Search Results for author:
Found 78 papers, 39 papers with code
PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terrain
Self-supervised learning is a powerful approach for developing traversability models for off-road navigation, but these models often struggle with inputs unseen during training.
VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video.
An Asymptotically Optimal Coordinate Descent Algorithm for Learning Bayesian Networks from Gaussian Models
To the best of our knowledge, our proposal is the first coordinate descent procedure endowed with optimality and statistical guarantees in the context of learning Bayesian networks.
Robust Deep Reinforcement Learning for Inverter-based Volt-Var Control in Partially Observable Distribution Networks
To address those problems, this paper proposes a robust DRL approach with a conservative critic and a surrogate reward.
Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
Specifically, the whole VNE process is decomposed into an upper-level policy for deciding whether to admit the arriving VNR or not and a lower-level policy for allocating resources of the physical network to meet the requirement of VNR through the HRL approach.
FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models
Large language models (LLMs) excel in generating coherent text, but they often struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information.
Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation
Despite the significant progress of large language models (LLMs) in various tasks, they often produce factual errors due to their limited internal knowledge.
In-Context Former: Lightning-fast Compressing Context for Large Language Model
With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus.
When Box Meets Graph Neural Network in Tag-aware Recommendation
Last year has witnessed the re-flourishment of tag-aware recommender systems supported by the LLM-enriched tags.
From a Social Cognitive Perspective: Context-aware Visual Social Relationship Recognition
People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e. g., wedding rings, roses, hugs, or holding hands.
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
With Video-MME, we extensively evaluate various state-of-the-art MLLMs, including GPT-4 series and Gemini 1. 5 Pro, as well as open-source image models like InternVL-Chat-V1. 5 and video models like LLaVA-NeXT-Video.
NoteLLM-2: Multimodal Large Representation Models for Recommendation
We propose two ways to enhance the focus on visual information.
Knowledge Graph Pruning for Recommendation
Recent years have witnessed the prosperity of knowledge graph based recommendation system (KGRS), which enriches the representation of users, items, and entities by structural knowledge with striking improvement.
DynLLM: When Large Language Models Meet Dynamic Graph Recommendation
To bridge this gap, in this paper, we propose a novel framework, called DynLLM, to deal with the dynamic graph recommendation task with LLMs.
Integer Programming for Learning Directed Acyclic Graphs from Non-identifiable Gaussian Models
We study the problem of learning directed acyclic graphs from continuous observational data, generated according to a linear Gaussian structural equation model.
Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models
Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs) by making predictions for missing links.
NoteLLM: A Retrievable Large Language Model for Note Recommendation
Indeed, learning to generate hashtags/categories can potentially enhance note embeddings, both of which compress key note information into limited content.
Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
To evaluate the editing impact on the behaviours of LLMs, we propose two model editing studies for medical domain: (1) editing factual knowledge for medical specialization and (2) editing the explanatory ability for complex knowledge.
CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
For each of these CRUD categories, we have developed comprehensive datasets to evaluate the performance of RAG systems.
Communication-Efficient Personalized Federated Learning for Speech-to-Text Tasks
To protect privacy and meet legal regulations, federated learning (FL) has gained significant attention for training speech-to-text (S2T) systems, including automatic speech recognition (ASR) and speech translation (ST).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Large Language Models for Generative Information Extraction: A Survey
Information extraction (IE) aims to extract structural knowledge (such as entities, relations, and events) from plain natural language texts.
Large Language Model based Long-tail Query Rewriting in Taobao Search
In the realm of e-commerce search, the significance of semantic matching cannot be overstated, as it directly impacts both user experience and company revenue.
Woodpecker: Hallucination Correction for Multimodal Large Language Models
Hallucination is a big shadow hanging over the rapidly evolving Multimodal Large Language Models (MLLMs), referring to the phenomenon that the generated text is inconsistent with the image content.
HEProto: A Hierarchical Enhancing ProtoNet based on Multi-Task Learning for Few-shot Named Entity Recognition
Great efforts have been made on this task with competitive performance, however, they usually treat the two subtasks, namely span detection and type classification, as mutually independent, and the integrity and correlation between subtasks have been largely ignored.
Ranked #3 on
Few-shot NER
on Few-NERD (INTER)
CgT-GAN: CLIP-guided Text GAN for Image Captioning
Particularly, we use adversarial training to teach CgT-GAN to mimic the phrases of an external text corpus and CLIP-based reward to provide semantic guidance.
Multi-Grained Multimodal Interaction Network for Entity Linking
Then, to derive the similarity matching score for each mention-entity pair, we device three interaction units to comprehensively explore the intra-modal interaction and inter-modal fusion among features of entities and mentions.
A Solution to CVPR'2023 AQTC Challenge: Video Alignment for Multi-Step Inference
In this paper, we present a solution for enhancing video alignment to improve multi-step inference.
A Survey on Multimodal Large Language Models
Recently, Multimodal Large Language Model (MLLM) represented by GPT-4V has been a new rising research hotspot, which uses powerful Large Language Models (LLMs) as a brain to perform multimodal tasks.
