Search Results for author:
Found 39 papers, 12 papers with code
Command A: An Enterprise-Ready Large Language Model
In this report we describe the development of Command A, a powerful large language model purpose-built to excel at real-world enterprise use cases.
Efficient Inference for Large Reasoning Models: A Survey
Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in complex task-solving.
Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
The hallucination of large multimodal models (LMMs), providing responses that appear correct but are actually incorrect, limits their reliability and applicability.
Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts
Large Language Models (LLMs) are increasingly employed as automated evaluators to assess the safety of generated content, yet their reliability in this role remains uncertain.
Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method
We then evaluate the detection performance of various fine-tuning strategies for VLMs and derive optimized model weights for object detection in remote sensing images.
EquiBench: Benchmarking Code Reasoning Capabilities of Large Language Models via Equivalence Checking
Equivalence checking, i. e., determining whether two programs produce identical outputs for all possible inputs, underpins a broad range of applications, including software refactoring, testing, and optimization.
Tumor Detection, Segmentation and Classification Challenge on Automated 3D Breast Ultrasound: The TDSC-ABUS Challenge
This initiative aims to spearhead research in this field and create a definitive benchmark for tasks associated with 3D ABUS image analysis.
PAID: A Framework of Product-Centric Advertising Image Design
An SDXL-based layout-controlled inpainting model is trained to generate an aesthetic background image.
MID: A Comprehensive Shore-Based Dataset for Multi-Scale Dense Ship Occlusion and Interaction Scenarios
This paper introduces the Maritime Ship Navigation Behavior Dataset (MID), designed to address challenges in ship detection within complex maritime environments using Oriented Bounding Boxes (OBB).
Prediction-Guided Active Experiments
In this work, we introduce a new framework for active experimentation, the Prediction-Guided Active Experiment (PGAE), which leverages predictions from an existing machine learning model to guide sampling and experimentation.
Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification
By leveraging this shared textual space as an anchor, we can prompt the ReID model to embed images from various domains into a unified semantic space, thereby alleviating catastrophic forgetting caused by domain shifts.
Advances in Photoacoustic Imaging Reconstruction and Quantitative Analysis for Biomedical Applications
Photoacoustic imaging (PAI) represents an innovative biomedical imaging modality that harnesses the advantages of optical resolution and acoustic penetration depth while ensuring enhanced safety.
A Visual Question Answering Method for SAR Ship: Breaking the Requirement for Multimodal Dataset Construction and Model Fine-Tuning
Based on these results, we selected the optimal model, YOLOv8n, as the most suitable detection network for this task.
Localization, balance and affinity: a stronger multifaceted collaborative salient object detector in remote sensing images
Despite significant advancements in salient object detection(SOD) in optical remote sensing images(ORSI), challenges persist due to the intricate edge structures of ORSIs and the complexity of their contextual relationships.
RSNet: A Light Framework for The Detection of Multi-scale Remote Sensing Targets
Recent advancements in synthetic aperture radar (SAR) ship detection using deep learning have significantly improved accuracy and speed, yet effectively detecting small objects in complex backgrounds with fewer parameters remains a challenge.
SAM-Swin: SAM-Driven Dual-Swin Transformers with Adaptive Lesion Enhancement for Laryngo-Pharyngeal Tumor Detection
Laryngo-pharyngeal cancer (LPC) is a highly lethal malignancy in the head and neck region.
EEG Emotion Copilot: Optimizing Lightweight LLMs for Emotional EEG Interpretation with Assisted Medical Record Generation
This paper presents the EEG Emotion Copilot, a system optimizing a lightweight large language model (LLM) with 0. 5B parameters operating in a local setting, which first recognizes emotional states directly from EEG signals, subsequently generates personalized diagnostic and treatment suggestions, and finally supports the automation of assisted electronic medical records.
Efficient One-Step Diffusion Refinement for Snapshot Compressive Imaging
Subsequently, a one-step diffusion model produces high-frequency residuals to enhance these initial predictions.
SAM-FNet: SAM-Guided Fusion Network for Laryngo-Pharyngeal Tumor Detection
However, they are still limited in their capabilities to accurately locate the lesion region and capture the discriminative feature information between the global and local branches.
