Search Results for author:
Found 58 papers, 20 papers with code
Multimodal Point Cloud Semantic Segmentation With Virtual Point Enhancement
Therefore, we introduce a spatial difference-driven adaptive filtering module that selectively extracts valuable pseudo points from these virtual points based on density and distance, enhancing the density of medium-range targets.
FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning
The first stage expands the test space with greater diversity, while the second enables a refined robustness evaluation across rare, frequent, and overall question distributions.
Audio-visual Question Answering
Audio-Visual Question Answering (AVQA)
+4
Single-Step Latent Consistency Model for Remote Sensing Image Super-Resolution
In the first stage, we pretrain a residual autoencoder to encode the differential information between high-resolution (HR) and low-resolution (LR) images, transitioning the diffusion process into a latent space to reduce computational costs.
Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection
The output voxel features are injected into the BEV space to compensate for the loss of 3D details caused by height compression.
A Survey on Knowledge-Oriented Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models.
FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object Detection
However, indiscriminate sampling and fusion often overlook the varying contributions of individual points and lead to exponentially increased complexity as the number of input frames grows.
Positioning-Aided Channel Estimation for Multi-LEO Satellite Downlink Communications
We investigate a multi-low Earth orbit (LEO) satellite system that simultaneously provides positioning and communication services to terrestrial user terminals.
Integrated Positioning and Communication via LEO Satellites: Opportunities and Challenges
Low Earth orbit (LEO) satellites, as a prominent technology in the 6G non-terrestrial network, offer both positioning and communication capabilities.
Latent Diffusion, Implicit Amplification: Efficient Continuous-Scale Super-Resolution for Remote Sensing Images
In the second stage, a conditional diffusion model is learned within the latent space to predict the true differential prior encoding.
Mind the Context: Attention-Guided Weak-to-Strong Consistency for Enhanced Semi-Supervised Medical Image Segmentation
Although weak-to-strong consistency is a prevalent method in semi-supervised image segmentation, there is a scarcity of research on perturbation strategies specifically tailored for semi-supervised medical image segmentation tasks.
Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone.
Detecting Training Data of Large Language Models via Expectation Maximization
Moreover, creating realistic MIA evaluation benchmarks is difficult as training and test data distributions are often unknown.
Active Evaluation Acquisition for Efficient LLM Benchmarking
Our approach models the dependencies across test examples, allowing accurate prediction of the evaluation outcomes for the remaining examples based on the outcomes of the selected ones.
Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models
Furthermore, the integration experiments with various LLMs on the mentioned datasets highlight the flexibility of DoG.
EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding
Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension.
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation
Image segmentation plays an important role in vision understanding.
Ranked #1 on
Image Segmentation
on PMD
AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
In this paper, we propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context through reinforcement learning.
Asymmetrical estimator for training encapsulated deep photonic neural networks
However, the training of PNN is known to be challenging, where the device-to-device and system-to-system variations create imperfect knowledge of the PNN.
Multi-Level Additive Modeling for Structured Non-IID Federated Learning
For every mid-level, it learns multiple models each assigned to a subgroup of clients, as clustered FL.
Diffusion-RSCC: Diffusion Probabilistic Model for Change Captioning in Remote Sensing Images
In training process, we construct a noise predictor conditioned on cross modal features to learn the distribution from the real caption distribution to the standard Gaussian distribution under the Markov chain.
General Purpose Verification for Chain of Thought Prompting
Many of the recent capabilities demonstrated by Large Language Models (LLMs) arise primarily from their ability to exploit contextual information.
Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
The former leads to a large, diverse test space, while the latter results in a comprehensive robustness evaluation on rare, frequent, and overall questions.
Audio-visual Question Answering
Audio-Visual Question Answering (AVQA)
+4
Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data.
Robust Visual Question Answering: Datasets, Methods, and Future Challenges
Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives.
Benchmarking Diverse-Modal Entity Linking with Generative Models
Entities can be expressed in diverse formats, such as texts, images, or column names and cell values in tables.
Taxonomy Expansion for Named Entity Recognition
We experiment with 6 diverse datasets and show that PLM consistently performs better than most other approaches (0. 5 - 2. 5 F1), including in novel settings for taxonomy expansion not considered in prior work.
Dual-Diffusion: Dual Conditional Denoising Diffusion Probabilistic Models for Blind Super-Resolution Reconstruction in RSIs
In our work, we introduce conditional denoising diffusion probabilistic models (DDPM) from two aspects: kernel estimation progress and re-construction progress, named as the dual-diffusion.
Scribble-Supervised Target Extraction Method Based on Inner Structure-Constraint for Remote Sensing Images
Weakly supervised learning based on scribble annotations in target extraction of remote sensing images has drawn much interest due to scribbles' flexibility in denoting winding objects and low cost of manually labeling.
Weakly-supervised ROI extraction method based on contrastive learning for remote sensing images
ROI extraction is an active but challenging task in remote sensing because of the complicated landform, the complex boundaries and the requirement of annotations.
Adaptive loose optimization for robust question answering
Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering).
Extractive Question-Answering
Machine Reading Comprehension
+2
Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization
Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews.
