Search Results for author:
Found 264 papers, 106 papers with code
An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism
Entity alignment (EA) aims to discover the equivalent entity pairs between KGs, which is a crucial step for integrating multi-source KGs. For a long time, most researchers have regarded EA as a pure graph representation learning task and focused on improving graph encoders while paying little attention to the decoding process. In this paper, we propose an effective and efficient EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI). Specifically, we derive two sets of isomorphism equations: (1) Adjacency tensor isomorphism equations and (2) Gramian tensor isomorphism equations. By combining these equations, DATTI could effectively utilize the adjacency and inner correlation isomorphisms of KGs to enhance the decoding process of EA. Extensive experiments on public datasets indicate that our decoding algorithm can deliver significant performance improvements even on the most advanced EA methods, while the extra required time is less than 3 seconds.
Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning
Discovering Out-of-Domain(OOD) intents is essential for developing new skills in a task-oriented dialogue system.
CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation
CQG employs a simple method to generate the multi-hop questions that contain key entities in multi-hop reasoning chains, which ensure the complexity and quality of the questions.
PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack
To reduce the potential side effects of using defense modules, we further propose a novel forgetting restricted adversarial training, which filters out bad adversarial examples that impair the performance of original ones.
Task-Oriented Clustering for Dialogues
A reliable clustering algorithm for task-oriented dialogues can help developer analysis and define dialogue tasks efficiently.
Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language Models
The key challenge of question answering over knowledge bases (KBQA) is the inconsistency between the natural language questions and the reasoning paths in the knowledge base (KB).
Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks
Specifically, we re-formulate both token and sentence classification tasks into a unified language modeling task, and map label spaces of different tasks into the same vocabulary space.
Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system.
From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in user values and needs.
UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection
Inspired by the impressive performance of State Space Models (SSM) achieved in the field of 2D vision tasks, in this paper, we propose a novel Unified Mamba (UniMamba), which seamlessly integrates the merits of 3D convolution and SSM in a concise multi-head manner, aiming to perform "local and global" spatial context aggregation efficiently and simultaneously.
Exploring the Performance Improvement of Tensor Processing Engines through Transformation in the Bit-weight Dimension of MACs
Based on this notation and its transformations, we propose four optimization techniques that improve timing, area, and power consumption.
Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs
Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models.
Classifying the Stoichiometry of Virus-like Particles with Interpretable Machine Learning
Virus-like particles (VLPs) are valuable for vaccine development due to their immune-triggering properties.
Theoretical Benefit and Limitation of Diffusion Language Model
In this paper, we present a rigorous theoretical analysis of a widely used type of diffusion language model, the Masked Diffusion Model (MDM), and find that its effectiveness heavily depends on the target evaluation metric.
Human Decision-making is Susceptible to AI-driven Manipulation
Through a randomized controlled trial with 233 participants, we examined human susceptibility to such manipulation in financial (e. g., purchases) and emotional (e. g., conflict resolution) decision-making contexts.
GENERator: A Long-Context Generative Genomic Foundation Model
Recent developments in genomic language models have underscored the potential of LLMs in deciphering DNA sequences.
Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning
It uses contrastive learning, with segments from the same neuron as positive pairs and those from different neurons as negative pairs.
Car-GS: Addressing Reflective and Transparent Surface Challenges in 3D Car Reconstruction
3D car modeling is crucial for applications in autonomous driving systems, virtual and augmented reality, and gaming.
Molecule-dynamic-based Aging Clock and Aging Roadmap Forecast with Sundial
Addressing the unavoidable bias inherent in supervised aging clocks, we introduce Sundial, a novel framework that models molecular dynamics through a diffusion field, capturing both the population-level aging process and the individual-level relative aging order.
ProtCLIP: Function-Informed Protein Multi-Modal Learning
However, these works were still unable to replicate the extraordinary success of language-supervised visual foundation models due to the ineffective usage of aligned protein-text paired data and the lack of an effective function-informed pre-training paradigm.
Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning
Generating detailed captions comprehending text-rich visual content in images has received growing attention for Large Vision-Language Models (LVLMs).
Physical Informed Driving World Model
Autonomous driving requires robust perception models trained on high-quality, large-scale multi-view driving videos for tasks like 3D object detection, segmentation and trajectory prediction.
