Search Results for author:
Found 255 papers, 91 papers with code
Natural Language Processing Meets Quantum Physics: A Survey and Categorization
Recent research has investigated quantum NLP, designing algorithms that process natural language in quantum computers, and also quantum-inspired algorithms that improve NLP performance on classical computers.
ClusterFormer: Neural Clustering Attention for Efficient and Effective Transformer
Other sparse methods use clustering patterns to select words, but the clustering process is separate from the training process of the target task, which causes a decrease in effectiveness.
HOSMEL: A Hot-Swappable Modularized Entity Linking Toolkit for Chinese
We investigate the usage of entity linking (EL)in downstream tasks and present the first modularized EL toolkit for easy task adaptation.
DoSEA: A Domain-specific Entity-aware Framework for Cross-Domain Named Entity Recogition
Cross-domain named entity recognition aims to improve performance in a target domain with shared knowledge from a well-studied source domain.
Cross-Domain Named Entity Recognition
Machine Reading Comprehension
+2
MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation
Generating long-term, coherent, and realistic music-conditioned dance sequences remains a challenging task in human motion synthesis.
Are MLMs Trapped in the Visual Room?
In implementation, we introduce a two-tier evaluation framework spanning perception and cognition.
LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems
Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs.
AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference
Assessing Large Language Models (LLMs)' underlying value differences enables comprehensive comparison of their misalignment, cultural adaptability, and biases.
Ultrasound Report Generation with Multimodal Large Language Models for Standardized Texts
In this study, we propose a unified framework for multi-organ and multilingual US report generation, integrating fragment-based multilingual training and leveraging the standardized nature of US reports.
Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models
We explore Generalizable Tumor Segmentation, aiming to train a single model for zero-shot tumor segmentation across diverse anatomical regions.
Fast-Slow Thinking for Large Vision-Language Model Reasoning
Recent advances in large vision-language models (LVLMs) have revealed an \textit{overthinking} phenomenon, where models generate verbose reasoning across all tasks regardless of questions.
FedCIA: Federated Collaborative Information Aggregation for Privacy-Preserving Recommendation
Based on this new paradigm, we introduce the federated collaborative information aggregation (FedCIA) method for privacy-preserving recommendation.
Self-Supervised Enhancement of Forward-Looking Sonar Images: Bridging Cross-Modal Degradation Gaps through Feature Space Transformation and Multi-Frame Fusion
Enhancing forward-looking sonar images is critical for accurate underwater target detection.
Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation
Span-level emotion-cause-category triplet extraction represents a novel and complex challenge within emotion cause analysis.
Spiking Neural Network for Intra-cortical Brain Signal Decoding
Decoding brain signals accurately and efficiently is crucial for intra-cortical brain-computer interfaces.
OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication
To address these limitations, we introduce OmniTalker, an end-to-end unified framework that simultaneously generates synchronized speech and talking head videos from text and reference video in real-time zero-shot scenarios, while preserving both speech style and facial styles.
Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories
Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions.
ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model
Real-time interactive video-chat portraits have been increasingly recognized as the future trend, particularly due to the remarkable progress made in text and voice chat technologies.
Stabilization Analysis and Mode Recognition of Kerosene Supersonic Combustion: A Deep Learning Approach Based on Res-CNN-beta-VAE
The scramjet engine is a key propulsion system for hypersonic vehicles, leveraging supersonic airflow to achieve high specific impulse, making it a promising technology for aerospace applications.
Dynamical Mode Recognition of Turbulent Flames in a Swirl-stabilized Annular Combustor by a Time-series Learning Approach
Thermoacoustic instability in annular combustors, essential to aero engines and modern gas turbines, can severely impair operational stability and efficiency, accurately recognizing and understanding various combustion modes is the prerequisite for understanding and controlling combustion instabilities.
Easy-Poly: A Easy Polyhedral Framework For 3D Multi-Object Tracking
Recent advancements in 3D multi-object tracking (3D MOT) have predominantly relied on tracking-by-detection pipelines.
AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations
However, the memory design in current methods causes user agents to introduce significant irrelevant information during decision-making in cross-domain scenarios and makes them unable to recognize the influence of other users' interactions, such as popularity factors.
Unbiased Collaborative Filtering with Fair Sampling
Recommender systems leverage extensive user interaction data to model preferences; however, directly modeling these data may introduce biases that disproportionately favor popular items.
Improving LLM-powered Recommendations with Personalized Information
Due to the lack of explicit reasoning modeling, existing LLM-powered recommendations fail to leverage LLMs' reasoning capabilities effectively.
Deep Reinforcement Learning-Based Bidding Strategies for Prosumers Trading in Double Auction-Based Transactive Energy Market
We also propose a deep reinforcement learning (DRL) model with distributed learning and execution to ensure the scalability and privacy of the market environment.
