Search

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These approaches commonly use a binary cross-entropy mechanism on pairwise samples, i.e., minimizing and maximizing the loss based on preferred or dis-preferred responses, respectively. However, while this training strategy omits the reward model, it also overlooks the varying preference degrees within different responses. We hypothesize that this is a key factor hindering LLMs from sufficiently understanding human preferences. To address this problem, we propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss, thereby helping LLMs improve their ability to understand the degree of preference. Extensive experiments are conducted on two widely used datasets of different tasks. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods and significantly boost their performance to achieve state-of-the-art performance. We also conduct detailed analyses to offer comprehensive insights into SPO, which verifies its effectiveness. The code is available at https://github.com/lijian16/SPO., Comment: Accepted at EMNLP 2024 Findings

The ability to fast reset a qubit state is crucial for quantum information processing. However, to actively reset a qubit requires engineering a pathway to interact with a dissipative bath, which often comes with the cost of reduced qubit protection from the environment. Here, we present a novel multi-purpose architecture that enables fast reset and protection of superconducting qubits during control and readout. In our design, two on-chip diplexers are connected by two transmission lines. The high-pass branch provides a flat passband for convenient allocation of readout resonators above the qubit frequencies, which is preferred for reducing measurement-induced state transitions. In the low-pass branch, we leverage a standing-wave mode below the maximum qubit frequency for a rapid reset. The qubits are located in the common stopband to inhibit dissipation during coherent operations. We demonstrate resetting a transmon qubit from its first excited state to the ground state in 100 ns, achieving a residual population of 2.7%, mostly limited by the thermal effect. The reset time may be further shortened to 27 ns by exploiting the coherent population inversion effect. We further extend the technique to resetting the qubit from its second excited state. Our approach promises scalable implementation of fast reset and qubit protection during control and readout, adding to the toolbox of dissipation engineering., Comment: 7 pages, 4 figures

This paper utilizes statistical data from various open datasets in Calgary to to uncover patterns and insights for community crimes, disorders, and traffic incidents. Community attributes like demographics, housing, and pet registration were collected and analyzed through geospatial visualization and correlation analysis. Strongly correlated features were identified using the chi-square test, and predictive models were built using association rule mining and machine learning algorithms. The findings suggest that crime rates are closely linked to factors such as population density, while pet registration has a smaller impact. This study offers valuable insights for city managers to enhance community safety strategies., Comment: 14 pages

The quality of Virtual Reality (VR) apps is vital, particularly the rendering quality of the VR Graphical User Interface (GUI). Different from traditional 2D apps, VR apps create a 3D digital scene for users, by rendering two distinct 2D images for the user's left and right eyes, respectively. Stereoscopic visual inconsistency (denoted as "SVI") issues, however, undermine the rendering process of the user's brain, leading to user discomfort and even adverse health effects. Such issues commonly exist but remain underexplored. We conduct an empirical analysis on 282 SVI bug reports from 15 VR platforms, summarizing 15 types of manifestations. The empirical analysis reveals that automatically detecting SVI issues is challenging, mainly because: (1) lack of training data; (2) the manifestations of SVI issues are diverse, complicated, and often application-specific; (3) most accessible VR apps are closed-source commercial software. Existing pattern-based supervised classification approaches may be inapplicable or ineffective in detecting the SVI issues. To counter these challenges, we propose an unsupervised black-box testing framework named StereoID to identify the stereoscopic visual inconsistencies, based only on the rendered GUI states. StereoID generates a synthetic right-eye image based on the actual left-eye image and computes distances between the synthetic right-eye image and the actual right-eye image to detect SVI issues. We propose a depth-aware conditional stereo image translator to power the image generation process, which captures the expected perspective shifts between left-eye and right-eye images. We build a large-scale unlabeled VR stereo screenshot dataset with larger than 171K images from 288 real-world VR apps for experiments. After substantial experiments, StereoID demonstrates superior performance for detecting SVI issues in both user reports and wild VR apps., Comment: This work has been accepted at the ACM International Conference on the Foundations of Software Engineering (FSE) 2024, Porto de Galinhas, Brazil. DOI: https://doi.org/10.1145/3660803