Health Monitoring of Movement Disorder Subject based on Diamond Stacked Sparse Autoencoder Ensemble Model
Machine learning-based processing of data collected from the human with movement disorders using wearable sensors is an effective method currently available for health monitoring.
Enhanced Soft Label for Semi-Supervised Semantic Segmentation
As a mainstream framework in the field of semi-supervised learning (SSL), self-training via pseudo labeling and its variants have witnessed impressive progress in semi-supervised semantic segmentation with the recent advance of deep neural networks.
Context-Aware Data Augmentation for LIDAR 3D Object Detection
For 3D object detection, labeling lidar point cloud is difficult, so data augmentation is an important module to make full use of precious annotated data.
A new Stack Autoencoder: Neighbouring Sample Envelope Embedded Stack Autoencoder Ensemble Model
Second, an embedded stack autoencoder (ESAE) is proposed and trained in each layer of sample space to consider the original samples during training and in the network structure, thereby better finding the relationship between original feature samples and deep feature samples.
Federated Learning from Pre-Trained Models: A Contrastive Learning Approach
To prevent these issues from hindering the deployment of FL systems, we propose a lightweight framework where clients jointly learn to fuse the representations generated by multiple fixed pre-trained models rather than training a large-scale model from scratch.
Label Semantics for Few Shot Named Entity Recognition
We study the problem of few shot learning for named entity recognition.
Visualizing and Understanding Patch Interactions in Vision Transformer
Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions.
On the Convergence of Clustered Federated Learning
Knowledge sharing and model personalization are essential components to tackle the non-IID challenge in federated learning (FL).
Pareto Policy Pool for Model-based Offline Reinforcement Learning
Model-based offline RL instead trains an environment model using a dataset of pre-collected experiences so online RL methods can learn in an offline manner by solely interacting with the model.
Leveraging Large-Scale Weakly Labeled Data for Semi-Supervised Mass Detection in Mammograms
Starting with a fully supervised model trained on the data with pixel-level masks, the proposed framework iteratively refines the model itself using the entire weakly labeled data (image-level soft label) in a self-training fashion.
DeepMMSA: A Novel Multimodal Deep Learning Method for Non-small Cell Lung Cancer Survival Analysis
To improve the survival prediction accuracy and help prognostic decision-making in clinical practice for medical experts, we for the first time propose a multimodal deep learning method for non-small cell lung cancer (NSCLC) survival analysis, named DeepMMSA.
Extremal problems of Erdős, Faudree, Schelp and Simonovits on paths and cycles
Many years ago, Erd\H{o}s, Faudree, Schelp and Simonovits proposed the study of the function $\phi(n, d, k)$, and conjectured that for any positive integers $n>d\geq k$, it holds that $\phi(n, d, k)\leq \lfloor\frac{k-1}{2}\rfloor\lfloor\frac{n}{d+1}\rfloor+\epsilon$, where $\epsilon=1$ if $k$ is odd and $\epsilon=2$ otherwise.
Combinatorics
Structured Prediction as Translation between Augmented Natural Languages
We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification, semantic role labeling, event extraction, coreference resolution, and dialogue state tracking.
Ranked #3 on
Relation Classification
on TACRED
Improvements on induced subgraphs of given sizes
al. Our second result considers infinitely many pairs $(m, f)$ of special forms, whose exact values of $\sigma(m, f)$ were conjectured by Erd\H{o}s et.
Combinatorics
Feature Interactive Representation for Point Cloud Registration
Point cloud registration is the process of using the common structures in two point clouds to splice them together.
When and Who? Conversation Transition Based on Bot-Agent Symbiosis Learning Network
In online customer service applications, multiple chatbots that are specialized in various topics are typically developed separately and are then merged with other human agents to a single platform, presenting to the users with a unified interface.
XTQA: Span-Level Explanations of the Textbook Question Answering
Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams.
To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging
Leveraging large amounts of unlabeled data using Transformer-like architectures, like BERT, has gained popularity in recent times owing to their effectiveness in learning general representations that can then be further fine-tuned for downstream tasks to much success.
Resource-Enhanced Neural Model for Event Argument Extraction
(2) Capturing the long-range dependency, specifically, the connection between an event trigger and a distant event argument.
Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer
SBA stochastically decides whether to augment at iterations controlled by the batch scheduler and in which a ''distilled'' dynamic soft label regularization is introduced by incorporating the similarity in the vicinity distribution respect to raw samples.
Severing the Edge Between Before and After: Neural Architectures for Temporal Ordering of Events
In this paper, we propose a neural architecture and a set of training methods for ordering events by predicting temporal relations.
Some exact results on $4$-cycles: stability and supersaturation
A longstanding conjecture of Erd\H{o}s and Simonovits states that every $n$-vertex graph with $ex(n, C_4)+1$ edges contains at least $(1+o(1))\sqrt{n}$ 4-cycles.
Combinatorics
Context-aware Attention Model for Coreference Resolution
Coreference resolution is an important task for gaining more complete understanding about texts by artificial intelligence.
Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability
Learning an efficient manager of dialogue agent from data with little manual intervention is important, especially for goal-oriented dialogues.
Deep joint rain and haze removal from single images
On the other hand, the accumulation of rain streaks from long distance makes the rain image look like haze veil.
MSR-net:Low-light Image Enhancement Using Deep Convolutional Network
In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed.
