ final state, since they have similar masses and widths. There is also evidence for a structure at around 4.75~GeV in both processes.

Storyboarding is an established method for designing user experiences. Generative AI can support this process by helping designers quickly create visual narratives. However, existing tools only focus on accurate text-to-image generation. Currently, it is not clear how to effectively support the entire creative process of storyboarding and how to develop AI-powered tools to support designers' individual workflows. In this work, we iteratively developed and implemented StoryDiffusion, a system that integrates text-to-text and text-to-image models, to support the generation of narratives and images in a single pipeline. With a user study, we observed 12 UX designers using the system for both concept ideation and illustration tasks. Our findings identified AI-directed vs. user-directed creative strategies in both tasks and revealed the importance of supporting the interchange between narrative iteration and image generation. We also found effects of the design tasks on their strategies and preferences, providing insights for future development.

Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthrough in text-to-video generation. In this work, we aim to offer insights into the video-to-audio generation paradigm, focusing on three crucial aspects: vision encoders, auxiliary embeddings, and data augmentation techniques. Beginning with a foundational model VTA-LDM built on a simple yet surprisingly effective intuition, we explore various vision encoders and auxiliary embeddings through ablation studies. Employing a comprehensive evaluation pipeline that emphasizes generation quality and video-audio synchronization alignment, we demonstrate that our model exhibits state-of-the-art video-to-audio generation capabilities. Furthermore, we provide critical insights into the impact of different data augmentation methods on enhancing the generation framework's overall capacity. We showcase possibilities to advance the challenge of generating synchronized audio from semantic and temporal perspectives. We hope these insights will serve as a stepping stone toward developing more realistic and accurate audio-visual generation models., Comment: https://sites.google.com/view/vta-ldm

This article presents constraints on dark-matter-electron interactions obtained from the first underground data-taking campaign with multiple SuperCDMS HVeV detectors operated in the same housing. An exposure of 7.63 g-days is used to set upper limits on the dark-matter-electron scattering cross section for dark matter masses between 0.5 and 1000 MeV/$c^2$, as well as upper limits on dark photon kinetic mixing and axion-like particle axioelectric coupling for masses between 1.2 and 23.3 eV/$c^2$. Compared to an earlier HVeV search, sensitivity was improved as a result of an increased overburden of 225 meters of water equivalent, an anticoincidence event selection, and better pile-up rejection. In the case of dark-matter-electron scattering via a heavy mediator, an improvement by up to a factor of 25 in cross-section sensitivity was achieved., Comment: 7 pages + title and references, 4 figures, and 1 table

Future lepton colliders such as the FCC-ee, CEPC, ILC, or a muon collider will collect large data samples that allow precision physics studies with unprecedented accuracy, especially when the data is collected by innovative state-of-the-art detectors. An electromagnetic calorimeter based on scintillating crystals, designed to separately record Cherenkov and scintillation light, can achieve precision measurements of electrons and photons without sacrificing jet energy resolution, given adequate light collection efficiency and separation. This paper presents initial measurements from a program aimed at developing such a calorimeter system for future colliders. We focus on using PbF2 crystals to enhance the understanding of Cherenkov light collection, marking the first step in this endeavor., Comment: 10 pages

The reconfiguration of human-LM interactions from simple sentence completions to complex, multi-domain, humanlike engagements necessitates new methodologies to understand how humans choose to rely on LMs. In our work, we contend that reliance is influenced by numerous factors within the interactional context of a generation, a departure from prior work that used verbalized confidence (e.g., "I'm certain the answer is...") as the key determinant of reliance. Here, we introduce Rel-A.I., an in situ, system-level evaluation approach to measure human reliance on LM-generated epistemic markers (e.g., "I think it's..", "Undoubtedly it's..."). Using this methodology, we measure reliance rates in three emergent human-LM interaction settings: long-term interactions, anthropomorphic generations, and variable subject matter. Our findings reveal that reliance is not solely based on verbalized confidence but is significantly affected by other features of the interaction context. Prior interactions, anthropomorphic cues, and subject domain all contribute to reliance variability. An expression such as, "I'm pretty sure it's...", can vary up to 20% in reliance frequency depending on its interactional context. Our work underscores the importance of context in understanding human reliance and offers future designers and researchers with a methodology to conduct such measurements., Comment: Preprint

