arXiv subjects

Yu Hong

Publications and source records attributed to Yu Hong.

35 records · Page 2Linked to original sources

arXiv2024

Ta2Pd3Te5 topological thermometer

In recent decades, there has been a persistent pursuit of applications for surface/edge states in topological systems, driven by their dissipationless transport effects. However, there have been limited tangible breakthroughs in this field. This work demonstrates the remarkable properties of the topological insulator Ta2Pd3Te5, as a thermometer. This material exhibits a power-law correlation in temperature-dependent resistance at low temperatures, stemming from its Luttinger liquid behavior of edge states, while exhibiting semiconductor behavior at high temperatures. The power-law behavior effectively addresses the issue of infinite resistance in semiconductor thermometers at ultra-low temperatures, thereby playing a crucial role in enabling efficient thermometry in refrigerators supporting millikelvin temperatures or below. By employing chemical doping, adjusting thickness, and controlling gate voltage, its power-law behavior and semiconductor behavior can be effectively modulated. This enables efficient thermometry spanning from millikelvin temperatures to room temperature, and allows for precise local temperature measurement. Furthermore, this thermometer exhibits excellent temperature sensitivity and resolution, and can be fine-tuned to show small magnetoresistance. In summary, the Ta2Pd3Te5 thermometer, also referred to as a topological thermometer, exhibits outstanding performance and significant potential for measuring a wider range of temperatures compared to conventional low-temperature thermometers.

cond-mat.mtrl-sci↗

arXiv2024

CopyNE: Better Contextual ASR by Copying Named Entities

End-to-end automatic speech recognition (ASR) systems have made significant progress in general scenarios. However, it remains challenging to transcribe contextual named entities (NEs) in the contextual ASR scenario. Previous approaches have attempted to address this by utilizing the NE dictionary. These approaches treat entities as individual tokens and generate them token-by-token, which may result in incomplete transcriptions of entities. In this paper, we treat entities as indivisible wholes and introduce the idea of copying into ASR. We design a systematic mechanism called CopyNE, which can copy entities from the NE dictionary. By copying all tokens of an entity at once, we can reduce errors during entity transcription, ensuring the completeness of the entity. Experiments demonstrate that CopyNE consistently improves the accuracy of transcribing entities compared to previous approaches. Even when based on the strong Whisper, CopyNE still achieves notable improvements.

cs.CL↗

arXiv2024

UniVision: A Unified Framework for Vision-Centric 3D Perception

The past few years have witnessed the rapid development of vision-centric 3D perception in autonomous driving. Although the 3D perception models share many structural and conceptual similarities, there still exist gaps in their feature representations, data formats, and objectives, posing challenges for unified and efficient 3D perception framework design. In this paper, we present UniVision, a simple and efficient framework that unifies two major tasks in vision-centric 3D perception, \ie, occupancy prediction and object detection. Specifically, we propose an explicit-implicit view transform module for complementary 2D-3D feature transformation. We propose a local-global feature extraction and fusion module for efficient and adaptive voxel and BEV feature extraction, enhancement, and interaction. Further, we propose a joint occupancy-detection data augmentation strategy and a progressive loss weight adjustment strategy which enables the efficiency and stability of the multi-task framework training. We conduct extensive experiments for different perception tasks on four public benchmarks, including nuScenes LiDAR segmentation, nuScenes detection, OpenOccupancy, and Occ3D. UniVision achieves state-of-the-art results with +1.5 mIoU, +1.8 NDS, +1.5 mIoU, and +1.8 mIoU gains on each benchmark, respectively. We believe that the UniVision framework can serve as a high-performance baseline for the unified vision-centric 3D perception task. The code will be available at \url{https://github.com/Cc-Hy/UniVision}.

cs.CV↗

arXiv2023

HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting

We have recently seen tremendous progress in photo-real human modeling and rendering. Yet, efficiently rendering realistic human performance and integrating it into the rasterization pipeline remains challenging. In this paper, we present HiFi4G, an explicit and compact Gaussian-based approach for high-fidelity human performance rendering from dense footage. Our core intuition is to marry the 3D Gaussian representation with non-rigid tracking, achieving a compact and compression-friendly representation. We first propose a dual-graph mechanism to obtain motion priors, with a coarse deformation graph for effective initialization and a fine-grained Gaussian graph to enforce subsequent constraints. Then, we utilize a 4D Gaussian optimization scheme with adaptive spatial-temporal regularizers to effectively balance the non-rigid prior and Gaussian updating. We also present a companion compression scheme with residual compensation for immersive experiences on various platforms. It achieves a substantial compression rate of approximately 25 times, with less than 2MB of storage per frame. Extensive experiments demonstrate the effectiveness of our approach, which significantly outperforms existing approaches in terms of optimization speed, rendering quality, and storage overhead.

