Search Results for author:
Found 18 papers, 8 papers with code
STS MICCAI 2023 Challenge: Grand challenge on 2D and 3D semi-supervised tooth segmentation
The Semi-supervised Teeth Segmentation (STS) Challenge, a pioneering event in tooth segmentation, was held as a part of the MICCAI 2023 ToothFairy Workshop on the Alibaba Tianchi platform.
Qwen2 Technical Report
This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models.
Ranked #1 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
MoE-CT: A Novel Approach For Large Language Models Training With Resistance To Catastrophic Forgetting
The advent of large language models (LLMs) has predominantly catered to high-resource languages, leaving a disparity in performance for low-resource languages.
Improving Fairness of Automated Chest X-ray Diagnosis by Contrastive Learning
Our proposed AI model utilizes supervised contrastive learning to minimize bias in CXR diagnosis.
Exploring Region-Word Alignment in Built-in Detector for Open-Vocabulary Object Detection
In the first stage an image-text dual encoder is trained to learn region-word alignment from a corpus of image-text pairs.
Controllability of networked multiagent systems based on linearized Turing's model
Under mild conditions on the parameters of the linearized Turing's model, we prove the equivalence between controllability of the linearized Turing's model and controllability of a Laplace dynamic system with agents of first order dynamics.
Vision-based Food Nutrition Estimation via RGB-D Fusion Network
In this paper, we designed one RGB-D fusion network, which integrated multimodal feature fusion (MMFF) and multi-scale fusion for visioin-based nutrition assessment.
PolyLM: An Open Source Polyglot Large Language Model
Large language models (LLMs) demonstrate remarkable ability to comprehend, reason, and generate following nature language instructions.
CancerGPT: Few-shot Drug Pair Synergy Prediction using Large Pre-trained Language Models
Large pre-trained language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data.
Steady state behavior of the free recall dynamics of working memory
Finally, we give a sufficient condition under which this model has a globally asymptotically stable equilibrium with synchronized minicolumn states in each hypercolumn, which implies that in this case recalling is impossible.
Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search
BERT-style models pre-trained on the general corpus (e. g., Wikipedia) and fine-tuned on specific task corpus, have recently emerged as breakthrough techniques in many NLP tasks: question answering, text classification, sequence labeling and so on.
SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata
In this paper, we proposed a novel and simple data augmentation method based on patient metadata and supervised knowledge to create clinically accurate positive and negative augmentations for chest X-rays.
Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
Instead, from a perspective on temporal grounding as a metric-learning problem, we present a Mutual Matching Network (MMN), to directly model the similarity between language queries and video moments in a joint embedding space.
Ranked #3 on
Temporal Sentence Grounding
on Charades-STA
Self Supervision to Distillation for Long-Tailed Visual Recognition
In this paper, we show that soft label can serve as a powerful solution to incorporate label correlation into a multi-stage training scheme for long-tailed recognition.
Ranked #44 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
A review on vision-based analysis for automatic dietary assessment
We also provide the latest ideas for future development of VBDA, e. g., fine-grained food analysis and accurate volume estimation.
A parallel-network continuous quantitative trading model with GARCH and PPO
It is a difficult task for both professional investors and individual traders continuously making profit in stock market.
Mean Field MARL Based Bandwidth Negotiation Method for Massive Devices Spectrum Sharing
In this paper, a novel bandwidth negotiation mechanism is proposed for massive devices wireless spectrum sharing, in which individual device locally negotiates bandwidth usage with neighbor devices and globally optimal spectrum utilization is achieved through distributed decision-making.
Learning Spatiotemporal Features via Video and Text Pair Discrimination
In addition, our CPD model yields a new state of the art for zero-shot action recognition on UCF101 by directly utilizing the learnt visual-textual embeddings.