STANet: A Novel Spatio-Temporal Aggregation Network for Depression Classification with Small and Unbalanced FMRI Data
In this study, we propose the Spatio-Temporal Aggregation Network (STANet) for diagnosing depression by integrating CNN and RNN to capture both temporal and spatial features of brain activity.
Neural Modulation Alteration to Positive and Negative Emotions in Depressed Patients: Insights from fMRI Using Positive/Negative Emotion Atlas
This research enhances our understanding of emotion modulation in depression, with implications for diagnosis and treatment evaluation.
A Tale of Single-channel Electroencephalogram: Devices, Datasets, Signal Processing, Applications, and Future Directions
Single-channel electroencephalogram (EEG) is a cost-effective, comfortable, and non-invasive method for monitoring brain activity, widely adopted by researchers, consumers, and clinicians.
Leveraging large language models for nano synthesis mechanism explanation: solid foundations or mere conjectures?
With the rapid development of artificial intelligence (AI), large language models (LLMs) such as GPT-4 have garnered significant attention in the scientific community, demonstrating great potential in advancing scientific discovery.
How Does Quantization Affect Multilingual LLMs?
Quantization techniques are widely used to improve inference speed and deployment of large language models.
MHNet: Multi-view High-order Network for Diagnosing Neurodevelopmental Disorders Using Resting-state fMRI
However, many models either use graph neural networks (GNN) to construct single-level brain functional networks (BFNs) or employ spatial convolution filtering for local information extraction from rs-fMRI data, often neglecting high-order features crucial for NDD classification.
A Cross Spatio-Temporal Pathology-based Lung Nodule Dataset
Recently, intelligent analysis of lung nodules with the assistant of computer aided detection (CAD) techniques can improve the accuracy rate of lung cancer diagnosis.
A Lung Nodule Dataset with Histopathology-based Cancer Type Annotation
Recently, Computer-Aided Diagnosis (CAD) systems have emerged as indispensable tools in clinical diagnostic workflows, significantly alleviating the burden on radiologists.
You Only Acquire Sparse-channel (YOAS): A Unified Framework for Dense-channel EEG Generation
The YOAS totally consists of four sequential stages: Data Preparation, Data Preprocessing, Biased-EEG Generation, and Synthetic EEG Generation.
MM-GTUNets: Unified Multi-Modal Graph Deep Learning for Brain Disorders Prediction
Graph deep learning (GDL) has demonstrated impressive performance in predicting population-based brain disorders (BDs) through the integration of both imaging and non-imaging data.
Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion
Meanwhile, a network, dubbed as Masked ControlNet, is designed to utilize these object masks for object generation in the misaligned visual control region.
Bayesian Online Multiple Testing: A Resource Allocation Approach
We start with general arrival distributions and show that a simple policy achieves a $O(\sqrt{T})$ regret.
Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences
To address these limitations, we explore the problem of Few-Shot Stylized Visual Captioning, which aims to generate captions in any desired style, using only a few examples as guidance during inference, without requiring further training.
Boundary-semantic collaborative guidance network with dual-stream feedback mechanism for salient object detection in optical remote sensing imagery
Finally, to obtain more complete saliency maps, we consider the uniqueness of the last layer of the decoder for the first time and propose the adaptive feedback refinement (AFR) module, which further refines feature representation and eliminates differences between features through a unique feedback mechanism.
An Empirical Study of Low Precision Quantization for TinyML
In this study, we focus on post-training quantization (PTQ) algorithms that quantize a model to low-bit (less than 8-bit) precision with only a small set of calibration data and benchmark them on different tinyML use cases.
2020 CATARACTS Semantic Segmentation Challenge
In 2020, we released pixel-wise semantic annotations for anatomy and instruments for 4670 images sampled from 25 videos of the CATARACTS training set.
A Zest of LIME: Towards Architecture-Independent Model Distances
In this paper, we instead propose to compute distance between black-box models by comparing their Local Interpretable Model-Agnostic Explanations (LIME).
Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods
In this paper, we consider stochastic second-order methods for minimizing a finite summation of nonconvex functions.
Towards Generation and Evaluation of Comprehensive Mapping Robot Datasets
This paper presents a fully hardware synchronized mapping robot with support for a hardware synchronized external tracking system, for super-precise timing and localization.
Robotics
Efficient GAN-based method for cyber-intrusion detection
Ubiquitous anomalies endanger the security of our system constantly.