Learning Visual Generative Priors without Text
Although text-to-image (T2I) models have recently thrived as visual generative priors, their reliance on high-quality text-image pairs makes scaling up expensive.
Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference
The ever-increasing sizes of large language models necessitate distributed solutions for fast inference that exploit multi-dimensional parallelism, where computational loads are split across various accelerators such as GPU clusters.
InfinityDrive: Breaking Time Limits in Driving World Models
Comprehensive experiments in multiple datasets validate InfinityDrive's ability to generate complex and varied scenarios, highlighting its potential as a next-generation driving world model built for the evolving demands of autonomous driving.
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
With the development of large language models (LLMs), the ability to handle longer contexts has become a key capability for Web applications such as cross-document understanding and LLM-powered search systems.
IRS-Enhanced Secure Semantic Communication Networks: Cross-Layer and Context-Awared Resource Allocation
In this paper, intelligent reflective surface (IRS)-enhanced secure semantic communication (IRS-SSC) is proposed to guarantee the physical layer security from a task-oriented semantic perspective.
Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
To fill these gaps, we propose Bridge-IF, a generative diffusion bridge model for inverse folding, which is designed to learn the probabilistic dependency between the distributions of backbone structures and protein sequences.
Enhancing binary classification: A new stacking method via leveraging computational geometry
Stacking, a potent ensemble learning method, leverages a meta-model to harness the strengths of multiple base models, thereby enhancing prediction accuracy.
Measuring Spiritual Values and Bias of Large Language Models
Large language models (LLMs) have become integral tool for users from various backgrounds.
Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG
In this paper, we propose Honest AI: a novel strategy to fine-tune "small" language models to say "I don't know" to reduce hallucination, along with several alternative RAG approaches.
LoTLIP: Improving Language-Image Pre-training for Long Text Understanding
Then, after incorporating corner tokens to aggregate diverse textual information, we manage to help the model catch up to its original level of short text understanding yet greatly enhance its capability of long text understanding.
Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding
Recent development of protein language models (pLMs) with supervised fine tuning provides a promising solution to this problem.
BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation
To this end, we propose BLEND, the behavior-guided neural population dynamics modeling framework via privileged knowledge distillation.
Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
In this paper, we propose a novel attention mechanism based on dynamic context, Grouped Cross Attention (GCA), which can generalize to 1000 times the pre-training context length while maintaining the ability to access distant information with a constant attention window size.
2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models
Tables are ubiquitous across various domains for concisely representing structured information.
Subjective and Objective Quality-of-Experience Evaluation Study for Live Video Streaming
For the subjective QoE study, we introduce the first live video streaming QoE dataset, TaoLive QoE, which consists of $42$ source videos collected from real live broadcasts and $1, 155$ corresponding distorted ones degraded due to a variety of streaming distortions, including conventional streaming distortions such as compression, stalling, as well as live streaming-specific distortions like frame skipping, variable frame rate, etc.
Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning
To train CodePlan, we construct a large-scale dataset of 2M examples that integrate code-form plans with standard prompt-response pairs from existing corpora.
DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving
Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.
Ranked #10 on
Bench2Drive
on Bench2Drive
MyGo: Consistent and Controllable Multi-View Driving Video Generation with Camera Control
High-quality driving video generation is crucial for providing training data for autonomous driving models.
SGC-VQGAN: Towards Complex Scene Representation via Semantic Guided Clustering Codebook
Utilizing inference results from segmentation model , our approach constructs a temporospatially consistent semantic codebook, addressing issues of codebook collapse and imbalanced token semantics.
DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation
However, existing approaches often struggle with multi-view video generation due to the challenges of integrating 3D information while maintaining spatial-temporal consistency and effectively learning from a unified model.
A Quantitative Approach for Evaluating Disease Focus and Interpretability of Deep Learning Models for Alzheimer's Disease Classification
To bridge such gap, in this study, we developed a quantitative disease-focusing strategy to first enhance the interpretability of DL models using saliency maps and brain segmentations; then we propose a disease-focus (DF) score that quantifies how much a DL model focuses on brain areas relevant to AD pathology based on clinically known MRI-based pathological regions of AD.
RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments
Reliable embodied perception from an egocentric perspective is challenging yet essential for autonomous navigation technology of intelligent mobile agents.
