Search Results for author:
Found 457 papers, 249 papers with code
TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation
The knowledge selector generally constructs a query based on the dialogue context and selects the most appropriate knowledge to help response generation.
CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild
Existing relation extraction (RE) methods typically focus on extracting relational facts between entity pairs within single sentences or documents.
Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation
To address the above issues, we propose a dual-generative model, Dual-Emp, to simultaneously construct the emotional consensus and utilize some external unpaired data.
RSGT: Relational Structure Guided Temporal Relation Extraction
In this paper, we propose RSGT: Relational Structure Guided Temporal Relation Extraction to extract the relational structure features that can fit for both inter-sentence and intra-sentence relations.
Ranked #1 on
Temporal Relation Classification
on MATRES
Natural Language Understanding
Temporal Relation Classification
Spatial Geometric Reasoning for Room Layout Estimation via Deep Reinforcement Learning
Unlike most existing works that define room layout on a 2D image, we model the layout in 3D as a configuration of the camera and the room.
Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach
In recent years, pre-trained language models (PLMs) have been shown to capture factual knowledge from massive texts, which encourages the proposal of PLM-based knowledge graph completion (KGC) models.
RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining
Large-scale pretrained language models have achieved SOTA results on NLP tasks.
MovieChats: Chat like Humans in a Closed Domain
In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.
Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?
Specifically, we disentangle the video representation into the temporal coherence and motion parts and randomly change the scale of the temporal motion features as the adversarial noise.
Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification
Experimental results demonstrate that our DCML method explores credible and valuable training data and improves the performance of unsupervised domain adaptation.
ECNU_ICA at SemEval-2022 Task 10: A Simple and Unified Model for Monolingual and Crosslingual Structured Sentiment Analysis
The task aims to extract the structured sentiment information (e. g., holder, target, expression and sentiment polarity) in a text.
Unsupervised Dependency Graph Network
We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task.
Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction
In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems.
Deep Hashing with Active Pairwise Supervision
n this paper, we propose a Deep Hashing method with Active Pairwise Supervision(DH-APS).
BMInf: An Efficient Toolkit for Big Model Inference and Tuning
In recent years, large-scale pre-trained language models (PLMs) containing billions of parameters have achieved promising results on various NLP tasks.
Rotation-robust Intersection over Union for 3D Object Detection
In this paper, we propose a Rotation-robust Intersection over Union ($ extit{RIoU}$) for 3D object detection, which aims to jointly learn the overlap of rotated bounding boxes.
Structural Deep Metric Learning for Room Layout Estimation
We employ a metric model and a layout encoder to map the RGB images and the ground-truth layouts to the embedding space, respectively, and a layout decoder to map the embeddings to the corresponding layouts, where the whole framework is trained in an end-to-end manner.
欺骗类动词的句法语义研究(On the Syntax and Semantics of Verbs of Cheating)
“欺骗是一种常见的社会现象, 但对欺骗类动词的研究十分有限。本文筛选“欺骗”类动词的单句并对其进行大规模的句法依存和语义依存分析。研究显示,“欺骗”类动词在句中作为从属词时, 可作为不同的句法成分和语义角色, 同时此类动词在句法功能上表现出高度的相似性。作为支配词的“欺骗”类动词, 承担不同句法功能时, 表现出不同的句法共现模式。语义上, 本文详细描述、解释了该类动词在语义密度、主客体角色、情境角色和事件关系等维度的语义依存特点。“欺骗”类动词的句法语义虽具有多样性, 但主要的句型为主谓宾句式, 而该句式中最常用的语义搭配模式是施事对涉事进行欺骗行为, 并对涉事产生影响。本研究结合依存语法和框架语义学, 融合定量统计和定性分析探究欺骗类动词的句法语义, 深化了对欺骗行为言语线索以及言说动词的研究。”
Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation
Here, we deal with these issues on two aspects: (1) We enhance the prior selection module with the necessary posterior information obtained from the specially designed Posterior Information Prediction Module (PIPM); (2) We propose a Knowledge Distillation Based Training Strategy (KDBTS) to train the decoder with the knowledge selected from the prior distribution, removing the exposure bias of knowledge selection.