LLM4GNAS: A Large Language Model Based Toolkit for Graph Neural Architecture Search
LLM4GNAS includes an algorithm library for graph neural architecture search algorithms based on LLMs, enabling the adaptation of GNAS methods to new search spaces through the modification of LLM prompts.
Leveraging Geolocation in Clinical Records to Improve Alzheimer's Disease Diagnosis Using DMV Framework
Alzheimer's Disease (AD) early detection is critical for enabling timely intervention and improving patient outcomes.
Every Image Listens, Every Image Dances: Music-Driven Image Animation
To advance research in this field, we present a new multimodal dataset comprising 2, 904 dance videos with corresponding background music and text descriptions.
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
Ranked #1 on
Mathematical Reasoning
on AIME24
Value Compass Leaderboard: A Platform for Fundamental and Validated Evaluation of LLMs Values
As Large Language Models (LLMs) achieve remarkable breakthroughs, aligning their values with humans has become imperative for their responsible development and customized applications.
The Scaling Law for LoRA Base on Mutual Information Upper Bound
In the fine-tuning process for large models, two types of knowledge are typically involved: the frozen, general knowledge acquired by the model during pre-training and the new knowledge learned through the LoRA module from the current data.
CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR
Scene Text Retrieval (STR) seeks to identify all images containing a given query string.
Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark
To bridge this gap, we introduce a new Natural Language-based Document Image Retrieval (NL-DIR) benchmark with corresponding evaluation metrics.
Exploring Timeline Control for Facial Motion Generation
Based on the annotations, we propose a diffusion-based generation model capable of generating facial motions that are natural and accurately aligned with input timelines.
Leveraging SD Map to Augment HD Map-based Trajectory Prediction
Latest trajectory prediction models in real-world autonomous driving systems often rely on online High-Definition (HD) maps to understand the road environment. However, online HD maps suffer from perception errors and feature redundancy, which hinder the performance of HD map-based trajectory prediction models. To address these issues, we introduce a framework, termed SD map-Augmented Trajectory Prediction (SATP), which leverages Standard-Definition (SD) maps to enhance HD map-based trajectory prediction models. First, we propose an SD-HD fusion approach to leverage SD maps across the diverse range of HD map-based trajectory prediction models.
DeepSeek-V3 Technical Report
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
Energy-Efficient RIS-Aided Cell-Free Massive MIMO Systems: Application, Opportunities, and Challenges
Reconfigurable intelligent surfaces (RIS)-assisted cell-free massive multiple-input multiple-output (CF mMIMO) systems have emerged as a promising technology for sixth-generation communication systems.
SEE: Sememe Entanglement Encoding for Transformer-bases Models Compression
Transformer-based large language models exhibit groundbreaking capabilities, but their storage and computational costs are prohibitively high, limiting their application in resource-constrained scenarios.
Oracle-guided Dynamic User Preference Modeling for Sequential Recommendation
Besides past information, future information is also available during training, which contains the ``oracle'' user preferences in the future and will be beneficial to model dynamic user preferences.
Online Voltage Regulation of Distribution Systems with Disturbance-Action Controllers
Inverter-based distributed energy resources facilitate the advanced voltage control algorithms in the online setting with the flexibility in both active and reactive power injections.
BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?
Dense retrieval, which aims to encode the semantic information of arbitrary text into dense vector representations or embeddings, has emerged as an effective and efficient paradigm for text retrieval, consequently becoming an essential component in various natural language processing systems.
Steam Turbine Anomaly Detection: An Unsupervised Learning Approach Using Enhanced Long Short-Term Memory Variational Autoencoder
Specifically, LSTMVAE, integrating LSTM with VAE, was used to project high-dimensional time-series data to a low-dimensional phase space.
DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship
Toxicity censorship is a complex process, wherein detection is just an initial task and a user can have further needs such as rationale understanding and content modification.
Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning
Trustworthiness is an essential prerequisite for the real-world application of large language models.
CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression
Through quantitative analysis of the quantization kernel, we find that these elements are crucial for maintaining the accuracy of quantized LLMs.
MDiff-FMT: Morphology-aware Diffusion Model for Fluorescence Molecular Tomography with Small-scale Datasets
Fluorescence molecular tomography (FMT) is a sensitive optical imaging technology widely used in biomedical research.
Filtering Discomforting Recommendations with Large Language Models
Personalized algorithms can inadvertently expose users to discomforting recommendations, potentially triggering negative consequences.
AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results
This paper presents the Video Super-Resolution (SR) Quality Assessment (QA) Challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024.
Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics
In this work, we introduce ZODIAC, an LLM-powered framework with cardiologist-level professionalism designed to engage LLMs in cardiological diagnostics.
