Search Results for author:
Found 118 papers, 53 papers with code
Treasures Outside Contexts: Improving Event Detection via Global Statistics
Event detection (ED) aims at identifying event instances of specified types in given texts, which has been formalized as a sequence labeling task.
An End-to-End Real-World Camera Imaging Pipeline
Nevertheless, the real-world imaging pipeline still faces challenges including the lack of joint optimization in system components, computational redundancies, and optical distortions such as lens shading. In light of this, we propose an end-to-end camera imaging pipeline (RealCamNet) to enhance real-world camera imaging performance.
Large Language Models Can Self-Improve in Long-context Reasoning
Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning.
MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition
The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models.
GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration
Graphs are widely used for modeling relational data in real-world scenarios, such as social networks and urban computing.
Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System
Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving, yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective parameter-updating optimization methods.
Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models
Our results underscore that the capabilities of LLMs in handling structured data are still under-explored, and show the effectiveness of LLM4Graph in enhancing LLMs' proficiency of graph analysis.
A Survey on the Honesty of Large Language Models
Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge.
GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
In this paper, we consider making a batch of neural network outputs satisfy bounded and general linear constraints.
Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models
Agents significantly enhance the capabilities of standalone Large Language Models (LLMs) by perceiving environments, making decisions, and executing actions.
Efficient Multi-task Prompt Tuning for Recommendation
A novel two-stage prompt-tuning MTL framework (MPT-Rec) is proposed to address task irrelevance and training efficiency problems in multi-task recommender systems.
Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?
By presenting the empirical results, we find that despite that LLMs can improve the robustness of GNNs, there is still an average decrease of 23. 1% in accuracy, implying that the GNNs remain extremely vulnerable against topology attack.
An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation
Existing work addresses this task through a classification model based on a neural network that maps the hidden vector of the input context into its corresponding label (i. e., the candidate target word is treated as a label).
LSReGen: Large-Scale Regional Generator via Backward Guidance Framework
The third approach depends on phenomena specific to certain model architectures, complicating its application to large-scale image generation. To address these issues, we propose a novel controllable generation framework that offers a generalized interpretation of backward guidance without relying on specific assumptions.
Solving General Natural-Language-Description Optimization Problems with Large Language Models
Optimization problems seek to find the best solution to an objective under a set of constraints, and have been widely investigated in real-world applications.
Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
The rapid advancement of large language models (LLMs) has paved the way for the development of highly capable autonomous agents.
A Pairwise DomMix Attentive Adversarial Network for Unsupervised Domain Adaptive Object Detection
Then a pairwise attentive adversarial network is applied with attentive encoding on both image-level and instance-level features at different scales and optimizes domain alignment by adversarial learning.
CountFormer: Multi-View Crowd Counting Transformer
Multi-view counting (MVC) methods have shown their superiority over single-view counterparts, particularly in situations characterized by heavy occlusion and severe perspective distortions.
ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models
To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH.
Environmental Variation or Instrumental Drift? A Probabilistic Approach to Gas Sensor Drift Modeling and Evaluation
Drift is a significant issue that undermines the reliability of gas sensors.
Data Issues in Industrial AI System: A Meta-Review and Research Strategy
How to address these data issues stands as a significant concern confronting both industry and academia.
Autonomous Agents for Collaborative Task under Information Asymmetry
Together with InfoNav, iAgents organizes human information in a mixed memory to provide agents with accurate and comprehensive information for exchange.
HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing
Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in natural language processing.
ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs).
Multi-Agent Software Development through Cross-Team Collaboration
We anticipate that our work will guide LLM agents towards a cross-team paradigm and contribute to their significant growth in but not limited to software development.
Scaling Large-Language-Model-based Multi-Agent Collaboration
Pioneering advancements in large language model-powered agents have underscored the design pattern of multi-agent collaboration, demonstrating that collective intelligence can surpass the capabilities of each individual.
Non-autoregressive Personalized Bundle Generation
The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation.
Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast
In MoE, each token in the input sequence activates a different subset of experts determined by a routing mechanism.