In the preclinical translational studies, drug candidates with remarkable anti-epileptic efficacy demonstrate long-term suppression of spontaneous recurrent seizures (SRSs), particularly convulsive seizures (CSs), in mouse models of chronic epilepsy. However, the current methods for monitoring CSs have limitations in terms of invasiveness, specific laboratory settings, high cost, and complex operation, which hinder drug screening efforts. In this study, a camera-based system for automated detection of CSs in chronically epileptic mice is first established to screen potential anti-epilepsy drugs.

Direct laser acceleration of electrons in near-critical-density (NCD) carbon nanotube foams (CNFs) has its advantages in the high-efficiency generation of relativistic electrons and broadband X-rays. Here, we report the first simultaneous measurement on the spectra of laser-driven electrons and X-rays from CNFs at moderately relativistic intensities of around 5\times{10}^{19}\ W/cm^2.\ The density and thickness of the CNFs were scanned in the experiments, indicating the optimized electrons temperature of 5.5 MeV and X-ray critical energy of 5 keV. Two-dimensional (2D) particle-in-cell (PIC) simulations confirm that the electrons, with a temperature significantly higher than the pondermotive scale, are directly accelerated by the laser along the NCD plasma channel, while the bright X-rays are emitted by these electrons through betatron radiation or Thomson backscattering inside the channel. The simultaneously generated electrons and X-rays, automatically synchronized with the femtosecond laser driver, are suitable for applications such as bi-modal radiography., Comment: arXiv admin note: text overlap with arXiv:2010.05702

During the COVID-19 pandemic, safely implementing in-person indoor instruction was a high priority for universities nationwide. To support this effort at the University, we developed a mathematical model for estimating the risk of SARS-CoV-2 transmission in university classrooms. This model was used to evaluate combinations of feasible interventions for classrooms at the University during the pandemic and optimize the set of interventions that would allow higher occupancy levels, matching the pre-pandemic numbers of in-person courses. Importantly, we determined that requiring masking in dense classrooms with unrestricted seating with more than 90% of students vaccinated was easy to implement, incurred little logistical or financial cost, and allowed classes to be held at full capacity. A retrospective analysis at the end of the semester confirmed the model's assessment that the proposed classroom configuration would be safe. Our framework is generalizable and was used to support reopening decisions at Stanford University. In addition, our framework is flexible and applies to a wide range of indoor settings. It was repurposed for large university events and gatherings and could be used to support planning indoor space use to avoid transmission of infectious diseases across various industries, from secondary schools to movie theaters and restaurants.

Multimodal large language models (MLLMs) have emerged as a prominent area of interest within the research community, given their proficiency in handling and reasoning with non-textual data, including images and videos. This study seeks to extend the application of MLLMs to the realm of autonomous driving by introducing DriveGPT4, a novel interpretable end-to-end autonomous driving system based on LLMs. Capable of processing multi-frame video inputs and textual queries, DriveGPT4 facilitates the interpretation of vehicle actions, offers pertinent reasoning, and effectively addresses a diverse range of questions posed by users. Furthermore, DriveGPT4 predicts low-level vehicle control signals in an end-to-end fashion.These advanced capabilities are achieved through the utilization of a bespoke visual instruction tuning dataset, specifically tailored for autonomous driving applications, in conjunction with a mix-finetuning training strategy. DriveGPT4 represents the pioneering effort to leverage LLMs for the development of an interpretable end-to-end autonomous driving solution. Evaluations conducted on the BDD-X dataset showcase the superior qualitative and quantitative performance of DriveGPT4. Additionally, the fine-tuning of domain-specific data enables DriveGPT4 to yield close or even improved results in terms of autonomous driving grounding when contrasted with GPT4-V., Comment: Accepted by RA-L. The project page is available at https://tonyxuqaq.github.io/projects/DriveGPT4/