CogVLM2: Visual Language Models for Image and Video Understanding
Beginning with VisualGLM and CogVLM, we are continuously exploring VLMs in pursuit of enhanced vision-language fusion, efficient higher-resolution architecture, and broader modalities and applications.
Ranked #10 on
Visual Question Answering
on MM-Vet
ConsistencyTrack: A Robust Multi-Object Tracker with a Generation Strategy of Consistency Model
Multi-object tracking (MOT) is a critical technology in computer vision, designed to detect multiple targets in video sequences and assign each target a unique ID per frame.
CL4KGE: A Curriculum Learning Method for Knowledge Graph Embedding
Knowledge graph embedding (KGE) constitutes a foundational task, directed towards learning representations for entities and relations within knowledge graphs (KGs), with the objective of crafting representations comprehensive enough to approximate the logical and symbolic interconnections among entities.
AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results
The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H. 264, HEVC/H. 265, AV1, and VVC/H. 266) and containing a comprehensive collection of compression artifacts.
Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval
Scene text retrieval aims to find all images containing the query text from an image gallery.
GLoCIM: Global-view Long Chain Interest Modeling for news recommendation
Then candidate news representation can be formed to match user representation to achieve news recommendation.
AOTree: Aspect Order Tree-based Model for Explainable Recommendation
Therefore, in this paper, we propose Aspect Order Tree-based (AOTree) explainable recommendation method, inspired by the Order Effects Theory from cognitive and decision psychology, in order to capture the dependency relationships among decisive factors.
Hybrid Deep Learning Framework for Enhanced Melanoma Detection
In this paper, we present a novel and highly efficient melanoma detection framework that synergistically combines the strengths of U-Net for segmentation and EfficientNet for the classification of skin images.
Urban Waterlogging Detection: A Challenging Benchmark and Large-Small Model Co-Adapter
Urban waterlogging poses a major risk to public safety and infrastructure.
Enhanced Safety in Autonomous Driving: Integrating Latent State Diffusion Model for End-to-End Navigation
With the advancement of autonomous driving, ensuring safety during motion planning and navigation is becoming more and more important.
Structure-Aware Consensus Network on Graphs with Few Labeled Nodes
Secondly, SACN uniquely integrates the graph's structural information to achieve strong-to-strong consensus learning, improving the utilization of unlabeled data while maintaining multiview learning.
Physics-Informed AI Inverter
This letter devises an AI-Inverter that pilots the use of a physics-informed neural network (PINN) to enable AI-based electromagnetic transient simulations (EMT) of grid-forming inverters.
3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding
3D-RPE is an advanced version of the widely used 2D Rotary Position Encoding (RoPE), with two major advantages for modeling long contexts: controllable long-term decay and improved position resolution.
QQQ: Quality Quattuor-Bit Quantization for Large Language Models
Quantization is a proven effective method for compressing large language models.
Quantum Implicit Neural Representations
In this paper, we propose Quantum Implicit Representation Network (QIREN), a novel quantum generalization of FNNs.
Decision-focused Graph Neural Networks for Combinatorial Optimization
In recent years, there has been notable interest in investigating combinatorial optimization (CO) problems by neural-based framework.
Combinatorial Optimization with Automated Graph Neural Networks
The idea of AutoGNP is to use graph neural architecture search algorithms to automatically find the best GNNs for a given NP-hard combinatorial optimization problem.
On Hardware-efficient Inference in Probabilistic Circuits
Hence, hardware-efficient computation of PCs is highly interesting for edge computing applications.
Joint Precoding for RIS-Assisted Wideband THz Cell-Free Massive MIMO Systems
After that, with knowledge of the optimal TDs of APs, we decouple the optimization problem into three subproblems of optimizing the baseband beamformers, RISs and TDs of RISs, respectively.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.
Dynamical Mode Recognition of Coupled Flame Oscillators by Supervised and Unsupervised Learning Approaches
Combustion instability in gas turbines and rocket engines, as one of the most challenging problems in combustion research, arises from the complex interactions among flames, which are also influenced by chemical reactions, heat and mass transfer, and acoustics.
PuLID: Pure and Lightning ID Customization via Contrastive Alignment
We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation.
MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering
To address this challenge, the approach of Table Question Answering (QA) has been developed to extract the relevant information.
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning
Recent methods try to alleviate the CF problem by modifying models or replaying data, which may only remember the surface-level pattern of instructions and get confused on held-out tasks.
Refining Segmentation On-the-Fly: An Interactive Framework for Point Cloud Semantic Segmentation
This paper concentrates on an unexplored yet meaningful task, i. e., interactive point cloud semantic segmentation, which assigns high-quality semantic labels to all points in a scene with user corrective clicks.
Learning Expressive And Generalizable Motion Features For Face Forgery Detection
However, current sequence-based face forgery detection methods use general video classification networks directly, which discard the special and discriminative motion information for face manipulation detection.
