Search

Polarization-entangled photon pairs are essential sources for photonic quantum information processing. However, generating entangled photon pairs with large detuning via spontaneous parametric down-conversion (SPDC) often requires complex configurations to compensate for phase matching. Here, we propose a simple and efficient scheme to generate polarization-entangled photon pairs based on type-0 SPDC in a thin-film lithium niobate waveguide with a single poling period. By utilizing the strong dispersion engineering capabilities of thin-film waveguides, we can achieve both degenerate and highly detuned entangled photon pairs. Furthermore, we demonstrate on-chip temporal compensation using an integrated waveguide structure. Our approach offers a compact and scalable solution for integrated quantum photonic circuits.

Arbitrary-resolution image generation still remains a challenging task in AIGC, as it requires handling varying resolutions and aspect ratios while maintaining high visual quality. Existing transformer-based diffusion methods suffer from quadratic computation cost and limited resolution extrapolation capabilities, making them less effective for this task. In this paper, we propose FlowDCN, a purely convolution-based generative model with linear time and memory complexity, that can efficiently generate high-quality images at arbitrary resolutions. Equipped with a new design of learnable group-wise deformable convolution block, our FlowDCN yields higher flexibility and capability to handle different resolutions with a single model. FlowDCN achieves the state-of-the-art 4.30 sFID on $256\times256$ ImageNet Benchmark and comparable resolution extrapolation results, surpassing transformer-based counterparts in terms of convergence speed (only $\frac{1}{5}$ images), visual quality, parameters ($8\%$ reduction) and FLOPs ($20\%$ reduction). We believe FlowDCN offers a promising solution to scalable and flexible image synthesis., Comment: Accepted on NeurIPS24

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in short video understanding. However, understanding long-form videos still remains challenging for MLLMs. This paper proposes TimeSuite, a collection of new designs to adapt the existing short-form video MLLMs for long video understanding, including a simple yet efficient framework to process long video sequence, a high-quality video dataset for grounded tuning of MLLMs, and a carefully-designed instruction tuning task to explicitly incorporate the grounding supervision in the traditional QA format. Specifically, based on VideoChat, we propose our long-video MLLM, coined as VideoChat-T, by implementing a token shuffling to compress long video tokens and introducing Temporal Adaptive Position Encoding (TAPE) to enhance the temporal awareness of visual representation. Meanwhile, we introduce the TimePro, a comprehensive grounding-centric instruction tuning dataset composed of 9 tasks and 349k high-quality grounded annotations. Notably, we design a new instruction tuning task type, called Temporal Grounded Caption, to peform detailed video descriptions with the corresponding time stamps prediction. This explicit temporal location prediction will guide MLLM to correctly attend on the visual content when generating description, and thus reduce the hallucination risk caused by the LLMs. Experimental results demonstrate that our TimeSuite provides a successful solution to enhance the long video understanding capability of short-form MLLM, achieving improvement of 5.6% and 6.8% on the benchmarks of Egoschema and VideoMME, respectively. In addition, VideoChat-T exhibits robust zero-shot temporal grounding capabilities, significantly outperforming the existing state-of-the-art MLLMs. After fine-tuning, it performs on par with the traditional supervised expert models.

Talking head generation intends to produce vivid and realistic talking head videos from a single portrait and speech audio clip. Although significant progress has been made in diffusion-based talking head generation, almost all methods rely on autoregressive strategies, which suffer from limited context utilization beyond the current generation step, error accumulation, and slower generation speed. To address these challenges, we present DAWN (Dynamic frame Avatar With Non-autoregressive diffusion), a framework that enables all-at-once generation of dynamic-length video sequences. Specifically, it consists of two main components: (1) audio-driven holistic facial dynamics generation in the latent motion space, and (2) audio-driven head pose and blink generation. Extensive experiments demonstrate that our method generates authentic and vivid videos with precise lip motions, and natural pose/blink movements. Additionally, with a high generation speed, DAWN possesses strong extrapolation capabilities, ensuring the stable production of high-quality long videos. These results highlight the considerable promise and potential impact of DAWN in the field of talking head video generation. Furthermore, we hope that DAWN sparks further exploration of non-autoregressive approaches in diffusion models. Our code will be publicly available at https://github.com/Hanbo-Cheng/DAWN-pytorch.

In recent years, censored quantile regression has enjoyed an increasing popularity for survival analysis while many existing works rely on linearity assumptions. In this work, we propose a Global Censored Quantile Random Forest (GCQRF) for predicting a conditional quantile process on data subject to right censoring, a forest-based flexible, competitive method able to capture complex nonlinear relationships. Taking into account the randomness in trees and connecting the proposed method to a randomized incomplete infinite degree U-process (IDUP), we quantify the prediction process' variation without assuming an infinite forest and establish its weak convergence. Moreover, feature importance ranking measures based on out-of-sample predictive accuracy are proposed. We demonstrate the superior predictive accuracy of the proposed method over a number of existing alternatives and illustrate the use of the proposed importance ranking measures on both simulated and real data.

In this paper, we introduce SPA, a novel representation learning framework that emphasizes the importance of 3D spatial awareness in embodied AI. Our approach leverages differentiable neural rendering on multi-view images to endow a vanilla Vision Transformer (ViT) with intrinsic spatial understanding. We present the most comprehensive evaluation of embodied representation learning to date, covering 268 tasks across 8 simulators with diverse policies in both single-task and language-conditioned multi-task scenarios. The results are compelling: SPA consistently outperforms more than 10 state-of-the-art representation methods, including those specifically designed for embodied AI, vision-centric tasks, and multi-modal applications, while using less training data. Furthermore, we conduct a series of real-world experiments to confirm its effectiveness in practical scenarios. These results highlight the critical role of 3D spatial awareness for embodied representation learning. Our strongest model takes more than 6000 GPU hours to train and we are committed to open-sourcing all code and model weights to foster future research in embodied representation learning. Project Page: https://haoyizhu.github.io/spa/., Comment: Project Page: https://haoyizhu.github.io/spa/