Dual Context-Guided Continuous Prompt Tuning for Few-Shot Learning
Prompt-based paradigm has shown its competitive performance in many NLP tasks.
Fingerprint Matching with Localized Deep Representation
The matching scores produced by LDRF also exhibit intuitive statistical characteristics, which led us to propose a matching score normalization technique to mitigate the uncertainty in the cases of very small overlapping area.
SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
Our SelfOcc outperforms the previous best method SceneRF by 58. 7% using a single frame as input on SemanticKITTI and is the first self-supervised work that produces reasonable 3D occupancy for surround cameras on nuScenes.
AKConv: Convolutional Kernel with Arbitrary Sampled Shapes and Arbitrary Number of Parameters
In response to the above questions, the Alterable Kernel Convolution (AKConv) is explored in this work, which gives the convolution kernel an arbitrary number of parameters and arbitrary sampled shapes to provide richer options for the trade-off between network overhead and performance.
LiDAR-HMR: 3D Human Mesh Recovery from LiDAR
In recent years, point cloud perception tasks have been garnering increasing attention.
MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation
Understanding events in texts is a core objective of natural language understanding, which requires detecting event occurrences, extracting event arguments, and analyzing inter-event relationships.
Enabling Large Language Models to Learn from Rules
That is, humans can grasp the new tasks or knowledge quickly and generalize well given only a detailed rule and a few optional examples.
RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge
Therefore, to evaluate the ability of LLMs to discern the reliability of external knowledge, we create a benchmark from existing knowledge bases.
Eval-GCSC: A New Metric for Evaluating ChatGPT's Performance in Chinese Spelling Correction
However, in the Chinese Spelling Correction (CSC) task, we observe a discrepancy: while ChatGPT performs well under human evaluation, it scores poorly according to traditional metrics.
TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models
Specifically, for the input from any modality, TEAL first discretizes it into a token sequence with the off-the-shelf tokenizer and embeds the token sequence into a joint embedding space with a learnable embedding matrix.
Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding
Contemporary translation engines built upon the encoder-decoder framework have reached a high level of development, while the emergence of Large Language Models (LLMs) has disrupted their position by offering the potential for achieving superior translation quality.
Universal Multi-modal Multi-domain Pre-trained Recommendation
There is a rapidly-growing research interest in modeling user preferences via pre-training multi-domain interactions for recommender systems.
Plot Retrieval as an Assessment of Abstract Semantic Association
Readers usually only give an abstract and vague description as the query based on their own understanding, summaries, or speculations of the plot, which requires the retrieval model to have a strong ability to estimate the abstract semantic associations between the query and candidate plots.
Exploring Unified Perspective For Fast Shapley Value Estimation
Shapley values have emerged as a widely accepted and trustworthy tool, grounded in theoretical axioms, for addressing challenges posed by black-box models like deep neural networks.
MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory
Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI.
Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules
Pre-trained language models (PLMs) have achieved remarkable results on NLP tasks but at the expense of huge parameter sizes and the consequent computational costs.
Thoroughly Modeling Multi-domain Pre-trained Recommendation as Language
With the thriving of pre-trained language model (PLM) widely verified in various of NLP tasks, pioneer efforts attempt to explore the possible cooperation of the general textual information in PLM with the personalized behavioral information in user historical behavior sequences to enhance sequential recommendation (SR).
Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models
Parameter-shared pre-trained language models (PLMs) have emerged as a successful approach in resource-constrained environments, enabling substantial reductions in model storage and memory costs without significant performance compromise.
DCRNN: A Deep Cross approach based on RNN for Partial Parameter Sharing in Multi-task Learning
The model has three innovations: 1) It adopts the idea of cross network and uses RNN network to cross-process the features, thereby effectively improves the expressive ability of the model; 2) It innovatively proposes the structure of partial parameter sharing; 3) It can effectively capture the potential correlation between different tasks to optimize the efficiency and methods for learning different tasks.