Miniaturized spectrometry system is playing an essential role for materials analysis in the development of in-situ or portable sensing platforms across research and industry. However, there unavoidably exists trade-offs between the resolution and operation bandwidth as the device scale down. Here, we report an extreme miniaturized computational photonic molecule (PM) spectrometer utilizing the diverse spectral characteristics and mode-hybridization effect of split eigenfrequencies and super-modes, which effectively eliminates the inherent periodicity and expands operation bandwidth with ultra-high spectral resolution. These results of dynamic control of the frequency, amplitude, and phase of photons in the photonic multi-atomic systems, pave the way to the development of benchtop sensing platforms for applications previously unfeasible due to resolution-bandwidth-footprint limitations, such as in gas sensing or nanoscale biomedical sensing.

In this paper, we propose a scribble-based video colorization network with temporal aggregation called SVCNet. It can colorize monochrome videos based on different user-given color scribbles. It addresses three common issues in the scribble-based video colorization area: colorization vividness, temporal consistency, and color bleeding. To improve the colorization quality and strengthen the temporal consistency, we adopt two sequential sub-networks in SVCNet for precise colorization and temporal smoothing, respectively. The first stage includes a pyramid feature encoder to incorporate color scribbles with a grayscale frame, and a semantic feature encoder to extract semantics. The second stage finetunes the output from the first stage by aggregating the information of neighboring colorized frames (as short-range connections) and the first colorized frame (as a long-range connection). To alleviate the color bleeding artifacts, we learn video colorization and segmentation simultaneously. Furthermore, we set the majority of operations on a fixed small image resolution and use a Super-resolution Module at the tail of SVCNet to recover original sizes. It allows the SVCNet to fit different image resolutions at the inference. Finally, we evaluate the proposed SVCNet on DAVIS and Videvo benchmarks. The experimental results demonstrate that SVCNet produces both higher-quality and more temporally consistent videos than other well-known video colorization approaches. The codes and models can be found at https://github.com/zhaoyuzhi/SVCNet., Comment: accepted by IEEE Transactions on Image Processing (TIP)

This paper proposes a novel visual simultaneous localization and mapping (SLAM) system called Hybrid Depth-augmented Panoramic Visual SLAM (HDPV-SLAM), that employs a panoramic camera and a tilted multi-beam LiDAR scanner to generate accurate and metrically-scaled trajectories. RGB-D SLAM was the design basis for HDPV-SLAM, which added depth information to visual features. It aims to solve the two major issues hindering the performance of similar SLAM systems. The first obstacle is the sparseness of LiDAR depth, which makes it difficult to correlate it with the extracted visual features of the RGB image. A deep learning-based depth estimation module for iteratively densifying sparse LiDAR depth was suggested to address this issue. The second issue pertains to the difficulties in depth association caused by a lack of horizontal overlap between the panoramic camera and the tilted LiDAR sensor. To surmount this difficulty, we present a hybrid depth association module that optimally combines depth information estimated by two independent procedures, feature-based triangulation and depth estimation. During a phase of feature tracking, this hybrid depth association module aims to maximize the use of more accurate depth information between the triangulated depth with visual features tracked and the deep learning-based corrected depth. We evaluated the efficacy of HDPV-SLAM using the 18.95 km-long York University and Teledyne Optech (YUTO) MMS dataset. The experimental results demonstrate that the two proposed modules contribute substantially to the performance of HDPV-SLAM, which surpasses that of the state-of-the-art (SOTA) SLAM systems., Comment: 8 pages, 3 figures, To be published in IEEE International Conference on Automation Science and Engineering (CASE) 2023

Supply Chain Platforms (SCPs) provide downstream industries with numerous raw materials. Compared with traditional e-commerce platforms, data in SCPs is more sparse due to limited user interests. To tackle the data sparsity problem, one can apply Cross-Domain Recommendation (CDR) which improves the recommendation performance of the target domain with the source domain information. However, applying CDR to SCPs directly ignores the hierarchical structure of commodities in SCPs, which reduce the recommendation performance. To leverage this feature, in this paper, we take the catering platform as an example and propose GReS, a graphical cross-domain recommendation model. The model first constructs a tree-shaped graph to represent the hierarchy of different nodes of dishes and ingredients, and then applies our proposed Tree2vec method combining GCN and BERT models to embed the graph for recommendations. Experimental results on a commercial dataset show that GReS significantly outperforms state-of-the-art methods in Cross-Domain Recommendation for Supply Chain Platforms.