It's widely perceived that Reconfigurable Intelligent Surfaces (RIS) cannot increase Degrees of Freedom (DoF) due to their relay nature. A notable exception is Jiang \& Yu's work. They demonstrate via simulation that in an ideal $K$-user interference channel, passive RIS can achieve the interference-free DoF. In this paper, we investigate the DoF gain of RIS in more realistic systems, namely cellular networks, and more challenging scenarios with direct links. We prove that RIS can boost the DoF per cell to that of the interference-free scenario even \textit{ with direct-links}. Furthermore, we \textit{theoretically} quantify the number of RIS elements required to achieve that goal, i.e. $max\left\{ {2L, (\sqrt L + c)\eta+L } \right\}$ (where $L=GM(GM-1)$, $c$ is a constant and $\eta$ denotes the ratio of channel strength) for the $G$-cells with more single-antenna users $K$ than base station antennas $M$ per cell. The main challenge lies in addressing the feasibility of a system of algebraic equations, which is difficult by itself in algebraic geometry. We tackle this problem in a probabilistic way, by exploiting the randomness of the involved coefficients and addressing the problem from the perspective of extreme value statistics and convex geometry. Moreover, numerical results confirm the tightness of our theoretical results.

Continuous glucose monitoring (CGM) has been increasingly used in US hospitals for the care of patients with diabetes. Time in range (TIR), which measures the percent of time over a specified time window with glucose values within a target range, has served as a pivotal CGM-metric for assessing glycemic control. However, inpatient CGM is prone to a prevailing issue that a limited length of hospital stay can cause insufficient CGM sampling, leading to a scenario with functional data plagued by complex missingness. Current analyses of inpatient CGM studies, however, ignore this issue and typically compute the TIR as the proportion of available CGM glucose values in range. As shown by simulation studies, this can result in considerably biased estimation and inference, largely owing to the nonstationary nature of inpatient CGM trajectories. In this work, we develop a rigorous statistical framework that confers valid inference on TIR in realistic inpatient CGM settings. Our proposals utilize a novel probabilistic representation of TIR, which enables leveraging the technique of inverse probability weighting and semiparametric survival modeling to obtain unbiased estimators of mean TIR that properly account for incompletely observed CGM trajectories. We establish desirable asymptotic properties of the proposed estimators. Results from our numerical studies demonstrate good finite-sample performance of the proposed method as well as its advantages over existing approaches. The proposed method is generally applicable to other functional data settings similar to CGM.

With the development of video understanding, there is a proliferation of tasks for clip-level temporal video analysis, including temporal action detection (TAD), temporal action segmentation (TAS), and generic event boundary detection (GEBD). While task-specific video understanding models have exhibited outstanding performance in each task, there remains a dearth of a unified framework capable of simultaneously addressing multiple tasks, which is a promising direction for the next generation of AI. To this end, in this paper, we propose a single unified framework, coined as Temporal2Seq, to formulate the output of these temporal video understanding tasks as a sequence of discrete tokens. With this unified token representation, Temporal2Seq can train a generalist model within a single architecture on different video understanding tasks. In the absence of multi-task learning (MTL) benchmarks, we compile a comprehensive co-training dataset by borrowing the datasets from TAD, TAS, and GEBD tasks. We evaluate our Temporal2Seq generalist model on the corresponding test sets of three tasks, demonstrating that Temporal2Seq can produce reasonable results on various tasks and achieve advantages compared with single-task training on this framework. We also investigate the generalization performance of our generalist model on new datasets from different tasks, which yields superior performance to the specific model.

The rise of malicious packages in public registries poses a significant threat to software supply chain (SSC) security. Although academia and industry employ methods like software composition analysis (SCA) to address this issue, existing approaches often lack timely and comprehensive intelligence updates. This paper introduces PackageIntel, a novel platform that revolutionizes the collection, processing, and retrieval of malicious package intelligence. By utilizing exhaustive search techniques, snowball sampling from diverse sources, and large language models (LLMs) with specialized prompts, PackageIntel ensures enhanced coverage, timeliness, and accuracy. We have developed a comprehensive database containing 20,692 malicious NPM and PyPI packages sourced from 21 distinct intelligence repositories. Empirical evaluations demonstrate that PackageIntel achieves a precision of 98.6% and an F1 score of 92.0 in intelligence extraction. Additionally, it detects threats on average 70% earlier than leading databases like Snyk and OSV, and operates cost-effectively at $0.094 per intelligence piece. The platform has successfully identified and reported over 1,000 malicious packages in downstream package manager mirror registries. This research provides a robust, efficient, and timely solution for identifying and mitigating threats within the software supply chain ecosystem.

4D millimeter-wave (MMW) radar, which provides both height information and dense point cloud data over 3D MMW radar, has become increasingly popular in 3D object detection. In recent years, radar-vision fusion models have demonstrated performance close to that of LiDAR-based models, offering advantages in terms of lower hardware costs and better resilience in extreme conditions. However, many radar-vision fusion models treat radar as a sparse LiDAR, underutilizing radar-specific information. Additionally, these multi-modal networks are often sensitive to the failure of a single modality, particularly vision. To address these challenges, we propose the Radar Depth Lift-Splat-Shoot (RDL) module, which integrates radar-specific data into the depth prediction process, enhancing the quality of visual Bird-Eye View (BEV) features. We further introduce a Unified Feature Fusion (UFF) approach that extracts BEV features across different modalities using shared module. To assess the robustness of multi-modal models, we develop a novel Failure Test (FT) ablation experiment, which simulates vision modality failure by injecting Gaussian noise. We conduct extensive experiments on the View-of-Delft (VoD) and TJ4D datasets. The results demonstrate that our proposed Unified BEVFusion (UniBEVFusion) network significantly outperforms state-of-the-art models on the TJ4D dataset, with improvements of 1.44 in 3D and 1.72 in BEV object detection accuracy., Comment: 6 pages, 4 figues, conference

Enhancement and active control of light-matter interactions at the atomic scale is important for developing next-generation nanophotonic and quantum optical devices. Here, we demonstrate electric control of both excitonic strong coupling and electroluminescence by integrating semiconductor monolayers into a nanometer gap of electrically driven nanocube-on-mirror plasmonic nanocavities. Particularly, in a strongly-coupled system of nanocavity plasmons and WSe2 excitons, the ultra-strong electric field generated in the nanocavity gap enables a reversible modulation of the Rabi splitting between ~102 and 80 meV with a bias below 2.5 V. In the quantum tunnelling regime, by injecting carriers into a nanocavity-integrated WS2 monolayer, bias-controlled spectrally tunable electroluminescence from charged or neutral excitons is achieved with an external quantum efficiency reaching ~3.5%. These results underline practical approaches to electric control of atomic-scale light-matter interactions for applications including nanoscale light sources, ultrafast electro-optic modulation, quantum information processing and sensing.