In the NISQ era, achieving large-scale quantum computing demands compact circuits to mitigate decoherence and gate error accumulation. Quantum operations with diverse degrees of freedom hold promise for circuit compression, but conventional approaches encounter challenges in simultaneously adjusting multiple parameters. Here, we propose a transition composite gate (TCG) scheme grounded on state-selective transition path engineering, enabling more expressive conditional operations. We experimentally validate a controlled unitary (CU) gate as an example, with independent and continuous parameters. By adjusting the parameters of $\rm X^{12}$ gate, we obtain the CU family with a fidelity range of 95.2% to 99.0% leveraging quantum process tomography (QPT). To demonstrate the capability of circuit compression, we use TCG scheme to prepare 3-qubit Greenberger-Horne-Zeilinger (GHZ) and W states, with the fidelity of 96.77% and 95.72%. TCG can achieve the reduction in circuit depth of about 40% and 44% compared with the use of CZ gates only. Moreover, we show that short-path TCG (SPTCG) can further reduce the state-preparation circuit time cost. The TCG scheme exhibits advantages in certain quantum circuits and shows significant potential for large-scale quantum algorithms., Comment: 21 pages, 12 figures

Employing Large Language Models (LLMs) to assess the quality of generated responses, such as prompting instruct-tuned models or fine-tuning judge models, has become a widely adopted evaluation method. It is also known that such evaluators are vulnerable to biases, such as favoring longer responses. While it is important to overcome this problem, the specifics of these biases remain under-explored. In this work, we qualitatively identify six types of biases inherent in various judge models. We propose EvalBiasBench as a meta-evaluation collection of hand-crafted test cases for each bias type. Additionally, we present de-biasing dataset construction methods and the associated preference dataset OffsetBias. Experimental results demonstrate that fine-tuning on our dataset significantly enhances the robustness of judge models against biases and improves performance across most evaluation scenarios. We release our datasets and the fine-tuned judge model to public., Comment: Work in Progress

Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. However, in 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant. This raises the question: Can we take the best of both worlds? To answer this question, we first empirically validate that integrating MAE-based point cloud pre-training with the standard contrastive learning paradigm, even with meticulous design, can lead to a decrease in performance. To address this limitation, we reintroduce CL into the MAE-based point cloud pre-training paradigm by leveraging the inherent contrastive properties of MAE. Specifically, rather than relying on extensive data augmentation as commonly used in the image domain, we randomly mask the input tokens twice to generate contrastive input pairs. Subsequently, a weight-sharing encoder and two identically structured decoders are utilized to perform masked token reconstruction. Additionally, we propose that for an input token masked by both masks simultaneously, the reconstructed features should be as similar as possible. This naturally establishes an explicit contrastive constraint within the generative MAE-based pre-training paradigm, resulting in our proposed method, Point-CMAE. Consequently, Point-CMAE effectively enhances the representation quality and transfer performance compared to its MAE counterpart. Experimental evaluations across various downstream applications, including classification, part segmentation, and few-shot learning, demonstrate the efficacy of our framework in surpassing state-of-the-art techniques under standard ViTs and single-modal settings. The source code and trained models are available at: https://github.com/Amazingren/Point-CMAE., Comment: Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning

Recent multimodal large language models (MLLM) such as GPT-4o and GPT-4v have shown great potential in autonomous driving. In this paper, we propose a cross-domain few-shot in-context learning method based on the MLLM for enhancing traffic sign recognition (TSR). We first construct a traffic sign detection network based on Vision Transformer Adapter and an extraction module to extract traffic signs from the original road images. To reduce the dependence on training data and improve the performance stability of cross-country TSR, we introduce a cross-domain few-shot in-context learning method based on the MLLM. To enhance MLLM's fine-grained recognition ability of traffic signs, the proposed method generates corresponding description texts using template traffic signs. These description texts contain key information about the shape, color, and composition of traffic signs, which can stimulate the ability of MLLM to perceive fine-grained traffic sign categories. By using the description texts, our method reduces the cross-domain differences between template and real traffic signs. Our approach requires only simple and uniform textual indications, without the need for large-scale traffic sign images and labels. We perform comprehensive evaluations on the German traffic sign recognition benchmark dataset, the Belgium traffic sign dataset, and two real-world datasets taken from Japan. The experimental results show that our method significantly enhances the TSR performance.

