Search arXiv⌕ Search

arXiv subjects

Chao Zhang

Publications and source records attributed to Chao Zhang.

At least 703 records · Page 39Linked to original sources
arXiv2023

FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow

This paper introduces a novel transformer-based network architecture, FlowFormer, along with the Masked Cost Volume AutoEncoding (MCVA) for pretraining it to tackle the problem of optical flow estimation. FlowFormer tokenizes the 4D cost-volume built from the source-target image pair and iteratively refines flow estimation with a cost-volume encoder-decoder architecture. The cost-volume encoder derives a cost memory with alternate-group transformer~(AGT) layers in a latent space and the decoder recurrently decodes flow from the cost memory with dynamic positional cost queries. On the Sintel benchmark, FlowFormer architecture achieves 1.16 and 2.09 average end-point-error~(AEPE) on the clean and final pass, a 16.5\% and 15.5\% error reduction from the GMA~(1.388 and 2.47). MCVA enhances FlowFormer by pretraining the cost-volume encoder with a masked autoencoding scheme, which further unleashes the capability of FlowFormer with unlabeled data. This is especially critical in optical flow estimation because ground truth flows are more expensive to acquire than labels in other vision tasks. MCVA improves FlowFormer all-sided and FlowFormer+MCVA ranks 1st among all published methods on both Sintel and KITTI-2015 benchmarks and achieves the best generalization performance. Specifically, FlowFormer+MCVA achieves 1.07 and 1.94 AEPE on the Sintel benchmark, leading to 7.76\% and 7.18\% error reductions from FlowFormer.

cs.CV↗
arXiv2023

Superconducting transition temperature of the Bose one-component plasma

We present results of first principle numerical simulations of the Bose one-component plasma, i.e., a Bose gas with pairwise Coulomb interactions among particles and a uniform neutralizing background. We compute the superconducting transition temperature for a wide range of densities, in two and three dimensions, for both continuous and lattice versions of the model. Our results are of direct relevance to quantitative studies of bipolaron mechanisms of (high-temperature) superconductivity.

cond-mat.quant-gas↗
arXiv2023

Local Boosting for Weakly-Supervised Learning

Boosting is a commonly used technique to enhance the performance of a set of base models by combining them into a strong ensemble model. Though widely adopted, boosting is typically used in supervised learning where the data is labeled accurately. However, in weakly supervised learning, where most of the data is labeled through weak and noisy sources, it remains nontrivial to design effective boosting approaches. In this work, we show that the standard implementation of the convex combination of base learners can hardly work due to the presence of noisy labels. Instead, we propose $\textit{LocalBoost}$, a novel framework for weakly-supervised boosting. LocalBoost iteratively boosts the ensemble model from two dimensions, i.e., intra-source and inter-source. The intra-source boosting introduces locality to the base learners and enables each base learner to focus on a particular feature regime by training new base learners on granularity-varying error regions. For the inter-source boosting, we leverage a conditional function to indicate the weak source where the sample is more likely to appear. To account for the weak labels, we further design an estimate-then-modify approach to compute the model weights. Experiments on seven datasets show that our method significantly outperforms vanilla boosting methods and other weakly-supervised methods.

cs.LG↗
arXiv2023

Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model

Model-free deep reinforcement learning has achieved great success in many domains, such as video games, recommendation systems and robotic control tasks. In continuous control tasks, widely used policies with Gaussian distributions results in ineffective exploration of environments and limited performance of algorithms in many cases. In this paper, we propose a density-free off-policy algorithm, Generative Actor-Critic(GAC), using the push-forward model to increase the expressiveness of policies, which also includes an entropy-like technique, MMD-entropy regularizer, to balance the exploration and exploitation. Additionnally, we devise an adaptive mechanism to automatically scale this regularizer, which further improves the stability and robustness of GAC. The experiment results show that push-forward policies possess desirable features, such as multi-modality, which can improve the efficiency of exploration and asymptotic performance of algorithms obviously.

cs.LG↗
arXiv2023

Zero-Point Quantum Diffusion of Proton in Hydrogen-rich Superconductor $LaH_{10}$

$LaH_{10}$, as a member of hydrogen-rich superconductors, has a superconducting critical temperature of 250 K at high pressures, which exhibits the possibility of solving the long-term goal of room temperature superconductivity. Considering the extreme pressure and low mass of hydrogen, the nuclear quantum effects in $LaH_{10}$ should be significant and have an impact on its various physical properties. Here, we adopt the method combines deep-potential (DP) and quantum thermal bath (QTB), which was verified to be able to account for quantum effects in high-accuracy large-scale molecular dynamics simulations. Our method can actually reproduce pressure-temperature phase diagrams of $LaH_{10}$ consistent with experimental and theoretical results. After incorporating quantum effects, the quantum fluctuation driven diffusion of proton is found even in the absence of thermal fluctuation near 0 K. The high mobility of proton is found to be compared to liquid, yet the structure of $LaH_{10}$ is still rigid. These results would greatly enrich our vision to study quantum behavior of hydrogen-rich superconductors.

cond-mat.mtrl-sci↗
arXiv2023

Can Contextual Biasing Remain Effective with Whisper and GPT-2?