Quantum entanglement plays a critical role in many quantum applications, but detecting entanglement, especially in multipartite or high-dimensional quantum systems, remains a challenge. In this paper, we propose several families of entanglement criteria for detecting entanglement in multipartite or high-dimensional quantum states by the generalized Wigner-Yanase skew information $I^s(\rho,X)$ for $-1\leq s\leq0$ and variance. We also reveal a complementary character between the criteria based on the generalized Wigner-Yanase skew information and an alternative one based on variance through specific examples. We illustrate the merits of these criteria and show that the combination of the entanglement criteria has a stronger detection capability, as it is capable of detecting entangled states that remain unrecognized by other criteria., Comment: 15 pages

Nonclassical correlation is an important concept in quantum information theory, referring to a special type of correlation that exists between quantum systems, which surpasses the scope of classical physics. In this paper, we introduce the concept of a family of information with important properties, namely the generalized Wigner-Yanase skew information, of which the famous quantum Fisher information and Wigner-Yanase skew information are special cases.We classify the local observables in the generalized Wigner-Yanase skew information into two categories (i.e., orthonormal bases and a Hermitian operator with a fixed nondegenerate spectrum), and based on this, we propose two different forms of indicators to quantify nonclassical correlations of bipartite quantum states. We have not only investigated some important properties of these two kinds of indicators but also illustrated through specific examples that they can indeed capture some nonclassical correlations. Furthermore, we find that these two types of indicators reduce to entanglement measure for bipartite pure states. Specifically, we also derive the relationship between these two indicators and the entanglement measure $I$-concurrence., Comment: 10 pages

We present Open-MAGVIT2, a family of auto-regressive image generation models ranging from 300M to 1.5B. The Open-MAGVIT2 project produces an open-source replication of Google's MAGVIT-v2 tokenizer, a tokenizer with a super-large codebook (i.e., $2^{18}$ codes), and achieves the state-of-the-art reconstruction performance (1.17 rFID) on ImageNet $256 \times 256$. Furthermore, we explore its application in plain auto-regressive models and validate scalability properties. To assist auto-regressive models in predicting with a super-large vocabulary, we factorize it into two sub-vocabulary of different sizes by asymmetric token factorization, and further introduce "next sub-token prediction" to enhance sub-token interaction for better generation quality. We release all models and codes to foster innovation and creativity in the field of auto-regressive visual generation.

Recent Vision Mamba models not only have much lower complexity for processing higher resolution images and longer videos but also the competitive performance with Vision Transformers (ViTs). However, they are stuck into overfitting and thus only present up to base size (about 80M). It is still unclear how vanilla Vision Mamba (Vim) can be efficiently scaled up to larger sizes, which is essentially for further exploitation. In this paper, we propose a stochastic layer-wise shuffle regularization, which empowers successfully scaling non-hierarchical Vision Mamba to a large size (about 300M) in a supervised setting. Specifically, our base and large-scale ShuffleMamba models can outperform the supervised ViTs of similar size by 0.8\% and 1.0\% classification accuracy on ImageNet1k, respectively, without auxiliary data. When evaluated on the ADE20K semantic segmentation and COCO detection tasks, our ShuffleMamba models also show significant improvements. Without bells and whistles, the stochastic layer-wise shuffle has the following highlights: (1) \textit{Plug and play:} it does not change model architectures and will be omitted in inference. (2) \textit{Simple but effective:} it can improve the overfitting in Vim training and only introduce random token permutation operations. (3) \textit{Intuitive:} the token sequences in deeper layers are more likely to be shuffled as they are expected to be more semantic and less sensitive to patch positions. Code and models will be available at https://github.com/huangzizheng01/ShuffleMamba.

Open-source software (OSS) has experienced a surge in popularity, attributed to its collaborative development model and cost-effective nature. However, the adoption of specific software versions in development projects may introduce security risks when these versions bring along vulnerabilities. Current methods of identifying vulnerable versions typically analyze and trace the code involved in vulnerability patches using static analysis with pre-defined rules. They then use syntactic-level code clone detection to identify the vulnerable versions. These methods are hindered by imprecisions due to (1) the inclusion of vulnerability-irrelevant code in the analysis and (2) the inadequacy of syntactic-level code clone detection. This paper presents Vercation, an approach designed to identify vulnerable versions of OSS written in C/C++. Vercation combines program slicing with a Large Language Model (LLM) to identify vulnerability-relevant code from vulnerability patches. It then backtraces historical commits to gather previous modifications of identified vulnerability-relevant code. We propose semantic-level code clone detection to compare the differences between pre-modification and post-modification code, thereby locating the vulnerability-introducing commit (vic) and enabling to identify the vulnerable versions between the patch commit and the vic. We curate a dataset linking 74 OSS vulnerabilities and 1013 versions to evaluate Vercation. On this dataset, our approach achieves the F1 score of 92.4%, outperforming current state-of-the-art methods. More importantly, Vercation detected 134 incorrect vulnerable OSS versions in NVD reports.