Quantitative Evaluation of the Saliency Map for Alzheimer's Disease Classifier with Anatomical Segmentation
In order to leverage the fact that the brain volume shrinkage happens in AD patients during disease progression, we define a new evaluation metric, brain volume change score (VCS), by computing the average Pearson correlation of the brain volume changes and the saliency values of a model in different brain regions for each patient.
Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules
More interestingly, with a fixed parameter budget, MoM-large enables an over 38% increase in depth for computation graphs compared to GPT-2-large, resulting in absolute gains of 1. 4 on GLUE and 1 on XSUM.
MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization
Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community.
From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis
To overcome the challenge, we first introduce a least-to-most visual reasoning paradigm, which interleaves steps of decomposing a question into sub-questions and invoking external tools for resolving sub-questions.
Unsupervised Morphological Tree Tokenizer
Specifically, the deep model jointly encodes internal structures and representations of words with a mechanism named $\textit{MorphOverriding}$ to ensure the indecomposability of morphemes.
SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
We have released all the code to promote the exploration of models for motion generation in the autonomous driving field.
FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models
Precise image editing with text-to-image models has attracted increasing interest due to their remarkable generative capabilities and user-friendly nature.
QNCD: Quantization Noise Correction for Diffusion Models
Diffusion models have revolutionized image synthesis, setting new benchmarks in quality and creativity.
InstructBrush: Learning Attention-based Instruction Optimization for Image Editing
Two key techniques are introduced into InstructBrush, Attention-based Instruction Optimization and Transformation-oriented Instruction Initialization, to address the limitations of the previous method in terms of inversion effects and instruction generalization.
AFDGCF: Adaptive Feature De-correlation Graph Collaborative Filtering for Recommendations
Collaborative filtering methods based on graph neural networks (GNNs) have witnessed significant success in recommender systems (RS), capitalizing on their ability to capture collaborative signals within intricate user-item relationships via message-passing mechanisms.
DreamLIP: Language-Image Pre-training with Long Captions
Motivated by this, we propose to dynamically sample sub-captions from the text label to construct multiple positive pairs, and introduce a grouping loss to match the embeddings of each sub-caption with its corresponding local image patches in a self-supervised manner.
Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale
A syntactic language model (SLM) incrementally generates a sentence with its syntactic tree in a left-to-right manner.
Intent-aware Recommendation via Disentangled Graph Contrastive Learning
The other is different behaviors have different intent distributions, so how to establish their relations for a more explainable recommender system.
HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative
Based on HoloVIC, we formulated four tasks to facilitate the development of related research.
"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas.
Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging
Such demographic biases present over a wide range of pathologies and demographic attributes.
AFPR-CIM: An Analog-Domain Floating-Point RRAM-based Compute-In-Memory Architecture with Dynamic Range Adaptive FP-ADC
Moreover, a novel FP-DAC is also implemented which reconstructs FP digital codes into analog values to perform analog computation.
Human Aesthetic Preference-Based Large Text-to-Image Model Personalization: Kandinsky Generation as an Example
This paper introduces a prompting-free generative approach that empowers users to automatically generate personalized painterly content that incorporates their aesthetic preferences in a customized artistic style.
AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback
We present AMOR, an agent framework based on open-source LLMs, which reasons with external knowledge bases and adapts to specific domains through human supervision to the reasoning process.
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data.
Adaptive Resource Allocation for Semantic Communication Networks
In order to investigate the performance of semantic communication networks, the quality of service for semantic communication (SC-QoS), including the semantic quantization efficiency (SQE) and transmission latency, is proposed for the first time.
See SIFT in a Rain
One is difference of Gaussian (DoG) pyramid recovery network (DPRNet) for SIFT detection, and the other gradients of Gaussian images recovery network (GGIRNet) for SIFT description.
GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence
Finally, we select the most fitting chains of evidence from the evidence forest and integrate them into the generated story, thereby enhancing the narrative's complexity and credibility.
Augmenting Transformers with Recursively Composed Multi-grained Representations
More interestingly, the hierarchical structures induced by ReCAT exhibit strong consistency with human-annotated syntactic trees, indicating good interpretability brought by the CIO layers.
Ranked #4 on
Semantic Role Labeling
on OntoNotes
Constituency Grammar Induction
Natural Language Inference
+2
Scalable Video Object Segmentation with Simplified Framework
The current popular methods for video object segmentation (VOS) implement feature matching through several hand-crafted modules that separately perform feature extraction and matching.
Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
To bring the useful knowledge back into light, we first identify a set of parameters that are important to a given downstream task, then attach a binary mask to each parameter, and finally optimize these masks on the downstream data with the parameters frozen.
Understanding Deep Neural Networks via Linear Separability of Hidden Layers
In this paper, we measure the linear separability of hidden layer outputs to study the characteristics of deep neural networks.
LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs
We reflect on human and LLMs' different sensitivities to instructions, stress the importance of enabling human-facing safeguards for LLMs, and discuss the potential of training humans and LLMs with complementary skill sets.
NTIRE 2023 Quality Assessment of Video Enhancement Challenge
61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions.
Feature Adversarial Distillation for Point Cloud Classification
Due to the point cloud's irregular and unordered geometry structure, conventional knowledge distillation technology lost a lot of information when directly used on point cloud tasks.
Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation
In this paper, we explore the compositional generalization for multi-attribute controllable dialogue generation where a model can learn from seen attribute values and generalize to unseen combinations.
T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing
Translating natural language queries into SQLs in a seq2seq manner has attracted much attention recently.
Ranked #11 on
Text-To-SQL
on spider
PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models
While transformer-based pre-trained language models (PLMs) have dominated a number of NLP applications, these models are heavy to deploy and expensive to use.
HUB: Guiding Learned Optimizers with Continuous Prompt Tuning
By incorporating hand-designed optimizers as the second component in our hybrid approach, we are able to retain the benefits of learned optimizers while stabilizing the training process and, more importantly, improving testing performance.
RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank
In this paper, we propose a novel approach, RankCSE, for unsupervised sentence representation learning, which incorporates ranking consistency and ranking distillation with contrastive learning into a unified framework.
Preference or Intent? Double Disentangled Collaborative Filtering
In this way, the low-rating items will be treated as positive samples for modeling intents while the negative samples for modeling preferences.
M2GNN: Metapath and Multi-interest Aggregated Graph Neural Network for Tag-based Cross-domain Recommendation
(2) From the CDR perspective, not all inter-domain interests are helpful to infer intra-domain interests.
MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos
User-generated content (UGC) live videos are often bothered by various distortions during capture procedures and thus exhibit diverse visual qualities.
Multi-task Transformer with Relation-attention and Type-attention for Named Entity Recognition
There are three types of NER tasks, including flat, nested and discontinuous entity recognition.
Time-aware Multiway Adaptive Fusion Network for Temporal Knowledge Graph Question Answering
For each given question, TMA first extracts the relevant concepts from the KG, and then feeds them into a multiway adaptive module to produce a \emph{temporal-specific} representation of the question.
Ranked #13 on
Question Answering
on TimeQuestions
Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflicts
To alleviate this problem, we propose a novel Dual Path Modeling Framework to enhance the model's ability to perceive subtle differences in sentence pairs by separately modeling affinity and difference semantics.
Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognition
We design an improved triplet network to map samples and prototype vectors into a low-dimensional space that is easier to be classified and propose an adaptive margin for each entity type.
FFHR: Fully and Flexible Hyperbolic Representation for Knowledge Graph Completion
Specifically, they suffer from two main limitations: 1) existing Graph Convolutional Network (GCN) methods in hyperbolic space rely on tangent space approximation, which would incur approximation error in representation learning, and 2) due to the lack of inner product operation definition in hyperbolic space, existing methods can only measure the plausibility of facts (links) with hyperbolic distance, which is difficult to capture complex data patterns.
RGB-T Multi-Modal Crowd Counting Based on Transformer
To better excavate multi-modal information, we use count-guided multi-modal fusion and modal-guided count enhancement to achieve the impressive performance.
LidarGait: Benchmarking 3D Gait Recognition with Point Clouds
Video-based gait recognition has achieved impressive results in constrained scenarios.
Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions
In daily HOIs, humans often interact with a variety of objects, e. g., holding and touching dozens of household items in cleaning.
Robust Lottery Tickets for Pre-trained Language Models
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.
A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Ranking
We noted that the distinctness of the domain-specific features is different, so in this paper, we propose to use a curriculum learning strategy based on keyword weight ranking to improve the performance of multi-domain text classification models.