Online Self-Preferring Language Models
To overcome this limitation, we propose Online Self-Preferring (OSP) language models to learn from self-generated response pairs and self-judged preference strengths.
Iterative Experience Refinement of Software-Developing Agents
We propose two fundamental patterns: the successive pattern, refining based on nearest experiences within a task batch, and the cumulative pattern, acquiring experiences across all previous task batches.
Federated Graph Condensation with Information Bottleneck Principles
However, existing graph condensation methods rely on centralized data storage, which is unfeasible for real-world decentralized data distribution, and overlook data holders' privacy-preserving requirements.
FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization
The F3 are expected to statistically neutralize the sensitive bias in node representations and provide additional nonsensitive information.
BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences
Effective attention modules have played a crucial role in the success of Transformer-based large language models (LLMs), but the quadratic time and memory complexities of these attention modules also pose a challenge when processing long sequences.
Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication
Natural language (NL) has long been the predominant format for human cognition and communication, and by extension, has been similarly pivotal in the development and application of Large Language Models (LLMs).
GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks
Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, especially for open-ended tasks.
AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
Evaluating large language models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications.
AllSpark: A Multimodal Spatio-Temporal General Intelligence Model with Thirteen Modalities
We introduce the Language as Reference Framework (LaRF), a fundamental principle for constructing a multimodal unified model, aiming to strike a trade-off between the cohesion and autonomy among different modalities.
Experiential Co-Learning of Software-Developing Agents
Recent advancements in large language models (LLMs) have brought significant changes to various domains, especially through LLM-driven autonomous agents.
Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization
In this paper, we propose a novel graph invariant learning method based on invariant and variant patterns co-mixup strategy, which is capable of jointly generating mixed multiple environments and capturing invariant patterns from the mixed graph data.
Graph Representation Learning
Out-of-Distribution Generalization
Improving Vision-and-Language Reasoning via Spatial Relations Modeling
Further, we design two pre-training tasks named object position regression (OPR) and spatial relation classification (SRC) to learn to reconstruct the spatial relation graph respectively.
Specialist or Generalist? Instruction Tuning for Specific NLP Tasks
Although instruction tuning has proven to be a data-efficient method for transforming LLMs into such generalist models, their performance still lags behind specialist models trained exclusively for specific tasks.
Towards Graph Foundation Models: A Survey and Beyond
Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and several other domains.
Data-centric Graph Learning: A Survey
Recently, instead of designing more complex neural architectures as model-centric approaches, the attention of AI community has shifted to data-centric ones, which focuses on better processing data to strengthen the ability of neural models.
A Stochastic Online Forecast-and-Optimize Framework for Real-Time Energy Dispatch in Virtual Power Plants under Uncertainty
Aggregating distributed energy resources in power systems significantly increases uncertainties, in particular caused by the fluctuation of renewable energy generation.
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks.
NewsDialogues: Towards Proactive News Grounded Conversation
In this paper, we propose a novel task, Proactive News Grounded Conversation, in which a dialogue system can proactively lead the conversation based on some key topics of the news.
AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models
Information-seeking conversation, which aims to help users gather information through conversation, has achieved great progress in recent years.
Deep Learning-Based Knowledge Injection for Metaphor Detection: A Comprehensive Review
Finally, we explore the current issues facing knowledge injection methods and provide an outlook on future research directions.
Does Correction Remain A Problem For Large Language Models?
As large language models, such as GPT, continue to advance the capabilities of natural language processing (NLP), the question arises: does the problem of correction still persist?
ChatDev: Communicative Agents for Software Development
Numerous studies used deep learning to improve specific phases in a waterfall model, such as design, coding, and testing.
An Efficient Virtual Data Generation Method for Reducing Communication in Federated Learning
Then the server aggregates all the proxy datasets to form a central dummy dataset, which is used to finetune aggregated global model.
Interactive Molecular Discovery with Natural Language
Natural language is expected to be a key medium for various human-machine interactions in the era of large language models.