Sub-cycle optical pulse is of great importance for ultrafast science and technology. While a narrower pulse can offer a higher temporal resolution, so far the pulse width has not exceeded the limit of half an optical cycle. Here we propose to break the half-cycle limit via inverse Compton scattering in a nano-slit optical mode, in which a deep-subwavelength-confined optical field can be converted into a deep-sub-cycle attosecond pulse by high-energy free electrons flying through. Our calculations show that, with experimentally reachable conditions, a measurable deep-sub-cycle attosecond pulse with a width narrower than half an optical cycle can be generated. Quantitatively, using a deep-subwavelength-confined 4.4-$\mu$m-wavelength 100-fs pulsed optical driving field and a 2-MeV 50-as 5-pC electron bunch, we can obtain an attosecond pulse with a peak frequency of 2.55 PHz, a pulse width of 99 as ($\sim$0.25 optical cycle), and a single-pulse photon number larger than 200 around the material damage threshold. Such pulses may open opportunities for studying light-matter interaction on the deep-sub-cycle level, and pave a way to unprecedented optical technology ranging from temporal super-resolution optical microscopy and spectroscopy to unconventional atom/molecule polarization and manipulation.

Recently, the remarkable success of pre-trained Vision Transformers (ViTs) from image-text matching has sparked an interest in image-to-video adaptation. However, most current approaches retain the full forward pass for each frame, leading to a high computation overhead for processing entire videos. In this paper, we present InTI, a novel approach for compressive image-to-video adaptation using dynamic Inter-frame Token Interpolation. InTI aims to softly preserve the informative tokens without disrupting their coherent spatiotemporal structure. Specifically, each token pair at identical positions within neighbor frames is linearly aggregated into a new token, where the aggregation weights are generated by a multi-scale context-aware network. In this way, the information of neighbor frames can be adaptively compressed in a point-by-point manner, thereby effectively reducing the number of processed frames by half each time. Importantly, InTI can be seamlessly integrated with existing adaptation methods, achieving strong performance without extra-complex design. On Kinetics-400, InTI reaches a top-1 accuracy of 87.1 with a remarkable 37.5% reduction in GFLOPs compared to naive adaptation. When combined with additional temporal modules, InTI achieves a top-1 accuracy of 87.6 with a 37% reduction in GFLOPs. Similar conclusions have been verified in other common datasets.

Vision-language models have showcased impressive zero-shot classification capabilities when equipped with suitable text prompts. Previous studies have shown the effectiveness of test-time prompt tuning; however, these methods typically require per-image prompt adaptation during inference, which incurs high computational budgets and limits scalability and practical deployment. To overcome this issue, we introduce Self-TPT, a novel framework leveraging Self-supervised learning for efficient Test-time Prompt Tuning. The key aspect of Self-TPT is that it turns to efficient predefined class adaptation via self-supervised learning, thus avoiding computation-heavy per-image adaptation at inference. Self-TPT begins by co-training the self-supervised and the classification task using source data, then applies the self-supervised task exclusively for test-time new class adaptation. Specifically, we propose Contrastive Prompt Learning (CPT) as the key task for self-supervision. CPT is designed to minimize the intra-class distances while enhancing inter-class distinguishability via contrastive learning. Furthermore, empirical evidence suggests that CPT could closely mimic back-propagated gradients of the classification task, offering a plausible explanation for its effectiveness. Motivated by this finding, we further introduce a gradient matching loss to explicitly enhance the gradient similarity. We evaluated Self-TPT across three challenging zero-shot benchmarks. The results consistently demonstrate that Self-TPT not only significantly reduces inference costs but also achieves state-of-the-art performance, effectively balancing the efficiency-efficacy trade-off.

Though many approaches have been proposed for Automated Program Repair (APR) and indeed achieved remarkable performance, they still have limitations in fixing bugs that require analyzing and reasoning about the logic of the buggy program. Recently, large language models (LLMs) instructed by prompt engineering have attracted much attention for their powerful ability to address many kinds of tasks including bug-fixing. However, the quality of the prompt will highly affect the ability of LLMs and manually constructing high-quality prompts is a costly endeavor. To address this limitation, we propose a self-directed LLM-based automated program repair, ThinkRepair, with two main phases: collection phase and fixing phase. The former phase automatically collects various chains of thoughts that constitute pre-fixed knowledge by instructing LLMs with the Chain-of-Thought (CoT) prompt. The latter phase targets fixing a bug by first selecting examples for few-shot learning and second automatically interacting with LLMs, optionally appending with feedback of testing information. Evaluations on two widely studied datasets (Defects4J and QuixBugs) by comparing ThinkRepair with 12 SOTA APRs indicate the priority of ThinkRepair in fixing bugs. Notably, ThinkRepair fixes 98 bugs and improves baselines by 27%-344.4% on Defects4J V1.2. On Defects4J V2.0, ThinkRepair fixes 12-65 more bugs than the SOTA APRs. Additionally, ThinkRepair also makes a considerable improvement on QuixBugs (31 for Java and 21 for Python at most)., Comment: Accepted By ISSTA'24

This study presents a comparative analysis of the a complex SQL benchmark, TPC-DS, with two existing text-to-SQL benchmarks, BIRD and Spider. Our findings reveal that TPC-DS queries exhibit a significantly higher level of structural complexity compared to the other two benchmarks. This underscores the need for more intricate benchmarks to simulate realistic scenarios effectively. To facilitate this comparison, we devised several measures of structural complexity and applied them across all three benchmarks. The results of this study can guide future research in the development of more sophisticated text-to-SQL benchmarks. We utilized 11 distinct Language Models (LLMs) to generate SQL queries based on the query descriptions provided by the TPC-DS benchmark. The prompt engineering process incorporated both the query description as outlined in the TPC-DS specification and the database schema of TPC-DS. Our findings indicate that the current state-of-the-art generative AI models fall short in generating accurate decision-making queries. We conducted a comparison of the generated queries with the TPC-DS gold standard queries using a series of fuzzy structure matching techniques based on query features. The results demonstrated that the accuracy of the generated queries is insufficient for practical real-world application.

Recognition and generation are two fundamental tasks in computer vision, which are often investigated separately in the exiting literature. However, these two tasks are highly correlated in essence as they both require understanding the underline semantics of visual concepts. In this paper, we propose a new learning framework, coined as CycleHOI, to boost the performance of human-object interaction (HOI) detection by bridging the DETR-based detection pipeline and the pre-trained text-to-image diffusion model. Our key design is to introduce a novel cycle consistency loss for the training of HOI detector, which is able to explicitly leverage the knowledge captured in the powerful diffusion model to guide the HOI detector training. Specifically, we build an extra generation task on top of the decoded instance representations from HOI detector to enforce a detection-generation cycle consistency. Moreover, we perform feature distillation from diffusion model to detector encoder to enhance its representation power. In addition, we further utilize the generation power of diffusion model to augment the training set in both aspects of label correction and sample generation. We perform extensive experiments to verify the effectiveness and generalization power of our CycleHOI with three HOI detection frameworks on two public datasets: HICO-DET and V-COCO. The experimental results demonstrate our CycleHOI can significantly improve the performance of the state-of-the-art HOI detectors.

