Search Results for author:
Found 70 papers, 33 papers with code
Automatic True/False Question Generation for Educational Purpose
In field of teaching, true/false questioning is an important educational method for assessing students’ general understanding of learning materials.
NoahNMT at WMT 2021: Dual Transfer for Very Low Resource Supervised Machine Translation
This paper describes the NoahNMT system submitted to the WMT 2021 shared task of Very Low Resource Supervised Machine Translation.
End-to-End Simultaneous Speech Translation with Pretraining and Distillation: Huawei Noah’s System for AutoSimTranS 2022
This paper describes the system submitted to AutoSimTrans 2022 from Huawei Noah’s Ark Lab, which won the first place in the audio input track of the Chinese-English translation task.
A Water Efficiency Dataset for African Data Centers
While most attention has been paid to developed countries such as the U. S., this paper presents the first-of-its-kind dataset that combines nation-level weather and electricity generation data to estimate water usage efficiency for data centers in 41 African countries across five different climate regions.
LLM-PySC2: Starcraft II learning environment for Large Language Models
This paper introduces a new environment LLM-PySC2 (the Large Language Model StarCraft II Learning Environment), a platform derived from DeepMind's StarCraft II Learning Environment that serves to develop Large Language Models (LLMs) based decision-making methodologies.
Online Budgeted Matching with General Bids
In this paper, we remove the FLM assumption and tackle the open problem of OBM with general bids.
Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding
Multimodal Large Language Models (MLLMs) inherit the superior text understanding capabilities of LLMs and extend these capabilities to multimodal scenarios.
Bench4Merge: A Comprehensive Benchmark for Merging in Realistic Dense Traffic with Micro-Interactive Vehicles
While the capabilities of autonomous driving have advanced rapidly, merging into dense traffic remains a significant challenge, many motion planning methods for this scenario have been proposed but it is hard to evaluate them.
OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving
Then, we build a unified multi-modal vocabulary for vision, language and action.
ChatSchema: A pipeline of extracting structured information with Large Multimodal Models based on schema
For the result of value extraction based on correct key extraction, the overall accuracy was 97. 2%, precision was 95. 8%, recall was 95. 8%, and F1-score was 95. 8%.
Optical Character Recognition
Optical Character Recognition (OCR)
Positive and Unlabeled Data: Model, Estimation, Inference, and Classification
This study introduces a new approach to addressing positive and unlabeled (PU) data through the double exponential tilting model (DETM).
ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting
Additionally, when handling traffic data, researchers tend to manually design the model structure based on the data features, which makes the structure of traffic prediction redundant and the model generalizability limited.
Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing
Inspired by intraspecific competition driving species evolution, we propose a Online Fast-Slow chasing DPO (OFS-DPO) for preference alignment, simulating competition through fast and slow chasing among models to facilitate rapid adaptation.
Exploring Adversarial Robustness of Deep State Space Models
We find that fixed-parameterized SSMs have output error bounds strictly related to their parameters, limiting their AT benefits, while input-dependent SSMs may face the problem of error explosion.
Building Socially-Equitable Public Models
Public models offer predictions to a variety of downstream tasks and have played a crucial role in various AI applications, showcasing their proficiency in accurate predictions.
PRICE: A Pretrained Model for Cross-Database Cardinality Estimation
It is generally applicable to any unseen new database to attain high estimation accuracy, while its preparation cost is as little as the basic one-dimensional histogram-based CardEst methods.
A Dataset for Research on Water Sustainability
Freshwater scarcity is a global problem that requires collective efforts across all industry sectors.
A New Method in Facial Registration in Clinics Based on Structure Light Images
To abundant traditional image methods with depth information, a method in registering with depth images and traditional clinical images was investigated.
Towards SAR Automatic Target Recognition MultiCategory SAR Image Classification Based on Light Weight Vision Transformer
Synthetic Aperture Radar has been extensively used in numerous fields and can gather a wealth of information about the area of interest.
TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the domain gap between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the lack of data with comprehensive box-caption pair annotations specifically tailored for outdoor scenes.
P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors
On the other hand, we exploit a masked autoencoder to capture the prior distribution of HDMap, which can serve as a refinement module to mitigate occlusions and artifacts.
GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping
In particular, we propose an Efficient Feature Distillation (EFD) module that employs contrastive learning to efficiently and accurately distill language embeddings derived from foundational models.
MonoOcc: Digging into Monocular Semantic Occupancy Prediction
However, existing methods rely on a complex cascaded framework with relatively limited information to restore 3D scenes, including a dependency on supervision solely on the whole network's output, single-frame input, and the utilization of a small backbone.
Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
In specific, a small size of synthesized negative reviews is obtained by rewriting the positive text via a large language model.
