Search Results for author:
Found 91 papers, 37 papers with code
Memetic Search for Green Vehicle Routing Problem with Private Capacitated Refueling Stations
The green vehicle routing problem with private capacitated alternative fuel stations (GVRP-PCAFS) extends the traditional green vehicle routing problem by considering refueling stations limited capacity, where a limited number of vehicles can refuel simultaneously with additional vehicles must wait.
Integrating mobile and fixed monitoring data for high-resolution PM2.5 mapping using machine learning
Constructing high resolution air pollution maps at lower cost is crucial for sustainable city management and public health risk assessment.
Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents
To address this challenge, we propose MIRROR, a chain-of-thought approach that generates character thoughts by retrieving memories, predicting character reactions, and synthesizing motivations.
A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization
A$^2$ATS aims to obtain an accurate approximation of attention scores by applying the vector quantization technique to key states, thereby enabling efficient and precise retrieval of the top-K tokens.
CoSER: Coordinating LLM-Based Persona Simulation of Established Roles
It provides authentic dialogues with real-world intricacies, as well as diverse data types such as conversation setups, character experiences and internal thoughts.
FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data
Prior research on training grounded factuality classification models to detect hallucinations in large language models (LLMs) has relied on public natural language inference (NLI) data and synthetic data.
SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain
Recent breakthroughs in large language models (LLMs) exemplified by the impressive mathematical and scientific reasoning capabilities of the o1 model have spotlighted the critical importance of high-quality training data in advancing LLM performance across STEM disciplines.
Wasserstein-regularized Conformal Prediction under General Distribution Shift
Conformal prediction yields a prediction set with guaranteed $1-\alpha$ coverage of the true target under the i. i. d.
DEFOM-Stereo: Depth Foundation Model Based Stereo Matching
Thus, to facilitate robust stereo matching with monocular depth cues, we incorporate a robust monocular relative depth model into the recurrent stereo-matching framework, building a new framework for depth foundation model-based stereo-matching, DEFOM-Stereo.
SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation.
InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance
The proliferation of AI-generated images has intensified the need for robust content authentication methods.
CFPNet: Improving Lightweight ToF Depth Completion via Cross-zone Feature Propagation
Previous methods fail to propagate depth features from the zone area to the outside-zone area effectively, thus suffering from degraded depth completion performance outside the zone.
MinerU: An Open-Source Solution for Precise Document Content Extraction
Document content analysis has been a crucial research area in computer vision.
Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
Our method employs low-frequency words as triggers, embedding the watermark by replacing their embeddings in the model's word embedding layer with those of specific medical terms.
SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection
Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection.
PathInsight: Instruction Tuning of Multimodal Datasets and Models for Intelligence Assisted Diagnosis in Histopathology
We conducted a qualitative assessment of the capabilities of the base model and the fine-tuned model in performing image captioning and classification tasks on the specific dataset.
Retinal IPA: Iterative KeyPoints Alignment for Multimodal Retinal Imaging
We propose a novel framework for retinal feature point alignment, designed for learning cross-modality features to enhance matching and registration across multi-modality retinal images.
MINDECHO: Role-Playing Language Agents for Key Opinion Leaders
Large language models~(LLMs) have demonstrated impressive performance in various applications, among which role-playing language agents (RPLAs) have engaged a broad user base.
Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data
Role-playing agents (RPA) have been a popular application area for large language models (LLMs), attracting significant interest from both industry and academia. While existing RPAs well portray the characters' knowledge and tones, they face challenges in capturing their minds, especially for small role-playing language models (RPLMs).
PuTR: A Pure Transformer for Decoupled and Online Multi-Object Tracking
Although graph-based approaches can address this issue by modeling trajectories as a graph in the decoupled manner, their non-online nature poses obstacles for real-time applications.
ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models
We show that the space spanned by the combination of dimensions and attributes is insufficiently sampled by existing training scheme of diffusion generative models, causing degraded test time performance.
NeurCross: A Self-Supervised Neural Approach for Representing Cross Fields in Quad Mesh Generation
Quadrilateral mesh generation plays a crucial role in numerical simulations within Computer-Aided Design and Engineering (CAD/E).
