Search Results for author:
Found 54 papers, 27 papers with code
Diffusion Models for Robotic Manipulation: A Survey
This paper also presents the two main frameworks of diffusion models and their integration with imitation learning and reinforcement learning.
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
Our pipeline generates detailed reasoning for various medical questions from 7 medical datasets, resulting in a dataset of 32, 682 question-answer pairs, each with detailed, step-by-step explanations.
VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility
To the best of our knowledge, VISO-Grasp is the first unified framework integrating FMs into target-aware active view planning and 6-DoF grasping in environments with severe occlusions and entire invisibility constraints.
OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition
The primary challenge in continuous sign language recognition (CSLR) mainly stems from the presence of multi-orientational and long-term motions.
OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse Problems
The TNN-regularized optimization problem is solved by the singular value thresholding (SVT) operator, which leverages the t-SVD framework to obtain the low-rank tensor.
Multimodal Instruction Tuning with Hybrid State Space Models
Remarkably, our model enhances inference efficiency for high-resolution images and high-frame-rate videos by about 4 times compared to current models, with efficiency gains increasing as image resolution or video frames rise.
Reducing Hallucinations in Vision-Language Models via Latent Space Steering
Unlike in large language models (LLMs), hallucination in LVLMs often arises from misalignments between visual inputs and textual outputs.
TFG: Unified Training-Free Guidance for Diffusion Models
Given an unconditional diffusion model and a predictor for a target property of interest (e. g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training.
MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine
Unlike the existing multimodal datasets, which are limited by the availability of image-text pairs, we have developed the first automated pipeline that scales up multimodal data by generating multigranular visual and textual annotations in the form of image-ROI-description triplets without the need for any paired text descriptions.
Automated radiotherapy treatment planning guided by GPT-4Vision
Objective: Radiotherapy treatment planning is a time-consuming and potentially subjective process that requires the iterative adjustment of model parameters to balance multiple conflicting objectives.
TextGrad: Automatic "Differentiation" via Text
Without modifying the framework, TextGrad improves the zero-shot accuracy of GPT-4o in Google-Proof Question Answering from $51\%$ to $55\%$, yields $20\%$ relative performance gain in optimizing LeetCode-Hard coding problem solutions, improves prompts for reasoning, designs new druglike small molecules with desirable in silico binding, and designs radiation oncology treatment plans with high specificity.
Ranked #5 on
on GPQA
GNSS Measurement-Based Context Recognition for Vehicle Navigation using Gated Recurrent Unit
Recent years, people have put forward higher and higher requirements for context-adaptive navigation (CAN).
Mapping the Increasing Use of LLMs in Scientific Papers
To address this gap, we conduct the first systematic, large-scale analysis across 950, 965 papers published between January 2020 and February 2024 on the arXiv, bioRxiv, and Nature portfolio journals, using a population-level statistical framework to measure the prevalence of LLM-modified content over time.
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM).
Data Reconstruction Attacks and Defenses: A Systematic Evaluation
Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning.
Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning
Language models trained via federated learning (FL) demonstrate impressive capabilities in handling complex tasks while protecting user privacy.
Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling
Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data.
In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
On a new query, instead of adding demonstrations to the prompt, we shift the latent states of the LLM using the ICV.
Channel-Wise Contrastive Learning for Learning with Noisy Labels
In real-world datasets, noisy labels are pervasive.
Unleashing the Potential of Regularization Strategies in Learning with Noisy Labels
In recent years, research on learning with noisy labels has focused on devising novel algorithms that can achieve robustness to noisy training labels while generalizing to clean data.
LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization
We present a simple yet effective self-supervised pre-training method for image harmonization which can leverage large-scale unannotated image datasets.
Swin MAE: Masked Autoencoders for Small Datasets
The development of deep learning models in medical image analysis is majorly limited by the lack of large-sized and well-annotated datasets.
Understanding and Improving Transfer Learning of Deep Models via Neural Collapse
In particular, we discovered a systematic pattern that emerges when linear probing pre-trained models on downstream training data: the more feature collapse of pre-trained models on downstream training data, the higher the transfer accuracy.
PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels
The early stopping strategy averts updating CNNs during the early training phase and is widely employed in the presence of noisy labels.
Avoiding spurious correlations via logit correction
Empirical studies suggest that machine learning models trained with empirical risk minimization (ERM) often rely on attributes that may be spuriously correlated with the class labels.
Recovering Sign Bits of DCT Coefficients in Digital Images as an Optimization Problem
Recovering unknown, missing, damaged, distorted, or lost information in DCT coefficients is a common task in multiple applications of digital image processing, including image compression, selective image encryption, and image communication.
Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning
The framework employs a novel self-paced sampling strategy to ensure the accuracy of pseudo labels.
