Search

There are unique challenges to developing item recommender systems for e-commerce platforms like eBay due to sparse data and diverse user interests. While rich user-item interactions are important, eBay's data sparsity exceeds other e-commerce sites by an order of magnitude. To address this challenge, we propose CoActionGraphRec (CAGR), a text based two-tower deep learning model (Item Tower and User Tower) utilizing co-action graph layers. In order to enhance user and item representations, a graph-based solution tailored to eBay's environment is utilized. For the Item Tower, we represent each item using its co-action items to capture collaborative signals in a co-action graph that is fully leveraged by the graph neural network component. For the User Tower, we build a fully connected graph of each user's behavior sequence, with edges encoding pairwise relationships. Furthermore, an explicit interaction module learns representations capturing behavior interactions. Extensive offline and online A/B test experiments demonstrate the effectiveness of our proposed approach and results show improved performance over state-of-the-art methods on key metrics.

Reinforcement learning method is extremely competitive in gait generation techniques for quadrupedal robot, which is mainly due to the fact that stochastic exploration in reinforcement training is beneficial to achieve an autonomous gait. Nevertheless, although incremental reinforcement learning is employed to improve training success and movement smoothness by relying on the continuity inherent during limb movements, challenges remain in adapting gait policy to diverse terrain and external disturbance. Inspired by the association between reinforcement learning and the evolution of animal motion behavior, a self-improvement mechanism for reference gait is introduced in this paper to enable incremental learning of action and self-improvement of reference action together to imitate the evolution of animal motion behavior. Further, a new framework for reinforcement training of quadruped gait is proposed. In this framework, genetic algorithm is specifically adopted to perform global probabilistic search for the initial value of the arbitrary foot trajectory to update the reference trajectory with better fitness. Subsequently, the improved reference gait is used for incremental reinforcement learning of gait. The above process is repeatedly and alternatively executed to finally train the gait policy. The analysis considering terrain, model dimensions, and locomotion condition is presented in detail based on simulation, and the results show that the framework is significantly more adaptive to terrain compared to regular incremental reinforcement learning.

Estimation of a model's confidence on its outputs is critical for Conversational AI systems based on large language models (LLMs), especially for reducing hallucination and preventing over-reliance. In this work, we provide an exhaustive exploration of methods, including approaches proposed for open- and closed-weight LLMs, aimed at quantifying and leveraging model uncertainty to improve the reliability of LLM-generated responses, specifically focusing on dialogue state tracking (DST) in task-oriented dialogue systems (TODS). Regardless of the model type, well-calibrated confidence scores are essential to handle uncertainties, thereby improving model performance. We evaluate four methods for estimating confidence scores based on softmax, raw token scores, verbalized confidences, and a combination of these methods, using the area under the curve (AUC) metric to assess calibration, with higher AUC indicating better calibration. We also enhance these with a self-probing mechanism, proposed for closed models. Furthermore, we assess these methods using an open-weight model fine-tuned for the task of DST, achieving superior joint goal accuracy (JGA). Our findings also suggest that fine-tuning open-weight LLMs can result in enhanced AUC performance, indicating better confidence score calibration., Comment: Accepted for publication at IEEE SLT 2024

Large Language Models (LLMs) have shown great potential in intelligent visualization systems, especially for domain-specific applications. Integrating LLMs into visualization systems presents challenges, and we categorize these challenges into three alignments: domain problems with LLMs, visualization with LLMs, and interaction with LLMs. To achieve these alignments, we propose a framework and outline a workflow to guide the application of fine-tuned LLMs to enhance visual interactions for domain-specific tasks. These alignment challenges are critical in education because of the need for an intelligent visualization system to support beginners' self-regulated learning. Therefore, we apply the framework to education and introduce Tailor-Mind, an interactive visualization system designed to facilitate self-regulated learning for artificial intelligence beginners. Drawing on insights from a preliminary study, we identify self-regulated learning tasks and fine-tuning objectives to guide visualization design and tuning data construction. Our focus on aligning visualization with fine-tuned LLM makes Tailor-Mind more like a personalized tutor. Tailor-Mind also supports interactive recommendations to help beginners better achieve their learning goals. Model performance evaluations and user studies confirm that Tailor-Mind improves the self-regulated learning experience, effectively validating the proposed framework.