AtomGS: Atomizing Gaussian Splatting for High-Fidelity Radiance Field
3D Gaussian Splatting (3DGS) has recently advanced radiance field reconstruction by offering superior capabilities for novel view synthesis and real-time rendering speed.
Visual Mamba: A Survey and New Outlooks
Mamba, a recent selective structured state space model, excels in long sequence modeling, which is vital in the large model era.
From Persona to Personalization: A Survey on Role-Playing Language Agents
Through this work, we aim to establish a clear taxonomy of RPLA research and applications, and facilitate future research in this critical and ever-evolving field, and pave the way for a future where humans and RPLAs coexist in harmony.
CWF: Consolidating Weak Features in High-quality Mesh Simplification
In mesh simplification, common requirements like accuracy, triangle quality, and feature alignment are often considered as a trade-off.
Uncertainty Quantification on Graph Learning: A Survey
Graphical models, including Graph Neural Networks (GNNs) and Probabilistic Graphical Models (PGMs), have demonstrated their exceptional capabilities across numerous fields.
NeurCADRecon: Neural Representation for Reconstructing CAD Surfaces by Enforcing Zero Gaussian Curvature
Despite recent advances in reconstructing an organic model with the neural signed distance function (SDF), the high-fidelity reconstruction of a CAD model directly from low-quality unoriented point clouds remains a significant challenge.
Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works
The prerequisite for these RPAs lies in the capability of LLMs to understand characters from fictional works.
Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?
Can Large Language Models (LLMs) simulate humans in making important decisions?
SurveyAgent: A Conversational System for Personalized and Efficient Research Survey
In the rapidly advancing research fields such as AI, managing and staying abreast of the latest scientific literature has become a significant challenge for researchers.
Robust Conformal Prediction under Distribution Shift via Physics-Informed Structural Causal Model
Uncertainty is critical to reliable decision-making with machine learning.
Coverage Axis++: Efficient Inner Point Selection for 3D Shape Skeletonization
We introduce Coverage Axis++, a novel and efficient approach to 3D shape skeletonization.
MAEDiff: Masked Autoencoder-enhanced Diffusion Models for Unsupervised Anomaly Detection in Brain Images
To address these two issues, we propose a novel Masked Autoencoder-enhanced Diffusion Model (MAEDiff) for unsupervised anomaly detection in brain images.
RomniStereo: Recurrent Omnidirectional Stereo Matching
To bridge the gap between OSM and RAFT, we mainly propose an opposite adaptive weighting scheme to seamlessly transform the outputs of spherical sweeping of OSM into the required inputs for the recurrent update, thus creating a recurrent omnidirectional stereo matching (RomniStereo) algorithm.
Multi-Attribute Interactions Matter for 3D Visual Grounding
3D visual grounding aims to localize 3D objects described by free-form language sentences.
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.
SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training
Deep Neural Networks (DNNs) are expected to provide explanation for users to understand their black-box predictions.
Assessing and Enhancing Robustness of Deep Learning Models with Corruption Emulation in Digital Pathology
Deep learning in digital pathology brings intelligence and automation as substantial enhancements to pathological analysis, the gold standard of clinical diagnosis.
What a Whole Slide Image Can Tell? Subtype-guided Masked Transformer for Pathological Image Captioning
Pathological captioning of Whole Slide Images (WSIs), though is essential in computer-aided pathological diagnosis, has rarely been studied due to the limitations in datasets and model training efficacy.
InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
Then, with InCharacter, we show that state-of-the-art RPAs exhibit personalities highly aligned with the human-perceived personalities of the characters, achieving an accuracy up to 80. 7%.
MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models
With the advancement of deep learning technologies, general-purpose large models such as GPT-4 have demonstrated exceptional capabilities across various domains.
Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian
Our approach enforces the Hessian of the neural implicit function to have a zero determinant for points near the surface.
Rethinking the Localization in Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) is one of the most popular and challenging tasks in computer vision.
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs).
A Task-driven Network for Mesh Classification and Semantic Part Segmentation
With the rapid development of geometric deep learning techniques, many mesh-based convolutional operators have been proposed to bridge irregular mesh structures and popular backbone networks.
DSHGT: Dual-Supervisors Heterogeneous Graph Transformer -- A pioneer study of using heterogeneous graph learning for detecting software vulnerabilities
Vulnerability detection is a critical problem in software security and attracts growing attention both from academia and industry.