On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns.
Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization
Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks.
DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction
Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions.
VN Network: Embedding Newly Emerging Entities with Virtual Neighbors
To address this issue, recent works apply the graph neural network on the existing neighbors of the unseen entities.
HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
In recent years, temporal knowledge graph (TKG) reasoning has received significant attention.
Frequency-aware Graph Signal Processing for Collaborative Filtering
Graph Signal Processing (GSP) based recommendation algorithms have recently attracted lots of attention due to its high efficiency.
APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding
The massive adoption of large language models (LLMs) demands efficient deployment strategies.
Re-evaluating the Memory-balanced Pipeline Parallelism: BPipe
Pipeline parallelism is an essential technique in the training of large-scale Transformer models.
Rapid Open-World Adaptation by Adaptation Principles Learning
This is an important characteristic of intelligent agents, as it allows them to continue to function effectively in novel or unexpected situations, but still stands as a critical challenge for deep reinforcement learning (DRL).
Heterogeneous Graph Neural Architecture Search with GPT-4
The basic idea of GHGNAS is to design a set of prompts that can guide GPT-4 toward the task of generating new heterogeneous graph neural architectures.
MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing
This enhances masked-based editing in local areas; second, we present a novel distillation strategy: Conditional Distillation on Geometry and Texture (CDGT).
Resilience-Assuring Hydrogen-Powered Microgrids
Green hydrogen has shown great potential to power microgrids as a primary source, yet the operation methodology under extreme events is still an open area.
Dimensionality Reduction and Dynamical Mode Recognition of Circular Arrays of Flame Oscillators Using Deep Neural Network
Oscillatory combustion in aero engines and modern gas turbines often has significant adverse effects on their operation, and accurately recognizing various oscillation modes is the prerequisite for understanding and controlling combustion instability.
VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior
Audio-driven talking head generation has drawn much attention in recent years, and many efforts have been made in lip-sync, expressive facial expressions, natural head pose generation, and high video quality.
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
Character Animation aims to generating character videos from still images through driving signals.
Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks
Large Language Models (LLMs) have demonstrated considerable advances, and several claims have been made about their exceeding human performance.
Software-Defined Virtual Synchronous Condenser
Synchronous condensers (SCs) play important roles in integrating wind energy into relatively weak power grids.
A Comprehensive Summarization and Evaluation of Feature Refinement Modules for CTR Prediction
In addition, we present a new architecture of assigning independent FR modules to separate sub-networks for parallel CTR models, as opposed to the conventional method of inserting a shared FR module on top of the embedding layer.
Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction
It is crucial to effectively model feature interactions to improve the prediction performance of CTR models.
Ranked #3 on
Click-Through Rate Prediction
on Criteo
Mid-Long Term Daily Electricity Consumption Forecasting Based on Piecewise Linear Regression and Dilated Causal CNN
This study decomposes the daily electricity consumption series into three components: trend, seasonal, and residual, and constructs a two-stage prediction method using piecewise linear regression as a filter and Dilated Causal CNN as a predictor.
Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
We discovered that most models are essentially misaligned, necessitating further ethical value alignment.
MuseChat: A Conversational Music Recommendation System for Videos
The reasoning module, equipped with the power of Large Language Model (Vicuna-7B) and extended to multi-modal inputs, is able to provide reasonable explanation for the recommended music.
Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering
In recent years, there has been a growing emphasis on the intersection of audio, vision, and text modalities, driving forward the advancements in multimodal research.
Early Warning Prediction with Automatic Labeling in Epilepsy Patients
Early warning for epilepsy patients is crucial for their safety and well-being, in particular to prevent or minimize the severity of seizures.
Graph Neural Architecture Search with GPT-4
In this paper, we integrate GPT-4 into GNAS and propose a new GPT-4 based Graph Neural Architecture Search method (GPT4GNAS for short).
Physics-Informed Induction Machine Modelling
This rapid communication devises a Neural Induction Machine (NeuIM) model, which pilots the use of physics-informed machine learning to enable AI-based electromagnetic transient simulations.
Physics-Aware Neural Dynamic Equivalence of Power Systems
The contributions are threefold: (1) an ODE-Net-enabled NeuDyE formulation to enable a continuous-time, data-driven dynamic equivalence of power systems; (2) a physics-informed NeuDyE learning method (PI-NeuDyE) to actively control the closed-loop accuracy of NeuDyE without an additional verification module; (3) a physics-guided NeuDyE (PG-NeuDyE) to enhance the method's applicability even in the absence of analytical physics models.
Scalable Neural Dynamic Equivalence for Power Systems
Traditional grid analytics are model-based, relying strongly on accurate models of power systems, especially the dynamic models of generators, controllers, loads and other dynamic components.