Nonlinear systems of affine control inputs overarch many sensor fusion instances. Analyzing whether a state variable in such a nonlinear system can be estimated (i.e., observability) informs better estimator design. Among the research on local observability of nonlinear systems, approaches based on differential geometry have attracted much attention for the solid theoretic foundation and suitability to automated deduction. Such approaches usually work with a system model of unconstrained control inputs and assume that the control inputs and observation outputs are timestamped by the same clock. To our knowledge, it has not been shown how to conduct the observability analysis with additional constraints enforced on the system's observations or control inputs. To this end, we propose procedures to convert a system model of affine control inputs with linear constraints into a constraint-free standard model which is apt to be analyzed by the classic observability analysis procedure. Then, the whole analysis procedure is illustrated by applying to the well-studied visual inertial odometry (VIO) system which estimates the camera-IMU relative pose and time offset. The findings about unobservable variables under degenerate motion concur with those obtained with linearized VIO systems in other studies, whereas the findings about observability of time offset extend those in previous studies. These findings are further validated by simulation., Comment: 20 pages, 5 figures

The appearances of children are inherited from their parents, which makes it feasible to predict them. Predicting realistic children's faces may help settle many social problems, such as age-invariant face recognition, kinship verification, and missing child identification. It can be regarded as an image-to-image translation task. Existing approaches usually assume domain information in the image-to-image translation can be interpreted by "style", i.e., the separation of image content and style. However, such separation is improper for the child face prediction, because the facial contours between children and parents are not the same. To address this issue, we propose a new disentangled learning strategy for children's face prediction. We assume that children's faces are determined by genetic factors (compact family features, e.g., face contour), external factors (facial attributes irrelevant to prediction, such as moustaches and glasses), and variety factors (individual properties for each child). On this basis, we formulate predictions as a mapping from parents' genetic factors to children's genetic factors, and disentangle them from external and variety factors. In order to obtain accurate genetic factors and perform the mapping, we propose a ChildPredictor framework. It transfers human faces to genetic factors by encoders and back by generators. Then, it learns the relationship between the genetic factors of parents and children through a mapping function. To ensure the generated faces are realistic, we collect a large Family Face Database to train ChildPredictor and evaluate it on the FF-Database validation set. Experimental results demonstrate that ChildPredictor is superior to other well-known image-to-image translation methods in predicting realistic and diverse child faces. Implementation codes can be found at https://github.com/zhaoyuzhi/ChildPredictor., Comment: accepted to IEEE Transactions on Multimedia

Lifestyle politics emerge when activities that have no substantive relevance to ideology become politically aligned and polarized. Homophily and social influence are able generate these fault lines on their own; however, social identities from demographics may serve as coordinating mechanisms through which lifestyle politics are mobilized are spread. Using a dataset of 137,661,886 observations from 299,327 Facebook interests aggregated across users of different racial/ethnic, education, age, gender, and income demographics, we find that the most extreme instances of lifestyle politics are those which are highly confounded by demographics such as race/ethnicity (e.g., Black artists and performers). After adjusting political alignment for demographic effects, lifestyle politics decreased by 27.36% toward the political "center" and demographically confounded interests were no longer among the most polarized interests. Instead, after demographic deconfounding, we found that the most liberal interests included electric cars, Planned Parenthood, and liberal satire while the most conservative interests included the Republican Party and conservative commentators. We validate our measures of political alignment and lifestyle politics using the General Social Survey and find similar demographic entanglements with lifestyle politics existed before social media such as Facebook were ubiquitous, giving us strong confidence that our results are not due to echo chambers or filter bubbles. Likewise, since demographic characteristics exist prior to ideological values, we argue that the demographic confounding we observe is causally responsible for the extreme instances of lifestyle politics that we find among the aggregated interests. We conclude our paper by relating our results to Simpson's paradox, cultural omnivorousness, and network autocorrelation., Comment: 29 pages (27 body, 2 supplemental material), 14 figures (12 body, 2 supplemental material), 2 tables