RethinkingTMSC: An Empirical Study for Target-Oriented Multimodal Sentiment Classification
Recently, Target-oriented Multimodal Sentiment Classification (TMSC) has gained significant attention among scholars.
XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners
During the selection of unlabeled data, we combine the predictive uncertainty of the encoder and the explanation score of the decoder to acquire informative data for annotation.
C^2M-DoT: Cross-modal consistent multi-view medical report generation with domain transfer network
In addition, word-level optimization based on numbers ignores the semantics of reports and medical images, and the generated reports often cannot achieve good performance.
Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information
However, we observe that merely concatenating sentences in a contextual window does not fully utilize contextual information and can sometimes lead to excessive attention on less informative sentences.
Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning
By this means, our model explores all sorts of reliable sub-relations within an action sequence in the condensed action space.
TCOVIS: Temporally Consistent Online Video Instance Segmentation
The core of our method consists of a global instance assignment strategy and a spatio-temporal enhancement module, which improve the temporal consistency of the features from two aspects.
Introspective Deep Metric Learning
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images.
Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering
2) the input text and image are often not perfectly matched, and thus the image may introduce noise into the model.
AMLP:Adaptive Masking Lesion Patches for Self-supervised Medical Image Segmentation
The proposed strategies effectively address limitations in applying masked modeling to medical images, tailored to capturing fine lesion details vital for segmentation tasks.
Large Language Models Are Not Robust Multiple Choice Selectors
Through extensive empirical analyses with 20 LLMs on three benchmarks, we pinpoint that this behavioral bias primarily stems from LLMs' token bias, where the model a priori assigns more probabilistic mass to specific option ID tokens (e. g., A/B/C/D) when predicting answers from the option IDs.
Exploring the Robustness of Human Parsers Towards Common Corruptions
The experimental results show that the proposed method demonstrates good universality which can improve the robustness of the human parsing models and even the semantic segmentation models when facing various image common corruptions.
PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction
To address this, we propose a cylindrical tri-perspective view to represent point clouds effectively and comprehensively and a PointOcc model to process them efficiently.
Improving Translation Faithfulness of Large Language Models via Augmenting Instructions
The experimental results demonstrate significant improvements in translation performance with SWIE based on BLOOMZ-3b, particularly in zero-shot and long text translations due to reduced instruction forgetting risk.
Instruction Position Matters in Sequence Generation with Large Language Models
Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning.
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks.
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
Moreover, we find that ALPACA can maintain more knowledge and capacity compared with LLAMA during the continual fine-tuning, which implies that general instruction tuning can help mitigate the forgetting phenomenon of LLMs in the further fine-tuning process.
Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation
To address this issue, we propose to utilize \textit{multiple references} to enhance the consistency between these metrics and human evaluations.
EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education
Currently, EduChat is available online as an open-source project, with its code, data, and model parameters available on platforms (e. g., GitHub https://github. com/icalk-nlp/EduChat, Hugging Face https://huggingface. co/ecnu-icalk ).
Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes
In this article, we propose Human-M3, an outdoor multi-modal multi-view multi-person human pose database which includes not only multi-view RGB videos of outdoor scenes but also corresponding pointclouds.
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
Based on ToolBench, we fine-tune LLaMA to obtain an LLM ToolLLaMA, and equip it with a neural API retriever to recommend appropriate APIs for each instruction.
Towards Codable Watermarking for Injecting Multi-bit Information to LLM
As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs.
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models
In this paper, we propose a novel 3D-to-2D generative pre-training method that is adaptable to any point cloud model.
Ranked #6 on
3D Part Segmentation
on ShapeNet-Part
TIM: Teaching Large Language Models to Translate with Comparison
Open-sourced large language models (LLMs) have demonstrated remarkable efficacy in various tasks with instruction tuning.
Soft Language Clustering for Multilingual Model Pre-training
Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from source languages or when pre-training data is limited in size.