The Ruddlesden-Popper (R-P) bilayer nickelate, La3Ni2O7, was recently found to show signatures of high-temperature superconductivity (HTSC) at pressures above 14 GPa. Subsequent investigations achieved zero resistance in single- and poly-crystalline samples under hydrostatic pressure conditions. Yet, obvious diamagnetic signals, the other hallmark of superconductors, are still lacking owing to the filamentary nature with low superconducting volume fraction. The presence of a novel "1313" polymorph and competing R-P phases obscured proper identification of the phase for HTSC. Thus, achieving bulk HTSC and identifying the phase at play are the most prominent tasks at present. Here, we address these issues in the praseodymium (Pr)-doped La2PrNi2O7 polycrystalline samples. We find that the substitutions of Pr for La effectively inhibits the intergrowth of different R-P phases, resulting in nearly pure bilayer structure. For La2PrNi2O7, pressure-induced orthorhombic-to-tetragonal structural transition takes place at Pc ~ 11 GPa, above which HTSC emerges gradually upon further compression. The superconducting transition temperatures at 18-20 GPa reach Tconset = 82.5 K and Tczero = 60 K, which are the highest values among known nickelate superconductors. More importantly, bulk HTSC was testified by detecting clear diamagnetic signals below ~75 K corresponding to an estimated superconducting volume fraction ~ 57(5)% at 20 GPa. Our results not only resolve the existing controversies but also illuminate directions for exploring bulk HTSC in the bilayer nickelates.

Reconstructing high-fidelity hand models with intricate textures plays a crucial role in enhancing human-object interaction and advancing real-world applications. Despite the state-of-the-art methods excelling in texture generation and image rendering, they often face challenges in accurately capturing geometric details. Learning-based approaches usually offer better robustness and faster inference, which tend to produce smoother results and require substantial amounts of training data. To address these issues, we present a novel fine-grained multi-view hand mesh reconstruction method that leverages inverse rendering to restore hand poses and intricate details. Firstly, our approach predicts a parametric hand mesh model through Graph Convolutional Networks (GCN) based method from multi-view images. We further introduce a novel Hand Albedo and Mesh (HAM) optimization module to refine both the hand mesh and textures, which is capable of preserving the mesh topology. In addition, we suggest an effective mesh-based neural rendering scheme to simultaneously generate photo-realistic image and optimize mesh geometry by fusing the pre-trained rendering network with vertex features. We conduct the comprehensive experiments on InterHand2.6M, DeepHandMesh and dataset collected by ourself, whose promising results show that our proposed approach outperforms the state-of-the-art methods on both reconstruction accuracy and rendering quality. Code and dataset are publicly available at https://github.com/agnJason/FMHR., Comment: Accepted by AAAI 2024

In recent years, self-supervised denoising methods have gained significant success and become critically important in the field of image restoration. Among them, the blind spot network based methods are the most typical type and have attracted the attentions of a large number of researchers. Although the introduction of blind spot operations can prevent identity mapping from noise to noise, it imposes stringent requirements on the receptive fields in the network design, thereby limiting overall performance. To address this challenge, we propose a single mask scheme for self-supervised denoising training, which eliminates the need for blind spot operation and thereby removes constraints on the network structure design. Furthermore, to achieve denoising across entire image during inference, we propose a multi-mask scheme. Our method, featuring the asymmetric mask scheme in training and inference, achieves state-of-the-art performance on existing real noisy image datasets. All the source code will be made available to the public.