AGI for Agriculture
Artificial General Intelligence (AGI) is poised to revolutionize a variety of sectors, including healthcare, finance, transportation, and education.
Unsupervised Cross-domain Pulmonary Nodule Detection without Source Data
Cross-domain pulmonary nodule detection suffers from performance degradation due to a large shift of data distributions between the source and target domain.
SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention
To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks.
POSTER++: A simpler and stronger facial expression recognition network
POSTER achieves the state-of-the-art (SOTA) performance in FER by effectively combining facial landmark and image features through two-stream pyramid cross-fusion design.
Ranked #8 on
Facial Expression Recognition (FER)
on AffectNet
Facial Expression Recognition
Facial Expression Recognition (FER)
More comprehensive facial inversion for more effective expression recognition
We extensively evaluate ASIT on facial datasets such as FFHQ and CelebA-HQ, showing that our approach achieves state-of-the-art facial inversion performance.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
Converge to the Truth: Factual Error Correction via Iterative Constrained Editing
Given a possibly false claim sentence, how can we automatically correct it with minimal editing?
An Improved RaftStereo Trained with A Mixed Dataset for the Robust Vision Challenge 2022
Stereo-matching is a fundamental problem in computer vision.
LSSANet: A Long Short Slice-Aware Network for Pulmonary Nodule Detection
Convolutional neural networks (CNNs) have been demonstrated to be highly effective in the field of pulmonary nodule detection.
An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learning
Spatial-temporal data contains rich information and has been widely studied in recent years due to the rapid development of relevant applications in many fields.
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints
To this end, we propose a plug-in algorithm for this line of work, i. e., Aligned Constrained Training (ACT), which alleviates this problem by familiarizing the model with the source-side context of the constraints.
E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning
Holding the belief that models capable of reasoning should be right for the right reasons, we propose a first-of-its-kind Explainable Knowledge-intensive Analogical Reasoning benchmark (E-KAR).
GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning
First, we propose a novel label prediction method, Isolated Graph Learning (IGL).
Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval
Then, we develop a generative adversarial network that combines the domain-specific features of the seen categories with the aligned domain-invariant features to synthesize samples, where the synthesized samples of the unseen categories are generated by using the corresponding word embeddings.
SSDL: Self-Supervised Dictionary Learning
Inspired by the concept of self-supervised learning (e. g., setting the pretext task to generate a universal model for the downstream task), we propose a Self-Supervised Dictionary Learning (SSDL) framework to address this challenge.
MDFM: Multi-Decision Fusing Model for Few-Shot Learning
Inspired by this assumption, we propose a novel method Multi-Decision Fusing Model (MDFM), which comprehensively considers the decisions based on multiple FEMs to enhance the efficacy and robustness of the model.
Uncertainty quantification and inverse modeling for subsurface flow in 3D heterogeneous formations using a theory-guided convolutional encoder-decoder network
The surrogate models are used to conduct uncertainty quantification considering a stochastic permeability field, as well as to infer unknown permeability information based on limited well production data and observation data of formation properties.
BSC: Block-based Stochastic Computing to Enable Accurate and Efficient TinyML
Unlike ML on the edge, TinyML with a limited energy supply has higher demands on low-power execution.
The Nuts and Bolts of Adopting Transformer in GANs
Transformer becomes prevalent in computer vision, especially for high-level vision tasks.
MHFC: Multi-Head Feature Collaboration for Few-Shot Learning
Apply the trained FEM to acquire the novel data's features and recognize them.
Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution
First, we design a cross-task distillation scheme that encourages DSR and DE networks to learn from each other in a teacher-student role-exchanging fashion.
BaPipe: Exploration of Balanced Pipeline Parallelism for DNN Training
The size of deep neural networks (DNNs) grows rapidly as the complexity of the machine learning algorithm increases.
Positional Encoding as Spatial Inductive Bias in GANs
In this work, taking SinGAN and StyleGAN2 as examples, we show that such capability, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators.
CARAFE++: Unified Content-Aware ReAssembly of FEatures
Feature reassembly, i. e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e. g., residual networks and feature pyramids.
Precessions of Spheroidal Stars under Lorentz Violation and Observational Consequences
The Standard-Model Extension (SME) is an effective-field-theoretic framework that catalogs all Lorentz-violating field operators.