Towards Accurate Data-free Quantization for Diffusion Models
On the contrary, we design group-wise quantization functions for activation discretization in different timesteps and sample the optimal timestep for informative calibration image generation, so that our quantized diffusion model can reduce the discretization errors with negligible computational overhead.
Emergent Modularity in Pre-trained Transformers
In analogy to human brains, we consider two main characteristics of modularity: (1) functional specialization of neurons: we evaluate whether each neuron is mainly specialized in a certain function, and find that the answer is yes.
Stochastic Bridges as Effective Regularizers for Parameter-Efficient Tuning
Since it is non-trivial to directly model the intermediate states and design a running cost function, we propose to use latent stochastic bridges to regularize the intermediate states and use the regularization as the running cost of PETs.
Plug-and-Play Knowledge Injection for Pre-trained Language Models
Experimental results on three knowledge-driven NLP tasks show that existing injection methods are not suitable for the new paradigm, while map-tuning effectively improves the performance of downstream models.
Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning
In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks.
Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model
Pretrained language models have achieved remarkable success in various natural language processing tasks.
D$^2$TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization
Further, we propose a dual knowledge distillation and target-oriented vision modeling framework for the M$^3$S task.
A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition
Particularly, we propose a Confidence-based Partial Label Learning (CPLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER.
GFDC: A Granule Fusion Density-Based Clustering with Evidential Reasoning
Further, three novel granule fusion strategies are utilized to combine granules into stable cluster structures, helping to detect clusters with arbitrary shapes.
Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion
It is seldom considered to adapt the decision boundary for new representations and in this paper we propose a Supervised Contrastive learning framework with adaptive classification criterion for Continual Learning (SCCL), In our method, a contrastive loss is used to directly learn representations for different tasks and a limited number of data samples are saved as the classification criterion.
VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks
We hope this model can set a new baseline for generalist vision and language models.
Personality Understanding of Fictional Characters during Book Reading
As readers engage with a story, their understanding of a character evolves based on new events and information; and multiple fine-grained aspects of personalities can be perceived.
Towards Unifying Multi-Lingual and Cross-Lingual Summarization
In this paper, we aim to unify MLS and CLS into a more general setting, i. e., many-to-many summarization (M2MS), where a single model could process documents in any language and generate their summaries also in any language.
Recyclable Tuning for Continual Pre-training
In pilot studies, we find that after continual pre-training, the upgraded PLM remains compatible with the outdated adapted weights to some extent.
RC3: Regularized Contrastive Cross-lingual Cross-modal Pre-training
In this paper, we propose Regularized Contrastive Cross-lingual Cross-modal (RC^3) pre-training, which further exploits more abundant weakly-aligned multilingual image-text pairs.
WeLayout: WeChat Layout Analysis System for the ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents
Our approach effectively demonstrates the benefits of combining query-based and anchor-free models for achieving robust layout segmentation in corporate documents.
WebCPM: Interactive Web Search for Chinese Long-form Question Answering
We recruit annotators to search for relevant information using our interface and then answer questions.
Investigating Forgetting in Pre-Trained Representations Through Continual Learning
Intuitively, the representation forgetting can influence the general knowledge stored in pre-trained language models (LMs), but the concrete effect is still unclear.
Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias
To settle this issue, we propose the Fine-purifying approach, which utilizes the diffusion theory to study the dynamic process of fine-tuning for finding potentially poisonous dimensions.
Attacking Pre-trained Recommendation
Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream recommendation tasks.
DSPDet3D: Dynamic Spatial Pruning for 3D Small Object Detection
We organize two benchmarks on ScanNet and TO-SCENE dataset to evaluate the ability of fine-grained 3D object detection, where our DSPDet3D improves the detection performance of small objects to a new level while achieving leading inference speed compared with existing 3D object detection methods.
BranchNorm: Robustly Scaling Extremely Deep Transformers
Recently, DeepNorm scales Transformers into extremely deep (i. e., 1000 layers) and reveals the promising potential of deep scaling.