The family of local maximum likelihood (LML) detectors, including the global maximum likelihood (GML) detector, and the family of likelihood ascent search (LAS) detectors are akin to each other and possess common properties significant in both theory and practical multi-input multi-output (MIMO) communications. It is proved that a large MIMO channel possesses the LML characteristic, implying and predicting that a local search detector with likelihood ascent, like a wide-sense sequential LAS (WSLAS) detector, can approach the GML detection. By the replica method, the bit error rate (BER) of an LML detector in the large MIMO channel is obtained. The BER indicates that in the high signal-to-noise ratio (SNR) regime, both the LML and GML detectors achieve the AWGN channel performance when the channel load is as high as up to 1.5086 bits/dimension with an equal-energy distribution, and the channel load can be higher with an unequal-energy distribution. The analytical result is verified by simulation in the equal-energy distribution that the sequential LAS (SLAS) detector, a linear-complexity LML detector, can approach the BER of the NP-hard GML detector. The LML and LAS detectors in the two families are successfully applied to symbol detection in massive antenna MIMO communications and demonstrate the performance near the GML detection. This book chapter reviews the LML and LAS detectors in a unified framework. The focus is on their formulation, relationships, properties, and GML performance in BER and spectral efficiency in large MIMO channels., Comment: 28 pages, 6 figures

As the novel topological states, the higher-order topological insulators have attracted great attentions in the past years. However, their realizations in realistic materials, in particular in two dimensional systems, remains the big challenge due to the lack of adequate candidates. Here, based on the first-principle calculation and tight-binding model simulations, we identify the currently \emph{existing} bilayer $\alpha_{5}$-phase borophenes as the two-dimensional second-order topological insulators, protected by the $C_{2}$-rotational symmetry. The formation of interlayer B-B covalent bonds, stabilizing the bilayer borophenes and opening the large direct bulk gaps ($\sim 0.55-0.62$ eV) at Fermi level, plays the key roles. The second-order topology is characterized by the bulk quantized quadrupole momentum. Our results enriches the candidates for the second-order topological insulators, and also provide a way to study topological states in borophenes., Comment: 9 Pages, 7 figures

The conceptualization and categorization of natural objects in the human mind have long intrigued cognitive scientists and neuroscientists, offering crucial insights into human perception and cognition. Recently, the rapid development of Large Language Models (LLMs) has raised the attractive question of whether these models can also develop human-like object representations through exposure to vast amounts of linguistic and multimodal data. In this study, we combined behavioral and neuroimaging analysis methods to uncover how the object concept representations in LLMs correlate with those of humans. By collecting large-scale datasets of 4.7 million triplet judgments from LLM and Multimodal LLM (MLLM), we were able to derive low-dimensional embeddings that capture the underlying similarity structure of 1,854 natural objects. The resulting 66-dimensional embeddings were found to be highly stable and predictive, and exhibited semantic clustering akin to human mental representations. Interestingly, the interpretability of the dimensions underlying these embeddings suggests that LLM and MLLM have developed human-like conceptual representations of natural objects. Further analysis demonstrated strong alignment between the identified model embeddings and neural activity patterns in many functionally defined brain ROIs (e.g., EBA, PPA, RSC and FFA). This provides compelling evidence that the object representations in LLMs, while not identical to those in the human, share fundamental commonalities that reflect key schemas of human conceptual knowledge. This study advances our understanding of machine intelligence and informs the development of more human-like artificial cognitive systems.