cs.CV↗

arXiv2023

UFO: Unified Fact Obtaining for Commonsense Question Answering

Leveraging external knowledge to enhance the reasoning ability is crucial for commonsense question answering. However, the existing knowledge bases heavily rely on manual annotation which unavoidably causes deficiency in coverage of world-wide commonsense knowledge. Accordingly, the knowledge bases fail to be flexible enough to support the reasoning over diverse questions. Recently, large-scale language models (LLMs) have dramatically improved the intelligence in capturing and leveraging knowledge, which opens up a new way to address the issue of eliciting knowledge from language models. We propose a Unified Facts Obtaining (UFO) approach. UFO turns LLMs into knowledge sources and produces relevant facts (knowledge statements) for the given question. We first develop a unified prompt consisting of demonstrations that cover different aspects of commonsense and different question styles. On this basis, we instruct the LLMs to generate question-related supporting facts for various commonsense questions via prompting. After facts generation, we apply a dense retrieval-based fact selection strategy to choose the best-matched fact. This kind of facts will be fed into the answer inference model along with the question. Notably, due to the design of unified prompts, UFO can support reasoning in various commonsense aspects (including general commonsense, scientific commonsense, and social commonsense). Extensive experiments on CommonsenseQA 2.0, OpenBookQA, QASC, and Social IQA benchmarks show that UFO significantly improves the performance of the inference model and outperforms manually constructed knowledge sources.

cs.CL↗

arXiv2023

Coreference-aware Double-channel Attention Network for Multi-party Dialogue Reading Comprehension

We tackle Multi-party Dialogue Reading Comprehension (abbr., MDRC). MDRC stands for an extractive reading comprehension task grounded on a batch of dialogues among multiple interlocutors. It is challenging due to the requirement of understanding cross-utterance contexts and relationships in a multi-turn multi-party conversation. Previous studies have made great efforts on the utterance profiling of a single interlocutor and graph-based interaction modeling. The corresponding solutions contribute to the answer-oriented reasoning on a series of well-organized and thread-aware conversational contexts. However, the current MDRC models still suffer from two bottlenecks. On the one hand, a pronoun like "it" most probably produces multi-skip reasoning throughout the utterances of different interlocutors. On the other hand, an MDRC encoder is potentially puzzled by fuzzy features, i.e., the mixture of inner linguistic features in utterances and external interactive features among utterances. To overcome the bottlenecks, we propose a coreference-aware attention modeling method to strengthen the reasoning ability. In addition, we construct a two-channel encoding network. It separately encodes utterance profiles and interactive relationships, so as to relieve the confusion among heterogeneous features. We experiment on the benchmark corpora Molweni and FriendsQA. Experimental results demonstrate that our approach yields substantial improvements on both corpora, compared to the fine-tuned BERT and ELECTRA baselines. The maximum performance gain is about 2.5\% F1-score. Besides, our MDRC models outperform the state-of-the-art in most cases.

cs.CL↗

arXiv2023

KEPR: Knowledge Enhancement and Plausibility Ranking for Generative Commonsense Question Answering

Generative commonsense question answering (GenCQA) is a task of automatically generating a list of answers given a question. The answer list is required to cover all reasonable answers. This presents the considerable challenges of producing diverse answers and ranking them properly. Incorporating a variety of closely-related background knowledge into the encoding of questions enables the generation of different answers. Meanwhile, learning to distinguish positive answers from negative ones potentially enhances the probabilistic estimation of plausibility, and accordingly, the plausibility-based ranking. Therefore, we propose a Knowledge Enhancement and Plausibility Ranking (KEPR) approach grounded on the Generate-Then-Rank pipeline architecture. Specifically, we expand questions in terms of Wiktionary commonsense knowledge of keywords, and reformulate them with normalized patterns. Dense passage retrieval is utilized for capturing relevant knowledge, and different PLM-based (BART, GPT2 and T5) networks are used for generating answers. On the other hand, we develop an ELECTRA-based answer ranking model, where logistic regression is conducted during training, with the aim of approximating different levels of plausibility in a polar classification scenario. Extensive experiments on the benchmark ProtoQA show that KEPR obtains substantial improvements, compared to the strong baselines. Within the experimental models, the T5-based GenCQA with KEPR obtains the best performance, which is up to 60.91% at the primary canonical metric Inc@3. It outperforms the existing GenCQA models on the current leaderboard of ProtoQA.