Unified Model Learning for Various Neural Machine Translation
Specifically, we propose a ``versatile'' model, i. e., the Unified Model Learning for NMT (UMLNMT) that works with data from different tasks, and can translate well in multiple settings simultaneously, and theoretically it can be as many as possible.
Learning Accurate Performance Predictors for Ultrafast Automated Model Compression
On the contrary, we obtain the optimal efficient networks by directly optimizing the compression policy with an accurate performance predictor, where the ultrafast automated model compression for various computational cost constraint is achieved without complex compression policy search and evaluation.
Triple Sequence Learning for Cross-domain Recommendation
To address this issue, we present a novel framework, termed triple sequence learning for cross-domain recommendation (Tri-CDR), which jointly models the source, target, and mixed behavior sequences to highlight the global and target preference and precisely model the triple correlation in CDR.
Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis
In this paper, we propose binary sparse convolutional networks called BSC-Net for efficient point cloud analysis.
Efficient Meshy Neural Fields for Animatable Human Avatars
Moreover, only minutes of optimization is enough for plausible reconstruction results.
A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
GPT series models, such as GPT-3, CodeX, InstructGPT, ChatGPT, and so on, have gained considerable attention due to their exceptional natural language processing capabilities.
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
Towards a more comprehensive perception of a 3D scene, in this paper, we propose a SurroundOcc method to predict the 3D occupancy with multi-camera images.
Precise Facial Landmark Detection by Reference Heatmap Transformer
Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results.
HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction
Multi-scenario & multi-task learning has been widely applied to many recommendation systems in industrial applications, wherein an effective and practical approach is to carry out multi-scenario transfer learning on the basis of the Mixture-of-Expert (MoE) architecture.
Is ChatGPT a Good NLG Evaluator? A Preliminary Study
In detail, we regard ChatGPT as a human evaluator and give task-specific (e. g., summarization) and aspect-specific (e. g., relevance) instruction to prompt ChatGPT to evaluate the generated results of NLG models.
Unleashing Text-to-Image Diffusion Models for Visual Perception
In this paper, we propose VPD (Visual Perception with a pre-trained Diffusion model), a new framework that exploits the semantic information of a pre-trained text-to-image diffusion model in visual perception tasks.
Ranked #4 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
The GPT-3. 5 models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks, showcasing their strong understanding and reasoning capabilities.
Natural Language Inference
Natural Language Understanding
+1
Zero-Shot Cross-Lingual Summarization via Large Language Models
Given a document in a source language, cross-lingual summarization (CLS) aims to generate a summary in a different target language.
A Flexible Multi-view Multi-modal Imaging System for Outdoor Scenes
The experimental results show that multi-view point clouds greatly improve 3D object detection and tracking accuracy regardless of complex and various outdoor environments.
Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotations
Gradient-based explanation methods play an important role in the field of interpreting complex deep neural networks for NLP models.
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
To lift image features to the 3D TPV space, we further propose a transformer-based TPV encoder (TPVFormer) to obtain the TPV features effectively.
Ranked #5 on
3D Semantic Scene Completion
on KITTI-360
Feature Decomposition for Reducing Negative Transfer: A Novel Multi-task Learning Method for Recommender System
In recent years, thanks to the rapid development of deep learning (DL), DL-based multi-task learning (MTL) has made significant progress, and it has been successfully applied to recommendation systems (RS).
A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation
To address these issues, in this paper, we propose a multi-task multi-stage transitional (MMT) training framework, where an NCT model is trained using the bilingual chat translation dataset and additional monolingual dialogues.
Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning
Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively in a data privacy-preserving manner.
When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learning
Federated Learning has become a widely-used framework which allows learning a global model on decentralized local datasets under the condition of protecting local data privacy.
Transformer-Patcher: One Mistake worth One Neuron
Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME).
AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers
In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion.
DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation
In this way, the proposed DiffTalk is capable of producing high-quality talking head videos in synchronization with the source audio, and more importantly, it can be naturally generalized across different identities without any further fine-tuning.