Generating 3D vehicle assets from in-the-wild observations is crucial to autonomous driving. Existing image-to-3D methods cannot well address this problem because they learn generation merely from image RGB information without a deeper understanding of in-the-wild vehicles (such as car models, manufacturers, etc.). This leads to their poor zero-shot prediction capability to handle real-world observations with occlusion or tricky viewing angles. To solve this problem, in this work, we propose VQA-Diff, a novel framework that leverages in-the-wild vehicle images to create photorealistic 3D vehicle assets for autonomous driving. VQA-Diff exploits the real-world knowledge inherited from the Large Language Model in the Visual Question Answering (VQA) model for robust zero-shot prediction and the rich image prior knowledge in the Diffusion model for structure and appearance generation. In particular, we utilize a multi-expert Diffusion Models strategy to generate the structure information and employ a subject-driven structure-controlled generation mechanism to model appearance information. As a result, without the necessity to learn from a large-scale image-to-3D vehicle dataset collected from the real world, VQA-Diff still has a robust zero-shot image-to-novel-view generation ability. We conduct experiments on various datasets, including Pascal 3D+, Waymo, and Objaverse, to demonstrate that VQA-Diff outperforms existing state-of-the-art methods both qualitatively and quantitatively.

We theoretically study the decoherence of a two-level quantum system coupled to the noisy environments exhibiting linear and quadratic fluctuations within the framework of stochastic Liouville equation. It is shown that the intrinsic energy levels of the quantum system renormalize under either the linear or quadratic influence of the environmental noise. In the case of quadratic dependence, the renormalization of the energy levels of the system emerges even if the environmental noise exhibits stationary statistical property. This is in contrast to the case under linear influence, where the intrinsic energy levels of the system renormalize only if the environmental noise displays nonstationary statistics. We derive the analytical expressions of the decoherence function in the cases that the fluctuation of the frequency difference depends linearly and quadratically on the nonstationary Ornstein-Uhlenbeck noise (OUN) and random telegraph noise (RTN) processes, respectively. In the case of linear dependence of the OUN, the environmental nonstationary statistical property can enhance the dynamical decoherence. However, the nonstationary statistics of the environmental noise can suppress the quantum decoherence in the case under the quadratic influence of the OUN. In the presence of the RTN, the quadratic influence of the environmental noise does not give rise to decoherence but only causes a determinate frequency renormalization in dynamical evolution. The environmental nonstationary statistical property can suppress the quantum decoherence for the case under the linear influence of the RTN., Comment: Accepted for publication in The Journal of Chemical Physics

In this manuscript we study multiple scattering and diffusion of scalar wave in a group of monodisperse spheroidal particles with random orientations. We begin by fixing a spheroid in a prolate spheroidal coordinate system, and attain the expansion of the scalar Green's function in this space. The expansion is firstly based on spheroidal wave functions, and then we transform it into the expansion of spherical wave functions. Next, we average the Green's function over the orientations of the spheroid to get the averaged transition operator. Finally, we calculate the transport mean free path and anisotropy factor for the spheroidal particles group, based on the irreducible vertex in the Bethe-Salpeter equation. The approaches to get the average transition operator and the mean free paths in this manuscript will be of benefit to the research area of multiple scattering by non-spherical particles., Comment: 18 pages, 3 figures

FeSe$_{1-x}$S$_{x}$ superconductors are commonly considered layered van der Waals materials with negligible inter-layer coupling. Here, using inelastic neutron scattering to study spin excitations in single-crystal samples, we reveal that the magnetic coupling between adjacent Fe layers is not only significant, as it affects excitations up to \textcolor{black}{15} meV, but also ferromagnetic in nature, making the system different from most unconventional superconductors including iron pnictides. Our observation provides a new standpoint to understand the absence of magnetic order in FeSe$_{1-x}$S$_{x}$. Since intercalating between the Fe layers is known to enhance superconductivity and suppress the inter-layer coupling, superconductivity appears to be a more robust phenomenon in the two-dimensional limit than antiferromagnetic order.

Lithium Niobate (LN) is a ferroelectric material with exceptional electrical characteristics, including high piezoelectricity, high Pockels effect, etc. These properties make it a promising platform for numerous fields such as high-speed communication, optical computation, and quantum information processing. Besides these, the introduction of magnetic structures to LN holds significant potential to achieve magnetoelectric coupling, which can be applied in magnetic memory and data-processing devices with high efficiency. Here, for the first time, we observe a special topological magnetic structure called magnetic skyrmion in LN (SK-LN) by the combination of magnetic field annealing and rapid annealing processes . Compared to the magnetic skyrmions reported in magnetic systems, SK-LN exhibit exceptionally high stability. Additionally, the center of the magnetic vortex exhibits spontaneous ferroelectric polarization, indicating its multiferroic characteristic. With the excitation of these multiferroic skyrmions, the modulation efficiency of the electro-optical (EO) modulator fabricated on thin film lithium niobate on insulator (LNOI) wafer was found to be enhanced from 1.98 V*cm to 0.63 V*cm. It is considered that the multiferroic skyrmions significantly enhance the Pockels coefficient of LN to 101 pm/V, nearly three times the result (32pm/V) reported previously.