cs.CL↗

arXiv2022

Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection

Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e.g., Pseudo-LiDAR methods. However, the existing methods usually apply non-end-to-end training strategies and insufficiently leverage the LiDAR information, where the rich potential of the LiDAR data has not been well exploited. In this paper, we propose the Cross-Modality Knowledge Distillation (CMKD) network for monocular 3D detection to efficiently and directly transfer the knowledge from LiDAR modality to image modality on both features and responses. Moreover, we further extend CMKD as a semi-supervised training framework by distilling knowledge from large-scale unlabeled data and significantly boost the performance. Until submission, CMKD ranks $1^{st}$ among the monocular 3D detectors with publications on both KITTI $test$ set and Waymo $val$ set with significant performance gains compared to previous state-of-the-art methods.

cs.CV↗

arXiv2022

Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing

This paper proposes to cast end-to-end span-based SRL as a word-based graph parsing task. The major challenge is how to represent spans at the word level. Borrowing ideas from research on Chinese word segmentation and named entity recognition, we propose and compare four different schemata of graph representation, i.e., BES, BE, BIES, and BII, among which we find that the BES schema performs the best. We further gain interesting insights through detailed analysis. Moreover, we propose a simple constrained Viterbi procedure to ensure the legality of the output graph according to the constraints of the SRL structure. We conduct experiments on two widely used benchmark datasets, i.e., CoNLL05 and CoNLL12. Results show that our word-based graph parsing approach achieves consistently better performance than previous results, under all settings of end-to-end and predicate-given, without and with pre-trained language models (PLMs). More importantly, our model can parse 669/252 sentences per second, without and with PLMs respectively.

cs.CL↗

arXiv2022

DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models

In this paper, we focus on studying robustness evaluation of Chinese question matching. Most of the previous work on analyzing robustness issue focus on just one or a few types of artificial adversarial examples. Instead, we argue that it is necessary to formulate a comprehensive evaluation about the linguistic capabilities of models on natural texts. For this purpose, we create a Chinese dataset namely DuQM which contains natural questions with linguistic perturbations to evaluate the robustness of question matching models. DuQM contains 3 categories and 13 subcategories with 32 linguistic perturbations. The extensive experiments demonstrate that DuQM has a better ability to distinguish different models. Importantly, the detailed breakdown of evaluation by linguistic phenomenon in DuQM helps us easily diagnose the strength and weakness of different models. Additionally, our experiment results show that the effect of artificial adversarial examples does not work on the natural texts.

cs.CL↗

arXiv2022

Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation

We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En translation scenarios. The test results show that our method produces substantial improvements, achieving the BLEU scores of 22.5, 28.0 and 18.1 respectively. In addition, the method is computationally efficient which reduces the consumption of training time by 63.8%, reaching the duration of 1.6 hours when training on a Tesla 16GB P100 GPU. All the models and source codes in the experiments will be made publicly available to support reproducible research.

cs.CL↗

arXiv2021

DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications

Machine reading comprehension (MRC) is a crucial task in natural language processing and has achieved remarkable advancements. However, most of the neural MRC models are still far from robust and fail to generalize well in real-world applications. In order to comprehensively verify the robustness and generalization of MRC models, we introduce a real-world Chinese dataset -- DuReader_robust. It is designed to evaluate the MRC models from three aspects: over-sensitivity, over-stability and generalization. Comparing to previous work, the instances in DuReader_robust are natural texts, rather than the altered unnatural texts. It presents the challenges when applying MRC models to real-world applications. The experimental results show that MRC models do not perform well on the challenge test set. Moreover, we analyze the behavior of existing models on the challenge test set, which may provide suggestions for future model development. The dataset and codes are publicly available at https://github.com/baidu/DuReader.

cs.CL↗

arXiv2021

Single-photon imaging over 200 km

Long-range active imaging has widespread applications in remote sensing and target recognition. Single-photon light detection and ranging (lidar) has been shown to have high sensitivity and temporal resolution. On the application front, however, the operating range of practical single-photon lidar systems is limited to about tens of kilometers over the Earth's atmosphere, mainly due to the weak echo signal mixed with high background noise. Here, we present a compact coaxial single-photon lidar system capable of realizing 3D imaging at up to 201.5 km. It is achieved by using high-efficiency optical devices for collection and detection, and what we believe is a new noise-suppression technique that is efficient for long-range applications. We show that photon-efficient computational algorithms enable accurate 3D imaging over hundreds of kilometers with as few as 0.44 signal photons per pixel. The results represent a significant step toward practical, low-power lidar over extra-long ranges.

