Search Results for author:
Found 28 papers, 15 papers with code
PingAnTech at SMM4H task1: Multiple pre-trained model approaches for Adverse Drug Reactions
For task 1a, the system achieved an F1 score of 0. 68; for task 1b Overlapping F1 score of 0. 65 and a Strict F1 score of 0. 49.
Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators
Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language.
On Task Performance and Model Calibration with Supervised and Self-Ensembled In-Context Learning
Following the standard supervised fine-tuning (SFT) paradigm, in-context learning (ICL) has become an efficient approach propelled by the recent advancements in large language models (LLMs), yielding promising performance across various tasks in few-shot data setups.
A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems
Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP.
Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning
Prompt-based learning has been an effective paradigm for large pretrained language models (LLM), enabling few-shot or even zero-shot learning.
A Corrected Expected Improvement Acquisition Function Under Noisy Observations
Sequential maximization of expected improvement (EI) is one of the most widely used policies in Bayesian optimization because of its simplicity and ability to handle noisy observations.
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs).
A Foundation Model for General Moving Object Segmentation in Medical Images
In this paper, we propose the first foundation model, named iMOS, for MOS in medical images.
Graph-based Asynchronous Event Processing for Rapid Object Recognition
Different from traditional video cameras, event cameras capture asynchronous events stream in which each event encodes pixel location, trigger time, and the polarity of the brightness changes.
OnUVS: Online Feature Decoupling Framework for High-Fidelity Ultrasound Video Synthesis
Second, to better preserve the integrity and textural information of US images, we implemented a dual-decoder that decouples the content and textural features in the generator.
Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems
Creating high-quality annotated data for task-oriented dialog (ToD) is known to be notoriously difficult, and the challenges are amplified when the goal is to create equitable, culturally adapted, and large-scale ToD datasets for multiple languages.
Instructive Feature Enhancement for Dichotomous Medical Image Segmentation
Deep neural networks have been widely applied in dichotomous medical image segmentation (DMIS) of many anatomical structures in several modalities, achieving promising performance.
Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt
To tackle these two challenges, we propose a novel two branch network that leverages 2D discrete wavelete transform (DWT), fast Fourier convolution (FFC) residual block and a pretrained ConvNeXt model.
Segment Anything Model for Medical Images?
To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks.
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
Large pretrained language models are widely used in downstream NLP tasks via task-specific fine-tuning, but such procedures can be costly.
GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost
Large pre-trained models have revolutionized natural language processing (NLP) research and applications, but high training costs and limited data resources have prevented their benefits from being shared equally amongst speakers of all the world's languages.
PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation
Recently, the practical deployment of open-domain dialogue systems has been plagued by the knowledge issue of information deficiency and factual inaccuracy.
DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image
Light-weight time-of-flight (ToF) depth sensors are small, cheap, low-energy and have been massively deployed on mobile devices for the purposes like autofocus, obstacle detection, etc.
Spatial-Temporal Deep Embedding for Vehicle Trajectory Reconstruction from High-Angle Video
In this paper, we developed Spatial-Temporal Deep Embedding (STDE) model that imposes parity constraints at both pixel and instance levels to generate instance-aware embeddings for vehicle stripe segmentation on STMap.
Link the World: Improving Open-domain Conversation with Dynamic Spatiotemporal-aware Knowledge
Making chatbots world aware in a conversation like a human is a crucial challenge, where the world may contain dynamic knowledge and spatiotemporal state.
Combinatorial optimization for low bit-width neural networks
In this paper, we explore methods of direct combinatorial optimization in the problem of risk minimization with binary weights, which can be made equivalent to a non-monotone submodular maximization under certain conditions.
XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking
Dialogue State Tracking (DST), a crucial component of task-oriented dialogue (ToD) systems, keeps track of all important information pertaining to dialogue history: filling slots with the most probable values throughout the conversation.
MC-UNet Multi-module Concatenation based on U-shape Network for Retinal Blood Vessels Segmentation
The proposed network structure retains three layers the essential structure of U-Net, in which the atrous convolution combining the multi-kernel pooling blocks are designed to obtain more contextual information.
Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering
In this paper, we present a novel neural scene rendering system, which learns an object-compositional neural radiance field and produces realistic rendering with editing capability for a clustered and real-world scene.
VS-Net: Voting with Segmentation for Visual Localization
To address this problem, we propose a novel visual localization framework that establishes 2D-to-3D correspondences between the query image and the 3D map with a series of learnable scene-specific landmarks.
A Unified Pre-training Framework for Conversational AI
In this work, we explore the application of PLATO-2 on various dialogue systems, including open-domain conversation, knowledge grounded dialogue, and task-oriented conversation.
Time-Efficient Mars Exploration of Simultaneous Coverage and Charging with Multiple Drones
This paper presents a time-efficient scheme for Mars exploration by the cooperation of multiple drones and a rover.