Non-Hermitian dynamics in quantum systems have unveiled novel phenomena, yet the implementation of valid non-Hermitian quantum measurement remains a challenge, because a universal quantum projective mechanism on the complete but skewed non-Hermitian eigenstates is not explicit in experiment. This limitation hinders the direct acquisition of non-Hermitian observable statistics (e.g., non-Hermitian population dynamics), also constrains investigations of non-Hermitian quantum measurement properties such as uncertainty relation. Here, we address these challenges by presenting a non-Hermitian projective protocol and investigating the non-Hermitian uncertainty relation. We derive the uncertainty relation for pseudo-Hermitian (PH) observables that is generalized beyond the Hermitian ones. We then investigate the projective properties of general quantum states onto complete non-Hermitian eigenvectors, and present a quantum simulating method to apply the valid non-Hermitian projective measurement on a direct-sum dilated space. Subsequently, we experimentally construct a quantum simulator in the quantum optical circuit and realize the 3-dimensional non-Hermitian quantum measurement on the single-photon qutrit. Employing this platform, we explore the uncertainty relation experimentally with different PH metrics. Our non-Hermitian quantum measurement method is state-independent and outputs directly the non-Hermitian quantum projective statistics, paving the way for studies of extensive non-Hermitian observable in quantum domain., Comment: 6 pages, 4 figures

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may include sensitive information. To address these concerns, machine unlearning has been proposed to erase specific data samples from models. While some unlearning techniques efficiently remove data at low costs, recent research highlights vulnerabilities where malicious users could request unlearning on manipulated data to compromise the model. Despite these attacks' effectiveness, perturbed data differs from original training data, failing hash verification. Existing attacks on machine unlearning also suffer from practical limitations and require substantial additional knowledge and resources. To fill the gaps in current unlearning attacks, we introduce the Unlearning Usability Attack. This model-agnostic, unlearning-agnostic, and budget-friendly attack distills data distribution information into a small set of benign data. These data are identified as benign by automatic poisoning detection tools due to their positive impact on model training. While benign for machine learning, unlearning these data significantly degrades model information. Our evaluation demonstrates that unlearning this benign data, comprising no more than 1% of the total training data, can reduce model accuracy by up to 50%. Furthermore, our findings show that well-prepared benign data poses challenges for recent unlearning techniques, as erasing these synthetic instances demands higher resources than regular data. These insights underscore the need for future research to reconsider "data poisoning" in the context of machine unlearning.

In this paper, we propose Varying Effects Regression with Graph Estimation (VERGE), a novel Bayesian method for feature selection in regression. Our model has key aspects that allow it to leverage the complex structure of data sets arising from genomics or imaging studies. We distinguish between the predictors, which are the features utilized in the outcome prediction model, and the subject-level covariates, which modulate the effects of the predictors on the outcome. We construct a varying coefficients modeling framework where we infer a network among the predictor variables and utilize this network information to encourage the selection of related predictors. We employ variable selection spike-and-slab priors that enable the selection of both network-linked predictor variables and covariates that modify the predictor effects. We demonstrate through simulation studies that our method outperforms existing alternative methods in terms of both feature selection and predictive accuracy. We illustrate VERGE with an application to characterizing the influence of gut microbiome features on obesity, where we identify a set of microbial taxa and their ecological dependence relations. We allow subject-level covariates including sex and dietary intake variables to modify the coefficients of the microbiome predictors, providing additional insight into the interplay between these factors.

Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning methods aimed at enhancing the efficiency of model training specifically for code LLMs. We present techniques that integrate various clustering and pruning metrics to selectively reduce training data without compromising the accuracy and functionality of the generated code. We observe significant redundancies in synthetic training data generation, where our experiments demonstrate that benchmark performance can be largely preserved by training on only 10% of the data. Moreover, we observe consistent improvements in benchmark results through moderate pruning of the training data. Our experiments show that these pruning strategies not only reduce the computational resources needed but also enhance the overall quality code generation.