Spatial Heterophily Aware Graph Neural Networks
However, urban graphs usually can be observed to possess a unique spatial heterophily property; that is, the dissimilarity of neighbors at different spatial distances can exhibit great diversity.
Multi-Temporal Relationship Inference in Urban Areas
Specifically, we propose a solution to Trial with a graph learning scheme, which includes a spatially evolving graph neural network (SEENet) with two collaborative components: spatially evolving graph convolution module (SEConv) and spatially evolving self-supervised learning strategy (SE-SSL).
Reversible Graph Neural Network-based Reaction Distribution Learning for Multiple Appropriate Facial Reactions Generation
This means that we approach this problem by considering the generation of a distribution of the listener's appropriate facial reactions instead of multiple different appropriate facial reactions, i. e., 'many' appropriate facial reaction labels are summarised as 'one' distribution label during training.
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark
Companies have begun to offer Embedding as a Service (EaaS) based on these LLMs, which can benefit various natural language processing (NLP) tasks for customers.
AU-aware graph convolutional network for Macro- and Micro-expression spotting
Automatic Micro-Expression (ME) spotting in long videos is a crucial step in ME analysis but also a challenging task due to the short duration and low intensity of MEs.
Simple and Scalable Nearest Neighbor Machine Translation
$k$NN-MT is a straightforward yet powerful approach for fast domain adaptation, which directly plugs pre-trained neural machine translation (NMT) models with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining.
Federated Nearest Neighbor Machine Translation
To protect user privacy and meet legal regulations, federated learning (FL) is attracting significant attention.
DAFD: Domain Adaptation via Feature Disentanglement for Image Classification
This so-called domain shift leads to a significant performance drop in image classification.
Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach
Although remarkable progress on the neural table-to-text methods has been made, the generalization issues hinder the applicability of these models due to the limited source tables.
More is Better: A Database for Spontaneous Micro-Expression with High Frame Rates
To solve the problem of ME data hunger, we construct a dynamic spontaneous ME dataset with the largest current ME data scale, called DFME (Dynamic Facial Micro-expressions), which includes 7, 526 well-labeled ME videos induced by 671 participants and annotated by more than 20 annotators throughout three years.
Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks
A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators.
A Contextual Master-Slave Framework on Urban Region Graph for Urban Village Detection
The core idea of such a framework is to firstly pre-train a basis (or master) model over the URG, and then to adaptively derive specific (or slave) models from the basis model for different regions.
BATT: Backdoor Attack with Transformation-based Triggers
The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoors that can be activated by adversary-specified trigger patterns during the training process.
Faithful Abstractive Summarization via Fact-aware Consistency-constrained Transformer
To deal with this challenge, in this paper, we propose a novel fact-aware abstractive summarization model, named Entity-Relation Pointer Generator Network (ERPGN).
Multi-modal Siamese Network for Entity Alignment
To deal with that problem, in this paper, we propose a novel Multi-modal Siamese Network for Entity Alignment (MSNEA) to align entities in different MMKGs, in which multi-modal knowledge could be comprehensively leveraged by the exploitation of inter-modal effect.
Ranked #7 on
Multi-modal Entity Alignment
on UMVM-oea-d-w-v1
(using extra training data)
Joint Attention-Driven Domain Fusion and Noise-Tolerant Learning for Multi-Source Domain Adaptation
As a study on the efficient usage of data, Multi-source Unsupervised Domain Adaptation transfers knowledge from multiple source domains with labeled data to an unlabeled target domain.
Multi-Source Unsupervised Domain Adaptation
Unsupervised Domain Adaptation
Efficient Inference of Spatially-varying Gaussian Markov Random Fields with Applications in Gene Regulatory Networks
In this paper, we study the problem of inferring spatially-varying Gaussian Markov random fields (SV-GMRF) where the goal is to learn a network of sparse, context-specific GMRFs representing network relationships between genes.
Winning the CVPR'2022 AQTC Challenge: A Two-stage Function-centric Approach
Affordance-centric Question-driven Task Completion for Egocentric Assistant(AQTC) is a novel task which helps AI assistant learn from instructional videos and scripts and guide the user step-by-step.
FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning
In order to learn a fair unified representation, we send it to each platform storing fairness-sensitive features and apply adversarial learning to remove bias from the unified representation inherited from the biased data.
Non-Parametric Domain Adaptation for End-to-End Speech Translation
End-to-End Speech Translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency, and fewer parameters.
Attention in Attention: Modeling Context Correlation for Efficient Video Classification
Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts.
AutoField: Automating Feature Selection in Deep Recommender Systems
Thereby, feature selection is a critical process in developing deep learning-based recommender systems.
Domain-Invariant Proposals based on a Balanced Domain Classifier for Object Detection
We embed a domain classification network in the region proposal network~(RPN) using adversarial learning.
Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement
In this paper, we attempt to model the joint probability of transcription and translation based on the speech input to directly leverage such triplet data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
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.
GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction
Though graph contrastive learning (GCL) methods have achieved extraordinary performance with insufficient labeled data, most focused on designing data augmentation schemes for general graphs.
Adversarial Neural Trip Recommendation
To that end, we propose an Adversarial Neural Trip Recommendation (ANT) framework to tackle the above challenges.
Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity
To this end, we propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool).
Ranked #3 on
Protein-Ligand Affinity Prediction
on PDBbind
Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning
Electric Vehicle (EV) has become a preferable choice in the modern transportation system due to its environmental and energy sustainability.
Multi-agent Reinforcement Learning
Multi-Objective Multi-Agent Reinforcement Learning
+2
Drug Package Recommendation via Interaction-aware Graph Induction
Then, the drug interaction graph will be initialized based on medical records and domain knowledge.
Out-of-Town Recommendation with Travel Intention Modeling
Second, a user-specific travel intention is formulated as an aggregation combining home-town preference and generic travel intention together, where the generic travel intention is regarded as a mixture of inherent intentions that can be learned by Neural Topic Model (NTM).
Inheritance-guided Hierarchical Assignment for Clinical Automatic Diagnosis
Clinical diagnosis, which aims to assign diagnosis codes for a patient based on the clinical note, plays an essential role in clinical decision-making.
Adam revisited: a weighted past gradients perspective
Though many algorithms, such as AMSGRAD and ADAMNC, have been proposed to fix the non-convergence issues, achieving a data-dependent regret bound similar to or better than ADAGRAD is still a challenge to these methods.
Distance-aware Molecule Graph Attention Network for Drug-Target Binding Affinity Prediction
The hierarchical attentive aggregation can capture spatial dependencies among atoms, as well as fuse the position-enhanced information with the capability of discriminating multiple spatial relations among atoms.
Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation
To improve adaptation efficiency, we learn to recover the user policy and reward from only a few interactions via an inverse reinforcement learning method to assist a meta-level recommendation agent.
Model-based Reinforcement Learning
Recommendation Systems
+2
BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models
Complex node interactions are common in knowledge graphs (KGs), and these interactions can be considered as contextualized knowledge exists in the topological structure of KGs.
MMEA: Entity Alignment for Multi-Modal Knowledge Graphs
To that end, in this paper, we propose a novel solution called Multi-Modal Entity Alignment (MMEA) to address the problem of entity alignment in a multi-modal view.
Data-driven Inverter-based Volt/VAr Control for Partially Observable Distribution Networks
To provide a practical Volt/Var control (VVC) strategy for such networks, a data-driven VVC method is proposed in this paper.
Disentangled Graph Collaborative Filtering
Such uniform approach to model user interests easily results in suboptimal representations, failing to model diverse relationships and disentangle user intents in representations.
Foreground-Background Imbalance Problem in Deep Object Detectors: A Review
Recent years have witnessed the remarkable developments made by deep learning techniques for object detection, a fundamentally challenging problem of computer vision.
Integrating Graph Contextualized Knowledge into Pre-trained Language Models
Complex node interactions are common in knowledge graphs, and these interactions also contain rich knowledge information.
A Machine Learning-enhanced Robust P-Phase Picker for Real-time Seismic Monitoring
To this end, in this paper, we present a machine learning-enhanced framework based on ensemble learning strategy, EL-Picker, for the automatic identification of seismic P-phase arrivals on continuous and massive waveforms.
Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification
Aspect-level sentiment classification is a crucial task for sentiment analysis, which aims to identify the sentiment polarities of specific targets in their context.
Is Heuristic Sampling Necessary in Training Deep Object Detectors?
In this paper, we challenge the necessity of such hard/soft sampling methods for training accurate deep object detectors.
STMARL: A Spatio-Temporal Multi-Agent Reinforcement Learning Approach for Cooperative Traffic Light Control
Moreover, based on the temporally-dependent traffic information, we design a Graph Neural Network based model to represent relationships among multiple traffic lights, and the decision for each traffic light will be made in a distributed way by the deep Q-learning method.
Residual Objectness for Imbalance Reduction
For a long time, object detectors have suffered from extreme imbalance between foregrounds and backgrounds.
Chinese Embedding via Stroke and Glyph Information: A Dual-channel View
Recent studies have consistently given positive hints that morphology is helpful in enriching word embeddings.
MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network
Recently, the Network Representation Learning (NRL) techniques, which represent graph structure via low-dimension vectors to support social-oriented application, have attracted wide attention.
Enhancing Person-Job Fit for Talent Recruitment: An Ability-aware Neural Network Approach
The wide spread use of online recruitment services has led to information explosion in the job market.
Regularizing Neural Machine Translation by Target-bidirectional Agreement
Although Neural Machine Translation (NMT) has achieved remarkable progress in the past several years, most NMT systems still suffer from a fundamental shortcoming as in other sequence generation tasks: errors made early in generation process are fed as inputs to the model and can be quickly amplified, harming subsequent sequence generation.