CLIP-Cluster: CLIP-Guided Attribute Hallucination for Face Clustering
Furthermore, we develop a neighbor-aware proxy generator that fuses the features describing various attributes into a proxy feature to build a bridge among different sub-clusters and reduce the intra-class variance.
LOGO: A Long-Form Video Dataset for Group Action Quality Assessment
Action quality assessment (AQA) has become an emerging topic since it can be extensively applied in numerous scenarios.
Deep Factorized Metric Learning
Learning a generalizable and comprehensive similarity metric to depict the semantic discrepancies between images is the foundation of many computer vision tasks.
DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion
Unlike previous work that relies on carefully designed network architectures and loss functions to fuse the information from the source and target faces, we reformulate the face swapping as a conditional inpainting task, performed by a powerful diffusion model guided by the desired face attributes (e. g., identity and landmarks).
Deep learning for size-agnostic inverse design of random-network 3D printed mechanical metamaterials
Practical applications of mechanical metamaterials often involve solving inverse problems where the objective is to find the (multiple) microarchitectures that give rise to a given set of properties.
Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint
Deep learning has revolutionized human society, yet the black-box nature of deep neural networks hinders further application to reliability-demanded industries.
Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization
However, less attention has been paid to the visual features from the perspective of the summary, which may limit the model performance, especially in the low- and zero-resource scenarios.
Understanding Translationese in Cross-Lingual Summarization
In detail, we find that (1) the translationese in documents or summaries of test sets might lead to the discrepancy between human judgment and automatic evaluation; (2) the translationese in training sets would harm model performance in real-world applications; (3) though machine-translated documents involve translationese, they are very useful for building CLS systems on low-resource languages under specific training strategies.
FLAG3D: A 3D Fitness Activity Dataset with Language Instruction
With the continuously thriving popularity around the world, fitness activity analytic has become an emerging research topic in computer vision.
DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding
In this work, we show that the issue arises from the un-consistency of label smoothing on the token-level and sequence-level distributions.
Diffusion-SDF: Text-to-Shape via Voxelized Diffusion
With the rising industrial attention to 3D virtual modeling technology, generating novel 3D content based on specified conditions (e. g. text) has become a hot issue.
Rephrasing the Reference for Non-Autoregressive Machine Translation
In response to this problem, we introduce a rephraser to provide a better training target for NAT by rephrasing the reference sentence according to the NAT output.
Findings of the WMT 2022 Shared Task on Translation Suggestion
We report the result of the first edition of the WMT shared task on Translation Suggestion (TS).
AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning
Recent studies have shown the impressive efficacy of counterfactually augmented data (CAD) for reducing NLU models' reliance on spurious features and improving their generalizability.
BJTU-WeChat's Systems for the WMT22 Chat Translation Task
Our systems achieve 0. 810 and 0. 946 COMET scores.
Summer: WeChat Neural Machine Translation Systems for the WMT22 Biomedical Translation Task
This paper introduces WeChat's participation in WMT 2022 shared biomedical translation task on Chinese to English.
SGCE-Font: Skeleton Guided Channel Expansion for Chinese Font Generation
Numerical results show that the mode collapse issue suffered by the known CycleGAN can be effectively alleviated by equipping with the proposed SGCE module, and the CycleGAN equipped with SGCE outperforms the state-of-the-art models in terms of four important evaluation metrics and visualization quality.
Reconstructing high-order sequence features of dynamic functional connectivity networks based on diversified covert attention patterns for Alzheimer's disease classification
Recent studies have applied deep learning methods such as convolutional recurrent neural networks (CRNs) and Transformers to brain disease classification based on dynamic functional connectivity networks (dFCNs), such as Alzheimer's disease (AD), achieving better performance than traditional machine learning methods.
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
The proposed method is verified with a wide spectrum of traditional and modern image backbones and achieves new SoTA results on the large-scale nuScenes dataset.
Ranked #4 on
3D Object Detection
on Rope3D
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.
Ranked #2 on
Object Detection
on LVIS v1.0 minival
(using extra training data)
Planning Irregular Object Packing via Hierarchical Reinforcement Learning
We compare our approach with existing robotic packing methods for irregular objects in a physics simulator.