Real-time Clock (RTC) has been widely used in various real-time systems to provide precise system time. In this paper, we reveal a new security vulnerability of the RTC circuit, where the internal storage time or timestamp can be arbitrarily modified forward or backward. The security threat of dynamic modifications of system time caused by this vulnerability is called TimeTravel. Based on acoustic resonance and piezoelectric effects, TimeTravel applies acoustic guide waves to the quartz crystal, thereby adjusting the characteristics of the oscillating signal transmitted into the RTC circuit. By manipulating the parameters of acoustic waves, TimeTravel can accelerate or decelerate the timing speed of system time at an adjustable rate, resulting in the relative drift of the timing, which can pose serious safety threats. To assess the severity of TimeTravel, we examine nine modules and two commercial devices under the RTC circuit. The experimental results show that TimeTravel can drift system time forward and backward at a chosen speed with a maximum 93% accuracy. Our analysis further shows that TimeTravel can maintain an attack success rate of no less than 77% under environments with typical obstacle items., Comment: Accepted by USENIX Security 2024 winter cycle and will appear in USENIX Security 2025

With the growth of high-quality data and advancement in visual pre-training paradigms, Video Foundation Models (VFMs) have made significant progress recently, demonstrating their remarkable performance on traditional video understanding benchmarks. However, the existing benchmarks (e.g. Kinetics) and their evaluation protocols are often limited by relatively poor diversity, high evaluation costs, and saturated performance metrics. In this paper, we build a comprehensive benchmark suite to address these issues, namely VideoEval. Specifically, we establish the Video Task Adaption Benchmark (VidTAB) and the Video Embedding Benchmark (VidEB) from two perspectives: evaluating the task adaptability of VFMs under few-shot conditions and assessing their representation power by directly applying to downstream tasks. With VideoEval, we conduct a large-scale study on 20 popular open-source vision foundation models. Our study reveals some insightful findings on VFMs: 1) overall, current VFMs exhibit weak generalization across diverse tasks, 2) increasing video data, whether labeled or weakly-labeled video-text pairs, does not necessarily improve task performance, 3) the effectiveness of some pre-training paradigms may not be fully validated in previous benchmarks, and 4) combining different pre-training paradigms can help improve the generalization capabilities. We believe this study serves as an important complement to the current evaluation for VFMs and offers valuable insights for the future research.

Given the current visual observations, the traditional procedure planning task in instructional videos requires a model to generate goal-directed plans within a given action space. All previous methods for this task conduct training and inference under the same action space, and they can only plan for pre-defined events in the training set. We argue this setting is not applicable for human assistance in real lives and aim to propose a more general and practical planning paradigm. Specifically, in this paper, we introduce a new task named Open-event Procedure Planning (OEPP), which extends the traditional procedure planning to the open-event setting. OEPP aims to verify whether a planner can transfer the learned knowledge to similar events that have not been seen during training. We rebuild a new benchmark of OpenEvent for this task based on existing datasets and divide the events involved into base and novel parts. During the data collection process, we carefully ensure the transfer ability of procedural knowledge for base and novel events by evaluating the similarity between the descriptions of different event steps with multiple stages. Based on the collected data, we further propose a simple and general framework specifically designed for OEPP, and conduct extensive study with various baseline methods, providing a detailed and insightful analysis on the results for this task., Comment: 9 pages(main text), 6 figures, 10 tables

Pre-trained vision-language models (VLMs) have shown impressive results in various visual classification tasks. However, we often fail to fully unleash their potential when adapting them for new concept understanding due to limited information on new classes. To address this limitation, we introduce a novel adaptation framework, AWT (Augment, Weight, then Transport). AWT comprises three key components: augmenting inputs with diverse visual perspectives and enriched class descriptions through image transformations and language models; dynamically weighting inputs based on the prediction entropy; and employing optimal transport to mine semantic correlations in the vision-language space. AWT can be seamlessly integrated into various VLMs, enhancing their zero-shot capabilities without additional training and facilitating few-shot learning through an integrated multimodal adapter module. We verify AWT in multiple challenging scenarios, including zero-shot and few-shot image classification, zero-shot video action recognition, and out-of-distribution generalization. AWT consistently outperforms the state-of-the-art methods in each setting. In addition, our extensive studies further demonstrate AWT's effectiveness and adaptability across different VLMs, architectures, and scales., Comment: Accepted by NeurIPS 2024

Inter-frame modeling is pivotal in generating intermediate frames for video frame interpolation (VFI). Current approaches predominantly rely on convolution or attention-based models, which often either lack sufficient receptive fields or entail significant computational overheads. Recently, Selective State Space Models (S6) have emerged, tailored specifically for long sequence modeling, offering both linear complexity and data-dependent modeling capabilities. In this paper, we propose VFIMamba, a novel frame interpolation method for efficient and dynamic inter-frame modeling by harnessing the S6 model. Our approach introduces the Mixed-SSM Block (MSB), which initially rearranges tokens from adjacent frames in an interleaved fashion and subsequently applies multi-directional S6 modeling. This design facilitates the efficient transmission of information across frames while upholding linear complexity. Furthermore, we introduce a novel curriculum learning strategy that progressively cultivates proficiency in modeling inter-frame dynamics across varying motion magnitudes, fully unleashing the potential of the S6 model. Experimental findings showcase that our method attains state-of-the-art performance across diverse benchmarks, particularly excelling in high-resolution scenarios. In particular, on the X-TEST dataset, VFIMamba demonstrates a noteworthy improvement of 0.80 dB for 4K frames and 0.96 dB for 2K frames.