End-to-end automatic speech recognition (ASR) and large language models, such as Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite the large amount of training data, infrequent content words that occur in a particular task may still exhibit poor ASR performance, with contextual biasing a possible remedy. This paper investigates the effectiveness of neural contextual biasing for Whisper combined with GPT-2. Specifically, this paper proposes integrating an adapted tree-constrained pointer generator (TCPGen) component for Whisper and a dedicated training scheme to dynamically adjust the final output without modifying any Whisper model parameters. Experiments across three datasets show a considerable reduction in errors on biasing words with a biasing list of 1000 words. Contextual biasing was more effective when applied to domain-specific data and can boost the performance of Whisper and GPT-2 without losing their generality.

cs.CL↗
arXiv2023

Odd-parity perturbations of the wormhole-like geometries and quasi-normal modes in Einstein-Æther theory

The Einstein-$Æ$ther theory has drawn a lot of attentions in recent years. As a representative case of gravitational theories that break the Lorentz symmetry, it plays an important role in testing the Lorentz-violating effects and shedding light on the attempts to construct quantum gravity. Since the first detection to the gravitational wave, the event GW150914, a brand new window has been opened to testing the theory of gravity with gravitational wave observations. At the same time, the study of gravitational waves itself also provides us a serendipity of accessing the nature of a theory. In this paper, we focus on the odd-parity gravitational perturbations to a background that describes a wormhole-like geometry under the Einstein-$Æ$ther theory. Taking advantage of this set of analytic background solutions, we are able to simplify the Lagrangian and construct a set of coupled single-parameter dependent master equations, from which we solve for the quasi-normal modes that carry the physical information of the emitted gravitational waves. Basically, the results reflect a consistency between Einstein-$Æ$ther theory and general relativity. More importantly, as long as the no-ghost condition and the latest observational constraints are concerned, we notice that the resultant quasi-normal mode solutions intimate a kind of dynamical instability. Thus, the solutions are ruled out based on their stability against small linear perturbations.

gr-qc↗
arXiv2023

Graph Reasoning for Question Answering with Triplet Retrieval

Answering complex questions often requires reasoning over knowledge graphs (KGs). State-of-the-art methods often utilize entities in questions to retrieve local subgraphs, which are then fed into KG encoder, e.g. graph neural networks (GNNs), to model their local structures and integrated into language models for question answering. However, this paradigm constrains retrieved knowledge in local subgraphs and discards more diverse triplets buried in KGs that are disconnected but useful for question answering. In this paper, we propose a simple yet effective method to first retrieve the most relevant triplets from KGs and then rerank them, which are then concatenated with questions to be fed into language models. Extensive results on both CommonsenseQA and OpenbookQA datasets show that our method can outperform state-of-the-art up to 4.6% absolute accuracy.

cs.CL↗
arXiv2023

Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator

The incorporation of biasing words obtained through contextual knowledge is of paramount importance in automatic speech recognition (ASR) applications. This paper proposes an innovative method for achieving end-to-end contextual ASR using graph neural network (GNN) encodings based on the tree-constrained pointer generator method. GNN node encodings facilitate lookahead for future word pieces in the process of ASR decoding at each tree node by incorporating information about all word pieces on the tree branches rooted from it. This results in a more precise prediction of the generation probability of the biasing words. The study explores three GNN encoding techniques, namely tree recursive neural networks, graph convolutional network (GCN), and GraphSAGE, along with different combinations of the complementary GCN and GraphSAGE structures. The performance of the systems was evaluated using the Librispeech and AMI corpus, following the visual-grounded contextual ASR pipeline. The findings indicate that using GNN encodings achieved consistent and significant reductions in word error rate (WER), particularly for words that are rare or have not been seen during the training process. Notably, the most effective combination of GNN encodings obtained more than 60% WER reduction for rare and unseen words compared to standard end-to-end systems.