Co-optimizing placement with congestion is integral to achieving high-quality designs. This paper presents GOALPlace, a new learning-based general approach to improving placement congestion by controlling cell density. Our method efficiently learns from an EDA tool's post-route optimized results and uses an empirical Bayes technique to adapt this goal/target to a specific placer's solutions, effectively beginning with the end in mind. It enhances correlation with the long-running heuristics of the tool's router and timing-opt engine -- while solving placement globally without expensive incremental congestion estimation and mitigation methods. A statistical analysis with a new hierarchical netlist clustering establishes the importance of density and the potential for an adequate cell density target across placements. Our experiments show that our method, integrated as a demonstration inside an academic GPU-accelerated global placer, consistently produces macro and standard cell placements of superior or comparable quality to commercial tools. Our empirical Bayes methodology also allows a substantial quality improvement over state-of-the-art academic mixed-size placers, achieving up to 10x fewer design rule check (DRC) violations, a 5% decrease in wirelength, and a 30% and 60% reduction in worst and total negative slack (WNS/TNS)., Comment: 10 pages, 7 figures, preprint

Generative adversarial network (GAN) based vocoders have achieved significant attention in speech synthesis with high quality and fast inference speed. However, there still exist many noticeable spectral artifacts, resulting in the quality decline of synthesized speech. In this work, we adopt a novel GAN-based vocoder designed for few artifacts and high fidelity, called FA-GAN. To suppress the aliasing artifacts caused by non-ideal upsampling layers in high-frequency components, we introduce the anti-aliased twin deconvolution module in the generator. To alleviate blurring artifacts and enrich the reconstruction of spectral details, we propose a novel fine-grained multi-resolution real and imaginary loss to assist in the modeling of phase information. Experimental results reveal that FA-GAN outperforms the compared approaches in promoting audio quality and alleviating spectral artifacts, and exhibits superior performance when applied to unseen speaker scenarios.

Let $p>3$ be a prime and $(\frac{.}{p})$ be the Legendre symbol. For any integer $d$ with $p\nmid d$ and any positive integer $m$, Sun introduced the determinants $$T_m(d,p)=\det\left[(i^2+dj^2)^m\left(\frac{i^2+dj^2}{p}\right)\right]_{1\leqslant i,j \leqslant (p-1)/2},$$ and $$D_p^{(m)}= \det\left[(i^2-j^2)^m\left(\frac{i^2-j^2}{p}\right)\right]_{1\leq i,j\leq (p-1)/2} .$$ In this paper, we obtain some properties of $T_m (d,p)$ and $ \sqrt{D_p^{(m)}}$ for some $m$. We also confirm some related conjectures posed by Zhi-Wei Sun., Comment: 20 pages

This work aims to extend the well-known high-order WENO finite-difference methods for systems of conservation laws to nonconservative hyperbolic systems. The main difficulty of these systems both from the theoretical and the numerical points of view comes from the fact that the definition of weak solution is not unique: according to the theory developed by Dal Maso, LeFloch, and Murat in 1995, it depends on the choice of a family of paths. A general strategy is proposed here in which WENO operators are not only used to reconstruct fluxes but also the nonconservative products of the system. Moreover, if a Roe linearization is available, the nonconservative products can be computed through matrix-vector operations instead of path-integrals. The methods are extended to problems with source terms and two different strategies are introduced to obtain well-balanced schemes. These numerical schemes will be then applied to the two-layer shallow water equations in one- and two- dimensions to obtain high-order methods that preserve water-at-rest steady states.