In this report, we present our solutions to the EgoVis Challenges in CVPR 2024, including five tracks in the Ego4D challenge and three tracks in the EPIC-Kitchens challenge. Building upon the video-language two-tower model and leveraging our meticulously organized egocentric video data, we introduce a novel foundation model called EgoVideo. This model is specifically designed to cater to the unique characteristics of egocentric videos and provides strong support for our competition submissions. In the Ego4D challenges, we tackle various tasks including Natural Language Queries, Step Grounding, Moment Queries, Short-term Object Interaction Anticipation, and Long-term Action Anticipation. In addition, we also participate in the EPIC-Kitchens challenge, where we engage in the Action Recognition, Multiple Instance Retrieval, and Domain Adaptation for Action Recognition tracks. By adapting EgoVideo to these diverse tasks, we showcase its versatility and effectiveness in different egocentric video analysis scenarios, demonstrating the powerful representation ability of EgoVideo as an egocentric foundation model. Our codebase and pretrained models are publicly available at https://github.com/OpenGVLab/EgoVideo., Comment: Champion solutions in the EgoVis CVPR 2024 workshop

We report a comprehensive study of Sperrylite (PtAs2), the main platinum source in natural minerals, as a function of applied pressures up to 150 GPa. While no structural phase transition was detected from pressure-dependent X-ray measurements, the unit cell volume shrinks monotonically with pressure following the third-order Birch-Murnaghan equation of state. The mildly semiconducting behavior found in pure synthesized crystals at ambient pressures becomes more insulating upon increasing applied pressure before metalizing at higher pressures, giving way to the appearance of an abrupt decrease in resistance near 3 K at pressures above 92 GPa consistent with the onset of a superconducing phase. The pressure evolution of the calculated electronic band structure reveals the same physical trend as our transport measurements, with a non-monotonic evolution explained by a hole band that is pushed below the Fermi energy and an electron band that approaches it as a function of pressure, both reaching a touching point suggestive of an excitonic state. A topological Lifshitz transition of the electronic structure and an increase in the density of states may naturally explain the onset of superconductivity in this material, Comment: 7 pages, 7 figures

The emission of neutrons from heavy ion reactions is an important observable for studying the asymmetric nuclear equation of state and the reaction dynamics. A 20-unit neutron array has been developed and mounted on the compact spectrometer for heavy ion experiments (CSHINE) to measure the neutron spectra, neutron-neutron and neutron-proton correlation functions. Each unit consists of a $\rm 15\times 15\times 15~cm^3$ plastic scintillator coupled to a $ \phi=52 ~\rm mm$ photomultiplier. The Geant4 simulation with optical process is performed to investigate the time resolution and the neutron detection efficiency. The inherent time resolution of 212 ps is obtained by cosmic ray coincidence test. The n-$\gamma$ discrimination and time-of-flight performance are given by $\rm ^{252}Cf$ radioactive source test and beam test. The neutron energy spectra have been obtained in the angle range $30^\circ \le \theta_{\rm lab} \le 51^\circ$ in the beam experiment of $^{124}$Sn+$^{124}$Sn at 25 MeV/u with CSHINE., Comment: 8 pages, 11 figures

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias, potential for unsafe actions, dataset poisoning, lack of explainability, hallucinations, and non-reproducibility. These risks necessitate the development of "guardrails" to align LLMs with desired behaviors and mitigate potential harm. This work explores the risks associated with deploying LLMs and evaluates current approaches to implementing guardrails and model alignment techniques. We examine intrinsic and extrinsic bias evaluation methods and discuss the importance of fairness metrics for responsible AI development. The safety and reliability of agentic LLMs (those capable of real-world actions) are explored, emphasizing the need for testability, fail-safes, and situational awareness. Technical strategies for securing LLMs are presented, including a layered protection model operating at external, secondary, and internal levels. System prompts, Retrieval-Augmented Generation (RAG) architectures, and techniques to minimize bias and protect privacy are highlighted. Effective guardrail design requires a deep understanding of the LLM's intended use case, relevant regulations, and ethical considerations. Striking a balance between competing requirements, such as accuracy and privacy, remains an ongoing challenge. This work underscores the importance of continuous research and development to ensure the safe and responsible use of LLMs in real-world applications., Comment: Independent study, Exploring LLMs, Deploying LLMs and their Risks

Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that such data aids multimodal in-context learning and maintains the capabilities of large language models during multimodal fine-tuning. However, the limited scale and diversity of current image-text interleaved data restrict the development of multimodal large language models. In this paper, we introduce OmniCorpus, a 10 billion-scale image-text interleaved dataset. Using an efficient data engine, we filter and extract large-scale high-quality documents, which contain 8.6 billion images and 1,696 billion text tokens. Compared to counterparts (e.g., MMC4, OBELICS), our dataset 1) has 15 times larger scales while maintaining good data quality; 2) features more diverse sources, including both English and non-English websites as well as video-centric websites; 3) is more flexible, easily degradable from an image-text interleaved format to pure text corpus and image-text pairs. Through comprehensive analysis and experiments, we validate the quality, usability, and effectiveness of the proposed dataset. We hope this could provide a solid data foundation for future multimodal model research. Code and data are released at https://github.com/OpenGVLab/OmniCorpus.

Accurately simulating non-Markovian quantum dynamics in system-bath coupled problems remains challenging. In this work, we present a novel memory truncation scheme for the iterative Quasi-Adiabatic Propagator Path Integral (iQuAPI) method to improve accuracy. Conventional memory truncation in iQuAPI discards all influence functional beyond a certain time interval, which is not effective for problems with a long memory time. Our proposed scheme selectively retains the most significant parts of the influence functional using the density matrix renormalization group algorithm. We validate the effectiveness of our scheme through simulations of the spin-boson model across various parameter sets, demonstrating faster convergence and improved accuracy compared to the conventional scheme. Our findings suggest that the new memory truncation scheme significantly advances the capabilities of iQuAPI for problems with a long memory time., Comment: 10 pages, 4 figures