Are All Losses Created Equal: A Neural Collapse Perspective
We extend such results and show through global solution and landscape analyses that a broad family of loss functions including commonly used label smoothing (LS) and focal loss (FL) exhibits Neural Collapse.
Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
Our proposed approach is extensively validated on the ViSha dataset and a self-annotated dataset.
Asymmetric Dual-Decoder U-Net for Joint Rain and Haze Removal
However, jointly removing the rain and haze in scene images is ill-posed and challenging, where the existence of haze and rain and the change of atmosphere light, can both degrade the scene information.
Parotid Gland MRI Segmentation Based on Swin-Unet and Multimodal Images
Preoperative tumor localization, differential diagnosis, and subsequent selection of appropriate treatment for parotid gland tumors are critical.
Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows
We demonstrate that our approach: (a) significantly improves the quality of 3-D reconstruction for our small-parallax setting, (b) does not cause any degradation for data with large-parallax, and (c) maintains the generalizability and scalability of geometry-based sparse SfM.
On Learning Contrastive Representations for Learning with Noisy Labels
To address this issue, we focus on learning robust contrastive representations of data on which the classifier is hard to memorize the label noise under the CE loss.
Robust Training under Label Noise by Over-parameterization
In this work, we propose a principled approach for robust training of over-parameterized deep networks in classification tasks where a proportion of training labels are corrupted.
Ranked #2 on
Learning with noisy labels
on CIFAR-10N-Random3
Uncertainty Detection and Reduction in Neural Decoding of EEG Signals
In this work, we proposed an uncertainty estimation and reduction model (UNCER) to quantify and mitigate the uncertainty during the EEG decoding process.
Deep Probability Estimation
Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty.
Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an "early-learning" phase, before eventually memorizing the false annotations.
Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning
Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications, whereas the data of rare fine-grained categories is very limited.
OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning
We introduce the task of open-vocabulary visual instance search (OVIS).
Multi-modal and frequency-weighted tensor nuclear norm for hyperspectral image denoising
In this paper, we propose the multi-modal and frequency-weighted tensor nuclear norm (MFWTNN) and the non-convex MFWTNN for HSI denoising tasks.
Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
Furthermore, we show that our ConvNorm can reduce the layerwise spectral norm of the weight matrices and hence improve the Lipschitzness of the network, leading to easier training and improved robustness for deep ConvNets.
Hyperspectral Image Denoising via Multi-modal and Double-weighted Tensor Nuclear Norm
In the Fourier transform domain of HSIs, different frequency slices (FS) contain different information; different singular values (SVs) of each FS also represent different information.
Adversarial Multiscale Feature Learning for Overlapping Chromosome Segmentation
Since manual analysis is highly time and effort consuming, computer-assisted automatic chromosome karyotype analysis based on images is routinely used to improve the efficiency and accuracy of the analysis.
Urban Bike Lane Planning with Bike Trajectories: Models, Algorithms, and a Real-World Case Study
We formalize the bike lane planning problem in view of the cyclists' utility functions and derive an integer optimization model to maximize the utility.
Early-Learning Regularization Prevents Memorization of Noisy Labels
In contrast with existing approaches, which use the model output during early learning to detect the examples with clean labels, and either ignore or attempt to correct the false labels, we take a different route and instead capitalize on early learning via regularization.
Ranked #5 on
Learning with noisy labels
on CIFAR-10N-Random2
Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition
We first formulate generation of adversarial skeleton actions as a constrained optimization problem by representing or approximating the physiological and physical constraints with mathematical formulations.
On the design of convolutional neural networks for automatic detection of Alzheimer's disease
Early detection is a crucial goal in the study of Alzheimer's Disease (AD).
Machine Discovery of Partial Differential Equations from Spatiotemporal Data
The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data.
Sparse Recovery Beyond Compressed Sensing: Separable Nonlinear Inverse Problems
In this work, we consider separable inverse problems, where the data are modeled as a linear combination of functions that depend nonlinearly on certain parameters of interest.
Time-Series Analysis via Low-Rank Matrix Factorization Applied to Infant-Sleep Data
We apply our methodology to detect anomalous individuals, to cluster the cohort into groups with different sleeping tendencies, and to obtain improved predictions of future sleep behavior.
Discovering Influential Factors in Variational Autoencoder
In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks.
Towards Clinical Diagnosis: Automated Stroke Lesion Segmentation on Multimodal MR Image Using Convolutional Neural Network
The patient with ischemic stroke can benefit most from the earliest possible definitive diagnosis.
Defect detection for patterned fabric images based on GHOG and low-rank decomposition
In order to accurately detect defects in patterned fabric images, a novel detection algorithm based on Gabor-HOG (GHOG) and low-rank decomposition is proposed in this paper.
