Search Results for author:
Found 25 papers, 10 papers with code
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
We introduce Seed1. 5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks.
CryptoX : Compositional Reasoning Evaluation of Large Language Models
In this paper, we introduce CryptoX, an evaluation framework that, for the first time, combines existing benchmarks and cryptographic, to quantify the compositional reasoning capacity of LLMs.
UI-TARS: Pioneering Automated GUI Interaction with Native Agents
This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions (e. g., keyboard and mouse operations).
SDM-Car: A Dataset for Small and Dim Moving Vehicles Detection in Satellite Videos
Vehicle detection and tracking in satellite video is essential in remote sensing (RS) applications.
DefFiller: Mask-Conditioned Diffusion for Salient Steel Surface Defect Generation
Current saliency-based defect detection methods show promise in industrial settings, but the unpredictability of defects in steel production environments complicates dataset creation, hampering model performance.
An Empirical Study on Information Extraction using Large Language Models
To demonstrate the latest representative progress in LLMs' information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from four perspectives: Performance, Evaluation Criteria, Robustness, and Error Types.
AI-based Automatic Segmentation of Prostate on Multi-modality Images: A Review
However, prostate segmentation is challenging due to imperfections in the images and the prostate's complex tissue structure.
Defect Image Sample Generation With Diffusion Prior for Steel Surface Defect Recognition
To this end, we propose Stable Surface Defect Generation (StableSDG), which transfers the vast generation distribution embedded in Stable Diffusion model for steel surface defect image generation.
RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation
This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces.
An Empirical Study on Information Extraction using Large Language Models
To demonstrate the latest representative progress in LLMs' information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from four perspectives: Performance, Evaluation Criteria, Robustness, and Error Types.
Document-level Relation Extraction with Relation Correlations
Document-level relation extraction faces two overlooked challenges: long-tail problem and multi-label problem.
BEV-Locator: An End-to-end Visual Semantic Localization Network Using Multi-View Images
Then a cross-model transformer associates the BEV features and semantic map queries.
Ghost translation
This translation mechanism opens a new direction for DNN-assisted ghost imaging and can be used in various computational imaging scenarios.
Recurrence-free Survival Prediction under the Guidance of Automatic Gross Tumor Volume Segmentation for Head and Neck Cancers
For Head and Neck Cancers (HNC) patient management, automatic gross tumor volume (GTV) segmentation and accurate pre-treatment cancer recurrence prediction are of great importance to assist physicians in designing personalized management plans, which have the potential to improve the treatment outcome and quality of life for HNC patients.
Retinex-qDPC: automatic background rectified quantitative differential phase contrast imaging
To tackle the mismatch of background and increases the experimental robustness, we propose the Retinex-qDPC in which we use the images edge features as data fidelity term yielding L2-Retinex-qDPC and L1-Retinex-qDPC for high background-robustness qDPC reconstruction.
Deep-learned speckle pattern and its application to ghost imaging
Our method, therefore, outperforms the other techniques for ghost imaging, particularly its ability to retrieve high-quality images with extremely low sampling ratios.
Graph neural network-based fault diagnosis: a review
Graph neural network (GNN)-based fault diagnosis (FD) has received increasing attention in recent years, due to the fact that data coming from several application domains can be advantageously represented as graphs.
RSS-based Multiple Sources Localization with Unknown Log-normal Shadow Fading
Then we utilize the K-means clustering method to obtain the rough locations of the off-grid sources as the initial feasible point of the ML estimator.
0.8% Nyquist computational ghost imaging via non-experimental deep learning
We present a framework for computational ghost imaging based on deep learning and customized pink noise speckle patterns.
Ranked #1 on
on VGG Face
(using extra training data)
Distantly Supervised Relation Extraction via Recursive Hierarchy-Interactive Attention and Entity-Order Perception
Based on the above, in this paper, we design a novel Recursive Hierarchy-Interactive Attention network (RHIA) to further handle long-tail relations, which models the heuristic effect between relation levels.
Superresolving second-order correlation imaging using synthesized colored noise speckles
We present a novel method to synthesize non-trivial speckles that can enable superresolving second-order correlation imaging.
Optics Image and Video Processing
High order Coherence Functions and Spectral Distributions as given by the Quantum Theory of Laser Radiation
We propose and demonstrate a method for measuring the time evolution of the off-diagonal elements $\rho_{n, n+k}(t)$ of the reduced density matrix obtained from the quantum theory of the laser.
Optics
Non-invasive imaging of object behind strongly scattering media via cross-spectrum
We develop a method based on the cross-spectrum of an intensity-modulated CW laser, which can extract a signal from an extremely noisy environment and image objects hidden in turbid media.
Optics Biological Physics
ALBERT-BiLSTM for Sequential Metaphor Detection
In our daily life, metaphor is a common way of expression.
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Results of 33 object detection algorithms are presented.