General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena High Energy Physics - Phenomenology
DLDL: Dynamic Label Dictionary Learning via Hypergraph Regularization
To tackle this issue, we propose a Dynamic Label Dictionary Learning (DLDL) algorithm to generate the soft label matrix for unlabeled data.
SAHDL: Sparse Attention Hypergraph Regularized Dictionary Learning
In this paper, we propose a hypergraph based sparse attention mechanism to tackle this issue and embed it into dictionary learning.
VolumeNet: A Lightweight Parallel Network for Super-Resolution of Medical Volumetric Data
We construct a parallel connection structure based on the group convolution and feature aggregation to build a 3D CNN that is as wide as possible with few parameters.
Texture Memory-Augmented Deep Patch-Based Image Inpainting
By bringing together the best of both paradigms, we propose a new deep inpainting framework where texture generation is guided by a texture memory of patch samples extracted from unmasked regions.
Weak Form Theory-guided Neural Network (TgNN-wf) for Deep Learning of Subsurface Single and Two-phase Flow
In the weak form, high order derivatives in the PDE can be transferred to the test functions by performing integration-by-parts, which reduces computational error.
Progressive Point Cloud Deconvolution Generation Network
Starting from the low-resolution point clouds, with the bilateral interpolation and max-pooling operations, the deconvolution network can progressively output high-resolution local and global feature maps.
Discovering Symbolic Models from Deep Learning with Inductive Biases
The technique works as follows: we first encourage sparse latent representations when we train a GNN in a supervised setting, then we apply symbolic regression to components of the learned model to extract explicit physical relations.
Boosting Connectivity in Retinal Vessel Segmentation via a Recursive Semantics-Guided Network
Many deep learning based methods have been proposed for retinal vessel segmentation, however few of them focus on the connectivity of segmented vessels, which is quite important for a practical computer-aided diagnosis system on retinal images.
Implications of the virus-encoded miRNA and host miRNA in the pathogenicity of SARS-CoV-2
The outbreak of COVID-19 caused by SARS-CoV-2 has rapidly spread worldwide and has caused over 1, 400, 000 infections and 80, 000 deaths.
Genomics Biomolecules
Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers
In this paper, we propose a new method, termed as Lip by Speech (LIBS), of which the goal is to strengthen lip reading by learning from speech recognizers.
Ranked #2 on
Lipreading
on CMLR
When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks
Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep neural networks.
Learning Symbolic Physics with Graph Networks
We introduce an approach for imposing physically motivated inductive biases on graph networks to learn interpretable representations and improved zero-shot generalization.
A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading
When trained on CMLR dataset, the proposed CSSMCM surpasses the performance of state-of-the-art lip reading frameworks, which confirms the effectiveness of explicit modeling of tones for Chinese Mandarin lip reading.
Ranked #3 on
Lipreading
on CMLR
Deep Flow-Guided Video Inpainting
Then the synthesized flow field is used to guide the propagation of pixels to fill up the missing regions in the video.
Ranked #8 on
Video Inpainting
on DAVIS
One-shot visual object segmentation
Optical Flow Estimation
+2
CARAFE: Content-Aware ReAssembly of FEatures
CARAFE introduces little computational overhead and can be readily integrated into modern network architectures.
Ranked #3 on
Feature Upsampling
on ImageNet
Class specific or shared? A cascaded dictionary learning framework for image classification
Dictionary learning methods can be split into: i) class specific dictionary learning ii) class shared dictionary learning.
Label Embedded Dictionary Learning for Image Classification
Recently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classification.
Power Plant Performance Modeling with Concept Drift
Power plant is a complex and nonstationary system for which the traditional machine learning modeling approaches fall short of expectations.
Concept Drift Learning with Alternating Learners
Data-driven predictive analytics are in use today across a number of industrial applications, but further integration is hindered by the requirement of similarity among model training and test data distributions.
Linear Vlasov theory of a magnetised, thermally stratified atmosphere
At sub-ion-Larmor scales, we discover an overstability driven by the electron temperature gradient of kinetic-Alfv\'en drift waves -- the electron MTI (eMTI) -- whose growth rate is even larger than the standard MTI.
High Energy Astrophysical Phenomena Plasma Physics