cs.CL↗
arXiv2023

AdaPlanner: Adaptive Planning from Feedback with Language Models

Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans that are not adaptable to environmental feedback. Consequently, the sequential decision-making performance of LLM agents degenerates with problem complexity and plan horizons increase. We propose a closed-loop approach, AdaPlanner, which allows the LLM agent to refine its self-generated plan adaptively in response to environmental feedback. In AdaPlanner, the LLM agent adaptively refines its plan from feedback with both in-plan and out-of-plan refinement strategies. To mitigate hallucination, we develop a code-style LLM prompt structure that facilitates plan generation across a variety of tasks, environments, and agent capabilities. Furthermore, we propose a skill discovery mechanism that leverages successful plans as few-shot exemplars, enabling the agent to plan and refine with fewer task demonstrations. Our experiments in the ALFWorld and MiniWoB++ environments demonstrate that AdaPlanner outperforms state-of-the-art baselines by 3.73% and 4.11% while utilizing 2x and 600x fewer samples, respectively.

cs.CL↗
arXiv2023

Extracting Shopping Interest-Related Product Types from the Web

Recommending a diversity of product types (PTs) is important for a good shopping experience when customers are looking for products around their high-level shopping interests (SIs) such as hiking. However, the SI-PT connection is typically absent in e-commerce product catalogs and expensive to construct manually due to the volume of potential SIs, which prevents us from establishing a recommender with easily accessible knowledge systems. To establish such connections, we propose to extract PTs from the Web pages containing hand-crafted PT recommendations for SIs. The extraction task is formulated as binary HTML node classification given the general observation that an HTML node in our target Web pages can present one and only one PT phrase. Accordingly, we introduce TrENC, which stands for Tree-Transformer Encoders for Node Classification. It improves the inter-node dependency modeling with modified attention mechanisms that preserve the long-term sibling and ancestor-descendant relations. TrENC also injects SI into node features for better semantic representation. Trained on pages regarding limited SIs, TrEnc is ready to be applied to other unobserved interests. Experiments on our manually constructed dataset, WebPT, show that TrENC outperforms the best baseline model by 2.37 F1 points in the zero-shot setup. The performance indicates the feasibility of constructing SI-PT relations and using them to power downstream applications such as search and recommendation.

cs.IR↗
arXiv2023

CCGen: Explainable Complementary Concept Generation in E-Commerce

We propose and study Complementary Concept Generation (CCGen): given a concept of interest, e.g., "Digital Cameras", generating a list of complementary concepts, e.g., 1) Camera Lenses 2) Batteries 3) Camera Cases 4) Memory Cards 5) Battery Chargers. CCGen is beneficial for various applications like query suggestion and item recommendation, especially in the e-commerce domain. To solve CCGen, we propose to train language models to generate ranked lists of concepts with a two-step training strategy. We also teach the models to generate explanations by incorporating explanations distilled from large teacher models. Extensive experiments and analysis demonstrate that our model can generate high-quality concepts complementary to the input concept while producing explanations to justify the predictions.

cs.CL↗
arXiv2023

Local regularity for nonlocal double phase equations in the Heisenberg group

We prove interior boundedness and Hölder continuity for the weak solutions of nonlocal double phase equations in the Heisenberg group $\mathbb{H}^n$. This solves a problem raised by Palatucci and Piccinini et. al. in 2022 and 2023 for nonlinear integro-differential problems in the Heisenberg group $\mathbb{H}^n$. Our proof of the a priori estiamtes bases on the spirit of De Giorgi-Nash-Moser theory, where the important ingredients are Caccioppoli-type inequality and Logarithmic estimate. To achieve this goal, we establish a new and crucial Sobolev-Poincaré type inequality in local domain, which may be of independent interest and potential applications.

math.AP↗
arXiv2023

ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval

With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks. Different from prior works that generate training data with billion-scale natural language generation (NLG) models, we propose a retrieval-enhanced framework to create training data from a general-domain unlabeled corpus. To realize this, we first conduct contrastive pretraining to learn an unsupervised dense retriever for extracting the most relevant documents using class-descriptive verbalizers. We then further propose two simple strategies, namely Verbalizer Augmentation with Demonstrations and Self-consistency Guided Filtering to improve the topic coverage of the dataset while removing noisy examples. Experiments on nine datasets demonstrate that REGEN achieves 4.3% gain over the strongest baselines and saves around 70% of the time compared to baselines using large NLG models. Besides, REGEN can be naturally integrated with recently proposed large language models to boost performance.