Solving partial differential equations (PDEs) and their inverse problems using Physics-informed neural networks (PINNs) is a rapidly growing approach in the physics and machine learning community. Although several architectures exist for PINNs that work remarkably in practice, our theoretical understanding of their performances is somewhat limited. In this work, we study the behavior of a Bayesian PINN estimator of the solution of a PDE from $n$ independent noisy measurement of the solution. We focus on a class of equations that are linear in their parameters (with unknown coefficients $\theta_\star$). We show that when the partial differential equation admits a classical solution (say $u_\star$), differentiable to order $\beta$, the mean square error of the Bayesian posterior mean is at least of order $n^{-2\beta/(2\beta + d)}$. Furthermore, we establish a convergence rate of the linear coefficients of $\theta_\star$ depending on the order of the underlying differential operator. Last but not least, our theoretical results are validated through extensive simulations., Comment: 35 Pages, 3 figures, and 2 tables

The ability to automatically and robustly self-verify periodicity present in time-series astronomical data is becoming more important as data sets rapidly increase in size. The age of large astronomical surveys has rendered manual inspection of time-series data less practical. Previous efforts in generating a false alarm probability to verify the periodicity of stars have been aimed towards the analysis of a constructed periodogram. However, these methods feature correlations with features that do not pertain to periodicity, such as light curve shape, slow trends and stochastic variability. The common assumption that photometric errors are Gaussian and well determined is also a limitation of analytic methods. We present a novel machine learning based technique which directly analyses the phase folded light curve for its false alarm probability. We show that the results of this method are largely insensitive to the shape of the light curve, and we establish minimum values for the number of data points and the amplitude to noise ratio.

The perception of transparent objects for grasp and manipulation remains a major challenge, because existing robotic grasp methods which heavily rely on depth maps are not suitable for transparent objects due to their unique visual properties. These properties lead to gaps and inaccuracies in the depth maps of the transparent objects captured by depth sensors. To address this issue, we propose an end-to-end network for transparent object depth completion that combines the strengths of single-view RGB-D based depth completion and multi-view depth estimation. Moreover, we introduce a depth refinement module based on confidence estimation to fuse predicted depth maps from single-view and multi-view modules, which further refines the restored depth map. The extensive experiments on the ClearPose and TransCG datasets demonstrate that our method achieves superior accuracy and robustness in complex scenarios with significant occlusion compared to the state-of-the-art methods.

Generating grasps for a dexterous hand often requires numerous grasping annotations. However, annotating high DoF dexterous hand poses is quite challenging. Especially for functional grasps, requiring the hand to grasp the object in a specific pose to facilitate subsequent manipulations. This prompts us to explore how people achieve manipulations on new objects based on past grasp experiences. We find that when grasping new items, people are adept at discovering and leveraging various similarities between objects, including shape, layout, and grasp type. Considering this, we analyze and collect grasp-related similarity relationships among 51 common tool-like object categories and annotate semantic grasp representation for 1768 objects. These objects are connected through similarities to form a knowledge graph, which helps infer our proposed cross-category functional grasp synthesis. Through extensive experiments, we demonstrate that the grasp-related knowledge indeed contributed to achieving functional grasp transfer across unknown or entirely new categories of objects.

With the proliferation of Audio Language Model (ALM) based deepfake audio, there is an urgent need for generalized detection methods. ALM-based deepfake audio currently exhibits widespread, high deception, and type versatility, posing a significant challenge to current audio deepfake detection (ADD) models trained solely on vocoded data. To effectively detect ALM-based deepfake audio, we focus on the mechanism of the ALM-based audio generation method, the conversion from neural codec to waveform. We initially construct the Codecfake dataset, an open-source large-scale dataset, including 2 languages, over 1M audio samples, and various test conditions, focus on ALM-based audio detection. As countermeasure, to achieve universal detection of deepfake audio and tackle domain ascent bias issue of original SAM, we propose the CSAM strategy to learn a domain balanced and generalized minima. In our experiments, we first demonstrate that ADD model training with the Codecfake dataset can effectively detects ALM-based audio. Furthermore, our proposed generalization countermeasure yields the lowest average Equal Error Rate (EER) of 0.616% across all test conditions compared to baseline models. The dataset and associated code are available online.