Honeypots, as a strategic cyber-deception mechanism designed to emulate authentic interactions and bait unauthorized entities, continue to struggle with balancing flexibility, interaction depth, and deceptive capability despite their evolution over decades. Often they also lack the capability of proactively adapting to an attacker's evolving tactics, which restricts the depth of engagement and subsequent information gathering. Under this context, the emergent capabilities of large language models, in tandem with pioneering prompt-based engineering techniques, offer a transformative shift in the design and deployment of honeypot technologies. In this paper, we introduce HoneyGPT, a pioneering honeypot architecture based on ChatGPT, heralding a new era of intelligent honeypot solutions characterized by their cost-effectiveness, high adaptability, and enhanced interactivity, coupled with a predisposition for proactive attacker engagement. Furthermore, we present a structured prompt engineering framework that augments long-term interaction memory and robust security analytics. This framework, integrating thought of chain tactics attuned to honeypot contexts, enhances interactivity and deception, deepens security analytics, and ensures sustained engagement. The evaluation of HoneyGPT includes two parts: a baseline comparison based on a collected dataset and a field evaluation in real scenarios for four weeks. The baseline comparison demonstrates HoneyGPT's remarkable ability to strike a balance among flexibility, interaction depth, and deceptive capability. The field evaluation further validates HoneyGPT's efficacy, showing its marked superiority in enticing attackers into more profound interactive engagements and capturing a wider array of novel attack vectors in comparison to existing honeypot technologies.

Biophotonic nanostructures in butterfly wing scales remain fascinating examples of biological functional materials, with intriguing open questions in regards to formation and evolutionary function. One particularly interesting butterfly species, Erora opisena (Lycaenidae: Theclinae), develops wing scales that contain three-dimensional photonic crystals that closely resemble a single gyroid geometry. Unlike most other gyroid forming butterflies, E. opisena develops discrete gyroid crystallites with a pronounced size gradient hinting at a developmental sequence frozen in time. Here, we use a hyperspectral (wavelength-resolved) microscopy technique to investigate the ultrastructural organisation of these gyroid crystallites in dry, adult wing scales. We show that reflectance corresponds to crystallite size, where larger crystallites reflect green wavelengths more intensely; this relationship could be used to infer size from the optical signal. We further successfully resolve the red-shifted reflectance signal from wing scales immersed in refractive index oils with varying refractive index, including values similar to water or cytosol. Such photonic crystals with lower refractive index contrast may be similar to the hypothesized nanostructural forms in the developing butterfly scales. The ability to resolve these fainter signals hints at the potential of this facile light microscopy method for in vivo analysis of nanostructure formation in developing butterflies.

Rough surface lubrication simulation is crucial for designing and optimizing tribological performance. Despite the growing application of Physical Information Neural Networks (PINNs) in hydrodynamic lubrication analysis, their use has been primarily limited to smooth surfaces. This is due to traditional PINN methods suffer from spectral bias, favoring to learn low-frequency features and thus failing to analyze rough surfaces with high-frequency signals. To date, no PINN methods have been reported for rough surface lubrication. To overcome these limitations, this work introduces a novel multi-scale lubrication neural network architecture that utilizes a trainable Fourier feature network. By incorporating learnable feature embedding frequencies, this architecture automatically adapts to various frequency components, thereby enhancing the analysis of rough surface characteristics. This method has been tested across multiple surface morphologies, and the results have been compared with those obtained using the finite element method (FEM). The comparative analysis demonstrates that this approach achieves a high consistency with FEM results. Furthermore, this novel architecture surpasses traditional Fourier feature networks with fixed feature embedding frequencies in both accuracy and computational efficiency. Consequently, the multi-scale lubrication neural network model offers a more efficient tool for rough surface lubrication analysis.

Spatio-temporal action detection (STAD) is an important fine-grained video understanding task. Current methods require box and label supervision for all action classes in advance. However, in real-world applications, it is very likely to come across new action classes not seen in training because the action category space is large and hard to enumerate. Also, the cost of data annotation and model training for new classes is extremely high for traditional methods, as we need to perform detailed box annotations and re-train the whole network from scratch. In this paper, we propose a new challenging setting by performing open-vocabulary STAD to better mimic the situation of action detection in an open world. Open-vocabulary spatio-temporal action detection (OV-STAD) requires training a model on a limited set of base classes with box and label supervision, which is expected to yield good generalization performance on novel action classes. For OV-STAD, we build two benchmarks based on the existing STAD datasets and propose a simple but effective method based on pretrained video-language models (VLM). To better adapt the holistic VLM for the fine-grained action detection task, we carefully fine-tune it on the localized video region-text pairs. This customized fine-tuning endows the VLM with better motion understanding, thus contributing to a more accurate alignment between video regions and texts. Local region feature and global video feature fusion before alignment is adopted to further improve the action detection performance by providing global context. Our method achieves a promising performance on novel classes.

The half-size prototype of the multi wire drift chamber (MWDC) for the cooling storage ring (CSR) external-target experiment (CEE) was assembled and tested in 350 MeV/u Kr+Fe reactions on the heavy ion research facility in Lanzhou (HIRFL). The prototype consists of 6 sense layers, where the sense wires are stretched in three directions X, U and V, meeting $0^\circ$, $30^\circ$ and $-30^\circ$ with respect to the vertical axis, respectively. The sensitive area of the prototype is $76 {\rm cm} \times 76 {\rm cm}$. The amplified and shaped signals from the anode wires are digitized in a serial capacity array. Being operated with 1500 V high voltage on the anode wires, the efficiency for each layer is beyond 95\%. The tracking residual is about $301 \pm 2 \rm \mu m$. The performance meets the requirements of CEE.