cs.CL↗
arXiv2023

DETRs with Hybrid Matching

One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections. This end-to-end signature is important for the versatility of DETR, and it has been generalized to broader vision tasks. However, we note that there are few queries assigned as positive samples and the one-to-one set matching significantly reduces the training efficacy of positive samples. We propose a simple yet effective method based on a hybrid matching scheme that combines the original one-to-one matching branch with an auxiliary one-to-many matching branch during training. Our hybrid strategy has been shown to significantly improve accuracy. In inference, only the original one-to-one match branch is used, thus maintaining the end-to-end merit and the same inference efficiency of DETR. The method is named H-DETR, and it shows that a wide range of representative DETR methods can be consistently improved across a wide range of visual tasks, including DeformableDETR, PETRv2, PETR, and TransTrack, among others. The code is available at: https://github.com/HDETR

cs.CV↗
arXiv2023

Resolving the $R_{\rm pA}$ and $v_2$ puzzle of $D^0$ mesons in $p-$Pb collisions at the LHC

It has been a challenge to understand the experimental data on both the nuclear modification factor and elliptic flow of $D^0$ mesons in $p-$Pb collisions at LHC energies. In this work, we study these collisions with an improved multi-phase transport model. By including the Cronin effect (i.e., transverse momentum broadening) and independent fragmentation for charm quarks, we provide the first simultaneous description of the $D^0$ meson $R_{\rm pA}$ and $v_2$ data at $p_{\rm T} \leq 8$ GeV$/c$. The model also reasonably describes the $D^0$ meson $p_{\rm T}$ spectra and the low-$p_{\rm T}$ charged hadron spectra, $R_{\rm pA}$ and $v_2$. Our results show that both parton interactions and the Cronin effect are important for the $D^0$ meson $R_{\rm pA}$, while parton interactions are mostly responsible for the $D^0$ meson $v_2$. It is thus essential to include the Cronin effect for the simultaneous description of the $D^0$ meson $R_{\rm pA}$ and $v_2$. This work implies that the Cronin effect could also be important for heavy hadrons in large systems.

nucl-th↗
arXiv2023

Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples

Anomaly detection, which is a critical and popular topic in computer vision, aims to detect anomalous samples that are different from the normal (i.e., non-anomalous) ones. The current mainstream methods focus on anomaly detection for images, whereas little attention has been paid to 3D point cloud. In this paper, drawing inspiration from the knowledge transfer ability of teacher-student architecture and the impressive feature extraction capability of recent neural networks, we design a teacher-student structured model for 3D anomaly detection. Specifically, we use feature space alignment, dimension zoom, and max pooling to extract the features of the point cloud and then minimize a multi-scale loss between the feature vectors produced by the teacher and the student networks. Moreover, our method only requires very few normal samples to train the student network due to the teacher-student distillation mechanism. Once trained, the teacher-student network pair can be leveraged jointly to fulfill 3D point cloud anomaly detection based on the calculated anomaly score. For evaluation, we compare our method against the reconstruction-based method on the ShapeNet-Part dataset. The experimental results and ablation studies quantitatively and qualitatively confirm that our model can achieve higher performance compared with the state of the arts in 3D anomaly detection with very few training samples.

cs.CV↗
arXiv2023

A Kriging-Random Forest Hybrid Model for Real-time Ground Property Prediction during Earth Pressure Balance Shield Tunneling

A kriging-random forest hybrid model is developed for real-time ground property prediction ahead of the earth pressure balanced shield by integrating Kriging extrapolation and random forest, which can guide shield operating parameter selection thereby mitigate construction risks. The proposed KRF algorithm synergizes two types of information: prior information and real-time information. The previously predicted ground properties with EPB operating parameters are extrapolated via the Kriging algorithm to provide prior information for the prediction of currently being excavated ground properties. The real-time information refers to the real-time operating parameters of the EPB shield, which are input into random forest to provide a real-time prediction of ground properties. The integration of these two predictions is achieved by assigning weights to each prediction according to their uncertainties, ensuring the prediction of KRF with minimum uncertainty. The performance of the KRF algorithm is assessed via a case study of the Changsha Metro Line 4 project. It reveals that the proposed KRF algorithm can predict ground properties with an accuracy of 93%, overperforming the existing algorithms of LightGBM, AdaBoost-CART, and DNN by 29%, 8%, and 12%, respectively. Another dataset from Shenzhen Metro Line 13 project is utilized to further evaluate the model generalization performance, revealing that the model can transfer its learned knowledge from one region to another with an accuracy of 89%.

cs.LG↗