The receiver design for multi-input multi-output (MIMO) ultra-reliable and low-latency communication (URLLC) systems can be a tough task due to the use of short channel codes and few pilot symbols. Consequently, error propagation can occur in traditional turbo receivers, leading to performance degradation. Moreover, the processing delay induced by information exchange between different modules may also be undesirable for URLLC. To address the issues, we advocate to perform joint channel estimation, detection, and decoding (JCDD) for MIMO URLLC systems encoded by short low-density parity-check (LDPC) codes. Specifically, we develop two novel JCDD problem formulations based on the maximum a posteriori (MAP) criterion for Gaussian MIMO channels and sparse mmWave MIMO channels, respectively, which integrate the pilots, the bit-to-symbol mapping, the LDPC code constraints, as well as the channel statistical information. Both the challenging large-scale non-convex problems are then solved based on the alternating direction method of multipliers (ADMM) algorithms, where closed-form solutions are achieved in each ADMM iteration. Furthermore, two JCDD neural networks, called JCDDNet-G and JCDDNet-S, are built by unfolding the derived ADMM algorithms and introducing trainable parameters. It is interesting to find via simulations that the proposed trainable JCDD receivers can outperform the turbo receivers with affordable computational complexities., Comment: 17 pages, 12 figures, accepted by IEEE Transactions on Wireless Communications

The hand plays a pivotal role in human ability to grasp and manipulate objects and controllable grasp synthesis is the key for successfully performing downstream tasks. Existing methods that use human intention or task-level language as control signals for grasping inherently face ambiguity. To address this challenge, we propose a grasp synthesis method guided by text prompts of object grasping parts, Text2Grasp, which provides more precise control. Specifically, we present a two-stage method that includes a text-guided diffusion model TextGraspDiff to first generate a coarse grasp pose, then apply a hand-object contact optimization process to ensure both plausibility and diversity. Furthermore, by leveraging Large Language Model, our method facilitates grasp synthesis guided by task-level and personalized text descriptions without additional manual annotations. Extensive experiments demonstrate that our method achieves not only accurate part-level grasp control but also comparable performance in grasp quality.

There is an increasing conflict between business incentives to hide models and data as trade secrets, and the societal need for algorithmic transparency. For example, a rightsholder wishing to know whether their copyrighted works have been used during training must convince the model provider to allow a third party to audit the model and data. Finding a mutually agreeable third party is difficult, and the associated costs often make this approach impractical. In this work, we show that it is possible to simultaneously allow model providers to keep their model weights (but not architecture) and data secret while allowing other parties to trustlessly audit model and data properties. We do this by designing a protocol called ZkAudit in which model providers publish cryptographic commitments of datasets and model weights, alongside a zero-knowledge proof (ZKP) certifying that published commitments are derived from training the model. Model providers can then respond to audit requests by privately computing any function F of the dataset (or model) and releasing the output of F alongside another ZKP certifying the correct execution of F. To enable ZkAudit, we develop new methods of computing ZKPs for SGD on modern neural nets for simple recommender systems and image classification models capable of high accuracies on ImageNet. Empirically, we show it is possible to provide trustless audits of DNNs, including copyright, censorship, and counterfactual audits with little to no loss in accuracy.