Reverse engineers would acquire valuable insights from descriptive function names, which are absent in publicly released binaries. Recent advances in binary function name prediction using data-driven machine learning show promise. However, existing approaches encounter difficulties in capturing function semantics in diverse optimized binaries and fail to reserve the meaning of labels in function names. We propose Epitome, a framework that enhances function name prediction using votes-based name tokenization and multi-task learning, specifically tailored for different compilation optimization binaries. Epitome learns comprehensive function semantics by pre-trained assembly language model and graph neural network, incorporating function semantics similarity prediction task, to maximize the similarity of function semantics in the context of different compilation optimization levels. In addition, we present two data preprocessing methods to improve the comprehensibility of function names. We evaluate the performance of Epitome using 2,597,346 functions extracted from binaries compiled with 5 optimizations (O0-Os) for 4 architectures (x64, x86, ARM, and MIPS). Epitome outperforms the state-of-the-art function name prediction tool by up to 44.34%, 64.16%, and 54.44% in precision, recall, and F1 score, while also exhibiting superior generalizability., Comment: 24 pages, 10 figures, ACM ESEC/FSE 2024

Pathology is the study of microscopic inspection of tissue, and a pathology diagnosis is often the medical gold standard to diagnose disease. Pathology images provide a unique challenge for computer-vision-based analysis: a single pathology Whole Slide Image (WSI) is gigapixel-sized and often contains hundreds of thousands to millions of objects of interest across multiple resolutions. In this work, we propose PathoLogy Universal TransfOrmer (PLUTO): a light-weight pathology FM that is pre-trained on a diverse dataset of 195 million image tiles collected from multiple sites and extracts meaningful representations across multiple WSI scales that enable a large variety of downstream pathology tasks. In particular, we design task-specific adaptation heads that utilize PLUTO's output embeddings for tasks which span pathology scales ranging from subcellular to slide-scale, including instance segmentation, tile classification, and slide-level prediction. We compare PLUTO's performance to other state-of-the-art methods on a diverse set of external and internal benchmarks covering multiple biologically relevant tasks, tissue types, resolutions, stains, and scanners. We find that PLUTO matches or outperforms existing task-specific baselines and pathology-specific foundation models, some of which use orders-of-magnitude larger datasets and model sizes when compared to PLUTO. Our findings present a path towards a universal embedding to power pathology image analysis, and motivate further exploration around pathology foundation models in terms of data diversity, architectural improvements, sample efficiency, and practical deployability in real-world applications.

Diffusion models have significantly advanced the state of the art in image, audio, and video generation tasks. However, their applications in practical scenarios are hindered by slow inference speed. Drawing inspiration from the approximation strategies utilized in consistency models, we propose the Sub-path Linear Approximation Model (SLAM), which accelerates diffusion models while maintaining high-quality image generation. SLAM treats the PF-ODE trajectory as a series of PF-ODE sub-paths divided by sampled points, and harnesses sub-path linear (SL) ODEs to form a progressive and continuous error estimation along each individual PF-ODE sub-path. The optimization on such SL-ODEs allows SLAM to construct denoising mappings with smaller cumulative approximated errors. An efficient distillation method is also developed to facilitate the incorporation of more advanced diffusion models, such as latent diffusion models. Our extensive experimental results demonstrate that SLAM achieves an efficient training regimen, requiring only 6 A100 GPU days to produce a high-quality generative model capable of 2 to 4-step generation with high performance. Comprehensive evaluations on LAION, MS COCO 2014, and MS COCO 2017 datasets also illustrate that SLAM surpasses existing acceleration methods in few-step generation tasks, achieving state-of-the-art performance both on FID and the quality of the generated images.

The system has addressed the error of "Bad character(s) in field Abstract" for no reason. Please refer to manuscript for the full abstract., Comment: 10 pages, 6 figures

Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for classification. This detection paradigm requires multi-stage training and inference, and the feature sampling is constrained inside the box, failing to effectively leverage richer context information outside. Recently, a few query-based action detectors have been proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and decoding, thus suffering from the issues of inferior performance or slower convergence. In this paper, we propose two core designs for a more flexible one-stage sparse action detector. First, we present a query-based adaptive feature sampling module, which endows the detector with the flexibility of mining a group of discriminative features from the entire spatio-temporal domain. Second, we devise a decoupled feature mixing module, which dynamically attends to and mixes video features along the spatial and temporal dimensions respectively for better feature decoding. Based on these designs, we instantiate two detection pipelines, that is, STMixer-K for keyframe action detection and STMixer-T for action tubelet detection. Without bells and whistles, our STMixer detectors obtain state-of-the-art results on five challenging spatio-temporal action detection benchmarks for keyframe action detection or action tube detection., Comment: Extended version of the paper arXiv:2303.15879 presented at CVPR 2023. Accepted by TPAMI 2024

Large motion poses a critical challenge in Video Frame Interpolation (VFI) task. Existing methods are often constrained by limited receptive fields, resulting in sub-optimal performance when handling scenarios with large motion. In this paper, we introduce a new pipeline for VFI, which can effectively integrate global-level information to alleviate issues associated with large motion. Specifically, we first estimate a pair of initial intermediate flows using a high-resolution feature map for extracting local details. Then, we incorporate a sparse global matching branch to compensate for flow estimation, which consists of identifying flaws in initial flows and generating sparse flow compensation with a global receptive field. Finally, we adaptively merge the initial flow estimation with global flow compensation, yielding a more accurate intermediate flow. To evaluate the effectiveness of our method in handling large motion, we carefully curate a more challenging subset from commonly used benchmarks. Our method demonstrates the state-of-the-art performance on these VFI subsets with large motion., Comment: Accepted by CVPR 2024. Project page: https://sgm-vfi.github.io/

Video-based visual relation detection tasks, such as video scene graph generation, play important roles in fine-grained video understanding. However, current video visual relation detection datasets have two main limitations that hinder the progress of research in this area. First, they do not explore complex human-human interactions in multi-person scenarios. Second, the relation types of existing datasets have relatively low-level semantics and can be often recognized by appearance or simple prior information, without the need for detailed spatio-temporal context reasoning. Nevertheless, comprehending high-level interactions between humans is crucial for understanding complex multi-person videos, such as sports and surveillance videos. To address this issue, we propose a new video visual relation detection task: video human-human interaction detection, and build a dataset named SportsHHI for it. SportsHHI contains 34 high-level interaction classes from basketball and volleyball sports. 118,075 human bounding boxes and 50,649 interaction instances are annotated on 11,398 keyframes. To benchmark this, we propose a two-stage baseline method and conduct extensive experiments to reveal the key factors for a successful human-human interaction detector. We hope that SportsHHI can stimulate research on human interaction understanding in videos and promote the development of spatio-temporal context modeling techniques in video visual relation detection., Comment: Accepted by CVPR 2024