Mixed communities of organisms are found in many environments (from the human gut to marine ecosystems) and can have profound impact on human health and the environment. Metagenomics studies the genomic material of such communities through high-throughput sequencing that yields DNA subsequences for subsequent analysis. A fundamental problem in the standard workflow, called binning, is to discover clusters, of genomic subsequences, associated with the unknown constituent organisms. Inherent noise in the subsequences, various biological constraints that need to be imposed on them and the skewed cluster size distribution exacerbate the difficulty of this unsupervised learning problem. In this paper, we present a new formulation using a graph where the nodes are subsequences and edges represent homophily information. In addition, we model biological constraints providing heterophilous signal about nodes that cannot be clustered together. We solve the binning problem by developing new algorithms for (i) graph representation learning that preserves both homophily relations and heterophily constraints (ii) constraint-based graph clustering method that addresses the problems of skewed cluster size distribution. Extensive experiments, on real and synthetic datasets, demonstrate that our approach, called RepBin, outperforms a wide variety of competing methods. Our constraint-based graph representation learning and clustering methods, that may be useful in other domains as well, advance the state-of-the-art in both metagenomics binning and graph representation learning., Comment: Accepted by AAAI-2022

Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled instances via feature similarity in the latent space while ignoring the intermediate state of the learned representations, which limits the overall performance. In this work, taking into account the degree of similarity of sampled instances as the intermediate state, we propose a novel pretext task - spatio-temporal overlap rate (STOR) prediction. It stems from the observation that humans are capable of discriminating the overlap rates of videos in space and time. This task encourages the model to discriminate the STOR of two generated samples to learn the representations. Moreover, we employ a joint optimization combining pretext tasks with contrastive learning to further enhance the spatio-temporal representation learning. We also study the mutual influence of each component in the proposed scheme. Extensive experiments demonstrate that our proposed STOR task can favor both contrastive learning and pretext tasks. The joint optimization scheme can significantly improve the spatio-temporal representation in video understanding. The code is available at https://github.com/Katou2/CSTP., Comment: Accepted by AAAI 2022, Preprint version with Appendix

Population-wide screening to identify and isolate infectious individuals is a powerful tool for controlling COVID-19 and other infectious diseases. Group testing can enable such screening despite limited testing resources. Samples' viral loads are often positively correlated, either because prevalence and sample collection are both correlated with geography, or through intentional enhancement, e.g., by pooling samples from people in similar risk groups. Such correlation is known to improve test efficiency in mathematical models with fixed sensitivity. In reality, however, dilution degrades a pooled test's sensitivity by an amount that varies with the number of positives in the pool. In the presence of this dilution effect, we study the impact of correlation on the most widely-used group testing procedure, the Dorfman procedure. We show that correlation's effects are significantly altered by the dilution effect. We prove that under a general correlation structure, pooling correlated samples together (called correlated pooling) achieves higher sensitivity but can degrade test efficiency compared to independently pooling the samples (called naive pooling) using the same pool size. We identify an alternative measure of test resource usage, the number of positives found per test consumed, which we argue is better aligned with infection control, and show that correlated pooling outperforms naive pooling on this measure. We build a realistic agent-based simulation to contextualize our theoretical results within an epidemic control framework. We argue that the dilution effect makes it even more important for policy-makers evaluating group testing protocols for large-scale screening to incorporate naturally arising correlation and to intentionally maximize correlation., Comment: 66 pages, 10 figures, 15 tables