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

In recent years, the rapid development of deep learning technology has brought new prospects to the field of vulnerability detection. Many vulnerability detection methods involve converting source code into images for detection, yet they often overlook the quality of the generated images. Due to the fact that vulnerability images lack clear and continuous contours, unlike images used in object detection, Convolutional Neural Networks (CNNs) tend to lose semantic information during the convolution and pooling processes. Therefore, this paper proposes a pixel row oversampling method based on code line concatenation to generate more continuous code features, addressing the issue of discontinuity in code image coloration.Building upon these contributions, we propose the vulnerability detection system VulMCI and conduct tests on the SARD and NVD datasets. Experimental results demonstrate that VulMCI outperforms seven state-of-the-art vulnerability detectors (namely Checkmarx, FlawFinder, RATS, VulDeePecker, SySeVR, VulCNN, and Devign). Compared to other image-based methods, VulMCI shows improvements in various metrics, including a 2.877\% increase in True Positive Rate (TPR), a 5.446\% increase in True Negative Rate (TNR), and a 5.91\% increase in Accuracy (ACC). On the NVD real-world dataset, VulMCI achieves an average accuracy of 5.162\%, confirming its value in practical vulnerability detection applications.

Robust metallic surface states (MSS) of topological insulator (TI) against imperfections and perturbations are important in broad applications such as chemical catalysis and quantum computing. Unfortunately, they are suffered from the narrow band gap that can be accessed. Searching for MSS with large bulk band gap beyond conventional TIs becomes a quest. In this work, inspired by the adiabatic connection principle in real space, we identify that all electrides, a new class of emerging materials, must host robust and universal MSS that resists any disturbances, in spite of the fact that some of them could be classified as trivial in standard topology theory. This counterintuitive property is traced to the specific charge localization-delocalization change intrinsic to electride when approaching the crystalline surface or interface, which is a kind of interstice-centered to atom-centered transition in the real-space topology of the charge density distribution, and is sharply different from the band inversion in the standard topology theory. The new mechanism circumvents the obstacle that limits the band gap of TI. Robust and universal MSS in an electride that conventionally-determined as trivial but with a colossal band gap beyond 6.13 eV are demonstrated. This gap size is about 6-fold larger than the highest record of known "wide-gap" TIs, thus opens up new avenues to universal MSS with gigantic bulk gap., Comment: 32 pages, 7 figures, with supporting information

Optical parametric oscillation (OPO) in Kerr microresonators can efficiently transfer near-infrared laser light into the visible spectrum. To date, however, chromatic dispersion has mostly limited output wavelengths to >560 nm, and robust access to the whole green light spectrum has not been demonstrated. In fact, wavelengths between 532 nm and 633 nm, commonly referred to as the "green gap", are especially challenging to produce with conventional laser gain. Hence, there is motivation to extend the Kerr OPO wavelength range and develop reliable device designs. Here, we experimentally show how to robustly access the entire green gap with Kerr OPO in silicon nitride microrings pumped near 780 nm. Our microring geometries are optimized for green-gap emission; in particular, we introduce a dispersion engineering technique, based on partially undercutting the microring, which not only expands wavelength access but also proves robust to variations in resonator dimensions, in particular, the microring width. Using just two devices, we generate >100 wavelengths evenly distributed throughout the green gap, as predicted by our dispersion simulations. Moreover, we establish the usefulness of Kerr OPO to coherent applications by demonstrating continuous frequency tuning (>50 GHz) and narrow optical linewidths (<1 MHz). Our work represents an important step in the quest to bring nonlinear nanophotonics and its advantages to the visible spectrum., Comment: 12 pages, 8 figures

Enabling multi-fingered robots to grasp and manipulate objects with human-like dexterity is especially challenging during the dynamic, continuous hand-object interactions. Closed-loop feedback control is essential for dexterous hands to dynamically finetune hand poses when performing precise functional grasps. This work proposes an adaptive motion planning method based on deep reinforcement learning to adjust grasping poses according to real-time feedback from joint torques from pre-grasp to goal grasp. We find the multi-joint torques of the dexterous hand can sense object positions through contacts and collisions, enabling real-time adjustment of grasps to generate varying grasping trajectories for objects in different positions. In our experiments, the performance gap with and without force feedback reveals the important role of force feedback in adaptive manipulation. Our approach utilizing force feedback preliminarily exhibits human-like flexibility, adaptability, and precision., Comment: 8 pages,7 figures