Focus Is What You Need For Chinese Grammatical Error Correction
Chinese Grammatical Error Correction (CGEC) aims to automatically detect and correct grammatical errors contained in Chinese text.
PATS: Sensitivity-aware Noisy Learning for Pretrained Language Models
A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs).
UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning
Specifically, we design a K-nearest neighbor contrastive learning (KNCL) objective for representation learning and introduce a KNN-based scoring function for OOD detection.
Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
Recent advances in neural approaches greatly improve task-oriented dialogue (TOD) systems which assist users to accomplish their goals.
Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery
For OOD clustering stage, we propose a KCC method to form compact clusters by mining true hard negative samples, which bridges the gap between clustering and representation learning.
Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion
Transformer-based pre-trained models like BERT have achieved great progress on Semantic Sentence Matching.
XPrompt: Exploring the Extreme of Prompt Tuning
Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner.
DABERT: Dual Attention Enhanced BERT for Semantic Matching
To alleviate this problem, we propose a novel Dual Attention Enhanced BERT (DABERT) to enhance the ability of BERT to capture fine-grained differences in sentence pairs.
From One to Many: Dynamic Cross Attention Networks for LiDAR and Camera Fusion
The whole fusion architecture named Dynamic Cross Attention Network (DCAN) exploits multi-level image features and adapts to multiple representations of point clouds, which allows DCA to serve as a plug-in fusion module.
One-to-Many Semantic Communication Systems: Design, Implementation, Performance Evaluation
To effectively exploit the benefits enabled by semantic communication, in this paper, we propose a one-to-many semantic communication system.
Generalized Intent Discovery: Learning from Open World Dialogue System
Traditional intent classification models are based on a pre-defined intent set and only recognize limited in-domain (IND) intent classes.
Structural Bias for Aspect Sentiment Triplet Extraction
Thus, a natural question arises: Is structural bias still a necessity in the context of PLMs?
Let Me Check the Examples: Enhancing Demonstration Learning via Explicit Imitation
Inspired by the human learning process, in this paper, we introduce Imitation DEMOnstration Learning (Imitation-Demo) to strengthen demonstration learning via explicitly imitating human review behaviour, which includes: (1) contrastive learning mechanism to concentrate on the similar demonstrations.
Unified Knowledge Prompt Pre-training for Customer Service Dialogues
In this paper, we propose a novel unified knowledge prompt pre-training framework, UFA (\textbf{U}nified Model \textbf{F}or \textbf{A}ll Tasks), for customer service dialogues.
Evaluating Point Cloud from Moving Camera Videos: A No-Reference Metric
To tackle the challenge of point cloud quality assessment (PCQA), many PCQA methods have been proposed to evaluate the visual quality levels of point clouds by assessing the rendered static 2D projections.
CLOWER: A Pre-trained Language Model with Contrastive Learning over Word and Character Representations
However, most current models use Chinese characters as inputs and are not able to encode semantic information contained in Chinese words.
Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries
In this work, we present the Knowledge Graph Transformer (kgTransformer) with masked pre-training and fine-tuning strategies.
Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation
In particular: 1) existing methods do not explicitly encode and capture the evolution of short-term preference as sequential methods do; 2) simply using last few interactions is not enough for modeling the changing trend.
Low-Complexity Acoustic Echo Cancellation with Neural Kalman Filtering
The Kalman filter has been adopted in acoustic echo cancellation due to its robustness to double-talk, fast convergence, and good steady-state performance.
HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints
The in-memory approximate nearest neighbor search (ANNS) algorithms have achieved great success for fast high-recall query processing, but are extremely inefficient when handling hybrid queries with unstructured (i. e., feature vectors) and structured (i. e., related attributes) constraints.
Perceptual Quality Assessment for Fine-Grained Compressed Images
Nowadays, the mainstream full-reference (FR) metrics are effective to predict the quality of compressed images at coarse-grained levels (the bit rates differences of compressed images are obvious), however, they may perform poorly for fine-grained compressed images whose bit rates differences are quite subtle.
Searching for Optimal Subword Tokenization in Cross-domain NER
Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA).
MiniDisc: Minimal Distillation Schedule for Language Model Compression
In particular, motivated by the finding that the performance of the student is positively correlated to the scale-performance tradeoff of the teacher assistant, MiniDisc is designed with a $\lambda$-tradeoff to measure the optimality of the teacher assistant without trial distillation to the student.