Cross-Modal Adapter for Text-Video Retrieval
However, as pre-trained models are scaling up, fully fine-tuning them on text-video retrieval datasets has a high risk of overfitting.
CSCD-IME: Correcting Spelling Errors Generated by Pinyin IME
In fact, most of Chinese input is based on pinyin input method, so the study of spelling errors in this process is more practical and valuable.
Probabilistic Deep Metric Learning for Hyperspectral Image Classification
We propose to learn a global probabilistic distribution for each pixel in the patch and a probabilistic metric to model the distance between distributions.
MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction
It contains 103, 193 event coreference chains, 1, 216, 217 temporal relations, 57, 992 causal relations, and 15, 841 subevent relations, which is larger than existing datasets of all the ERE tasks by at least an order of magnitude.
Demystify Transformers & Convolutions in Modern Image Deep Networks
Our experiments on various tasks and an analysis of inductive bias show a significant performance boost due to advanced network-level and block-level designs, but performance differences persist among different STMs.
Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
When reading a story, humans can rapidly understand new fictional characters with a few observations, mainly by drawing analogy to fictional and real people they met before in their lives.
Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues
The dialogue data admits a wide variety of responses for a given dialogue history, especially responses with different semantics.
Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension
Although these tasks are effective, there are still urging problems: (1) randomly masking speakers regardless of the question cannot map the speaker mentioned in the question to the corresponding speaker in the dialogue, and ignores the speaker-centric nature of utterances.
Exploring Mode Connectivity for Pre-trained Language Models
(3) How does the PLM's task knowledge change along the path connecting two minima?
Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning
To fathom the mystery, we hypothesize that the adaptations of different DETs could all be reparameterized as low-dimensional optimizations in a unified optimization subspace, which could be found by jointly decomposing independent solutions of different DETs.
Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection
We use a fine-grained encoding strategy which is more sensitive to the emotion dynamics (emotion flow) in the conversations to predict the emotion-intent characteristic of response.
ROSE: Robust Selective Fine-tuning for Pre-trained Language Models
Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks.
Towards Robust k-Nearest-Neighbor Machine Translation
Meanwhile we inject two types of perturbations into the retrieved pairs for robust training.
Cerebrovascular Segmentation via Vessel Oriented Filtering Network
Accurate cerebrovascular segmentation from Magnetic Resonance Angiography (MRA) and Computed Tomography Angiography (CTA) is of great significance in diagnosis and treatment of cerebrovascular pathology.
Dynamics-aware Adversarial Attack of Adaptive Neural Networks
To address this issue, we propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient.
Categorizing Semantic Representations for Neural Machine Translation
Modern neural machine translation (NMT) models have achieved competitive performance in standard benchmarks.
Token-Label Alignment for Vision Transformers
Data mixing strategies (e. g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs).
A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models
In response to the efficiency problem, recent studies show that dense PLMs can be replaced with sparse subnetworks without hurting the performance.
Mixture of Attention Heads: Selecting Attention Heads Per Token
This paper proposes the Mixture of Attention Heads (MoA), a new architecture that combines multi-head attention with the MoE mechanism.
From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
We then design a Model Uncertainty--aware Knowledge Integration (MUKI) framework to recover the golden supervision for the student.
OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions
The pretrain-finetune paradigm in modern computer vision facilitates the success of self-supervised learning, which tends to achieve better transferability than supervised learning.
Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning
However, these models reveal a trade-off that the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data (which is dominated by the biased samples).
Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA
To overcome this limitation, we propose a new dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.
Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment
Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing.
Causal Intervention-based Prompt Debiasing for Event Argument Extraction
Prompt-based methods have become increasingly popular among information extraction tasks, especially in low-data scenarios.
An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning
To address this problem, we present an information minimization based contrastive learning (InforMin-CL) model to retain the useful information and discard the redundant information by maximizing the mutual information and minimizing the information entropy between positive instances meanwhile for unsupervised sentence representation learning.