Question Answering as Programming for Solving Time-Sensitive Questions
Question answering plays a pivotal role in human daily life because it involves our acquisition of knowledge about the world.
Real-World Denoising via Diffusion Model
We introduce a diffusion process with linear interpolation, and the intermediate noisy image is interpolated from the original clean image and the corresponding real-world noisy image, so that this diffusion model can handle the level of added noise.
Tool Learning with Foundation Models
Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools.
Abnormal Event Detection via Hypergraph Contrastive Learning
AEHCL designs the intra-event and inter-event contrastive modules to exploit self-supervised AHIN information.
Graph Mining for Cybersecurity: A Survey
In recent years, with the proliferation of graph mining techniques, many researchers investigated these techniques for capturing correlations between cyber entities and achieving high performance.
Neural Partial Differential Equations with Functional Convolution
We present a lightweighted neural PDE representation to discover the hidden structure and predict the solution of different nonlinear PDEs.
Vision Learners Meet Web Image-Text Pairs
In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data.
A Simple Framework for Text-Supervised Semantic Segmentation
LoDA and SimSeg jointly ameliorate a vanilla CLIP to produce impressive semantic segmentation results.
MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning
We argue that typical data augmentation techniques (e. g., edge dropping) in GCL cannot generate diverse enough contrastive views to filter out noises.
xTrimoABFold: De novo Antibody Structure Prediction without MSA
Its improvement in both accuracy and efficiency makes it a valuable tool for de novo antibody design and could make further improvements in immuno-theory.
GReS: Graphical Cross-domain Recommendation for Supply Chain Platform
Supply Chain Platforms (SCPs) provide downstream industries with numerous raw materials.
KDD CUP 2022 Wind Power Forecasting Team 88VIP Solution
KDD CUP 2022 proposes a time-series forecasting task on spatial dynamic wind power dataset, in which the participants are required to predict the future generation given the historical context factors.
GUIM -- General User and Item Embedding with Mixture of Representation in E-commerce
Our goal is to build general representation (embedding) for each user and each product item across Alibaba's businesses, including Taobao and Tmall which are among the world's biggest e-commerce websites.
Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives
Following SimCSE, contrastive learning based methods have achieved the state-of-the-art (SOTA) performance in learning sentence embeddings.
An Adaptive Contrastive Learning Model for Spike Sorting
But for BCIs used in neuroscience research, it is important to separate out the activity of individual neurons.
Spatial Autoregressive Coding for Graph Neural Recommendation
To adequately leverage neighbor proximity and high-order information, we design a novel spatial autoregressive paradigm.
Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios.
PartImageNet: A Large, High-Quality Dataset of Parts
To help address this problem, we propose PartImageNet, a large, high-quality dataset with part segmentation annotations.
3rd Place Solution to Google Landmark Recognition Competition 2021
In this paper, we show our solution to the Google Landmark Recognition 2021 Competition.
Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration
Specifically, we first verify that the confidence distribution in a graph has homophily property, and this finding inspires us to design a calibration GNN model (CaGCN) to learn the calibration function.
Unfolding Projection-free SDP Relaxation of Binary Graph Classifier via GDPA Linearization
Algorithm unfolding creates an interpretable and parsimonious neural network architecture by implementing each iteration of a model-based algorithm as a neural layer.
Hand Image Understanding via Deep Multi-Task Learning
To further improve the performance of these tasks, we propose a novel Hand Image Understanding (HIU) framework to extract comprehensive information of the hand object from a single RGB image, by jointly considering the relationships between these tasks.
Ranked #19 on
3D Hand Pose Estimation
on FreiHAND
OLR 2021 Challenge: Datasets, Rules and Baselines
In addition to the Language Identification (LID) tasks, multilingual Automatic Speech Recognition (ASR) tasks are introduced to OLR 2021 Challenge for the first time.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Copy and Paste method based on Pose for Re-identification
To solve the aforementioned problem, a simple and effective method to generate images in several new scenarios was proposed, which is names the Copy and Paste method based on Pose(CPP).
