Search Results for author:
Found 80 papers, 27 papers with code
A state reduction approach for learning-based model predictive control for train rescheduling
This paper proposes a state reduction method for learning-based model predictive control (MPC) for train rescheduling in urban rail transit systems.
Distributed model predictive control without terminal cost under inexact distributed optimization
This paper presents a novel distributed model predictive control (MPC) formulation without terminal cost and a corresponding distributed synthesis approach for distributed linear discrete-time systems with coupled constraints.
KAN or MLP? Point Cloud Shows the Way Forward
To overcome the high parameter counts and computational inefficiency of standard KANs, we develop Efficient-KANs in the PointKAN-elite variant, which significantly reduces parameters while maintaining accuracy.
Are Deep Speech Denoising Models Robust to Adversarial Noise?
Deep noise suppression (DNS) models enjoy widespread use throughout a variety of high-stakes speech applications.
ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration
Furthermore, we propose a more accessible method for enhancing object generalization in VLA models, using a smartphone to capture a few images and fine-tune the pre-trained model.
Learning-based Model Predictive Control for Passenger-Oriented Train Rescheduling with Flexible Train Composition
This paper focuses on passenger-oriented real-time train rescheduling, considering flexible train composition and rolling stock circulation, by integrating learning-based and optimization-based approaches.
Soybean pod and seed counting in both outdoor fields and indoor laboratories using unions of deep neural networks
Automatic counting soybean pods and seeds in outdoor fields allows for rapid yield estimation before harvesting, while indoor laboratory counting offers greater accuracy.
QMamba: Post-Training Quantization for Vision State Space Models
State Space Models (SSMs), as key components of Mamaba, have gained increasing attention for vision models recently, thanks to their efficient long sequence modeling capability.
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction.
Diffusion-VLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression
In this paper, we present DiffusionVLA, a novel framework that seamlessly combines the autoregression model with the diffusion model for learning visuomotor policy.
Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
The remarkable capabilities of Large Language Models (LLMs) make them increasingly compelling for adoption in real-world healthcare applications.
FANCL: Feature-Guided Attention Network with Curriculum Learning for Brain Metastases Segmentation
Furthermore, FANCL applies the voxel-level curriculum learning strategy to help the model gradually learn the structure and details of BMs.
Predicting 30-Day Hospital Readmission in Medicare Patients: Insights from an LSTM Deep Learning Model
The LSTM model is designed to capture temporal dynamics from admission-level and patient-level data.
Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation
Audio token modeling has become a powerful framework for speech synthesis, with two-stage approaches employing semantic tokens remaining prevalent.
Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibility
We do so by boosting the speech encoder component of MaskSR with predictions of semantic representations of the target speech, using a pre-trained self-supervised teacher model.
CSRec: Rethinking Sequential Recommendation from A Causal Perspective
The essence of sequential recommender systems (RecSys) lies in understanding how users make decisions.
Challenge Summary U-MedSAM: Uncertainty-aware MedSAM for Medical Image Segmentation
Medical Image Foundation Models have proven to be powerful tools for mask prediction across various datasets.
Deep Mutual Learning among Partially Labeled Datasets for Multi-Organ Segmentation
The task of labeling multiple organs for segmentation is a complex and time-consuming process, resulting in a scarcity of comprehensively labeled multi-organ datasets while the emergence of numerous partially labeled datasets.
Multi-Granularity Semantic Revision for Large Language Model Distillation
At the sequence level, we propose a sequence correction and re-generation (SCRG) strategy.
Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation
Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive.
AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models
This motivates the development of AutoHallusion, the first automated benchmark generation approach that employs several key strategies to create a diverse range of hallucination examples.
Ranked #1 on
Visual Question Answering (VQA)
on AutoHallusion
M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation
Document translation poses a challenge for Neural Machine Translation (NMT) systems.
ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagery
Scene Graph Generation (SGG) is a high-level visual understanding and reasoning task aimed at extracting entities (such as objects) and their interrelationships from images.
MaskSR: Masked Language Model for Full-band Speech Restoration
Speech restoration aims at restoring high quality speech in the presence of a diverse set of distortions.
TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction
Autoregressive next-token prediction is a standard pretraining method for large-scale language models, but its application to vision tasks is hindered by the non-sequential nature of image data, leading to cumulative errors.
UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation
In the field of medical image compression, Implicit Neural Representation (INR) networks have shown remarkable versatility due to their flexible compression ratios, yet they are constrained by a one-to-one fitting approach that results in lengthy encoding times.
Calibrated Dataset Condensation for Faster Hyperparameter Search
We aim to generate a synthetic validation dataset so that the validation-performance rankings of the models, with different hyperparameters, on the condensed and original datasets are comparable.
SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions
The key idea of our SmartControl is to relax the visual condition on the areas that are conflicted with text prompts.
Distilling Semantic Priors from SAM to Efficient Image Restoration Models
SPD leverages a self-distillation manner to distill the fused semantic priors to boost the performance of original IR models.
BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval
The burgeoning integration of 3D medical imaging into healthcare has led to a substantial increase in the workload of medical professionals.
Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey
Causal inference has shown potential in enhancing the predictive accuracy, fairness, robustness, and explainability of Natural Language Processing (NLP) models by capturing causal relationships among variables.
Steering LLMs Towards Unbiased Responses: A Causality-Guided Debiasing Framework
Large language models (LLMs) can easily generate biased and discriminative responses.
PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learning
However, instead of pre-training, when trivially combining CRL loss with LNL methods as an end-to-end framework, the empirical experiments show severe degeneration of the performance.
Unmasking and Quantifying Racial Bias of Large Language Models in Medical Report Generation
Large language models like GPT-3. 5-turbo and GPT-4 hold promise for healthcare professionals, but they may inadvertently inherit biases during their training, potentially affecting their utility in medical applications.
Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image, and the ability of modern MLLMs to extrapolate from image sequences, which is essential for understanding our ever-changing world, has been less investigated.
Graph Relation Distillation for Efficient Biomedical Instance Segmentation
IGD constructs a graph representing instance features and relations, transferring these two types of knowledge by enforcing instance graph consistency.
conv_einsum: A Framework for Representation and Fast Evaluation of Multilinear Operations in Convolutional Tensorial Neural Networks
Modern ConvNets continue to achieve state-of-the-art results over a vast array of vision and image classification tasks, but at the cost of increasing parameters.
Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation
Recent advancements utilize 3D CNNs to predict a 3D affinity map with improved accuracy but suffer from two challenges: high computational cost and limited input size especially for practical deployment for large-scale EM volumes.
CBQ: Cross-Block Quantization for Large Language Models
Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs.
Explore Spurious Correlations at the Concept Level in Language Models for Text Classification
We find that LMs, when encountering spurious correlations between a concept and a label in training or prompts, resort to shortcuts for predictions.
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
To quantify this inactivity, we adopt dormant ratio as a metric to measure inactivity in the RL agent's network.
C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder
Representation learning assumes that real-world data is generated by a few semantically meaningful generative factors (i. e., sources of variation) and aims to discover them in the latent space.
HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models
Our comprehensive case studies within HallusionBench shed light on the challenges of hallucination and illusion in LVLMs.
Ranked #1 on
Visual Question Answering (VQA)
on HallusionBench
GASS: Generalizing Audio Source Separation with Large-scale Data
Here, we study a single general audio source separation (GASS) model trained to separate speech, music, and sound events in a supervised fashion with a large-scale dataset.
Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition
In this paper, we circumvent this issue by presenting a joint framework for both unbounded recommendation of camera view and image composition (i. e., UNIC).
Semi-Supervised SAR ATR Framework with Transductive Auxiliary Segmentation
The recognition performance of 94. 18\% can be achieved under 20 training samples in each class with simultaneous accurate segmentation results.
An Entropy-Awareness Meta-Learning Method for SAR Open-Set ATR
In this letter, we propose an entropy-awareness meta-learning method that improves the exclusiveness of feature distribution of known classes which means our method is effective for not only classifying the seen classes but also encountering the unseen other classes.
Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation
Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations.
Global in Local: A Convolutional Transformer for SAR ATR FSL
Convolutional neural networks (CNNs) have dominated the synthetic aperture radar (SAR) automatic target recognition (ATR) for years.
SAR Target Image Generation Method Using Azimuth-Controllable Generative Adversarial Network
The similarity discriminator can differentiate the generated SAR target images from the real SAR images to ensure the accuracy of the generated, while the azimuth predictor measures the difference of azimuth between the generated and the desired to ensure the azimuth controllability of the generated.
Seasonality Based Reranking of E-commerce Autocomplete Using Natural Language Queries
Query autocomplete (QAC) also known as typeahead, suggests list of complete queries as user types prefix in the search box.
CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models
Our results show the effectiveness of the proposed method, and that the pretrained diffusion prior can reduce the modality transfer gap.
Dynamically Conservative Self-Driving Planner for Long-Tail Cases
In this way, the DCP is designed to automatically adjust to be more conservative in low-confidence "long-tail" cases while keeping efficient otherwise.
Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising
And we extend the blind-spot network to a blind-neighborhood network (BNN) for providing supervision on flat areas.
Towards more precise automatic analysis: a comprehensive survey of deep learning-based multi-organ segmentation
Accurate segmentation of multiple organs of the head, neck, chest, and abdomen from medical images is an essential step in computer-aided diagnosis, surgical navigation, and radiation therapy.
Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation
Sparse instance-level supervision has recently been explored to address insufficient annotation in biomedical instance segmentation, which is easier to annotate crowded instances and better preserves instance completeness for 3D volumetric datasets compared to common semi-supervision. In this paper, we propose a sparsely supervised biomedical instance segmentation framework via cross-representation affinity consistency regularization.
A Soma Segmentation Benchmark in Full Adult Fly Brain
Finally, we provide quantitative and qualitative benchmark comparisons on the testset to validate the superiority of the proposed method, as well as preliminary statistics of the reconstructed somas in the full adult fly brain from the biological perspective.
Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation
Single channel target speaker separation (TSS) aims at extracting a speaker's voice from a mixture of multiple talkers given an enrollment utterance of that speaker.
Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP).
Swin-transformer-yolov5 For Real-time Wine Grape Bunch Detection
Results showed that the proposed Swin-T-YOLOv5 outperformed all other studied models for grape bunch detection, with up to 97% of mean Average Precision (mAP) and 0. 89 of F1-score when the weather was cloudy.
Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis
Histopathological images contain abundant phenotypic information and pathological patterns, which are the gold standards for disease diagnosis and essential for the prediction of patient prognosis and treatment outcome.
Long-Tail Prediction Uncertainty Aware Trajectory Planning for Self-driving Vehicles
To this end, this work proposes a trajectory planner to consider the prediction model uncertainty arising from insufficient data for safer performance.
AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations
This scenario motivates the code adaptation task -- a variant of program repair which aims to adapt variable identifiers in a pasted snippet of code to the surrounding, preexisting source code.
Learning to Reduce False Positives in Analytic Bug Detectors
Due to increasingly complex software design and rapid iterative development, code defects and security vulnerabilities are prevalent in modern software.
Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge
To promote the development of occlusion understanding, we collect a large-scale dataset called OVIS for video instance segmentation in the occluded scenario.
LMSA: Low-relation Mutil-head Self-Attention Mechanism in Visual Transformer
By appropriately compressing the dimensions of the self-attention relationship variables, the Transformer network can be more efficient and even perform better.
Tuformer: Data-Driven Design of Expressive Transformer by Tucker Tensor Representation
Guided by tensor diagram representations, we formulate a design space where we can analyze the expressive power of the network structure, providing new directions and possibilities for enhanced performance.
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
While there are many efforts to extend the context window, we introduce an architecture-independent approach for leveraging the syntactic hierarchies of source code for incorporating entire file-level context into a fixed-length window.
Advanced Deep Networks for 3D Mitochondria Instance Segmentation
Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods.
Ranked #1 on
3D Instance Segmentation
on MitoEM
On permutation invariant training for speech source separation
We study permutation invariant training (PIT), which targets at the permutation ambiguity problem for speaker independent source separation models.
Occluded Video Instance Segmentation: A Benchmark
On the OVIS dataset, the highest AP achieved by state-of-the-art algorithms is only 16. 3, which reveals that we are still at a nascent stage for understanding objects, instances, and videos in a real-world scenario.
Ranked #33 on
Video Instance Segmentation
on YouTube-VIS validation
Ensemble Wrapper Subsampling for Deep Modulation Classification
Subsampling of received wireless signals is important for relaxing hardware requirements as well as the computational cost of signal processing algorithms that rely on the output samples.
An empirical study of Conv-TasNet
Furthermore, we offer insights into the generalization capabilities of Conv-TasNet and the potential value of improvements to the encoder/decoder.
Histogram Transform Ensembles for Large-scale Regression
Instead, we apply kernel histogram transforms (KHT) equipped with smoother regressors such as support vector machines (SVMs), and it turns out that both single and ensemble KHT enjoy almost optimal convergence rates.
Towards fully automated post-event data collection and analysis: pre-event and post-event information fusion
A typical post-event reconnaissance mission is conducted by first doing a preliminary survey, followed by a detailed survey.
Best-scored Random Forest Classification
We propose an algorithm named best-scored random forest for binary classification problems.
Fast Deep Learning for Automatic Modulation Classification
We then study algorithms to reduce the training time by minimizing the size of the training data set, while incurring a minimal loss in classification accuracy.
Dual-label Deep LSTM Dereverberation For Speaker Verification
In this paper, we present a reverberation removal approach for speaker verification, utilizing dual-label deep neural networks (DNNs).
Model Interpretation: A Unified Derivative-based Framework for Nonparametric Regression and Supervised Machine Learning
Interpreting a nonparametric regression model with many predictors is known to be a challenging problem.
Deep Neural Network Architectures for Modulation Classification
Finally, we introduce a Convolutional Long Short-term Deep Neural Network (CLDNN [4]) to achieve an accuracy of approximately 88. 5% at high SNR.
