Search Results for author:
Found 32 papers, 19 papers with code
CNN-Transformer Rectified Collaborative Learning for Medical Image Segmentation
We also propose a class-aware feature-wise collaborative learning (CFCL) strategy to achieve effective knowledge transfer between CNN-based and Transformer-based models in the feature space by granting their intermediate features the similar capability of category perception.
Secure Transmission for Movable Antennas Empowered Cell-Free Symbiotic Radio Communications
The MAs deployed at the APs can adjust their positions flexibly to improve channel conditions between the APs and the PU/SU/BD and suppress the eavesdropping from the Eve on confidential information at the PU.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Multi-task Language Understanding
on MMLU
Knowledge Acquisition Disentanglement for Knowledge-based Visual Question Answering with Large Language Models
Knowledge-based Visual Question Answering (KVQA) requires both image and world knowledge to answer questions.
Timestep-Aware Correction for Quantized Diffusion Models
This accumulation of error becomes particularly problematic in low-precision scenarios, leading to significant distortions in the generated images.
AGLA: Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
To this end, we propose Assembly of Global and Local Attention (AGLA), a training-free and plug-and-play approach that mitigates object hallucinations by exploring an ensemble of global features for response generation and local features for visual discrimination simultaneously.
Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition
Disordered speech recognition profound implications for improving the quality of life for individuals afflicted with, for example, dysarthria.
Large Language Models Enhanced Sequential Recommendation for Long-tail User and Item
These challenges, termed as the long-tail user and long-tail item dilemmas, often create obstacles for traditional SRS methods.
STAR-RIS Assisted Wireless-Powered and Backscattering Mobile Edge Computing Networks
Wireless powered and backscattering mobile edge computing (WPB-MEC) network is a novel network paradigm to supply energy supplies and computing resource to wireless sensors (WSs).
Bring Your Own Character: A Holistic Solution for Automatic Facial Animation Generation of Customized Characters
In our solution, a deep learning model was first trained to retarget the facial expression from input face images to virtual human faces by estimating the blendshape coefficients.
Large Language Model Distilling Medication Recommendation Model
In this paper, we introduce a novel approach called Large Language Model Distilling Medication Recommendation (LEADER).
Transfer and Alignment Network for Generalized Category Discovery
On the other hand, we use these prototypes to calibrate noisy prototypes estimated from unlabeled data based on category similarities, which allows for more accurate estimation of prototypes for novel categories that can be used as reliable learning targets later.
Generalized Category Discovery with Large Language Models in the Loop
Then we propose a Scalable Query strategy to allow LLMs to choose true neighbors of the selected samples from multiple candidate samples.
A Diffusion Weighted Graph Framework for New Intent Discovery
New Intent Discovery (NID) aims to recognize both new and known intents from unlabeled data with the aid of limited labeled data containing only known intents.
When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications
To address these two problems, we propose a novel parameter efficient fine-tuning framework for multi-task medical applications, dubbed as MOELoRA.
DNA: Denoised Neighborhood Aggregation for Fine-grained Category Discovery
Specifically, we retrieve k-nearest neighbors of a query as its positive keys to capture semantic similarities between data and then aggregate information from the neighbors to learn compact cluster representations, which can make fine-grained categories more separatable.
Diffusion Augmentation for Sequential Recommendation
However, sequential recommendation often faces the problem of data sparsity, which widely exists in recommender systems.
Mega-cities dominate China's urban greening
Trees play a crucial role in urban environments, offering various ecosystem services that contribute to public health and human well-being.
Tight and fast generalization error bound of graph embedding in metric space
However, recent theoretical analyses have shown a much higher upper bound on non-Euclidean graph embedding's generalization error than Euclidean one's, where a high generalization error indicates that the incompleteness and noise in the data can significantly damage learning performance.
M$^{2}$SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation
Next, we expand the single-scale SU to the intra-layer multi-scale SU, which can provide the decoder with both pixel-level and structure-level difference information.
Generalized Category Discovery with Decoupled Prototypical Network
Furthermore, the coupled training approach prevents these models transferring category-specific knowledge explicitly from labeled data to unlabeled data, which can lose high-level semantic information and impair model performance.
Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning
Novel category discovery aims at adapting models trained on known categories to novel categories.
Noise-Tolerant Learning for Audio-Visual Action Recognition
To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence.
"Brilliant AI Doctor" in Rural China: Tensions and Challenges in AI-Powered CDSS Deployment
Artificial intelligence (AI) technology has been increasingly used in the implementation of advanced Clinical Decision Support Systems (CDSS).
CASS: Towards Building a Social-Support Chatbot for Online Health Community
Chatbots systems, despite their popularity in today's HCI and CSCW research, fall short for one of the two reasons: 1) many of the systems use a rule-based dialog flow, thus they can only respond to a limited number of pre-defined inputs with pre-scripted responses; or 2) they are designed with a focus on single-user scenarios, thus it is unclear how these systems may affect other users or the community.
FISHING Net: Future Inference of Semantic Heatmaps In Grids
Managing the different reference frames and characteristics of the sensors, and merging their observations into a single representation complicates perception.
Feature Super-Resolution Based Facial Expression Recognition for Multi-scale Low-Resolution Faces
The main cause of this problem is the loss of discriminative feature due to reduced resolution.
Facial Expression Recognition
Facial Expression Recognition (FER)
+4
Small traffic sign detection from large image
It concatenates the features of the different layers into a fused feature map to provide sufficient information for small traffic sign detection.
Modeling e-Learners' Cognitive and Metacognitive Strategy in Comparative Question Solving
from "The C Programming Language" course and "What are similarities and differences between packet switching and circuit switching?"
The MUSCLES Treasury Survey. V. FUV Flares on Active and Inactive M Dwarfs
The rate and distribution of flares are such that they could dominate the FUV energy budget of M dwarfs, assuming the same distribution holds to flares as energetic as those cataloged by Kepler and ground-based surveys.
Solar and Stellar Astrophysics
Outer Product-based Neural Collaborative Filtering
In this work, we contribute a new multi-layer neural network architecture named ONCF to perform collaborative filtering.
Ranked #1 on
Recommendation Systems
on Gowalla