ChatMusician: Understanding and Generating Music Intrinsically with LLM
It is based on continual pre-training and finetuning LLaMA2 on a text-compatible music representation, ABC notation, and the music is treated as a second language.
PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging
In this paper, we propose a parameter efficient framework for fine-tuning MLLMs, specifically validated on medical visual question answering (Med-VQA) and medical report generation (MRG) tasks, using public benchmark datasets.
Ranked #1 on
Medical Visual Question Answering
on VQA-RAD
(using extra training data)
Medical Report Generation
Medical Visual Question Answering
+5
Reputation-Based Federated Learning Defense to Mitigate Threats in EEG Signal Classification
This paper presents a reputation-based threat mitigation framework that defends potential security threats in electroencephalogram (EEG) signal classification during model aggregation of Federated Learning.
A Robust Adversary Detection-Deactivation Method for Metaverse-oriented Collaborative Deep Learning
Metaverse is trending to create a digital circumstance that can transfer the real world to an online platform supported by large quantities of real-time interactions.
Learning Point-wise Abstaining Penalty for Point Cloud Anomaly Detection
We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance.
3D Implicit Transporter for Temporally Consistent Keypoint Discovery
To address this issue, the Transporter method was introduced for 2D data, which reconstructs the target frame from the source frame to incorporate both spatial and temporal information.
Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering
Medical visual question answering (VQA) is a challenging task that requires answering clinical questions of a given medical image, by taking consider of both visual and language information.
Ranked #2 on
Medical Visual Question Answering
on PathVQA
Towards Environmentally Equitable AI via Geographical Load Balancing
The results demonstrate that existing GLB approaches may amplify environmental inequity while our proposed equity-aware GLB can significantly reduce the regional disparity in terms of carbon and water footprints.
Learning-Augmented Decentralized Online Convex Optimization in Networks
This paper studies decentralized online convex optimization in a networked multi-agent system and proposes a novel algorithm, Learning-Augmented Decentralized Online optimization (LADO), for individual agents to select actions only based on local online information.
Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees
The key novelty of LOMAR is a new online switching operation which, based on a judicious condition to hedge against future uncertainties, decides whether to follow the expert's decision or the RL decision for each online item.
Robustified Learning for Online Optimization with Memory Costs
In this paper, we propose a novel expert-robustified learning (ERL) approach, achieving {both} good average performance and robustness.
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection
While this paradigm is natural for image-level or pixel-level prediction, adapting it to the detection problem is challenged by the issue of proposal matching.
Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models
To respond to the global water challenges, AI models can, and also must, take social responsibility and lead by example by addressing their own water footprint.
PanGu-Σ: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing
In this work, we develop a system that trained a trillion-parameter language model on a cluster of Ascend 910 AI processors and MindSpore framework, and present the language model with 1. 085T parameters named PanGu-{\Sigma}.
LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR
In this paper, we propose a novel Eikonal formulation that conditions the implicit representation on localized shape priors which function as dense boundary value constraints, and demonstrate it works on SemanticKITTI and SemanticPOSS.
STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation
By fitting a bridge-shaped curve to the illumination map distribution, both regions are suppressed and two tasks are bridged naturally.
ADAPT: Action-aware Driving Caption Transformer
To bridge the gap, we propose an end-to-end transformer-based architecture, ADAPT (Action-aware Driving cAPtion Transformer), which provides user-friendly natural language narrations and reasoning for each decision making step of autonomous vehicular control and action.
From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds
But adapting this scheme to the state-of-the-art (SOTA) solution for PC-based layout estimation is not straightforward.
INT2: Interactive Trajectory Prediction at Intersections
One of the most challenging problems in motion forecasting is interactive trajectory prediction, whose goal is to jointly forecasts the future trajectories of interacting agents.
Self-supervised vision-language pretraining for Medical visual question answering
Medical image visual question answering (VQA) is a task to answer clinical questions, given a radiographic image, which is a challenging problem that requires a model to integrate both vision and language information.
Ranked #4 on
Medical Visual Question Answering
on PathVQA
TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation
As such, we study the challenging problem of task oriented detection, which aims to find objects that best afford an action indicated by verbs like sit comfortably on.
City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation
Neural implicit representations are drawing a lot of attention from the robotics community recently, as they are expressive, continuous and compact.
LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF
In this paper, we present LATITUDE: Global Localization with Truncated Dynamic Low-pass Filter, which introduces a two-stage localization mechanism in city-scale NeRF.
Constrained Update Projection Approach to Safe Policy Optimization
Compared to previous safe RL methods, CUP enjoys the benefits of 1) CUP generalizes the surrogate functions to generalized advantage estimator (GAE), leading to strong empirical performance.
TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents
Most existing methods divide this task into two subparts: the text reading part for obtaining the plain text from the original document images and the information extraction part for extracting key contents.
DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding
Compared with the previous opensource OCR toolbox, DavarOCR has relatively more complete support for the sub-tasks of the cutting-edge technology of document understanding.
An Extendable Maneuver Management Framework with Fault-Tolerant Mechanism for Vehicle Platoon Control System in Highway Scenario
To deal with this problem, this paper introduces a two-dimensional maneuver management framework with a fault-tolerant mechanism on the basis of the proposed hierarchical architecture for the platoon control system.
Expert-Calibrated Learning for Online Optimization with Switching Costs
Nonetheless, by using the standard practice of training an ML model as a standalone optimizer and plugging it into an ML-augmented algorithm, the average cost performance can be highly unsatisfactory.
Universal Conditional Masked Language Pre-training for Neural Machine Translation
To the best of our knowledge, this is the first work to pre-train a unified model for fine-tuning on both NMT tasks.
CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning
Although using bounds as surrogate functions to design safe RL algorithms have appeared in some existing works, we develop them at least three aspects: (i) We provide a rigorous theoretical analysis to extend the surrogate functions to generalized advantage estimator (GAE).
Semi-supervised Implicit Scene Completion from Sparse LiDAR
Recent advances show that semi-supervised implicit representation learning can be achieved through physical constraints like Eikonal equations.
Rapid Assessments of Light-Duty Gasoline Vehicle Emissions Using On-Road Remote Sensing and Machine Learning
Our results show that the ORRS measurements, assisted by the machine-learning-based ensemble model developed here, can realize day-to-day supervision of on-road vehicle-specific emissions.
1st Place Solution to ICDAR 2021 RRC-ICTEXT End-to-end Text Spotting and Aesthetic Assessment on Integrated Circuit
For the text spotting task, we detect the characters on integrated circuit and classify them based on yolov5 detection model.
A cautionary tale in fitting galaxy rotation curves with Bayesian techniques: does Newton's constant vary from galaxy to galaxy?
The application of Bayesian techniques to astronomical data is generally non-trivial because the fitting parameters can be strongly degenerated and the formal uncertainties are themselves uncertain.
Astrophysics of Galaxies Cosmology and Nongalactic Astrophysics Instrumentation and Methods for Astrophysics
Towards Reducing Severe Defocus Spread Effects for Multi-Focus Image Fusion via an Optimization Based Strategy
According to the idea that each local region in the fused image should be similar to the sharpest one among source images, this paper presents an optimization-based approach to reduce defocus spread effects.
CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts
Experimental results on two large-scale datasets support our hypothesis and show that our model can produce more accurate and commonsense-aware emotional responses and achieve better human ratings than state-of-the-art models that only specialize in one aspect.
On Convergence of Gradient Expected Sarsa($λ$)
We study the convergence of $\mathtt{Expected~Sarsa}(\lambda)$ with linear function approximation.
Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry
In this paper, we depart from the multi-person 3D pose estimation formulation, and instead reformulate it as crowd pose estimation.
Ranked #13 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
3D Multi-Person Human Pose Estimation
3D Multi-Person Pose Estimation
+2
DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion
Infrared and visible image fusion, a hot topic in the field of image processing, aims at obtaining fused images keeping the advantages of source images.
Ranked #8 on
Semantic Segmentation
on FMB Dataset
Car Pose in Context: Accurate Pose Estimation with Ground Plane Constraints
Scene context is a powerful constraint on the geometry of objects within the scene in cases, such as surveillance, where the camera geometry is unknown and image quality may be poor.
Improving Relation Extraction with Knowledge-attention
While attention mechanisms have been proven to be effective in many NLP tasks, majority of them are data-driven.
Gradient Q$(σ, λ)$: A Unified Algorithm with Function Approximation for Reinforcement Learning
To address above problem, we propose a GQ$(\sigma,\lambda)$ that extends tabular Q$(\sigma,\lambda)$ with linear function approximation.
Policy Optimization with Stochastic Mirror Descent
Improving sample efficiency has been a longstanding goal in reinforcement learning.
Expected Sarsa($λ$) with Control Variate for Variance Reduction
In this paper, for reducing the variance, we introduce control variate technique to $\mathtt{Expected}$ $\mathtt{Sarsa}$($\lambda$) and propose a tabular $\mathtt{ES}$($\lambda$)-$\mathtt{CV}$ algorithm.
A Scalable Learned Index Scheme in Storage Systems
Index structures are important for efficient data access, which have been widely used to improve the performance in many in-memory systems.
Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network
In this paper, we propose a general framework to combine DQN and most of the return-based reinforcement learning algorithms, named R-DQN.