Evaluating Modules in Graph Contrastive Learning
The recent emergence of contrastive learning approaches facilitates the application on graph representation learning (GRL), introducing graph contrastive learning (GCL) into the literature.
SAS: Self-Augmentation Strategy for Language Model Pre-training
In this paper, we propose a self-augmentation strategy (SAS) where a single network is utilized for both regular pre-training and contextualized data augmentation for the training in later epochs.
Projection-free Graph-based Classifier Learning using Gershgorin Disc Perfect Alignment
We repose the SDR dual for solution $\bar{\mathbf{H}}$, then replace the PSD cone constraint $\bar{\mathbf{H}} \succeq 0$ with linear constraints derived from GDPA -- sufficient conditions to ensure $\bar{\mathbf{H}}$ is PSD -- so that the optimization becomes an LP per iteration.
Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning
In particular, we decouple the training of the representation and the classifier, and systematically investigate the effects of different data re-sampling techniques when training the whole network including a classifier as well as fine-tuning the feature extractor only.
Markdowns in E-Commerce Fresh Retail: A Counterfactual Prediction and Multi-Period Optimization Approach
In this paper, by leveraging abundant observational transaction data, we propose a novel data-driven and interpretable pricing approach for markdowns, consisting of counterfactual prediction and multi-period price optimization.
Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
Single-image room layout reconstruction aims to reconstruct the enclosed 3D structure of a room from a single image.
TransFG: A Transformer Architecture for Fine-grained Recognition
Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences.
Ranked #4 on
Fine-Grained Image Classification
on CUB-200-2011
Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
Our framework extracts the knowledge of an arbitrary learned GNN model (teacher model), and injects it into a well-designed student model.
Ranked #1 on
Node Classification
on Cora (0.5%)
Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition
In this paper, a retrieval-based coarse-to-fine framework is proposed, where we re-rank the TopN classification results by using the local region enhanced embedding features to improve the Top1 accuracy (based on the observation that the correct category usually resides in TopN results).
Ranked #12 on
Fine-Grained Image Classification
on FGVC Aircraft
Fine-Grained Image Classification
Fine-Grained Image Recognition
+2
Incorporating Vision Bias into Click Models for Image-oriented Search Engine
Most typical click models assume that the probability of a document to be examined by users only depends on position, such as PBM and UBM.
CoRe: An Efficient Coarse-refined Training Framework for BERT
In the second phase, we transform the trained relaxed BERT model into the original BERT and further retrain the model.
Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup
In BERT training, the backward computation is much more time-consuming than the forward computation, especially in the distributed training setting in which the backward computation time further includes the communication time for gradient synchronization.
Nonseparable Symplectic Neural Networks
The enabling mechanics of our approach is an augmented symplectic time integrator to decouple the position and momentum energy terms and facilitate their evolution.
Identification of deep breath while moving forward based on multiple body regions and graph signal analysis
This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera.
Few-shot Knowledge Transfer for Fine-grained Cartoon Face Generation
In this paper, we are interested in generating fine-grained cartoon faces for various groups.
Adaptive Graph Encoder for Attributed Graph Embedding
Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on these tasks.
Ranked #6 on
Node Clustering
on Cora
Graph Neural News Recommendation with Unsupervised Preference Disentanglement
Furthermore, the learned representations are disentangled with latent preference factors by a neighborhood routing algorithm, which can enhance expressiveness and interpretability.
Signed Graph Metric Learning via Gershgorin Disc Perfect Alignment
Given a convex and differentiable objective $Q(\M)$ for a real symmetric matrix $\M$ in the positive definite (PD) cone -- used to compute Mahalanobis distances -- we propose a fast general metric learning framework that is entirely projection-free.
AP20-OLR Challenge: Three Tasks and Their Baselines
Based on Kaldi and Pytorch, recipes for i-vector and x-vector systems are also conducted as baselines for the three tasks.
Fast Network Embedding Enhancement via High Order Proximity Approximation
Many Network Representation Learning (NRL) methods have been proposed to learn vector representations for vertices in a network recently.
KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
Based on the datasets, we propose novel tasks such as multi-hop knowledge abstraction (MKA), multi-hop knowledge concretization (MKC) and then design a comprehensive benchmark.
DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation
Neural Architecture Search (NAS) has shown great potentials in automatically designing scalable network architectures for dense image predictions.
Ranked #13 on
Semantic Segmentation
on Cityscapes test
(using extra training data)
MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
Though recent neural models make prominent progress in some criteria of poetry quality, generated poems still suffer from the problem of poor diversity.
Graph Metric Learning via Gershgorin Disc Alignment
We propose a fast general projection-free metric learning framework, where the minimization objective $\min_{\textbf{M} \in \mathcal{S}} Q(\textbf{M})$ is a convex differentiable function of the metric matrix $\textbf{M}$, and $\textbf{M}$ resides in the set $\mathcal{S}$ of generalized graph Laplacian matrices for connected graphs with positive edge weights and node degrees.
Improving Distantly-Supervised Relation Extraction with Joint Label Embedding
Distantly-supervised relation extraction has proven to be effective to find relational facts from texts.
Graph Neural News Recommendation with Long-term and Short-term Interest Modeling
Existing methods on news recommendation mainly include collaborative filtering methods which rely on direct user-item interactions and content based methods which characterize the content of user reading history.
Improving Sequence Modeling Ability of Recurrent Neural Networks via Sememes
Sememes, the minimum semantic units of human languages, have been successfully utilized in various natural language processing applications.
GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification
Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to verify given claims.
Ranked #7 on
Fact Verification
on FEVER
Jiuge: A Human-Machine Collaborative Chinese Classical Poetry Generation System
By exposing the options of poetry genres, styles and revision modes, Jiuge, acting as a professional assistant, allows constant and active participation of users in poetic creation.
A Unified Framework for Marketing Budget Allocation
In our approach, a semi-black-box model is built to forecast the dynamic market response and an efficient optimization method is proposed to solve the complex allocation task.
COSINE: Compressive Network Embedding on Large-scale Information Networks
There is recently a surge in approaches that learn low-dimensional embeddings of nodes in networks.
Neural Diffusion Model for Microscopic Cascade Prediction
The strong assumptions oversimplify the complex diffusion mechanism and prevent these models from better fitting real-world cascade data.
Social and Information Networks Physics and Society
Graph Neural Networks: A Review of Methods and Applications
Lots of learning tasks require dealing with graph data which contains rich relation information among elements.
CED: Credible Early Detection of Social Media Rumors
By regarding all reposts to a rumor candidate as a sequence, the proposed model will seek an early point-in-time for making a credible prediction.
Social and Information Networks
Stylistic Chinese Poetry Generation via Unsupervised Style Disentanglement
The ability to write diverse poems in different styles under the same poetic imagery is an important characteristic of human poetry writing.
3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model
Due to discrete observations of the patches on the manifold, we approximate the manifold dimension computation defined in the continuous domain with a patch-based graph Laplacian regularizer and propose a new discrete patch distance measure to quantify the similarity between two same-sized surface patches for graph construction that is robust to noise.
Adaptive Recurrent Neural Network Based on Mixture Layer
By leveraging the mixture layer, the proposed method can adaptively update states according to the similarities between encoded inputs and prototype vectors, leading to a stronger capacity in assimilating sequences with multiple patterns.
Learning and Transferring IDs Representation in E-commerce
Many machine intelligence techniques are developed in E-commerce and one of the most essential components is the representation of IDs, including user ID, item ID, product ID, store ID, brand ID, category ID etc.
Network Representation Learning with Rich Text Information
Representation learning has shown its effectiveness in many tasks such as image classification and text mining.
Comprehend DeepWalk as Matrix Factorization
Word2vec, as an efficient tool for learning vector representation of words has shown its effectiveness in many natural language processing tasks.
Real-time Topic-aware Influence Maximization Using Preprocessing
In this paper, we focus on the topic-aware influence maximization task.