Ensemble Multi-Relational Graph Neural Networks
This EMR optimization objective is able to derive an iterative updating rule, which can be formalized as an ensemble message passing (EnMP) layer with multi-relations.
Boosting Camouflaged Object Detection with Dual-Task Interactive Transformer
The foreground is just object, while foreground minus background is considered as boundary.
Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification
Existing studies in this task attach more attention to the sequence modeling of sentences while largely ignoring the rich domain-invariant semantics embedded in graph structures (i. e., the part-of-speech tags and dependency relations).
Making Pretrained Language Models Good Long-tailed Learners
Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge.
Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention.
Hierarchical Locality Sensitive Hashing for Structured Data: A Survey
Data similarity (or distance) computation is a fundamental research topic which fosters a variety of similarity-based machine learning and data mining applications.
GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval
To enhance the performance of dense retrieval models without loss of efficiency, we propose a GNN-encoder model in which query (passage) information is fused into passage (query) representations via graph neural networks that are constructed by queries and their top retrieved passages.
Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain.
Learning to Express in Knowledge-Grounded Conversation
Grounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses.
TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization
Another is that applying the existing pre-trained models to this task is tricky because of the structural dependence within the conversation and its informal expression, etc.
Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization
The most advanced abstractive dialogue summarizers lack generalization ability on new domains and the existing researches for domain adaptation in summarization generally rely on large-scale pre-trainings.
Unsupervised Learning of Accurate Siamese Tracking
As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward.
Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) predicts sentiment polarity towards a specific aspect in the given sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision
Specifically, i) to fully exploit user behavioral information, we extract candidate hyponymy relations that match user interests from query-click concepts; ii) to enhance the semantic information of new concepts and better detect hyponymy relations, we model concepts and relations through both user-generated content and structural information in existing taxonomies and user click logs, by leveraging Pre-trained Language Models and Graph Neural Network combined with Contrastive Learning; iii) to reduce the cost of dataset construction and overcome data skews, we construct a high-quality and balanced training dataset from existing taxonomy with no supervision.
Data-Driven, Soft Alignment of Functional Data Using Shapes and Landmarks
Alignment or registration of functions is a fundamental problem in statistical analysis of functions and shapes.
ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation
We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions.
Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest.
InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER
Recently, prompt-based methods have achieved significant performance in few-shot learning scenarios by bridging the gap between language model pre-training and fine-tuning for downstream tasks.
Graph Neural Network-Based Scheduling for Multi-UAV-Enabled Communications in D2D Networks
In this paper, we propose a novel graph neural networks (GNN) based approach that can map the considered system into a specific graph structure and achieve the optimal solution in a low complexity manner.
Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification
Image-to-video person re-identification aims to retrieve the same pedestrian as the image-based query from a video-based gallery set.
Deep Reinforcement Learning
Image-To-Video Person Re-Identification
+5
Learning Video Representations of Human Motion From Synthetic Data
In this paper, we take an early step towards video representation learning of human actions with the help of largescale synthetic videos, particularly for human motion representation enhancement.
Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQL
Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL (Structured Query Language) representations.
Ranked #2 on
Text-To-SQL
on SParC
VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction
With the booming of pre-trained transformers, representation-based models based on Siamese transformer encoders have become mainstream techniques for efficient text matching.
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
Different from pixel-based anomaly detection methods, pose-based methods utilize highly-structured skeleton data, which decreases the computational burden and also avoids the negative impact of background noise.
Ranked #2 on
Video Anomaly Detection
on HR-ShanghaiTech
Anomaly Detection In Surveillance Videos
Optical Flow Estimation
+1
Calibrated Feature Decomposition for Generalizable Person Re-Identification
The calibrated person representation is subtly decomposed into the identity-relevant feature, domain feature, and the remaining entangled one.
Domain Generalization
Generalizable Person Re-identification
TODSum: Task-Oriented Dialogue Summarization with State Tracking
Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues, while summarization datasets for the broadly used task-oriented dialogue haven't been explored yet.
Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation
To sufficiently exploit such important information for recommendation, it is essential to disentangle the benign popularity bias caused by item quality from the harmful popularity bias caused by conformity.