3D Multiple Object Tracking on Autonomous Driving: A Literature Review
This paper undertakes a comprehensive examination, assessment, and synthesis of the research landscape in this domain, remaining attuned to the latest developments in 3D MOT while suggesting prospective avenues for future investigation.
UGC: Unified GAN Compression for Efficient Image-to-Image Translation
Recent years have witnessed the prevailing progress of Generative Adversarial Networks (GANs) in image-to-image translation.
UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection
While many approaches have crafted task-specific training paradigms for either video saliency prediction or video salient object detection tasks, few attention has been devoted to devising a generalized saliency modeling framework that seamlessly bridges both these distinct tasks.
Segment Anything Model for Brain Tumor Segmentation
Glioma is a prevalent brain tumor that poses a significant health risk to individuals.
RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents
The rapid evolution of the web has led to an exponential growth in content.
Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning
Different from existing methods which integrate multiple-granularity features or multiple outputs, we resort to the perspective of representation learning in which auxiliary tasks are utilized to enable the encoder to jointly learn robust features with the main task of per-pixel classification during optimization.
AutoSeqRec: Autoencoder for Efficient Sequential Recommendation
Sequential recommendation demonstrates the capability to recommend items by modeling the sequential behavior of users.
Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization
By decoupling the gradients of visual and audio modalities, the discriminative visual representations of sound sources can be learned with the designed Induction Vector in a bootstrap manner, which also enables the audio modality to be aligned with the visual modality consistently.
Recommendation Unlearning via Matrix Correction
We conducted comprehensive experiments to validate the effectiveness of IMCorrect and the results demonstrate that IMCorrect is superior in completeness, utility, and efficiency, and is applicable in many recommendation unlearning scenarios.
Improving Semi-Supervised Semantic Segmentation with Dual-Level Siamese Structure Network
Semi-supervised semantic segmentation (SSS) is an important task that utilizes both labeled and unlabeled data to reduce expenses on labeling training examples.
Entropy Neural Estimation for Graph Contrastive Learning
In this paper, we theoretically illustrate that the entropy of a dataset can be approximated by maximizing the lower bound of the mutual information across different views of a graph, \ie, entropy is estimated by a neural network.
Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs.
Learning Stochastic Dynamical Systems as an Implicit Regularization with Graph Neural Networks
To that end, the observed randomness and spatial-correlations are captured by learning the drift and diffusion terms of the stochastic differential equation with a Gumble matrix embedding, respectively.
FTFDNet: Learning to Detect Talking Face Video Manipulation with Tri-Modality Interaction
DeepFake based digital facial forgery is threatening public media security, especially when lip manipulation has been used in talking face generation, and the difficulty of fake video detection is further improved.
VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering
We present Visual Knowledge oriented Programming platform (VisKoP), a knowledge base question answering (KBQA) system that integrates human into the loop to edit and debug the knowledge base (KB) queries.
MachMap: End-to-End Vectorized Solution for Compact HD-Map Construction
This report introduces the 1st place winning solution for the Autonomous Driving Challenge 2023 - Online HD-map Construction.
WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences
We present WebGLM, a web-enhanced question-answering system based on the General Language Model (GLM).
Deep learning radiomics for assessment of gastroesophageal varices in people with compensated advanced chronic liver disease
Validation analysis revealed that the AUCs of DLRP were 0. 91 for GEV (95% CI 0. 90 to 0. 93, p < 0. 05) and 0. 88 for HRV (95% CI 0. 86 to 0. 89, p < 0. 01), which were significantly and robustly better than canonical risk indicators, including the value of LSM and SSM.
Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation Method
To address these problems, we propose a general language model distillation (GLMD) method that performs two-stage word prediction distillation and vocabulary compression, which is simple and surprisingly shows extremely strong performance.
GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model
Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices.
Revisiting Acceptability Judgements
We introduce CoLAC - Corpus of Linguistic Acceptability in Chinese, the first large-scale acceptability dataset for a non-Indo-European language.
Binary stochasticity enabled highly efficient neuromorphic deep learning achieves better-than-software accuracy
We propose a binary stochastic learning algorithm that modifies all elementary neural network operations, by introducing (i) stochastic binarization of both the forwarding signals and the activation function derivatives, (ii) signed binarization of the backpropagating errors, and (iii) step-wised weight updates.
Triple Structural Information Modelling for Accurate, Explainable and Interactive Recommendation
Specifically, TriSIM4Rec consists of 1) a dynamic ideal low-pass graph filter to dynamically mine co-occurrence information in user-item interactions, which is implemented by incremental singular value decomposition (SVD); 2) a parameter-free attention module to capture sequential information of user interactions effectively and efficiently; and 3) an item transition matrix to store the transition probabilities of item pairs.
