Search Results for author:
Found 20 papers, 16 papers with code
EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models
Additionally, we contribute to the first multi-modal industrial anomaly detection training dataset, named Defect Detection Question Answering (DDQA), encompassing a wide range of defect types and industrial scenarios.
ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews
In this paper, we address this challenge by proposing ReviewAgents, a framework that leverages large language models (LLMs) to generate academic paper reviews.
VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models
Specifically, process RMs evaluate each reasoning step, outcome RMs focus on the assessment of reasoning results, and critique RMs perform error analysis on the entire reasoning process, followed by corrections.
From Motion Signals to Insights: A Unified Framework for Student Behavior Analysis and Feedback in Physical Education Classes
Analyzing student behavior in educational scenarios is crucial for enhancing teaching quality and student engagement.
FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion
Based on this, we introduce the Flow Text with Image Insertion Benchmark (FTII-Bench), which includes 318 high-quality Chinese image-text news articles and 307 high-quality English image-text news articles, covering 10 different news domains.
Understanding Robustness of Parameter-Efficient Tuning for Image Classification
Parameter-efficient tuning (PET) techniques calibrate the model's predictions on downstream tasks by freezing the pre-trained models and introducing a small number of learnable parameters.
MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object Scenarios
CamObj-Instruct is collected for fine-tuning the LVLMs with improved instruction-following capabilities, and it includes 11, 363 images and 68, 849 conversations with diverse instructions.
LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
Motivated by this limit, we investigate building MoE models from existing dense large language models.
Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts
Mixture-of-Experts (MoE) models have shown remarkable capability in instruction tuning, especially when the number of tasks scales.
iDAT: inverse Distillation Adapter-Tuning
Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better adaptation to downstream tasks.
VM-UNet: Vision Mamba UNet for Medical Image Segmentation
To our best knowledge, this is the first medical image segmentation model constructed based on the pure SSM-based model.
Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition
While audio retrieval tasks are well-established in general audio classification, they have not been explored in the context of underwater audio recognition.
Learning Multi-axis Representation in Frequency Domain for Medical Image Segmentation
Specifically, our block performs a Fourier transform on the three axes of the input features and assigns the external weight in the frequency domain, which is generated by our External Weights Generator.
LAMM: Label Alignment for Multi-Modal Prompt Learning
We conduct experiments on 11 downstream vision datasets and demonstrate that our method significantly improves the performance of existing multi-modal prompt learning models in few-shot scenarios, exhibiting an average accuracy improvement of 2. 31(\%) compared to the state-of-the-art methods on 16 shots.
GIST: Improving Parameter Efficient Fine Tuning via Knowledge Interaction
2) They neglect the interaction between the intrinsic task-agnostic knowledge of pre-trained models and the task-specific knowledge in downstream tasks.
EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation
Moreover, to our best knowledge, this is the first model with a parameter count limited to just 50KB.
Learning Robust Visual-Semantic Embedding for Generalizable Person Re-identification
In this paper, we propose a Multi-Modal Equivalent Transformer called MMET for more robust visual-semantic embedding learning on visual, textual and visual-textual tasks respectively.
Generalizable Person Re-identification
Representation Learning
MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation
To address this challenge, we propose a light-weight model to achieve competitive performances for skin lesion segmentation at the lowest cost of parameters and computational complexity so far.
MEW-UNet: Multi-axis representation learning in frequency domain for medical image segmentation
Specifically, our block performs a Fourier transform on the three axes of the input feature and assigns the external weight in the frequency domain, which is generated by our Weights Generator.
Adaptive Generation Model: A New Ensemble Method
As a common method in Machine Learning, Ensemble Method is used to train multiple models from a data set and obtain better results through certain combination strategies.