Stock Price Prediction Under Anomalous Circumstances
The stock market is volatile and complicated, especially in 2020.
Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models
To solve this issue, various data augmentation techniques are proposed to improve the robustness of PLMs.
DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network
Knowledge graph completion (KGC) has become a focus of attention across deep learning community owing to its excellent contribution to numerous downstream tasks.
Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues
To tackle these challenges, we propose a representation[K]-interaction[L]-matching framework that explores multiple types of deep interactive representations to build context-response matching models for response selection.
The impact of model risk on dynamic portfolio selection under multi-period mean-standard-deviation criterion
In the worst case scenario, the optimal robust strategy can be obtained in a semi-analytical form as a solution of a system of nonlinear equations.
Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification
Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification.
Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-Supervised Learning Track.
Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder
Capturing interactions among event arguments is an essential step towards robust event argument extraction (EAE).
TSI: Temporal Saliency Integration for Video Action Recognition
Specifically, SME aims to highlight the motion-sensitive area through local-global motion modeling, where the saliency alignment and pyramidal feature difference are conducted successively between neighboring frames to capture motion dynamics with less noises caused by misaligned background.
A Novel Automatic Modulation Classification Scheme Based on Multi-Scale Networks
Moreover, a novel loss function that combines the center loss and the cross entropy loss is exploited to learn both discriminative and separable features in order to further improve the classification performance.
Hashing-Accelerated Graph Neural Networks for Link Prediction
Networks are ubiquitous in the real world.
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer
Learning high-quality sentence representations benefits a wide range of natural language processing tasks.
Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval
Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models.
Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video sequences.
Ranked #10 on
Video Deinterlacing
on MSU Deinterlacer Benchmark
Temporal Context Aggregation Network for Temporal Action Proposal Refinement
In this paper, we propose Temporal Context Aggregation Network (TCANet) to generate high-quality action proposals through "local and global" temporal context aggregation and complementary as well as progressive boundary refinement.
Ranked #10 on
Temporal Action Localization
on ActivityNet-1.3
Incorporating Convolution Designs into Visual Transformers
Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e. g., ViT and DeiT) to apply Transformers to the vision domain.
Ranked #1 on
Image Classification
on Oxford-IIIT Pets
Real-Time Visual Object Tracking via Few-Shot Learning
Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL).
Higher Performance Visual Tracking with Dual-Modal Localization
Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy.
ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction
Aspect category sentiment analysis (ACSA) and review rating prediction (RP) are two essential tasks to detect the fine-to-coarse sentiment polarities.
Learning Statistical Texture for Semantic Segmentation
In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation.
BaPipe: Exploration of Balanced Pipeline Parallelism for DNN Training
The size of deep neural networks (DNNs) grows rapidly as the complexity of the machine learning algorithm increases.
Improving EEG Decoding via Clustering-based Multi-task Feature Learning
With the encoded label matrix, we devise a novel multi-task learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses.
Context-Aware Graph Convolution Network for Target Re-identification
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks.
Social Media Study of Public Opinions on Potential COVID-19 Vaccines: Informing Dissent, Disparities, and Dissemination
People who have the worst personal pandemic experience are more likely to hold the anti-vaccine opinion.
Social and Information Networks
Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
We study knowledge-grounded dialogue generation with pre-trained language models.
Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning
However, this comes at the cost of manually labeling similar questions to learn a retrieval model, which is tedious and expensive.
Less is More: Data-Efficient Complex Question Answering over Knowledge Bases
Our framework consists of a neural generator and a symbolic executor that, respectively, transforms a natural-language question into a sequence of primitive actions, and executes them over the knowledge base to compute the answer.
Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
We study knowledge-grounded dialogue generation with pre-trained language models.
StyleDGPT: Stylized Response Generation with Pre-trained Language Models
Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training.
SAMOT: Switcher-Aware Multi-Object Tracking and Still Another MOT Measure
Besides, we propose a new MOT evaluation measure, Still Another IDF score (SAIDF), aiming to focus more on identity issues. This new measure may overcome some problems of the previous measures and provide a better insight for identity issues in MOT.
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
In this paper, we present BSN++, a new framework which exploits complementary boundary regressor and relation modeling for temporal proposal generation.
Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
Second, the parameter frequency distribution is further adopted to guide the student network to learn the appearance modeling process from the teacher.