A Measurement-Based Quantum-Like Language Model for Text Matching
We take the word density matrix in one sentence as a set of measurement operators to measure another sentence, which is consistent with the definition of measurement operators in quantum theory and has a specific semantic interpretation.
CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective
Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain.
NovPhy: A Testbed for Physical Reasoning in Open-world Environments
But is it enough to only have physical reasoning capabilities to operate in a real physical environment?
A network-based biomarkers discovery of Cold/Hot ZHENG chronic gastritis and Cold/Hot herbs of formulae
And we collected 25 formulae (with traditional effects related to Cold/Hot ZHENG) for CG and corresponding 89 Cold/Hot herbs (including Warm/Cool herbs) to discover features and construct target networks of Cold/Hot herbs on the basis of network target and enrichment analysis.
Personalized Graph Signal Processing for Collaborative Filtering
However, the interaction signal may not be sufficient to accurately characterize user interests and the low-pass filters may ignore the useful information contained in the high-frequency component of the observed signals, resulting in suboptimal accuracy.
ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing
Specifically, in Phase I, a W-space-oriented StyleGAN inversion network is trained and used to perform image inversion and editing, which assures the editability but sacrifices reconstruction quality.
Model Based Reinforcement Learning with Non-Gaussian Environment Dynamics and its Application to Portfolio Optimization
With the fast development of quantitative portfolio optimization in financial engineering, lots of AI-based algorithmic trading strategies have demonstrated promising results, among which reinforcement learning begins to manifest competitive advantages.
GIPA: A General Information Propagation Algorithm for Graph Learning
Specifically, the bit-wise correlation calculates the element-wise attention weight through a multi-layer perceptron (MLP) based on the dense representations of two nodes and their edge; The feature-wise correlation is based on the one-hot representations of node attribute features for feature selection.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective
Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain.
A Sequential Flow Control Framework for Multi-hop Knowledge Base Question Answering
One of the key challenges of knowledge base question answering (KBQA) is the multi-hop reasoning.
CL4CTR: A Contrastive Learning Framework for CTR Prediction
Many Click-Through Rate (CTR) prediction works focused on designing advanced architectures to model complex feature interactions but neglected the importance of feature representation learning, e. g., adopting a plain embedding layer for each feature, which results in sub-optimal feature representations and thus inferior CTR prediction performance.
Recovering Fine Details for Neural Implicit Surface Reconstruction
Recent works on implicit neural representations have made significant strides.
AS-PD: An Arbitrary-Size Downsampling Framework for Point Clouds
Given an input point cloud of arbitrary size, we first perform a task-agnostic pre-sampling on the input point cloud to a specified sample size.
Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotations
Secondly, the WHCN takes the hypergraph as input and learns to predict high-precision point-level pseudo labels by label propagation.
Knowing the Past to Predict the Future: Reinforcement Virtual Learning
Reinforcement Learning (RL)-based control system has received considerable attention in recent decades.
MorphTE: Injecting Morphology in Tensorized Embeddings
In the era of deep learning, word embeddings are essential when dealing with text tasks.
Parameter-free Dynamic Graph Embedding for Link Prediction
Dynamic interaction graphs have been widely adopted to model the evolution of user-item interactions over time.
DART: Articulated Hand Model with Diverse Accessories and Rich Textures
Unity GUI is also provided to generate synthetic hand data with user-defined settings, e. g., pose, camera, background, lighting, textures, and accessories.
Multi-Scale Wavelet Transformer for Face Forgery Detection
To overcome these limitations, we propose a multi-scale wavelet transformer framework for face forgery detection.
GLM-130B: An Open Bilingual Pre-trained Model
We introduce GLM-130B, a bilingual (English and Chinese) pre-trained language model with 130 billion parameters.
Ranked #1 on
Language Modelling
on CLUE (OCNLI_50K)
Enhanced Secure Wireless Transmission Using IRS-aided Directional Modulation
To reduce the computational complexity, a new method of maximizing receive power with zero-forcing constraint (Max-RP-ZFC) of only reflecting CM and no AN is proposed.
Multi-frequency PolSAR Image Fusion Classification Based on Semantic Interactive Information and Topological Structure
Finally, an adaptive weighting fusion (AWF) strategy is proposed to merge inference from different bands, so as to make the MF joint classification decisions of SIC and TPC.
Neuro-Dynamic State Estimation for Networked Microgrids
We devise neuro-dynamic state estimation (Neuro-DSE), a learning-based dynamic state estimation (DSE) algorithm for networked microgrids (NMs) under unknown subsystems.
AMinerGNN: Heterogeneous Graph Neural Network for Paper Click-through Rate Prediction with Fusion Query
Paper recommendation with user-generated keyword is to suggest papers that simultaneously meet user's interests and are relevant to the input keyword.
Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs
Inductive link prediction for knowledge graph aims at predicting missing links between unseen entities, those not shown in training stage.
Measuring Difficulty of Novelty Reaction
In this paper, we propose to define the novelty reaction difficulty as a relative difficulty of performing the known task after the introduction of the novelty.
TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents
Most existing methods divide this task into two subparts: the text reading part for obtaining the plain text from the original document images and the information extraction part for extracting key contents.
A Framework Based on Generational and Environmental Response Strategies for Dynamic Multi-objective Optimization
In this paper, a novel framework based on generational and environmental response strategies (FGERS) is proposed, in which response strategies are run both in the environmental change stage and the environmental static stage to obtain population evolution information of those both stages.
Resilience in Industrial Internet of Things Systems: A Communication Perspective
Industrial Internet of Things is an ultra-large-scale system that is much more sophisticated and fragile than conventional industrial platforms.
Measurement of carbon finance level and exploration of its influencing factors
Faced with increasingly severe environmental problems, carbon trading markets and related financial activities aiming at limiting carbon dioxide emissions are booming.
Stock Trading Optimization through Model-based Reinforcement Learning with Resistance Support Relative Strength
Reinforcement learning (RL) is gaining attention by more and more researchers in quantitative finance as the agent-environment interaction framework is aligned with decision making process in many business problems.
AI-aided multiscale modeling of physiologically-significant blood clots
We have developed an AI-aided multiple time stepping (AI-MTS) algorithm and multiscale modeling framework (AI-MSM) and implemented them on the Summit-like supercomputer, AIMOS.
Rapid Phase Ambiguity Elimination Methods for DOA Estimator via Hybrid Massive MIMO Receive Array
In the proposed Max-RP-QI, a quadratic interpolation scheme is adopted to interpolate the three DOA values corresponding to the largest three receive powers of Max-RP.
Enhancing CTR Prediction with Context-Aware Feature Representation Learning
However, most methods only learn a fixed representation for each feature without considering the varying importance of each feature under different contexts, resulting in inferior performance.
A Multi-Metric Latent Factor Model for Analyzing High-Dimensional and Sparse data
High-dimensional and sparse (HiDS) matrices are omnipresent in a variety of big data-related applications.
Personalized Image Aesthetics Assessment with Rich Attributes
To solve the dilemma, we conduct so far, the most comprehensive subjective study of personalized image aesthetics and introduce a new Personalized image Aesthetics database with Rich Attributes (PARA), which consists of 31, 220 images with annotations by 438 subjects.
An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection
DeepFake based digital facial forgery is threatening the public media security, especially when lip manipulation has been used in talking face generation, the difficulty of fake video detection is further improved.
Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild
Rather than focusing on the unimportant regions of the face image, the proposed AttnWav2Lip model is able to pay more attention on the lip region reconstruction.
Audio-visual speech separation based on joint feature representation with cross-modal attention
Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments.
Look\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement
Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding.
Absolute Zero-Shot Learning
Considering the increasing concerns about data copyright and privacy issues, we present a novel Absolute Zero-Shot Learning (AZSL) paradigm, i. e., training a classifier with zero real data.
Learning Multiple Explainable and Generalizable Cues for Face Anti-spoofing
However, many other generalizable cues are unexplored for face anti-spoofing, which limits their performance under cross-dataset testing.
AD-NEGF: An End-to-End Differentiable Quantum Transport Simulator for Sensitivity Analysis and Inverse Problems
Since proposed in the 70s, the Non-Equilibrium Green Function (NEGF) method has been recognized as a standard approach to quantum transport simulations.
Signal Shaping for Semantic Communication Systems with A Few Message Candidates
Semantic communications target to reliably convey the semantic meaning of messages.
An Intelligent Self-driving Truck System For Highway Transportation
Recently, there have been many advances in autonomous driving society, attracting a lot of attention from academia and industry.
MSHT: Multi-stage Hybrid Transformer for the ROSE Image Analysis of Pancreatic Cancer
Pancreatic cancer is one of the most malignant cancers in the world, which deteriorates rapidly with very high mortality.
Automated assessment of disease severity of COVID-19 using artificial intelligence with synthetic chest CT
Correlations between imaging findings and clinical lab tests suggested the value of this system as a potential tool to assess disease severity of COVID-19.
Prior Attention Network for Multi-Lesion Segmentation in Medical Images
The proposed network can be regarded as a universal solution to multi-lesion segmentation in both 2D and 3D tasks.
Modeling Variable Space with Residual Tensor Networks for Multivariate Time Series
In this framework, we derive the mathematical representation of the variable space, and then use a tensor network based on the idea of low-rank approximation to model the variable space.
DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing
To address these limitations, we design a Dynamic Style Manipulation Network (DyStyle) whose structure and parameters vary by input samples, to perform nonlinear and adaptive manipulation of latent codes for flexible and precise attribute control.
Phy-Q as a measure for physical reasoning intelligence
Inspired by how human IQ is calculated, we define the physical reasoning quotient (Phy-Q score) that reflects the physical reasoning intelligence of an agent using the physical scenarios we considered.
Graph Contrastive Learning for Anomaly Detection
To achieve the contrastive objective, we design a graph neural network encoder that can infer and further remove suspicious links during message passing, as well as learn the global context of the input graph.
Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking
To solve this problem, we propose to distill representations of the TIR modality from the RGB modality with Cross-Modal Distillation (CMD) on a large amount of unlabeled paired RGB-TIR data.
Hi-Phy: A Benchmark for Hierarchical Physical Reasoning
In this paper, we propose a new benchmark for physical reasoning that allows us to test individual physical reasoning capabilities.
WASE: Learning When to Attend for Speaker Extraction in Cocktail Party Environments
In the speaker extraction problem, it is found that additional information from the target speaker contributes to the tracking and extraction of the target speaker, which includes voiceprint, lip movement, facial expression, and spatial information.
Path-based Deep Network for Candidate Item Matching in Recommenders
PDN utilizes Trigger Net to capture the user's interest in each of his/her interacted item, and Similarity Net to evaluate the similarity between each interacted item and the target item based on these items' profile and CF information.
GIPA: General Information Propagation Algorithm for Graph Learning
Graph neural networks (GNNs) have been popularly used in analyzing graph-structured data, showing promising results in various applications such as node classification, link prediction and network recommendation.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations
To address the above limitations, we propose a unified framework VSR for document layout analysis, combining vision, semantics and relations.
Ranked #3 on
Document Layout Analysis
on PubLayNet val
LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment
In this paper, we aim to obtain more reliable aligned bounding boxes by fully utilizing the visual information from both text regions in proposed local features and cell relations in global features.
Ranked #8 on
Table Recognition
on PubTabNet
A Feature Fusion-Net Using Deep Spatial Context Encoder and Nonstationary Joint Statistical Model for High Resolution SAR Image Classification
To address this problem, a novel end-to-end supervised classification method is proposed for HR SAR images by considering both spatial context and statistical features.
GraphTheta: A Distributed Graph Neural Network Learning System With Flexible Training Strategy
Herein, we present GraphTheta, the first distributed and scalable graph learning system built upon vertex-centric distributed graph processing with neural network operators implemented as user-defined functions.
Noise-Resilient Quantum Machine Learning for Stability Assessment of Power Systems
Transient stability assessment (TSA) is a cornerstone for resilient operations of today's interconnected power grids.
Learning Position and Target Consistency for Memory-based Video Object Segmentation
To address this limitation, we propose to Learn position and target Consistency framework for Memory-based video object segmentation, termed as LCM.
A review of artificial intelligence methods combined with Raman spectroscopy to identify the composition of substances
This review summarizes the work of Raman spectroscopy in identifying the composition of substances and reviews the preprocessing process of Raman spectroscopy, the analysis methods and applications of artificial intelligence.
OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Services
Academic knowledge services have substantially facilitated the development of the science enterprise by providing a plenitude of efficient research tools.
CogDL: A Comprehensive Library for Graph Deep Learning
In CogDL, we propose a unified design for the training and evaluation of GNN models for various graph tasks, making it unique among existing graph learning libraries.
D2A U-Net: Automatic Segmentation of COVID-19 Lesions from CT Slices with Dilated Convolution and Dual Attention Mechanism
In this paper we propose a dilated dual attention U-Net (D2A U-Net) for COVID-19 lesion segmentation in CT slices based on dilated convolution and a novel dual attention mechanism to address the issues above.
Neuro-Reachability of Networked Microgrids
A neural ordinary differential equations network (ODE-Net)-enabled reachability method (Neuro-Reachability) is devised for the dynamic verification of networked microgrids (NMs) with unidentified subsystems and heterogeneous uncertainties.
TextTN: Probabilistic Encoding of Language on Tensor Network
As a novel model that bridges machine learning and quantum theory, tensor network (TN) has recently gained increasing attention and successful applications for processing natural images.
Understanding and Leveraging Causal Relations in Deep Reinforcement Learning
Reinforcement Learning (RL) has shown great potential to deal with sequential decision-making problems.
Fluctuations in crystalline plasticity
We link this new size effect with other related phenomena like size dependence of strength ("smaller is stronger") and the size induced switch between different hardening mechanisms.
Mesoscale and Nanoscale Physics Materials Science Statistical Mechanics Computational Physics
Residual Matrix Product State for Machine Learning
Tensor network, which originates from quantum physics, is emerging as an efficient tool for classical and quantum machine learning.