eess.IV↗

arXiv2020

Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing local surface manifolds embedded in 3D Euclidean space to discriminate semantic classes or object parts as additional supervision signals. This paper is the first attempt to propose a unique multi-task geometric learning network to improve semantic analysis by auxiliary geometric learning with local shape properties, which can be either generated via physical computation from point clouds themselves as self-supervision signals or provided as privileged information. Owing to explicitly encoding local shape manifolds in favor of semantic analysis, the proposed geometric self-supervised and privileged learning algorithms can achieve superior performance to their backbone baselines and other state-of-the-art methods, which are verified in the experiments on the popular benchmarks.

cs.CV↗

arXiv2020

Super-resolution single-photon imaging at 8.2 kilometers

Single-photon light detection and ranging (LiDAR), offering single-photon sensitivity and picosecond time resolution, has been widely adopted for active imaging applications. Long-range active imaging is a great challenge, because the spatial resolution degrades significantly with the imaging range due to the diffraction limit of the optics, and only weak echo signal photons can return but mixed with a strong background noise. Here we propose and demonstrate a photon-efficient LiDAR approach that can achieve sub-Rayleigh resolution imaging over long ranges. This approach exploits fine sub-pixel scanning and a deconvolution algorithm tailored to this long-range application. Using this approach, we experimentally demonstrated active three-dimensional (3D) single-photon imaging by recognizing different postures of a mannequin model at a stand-off distance of 8.2 km in both daylight and night. The observed spatial (transversal) resolution is about 5.5 cm at 8.2 km, which is about twice of the system's resolution. This also beats the optical system's Rayleigh criterion. The results are valuable for geosciences and target recognition over long ranges.

eess.IV↗

arXiv2018

Superior Structural, Elastic and Electronic Properties of 2D Titanium Nitride MXenes Over Carbide MXenes: A Comprehensive First Principles Study

The structural, elastic and electronic properties of two-dimensional (2D) titanium carbide/nitride based pristine (Tin+1Cn/Tin+1Nn) and functionalized MXenes (Tin+1CnT2/Tin+1NnT2, T stands for the terminal groups: -F, -O and -OH, n = 1, 2, 3) are investigated by density functional theory calculations. Carbide-based MXenes possess larger lattice constants and monolayer thicknesses than nitride-based MXenes. The in-plane Young's moduli of Tin+1Nn are larger than those of Tin+1Cn, whereas in both systems they decrease with the increase of the monolayer thickness. Cohesive energy calculations indicate that MXenes with a larger monolayer thickness have a better structural stability. Adsorption energy calculations imply that Tin+1Nn have stronger preference to adhere to the terminal groups, which suggests more active surfaces for nitride-based MXenes. More importantly, nearly free electron states are observed to exist outside the surfaces of -OH functionalized carbide/nitride based MXenes, especially in Tin+1Nn(OH)2, which provide almost perfect transmission channels without nuclear scattering for electron transport. The overall electrical conductivity of nitride-based MXenes is determined to be higher than that of carbide-based MXenes. The exceptional properties of titanium nitride-based MXenes, including strong surface adsorption, high elastic constant and Young's modulus, and good metallic conductivity, make them promising materials for catalysis and energy storage applications.

cond-mat.mtrl-sci↗

arXiv2006

Bow-tie topological features of metabolic networks and the functional significance

Exploring the structural topology of genome-based large-scale metabolic network is essential for investigating possible relations between structure and functionality. Visualization would be helpful for obtaining immediate information about structural organization. In this work, metabolic networks of 75 organisms were investigated from a topological point of view. A spread bow-tie model was proposed to give a clear visualization of the bow-tie structure for metabolic networks. The revealed topological pattern helps to design more efficient algorithm specifically for metabolic networks. This coarse-grained graph also visualizes the vulnerable connections in the network, and thus could have important implication for disease studies and drug target identifications. In addition, analysis on the reciprocal links and main cores in the GSC part of bow-tie also reveals that the bow-tie structure of metabolic networks has its own intrinsic and significant features which are significantly different from those of random networks.

q-bio.MN↗