Zero-Resource Knowledge-Grounded Dialogue Generation
While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to obtain.
Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
Specifically, in order to generate high-quality proposals, we consider several factors including the video feature encoder, the proposal generator, the proposal-proposal relations, the scale imbalance, and ensemble strategy.
Class-wise Dynamic Graph Convolution for Semantic Segmentation
Specifically, the CDGC module takes the coarse segmentation result as class mask to extract node features for graph construction and performs dynamic graph convolutions on the constructed graph to learn the feature aggregation and weight allocation.
CorefQA: Coreference Resolution as Query-based Span Prediction
In this paper, we present CorefQA, an accurate and extensible approach for the coreference resolution task.
Ranked #3 on
Coreference Resolution
on CoNLL 2012
(using extra training data)
Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning
In this paper, we formalize the music-conditioned dance generation as a sequence-to-sequence learning problem and devise a novel seq2seq architecture to efficiently process long sequences of music features and capture the fine-grained correspondence between music and dance.
Ranked #1 on
Motion Synthesis
on BRACE
Deep learning to estimate the physical proportion of infected region of lung for COVID-19 pneumonia with CT image set
For the segmented masks of intact lung and infected regions, the best method could achieve 0. 972 and 0. 757 measure in mean Dice similarity coefficient on our test benchmark.
Hierarchical Feature Embedding for Attribute Recognition
Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc.
Scope Head for Accurate Localization in Object Detection
Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance.
Estimation of the Laser Frequency Nosie Spectrum by Continuous Dynamical Decoupling
Decoherence induced by the laser frequency noise is one of the most important obstacles in the quantum information processing.
Quantum Physics
Open Domain Dialogue Generation with Latent Images
Thus, we propose learning a response generation model with both image-grounded dialogues and textual dialogues by assuming that the visual scene information at the time of a conversation can be represented by an image, and trying to recover the latent images of the textual dialogues through text-to-image generation techniques.
Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks
We study multi-turn response generation for open-domain dialogues.
Towards information-rich, logical text generation with knowledge-enhanced neural models
Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life.
Low-Resource Knowledge-Grounded Dialogue Generation
In such a low-resource setting, we devise a disentangled response decoder in order to isolate parameters that depend on knowledge-grounded dialogues from the entire generation model.
Deep Learning System to Screen Coronavirus Disease 2019 Pneumonia
We found that the real time reverse transcription-polymerase chain reaction (RT-PCR) detection of viral RNA from sputum or nasopharyngeal swab has a relatively low positive rate in the early stage to determine COVID-19 (named by the World Health Organization).
Description Based Text Classification with Reinforcement Learning
We observe significant performance boosts over strong baselines on a wide range of text classification tasks including single-label classification, multi-label classification and multi-aspect sentiment analysis.
Computation Reallocation for Object Detection
However, classification allocation pattern is usually adopted directly to object detector, which is proved to be sub-optimal.
Coreference Resolution as Query-based Span Prediction
In this paper, we present an accurate and extensible approach for the coreference resolution task.
Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems
We study how to sample negative examples to automatically construct a training set for effective model learning in retrieval-based dialogue systems.
Improving One-shot NAS by Suppressing the Posterior Fading
In this paper, we analyse existing weight sharing one-shot NAS approaches from a Bayesian point of view and identify the posterior fading problem, which compromises the effectiveness of shared weights.
A Deep Learning System That Generates Quantitative CT Reports for Diagnosing Pulmonary Tuberculosis
The best model was selected to annotate the spatial location of lesions and classify them into miliary, infiltrative, caseous, tuberculoma and cavitary types simultaneously. Then the Noisy-Or Bayesian function was used to generate an overall infection probability. Finally, a quantitative diagnostic report was exported. The results showed that the recall and precision rates, from the perspective of a single lesion region of PTB, were 85. 9% and 89. 2% respectively.
Read, Attend and Comment: A Deep Architecture for Automatic NewsComment Generation
Automatic news comment generation is a new testbed for techniques of natural language generation.
Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation
Automatic news comment generation is a new testbed for techniques of natural language generation.
Low-Resource Response Generation with Template Prior
Since the paired data now is no longer enough to train a neural generation model, we consider leveraging the large scale of unpaired data that are much easier to obtain, and propose response generation with both paired and unpaired data.