In safety-critical robot planning or control, manually specifying safety constraints or learning them from demonstrations can be challenging. In this paper, we propose a certifiable alignment method for a robot to learn a safety constraint in its model predictive control (MPC) policy with human online directional feedback. To our knowledge, it is the first method to learn safety constraints from human feedback. The proposed method is based on an empirical observation: human directional feedback, when available, tends to guide the robot toward safer regions. The method only requires the direction of human feedback to update the learning hypothesis space. It is certifiable, providing an upper bound on the total number of human feedback in the case of successful learning of safety constraints, or declaring the misspecification of the hypothesis space, i.e., the true implicit safety constraint cannot be found within the specified hypothesis space. We evaluated the proposed method using numerical examples and user studies in two developed simulation games. Additionally, we implemented and tested the proposed method on a real-world Franka robot arm performing mobile water-pouring tasks in a user study. The simulation and experimental results demonstrate the efficacy and efficiency of our method, showing that it enables a robot to successfully learn safety constraints with a small handful (tens) of human directional corrections., Comment: 18 pages, submission to T-RO

Environment induced steady state quantum coherence (SSQC) is a captivating phenomenon that challenges conventional understandings of decoherence. In this letter, we delve into the foundational aspects of environment-induced SSQC, shedding light on its emergence within the framework of system-bath interactions. Starting from a microscopic system-bath coupled model, we investigate the dependence of SSQC on environmental memory effects, bath temperature, system-bath coupling strength, and squeezing parameters. Our findings reveal that the environment not only acts as a generator but also as a disruptor of SSQC. A peak will exist for a non-Markovian bath, which is a result of competition between these two mechanisms. Interestingly, the peak disappears in Markovian case. Additionally, we observe that the generated SSQC can be further amplified through environment squeezing., Comment: 8 pages, 3 figures

Enlarging bandwidth capacity of the integrated photonic systems demands efficient and broadband light coupling among optical elements, which has been a vital issue in integrated photonics. Here, we have developed a compact ultra-broadband light coupling strategy based on nonadiabatic pumping in coupled optical waveguides, and experimentally demonstrated the designs in thin-film lithium niobate on insulator (LNOI) platform. We found that nonadiabatic transition would produce a decreased dispersion of the phases related to eigenstates in the waveguides. As a consequence, we realized high-efficiency directional transfer between edgestates for various wavelengths covering a 1-dB bandwidth of ~320 nm in experiment (>400 nm in simulation), with a coupling length (~50 {\mu}m) approximately 1/10 of that required in the adiabatic regime. Furthermore, we have constructed complex functional devices including beamsplitter and multiple-level cascaded networks for broadband light routing and splitting. Our work preserves significant advantages simultaneously in extending the operation bandwidth and minimizing the footprint, which demonstrates great potential for large-scale and compact photonic integration on chip.

In this paper, we investigate a movable antenna (MA)-aided integrated sensing and communication (ISAC) system, where a reconfigurable intelligent surface (RIS) is employed to enhance wireless communication and sensing performance in dead zones. Specifically, this paper aims to maximize the minimum beampattern gain at the RIS by jointly optimizing beamforming matrix at the base station (BS), the reflecting coefficients at the RIS and the positions of the MAs, subject to signal-to-interference-plus-noise ratio (SINR) constraint for the users and maximum transmit power at the BS. To tackle this non-convex optimization problem, we propose an alternating optimization (AO) algorithm and employ semidefinite relaxation (SDR), sequential rank-one constraint relaxation (SRCR) and successive convex approximation (SCA) techniques. Numerical results indicate that the MA and RIS-aided ISAC system outperforms conventional fixed position antenna (FPA) and RIS-aided systems. In addition, the application of MAs can reduce the similarity of user channels and enhance channel gain in the ISAC system., Comment: 14 pages, 11 figures

Frequency conversion is a widely realized physical process in nonlinear systems of optics and electronics. As an emerging nonlinear platform, spintronic devices have the potential to achieve stronger frequency conversion. Here, we demonstrated a microwave frequency conversion method in a hybrid quantum system, integrating nitrogen-vacancy centers in diamond with magnetic thin film CoFeB. We achieve a conversion bandwidth ranging from 0.1 to 12GHz, presenting an up to $\mathrm{25^{th}}$ order frequency conversion and further display the application of this method for frequency detection and qubits coherent control. Distinct from traditional frequency conversion techniques based on nonlinear electric response, our approach employs nonlinear magnetic response in spintronic devices. The nonlinearity, originating from the symmetry breaking such as domain walls in magnetic films, presents that our method can be adapted to hybrid systems of other spintronic devices and spin qubits, expanding the application scope of spintronic devices and providing a promising on-chip platform for coupling quantum systems., Comment: 11 pages, 5 figures