Search Results for author:
Found 58 papers, 13 papers with code
DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction
Event extraction aims to identify an event and then extract the arguments participating in the event.
先秦词网构建及梵汉对比研究(The Construction of Pre-Qin Ancient Chinese WordNet and Cross Language Comparative Study between Ancient Sanskrit WordNet and Pre-Qin Ancient Chinese WordNet)
“先秦汉语在汉语史研究上具有重要地位, 然而以往的研究始终没有形成结构化的先秦词汇资源, 难以满足古汉语信息处理和跨语言对比的研究需要。国际上以英文词网(WordNet)的义类架构为基础, 已经建立了数十种语言的词网, 已经成为多语言自然语言处理和跨语言对比的基础资源。本文综述了国内外各种词网的构建情况, 特别是古代语言的词网和汉语词网, 然后详细介绍了先秦词网的构建和校正过程, 构建起了涵盖43591个词语、61227个义项、17975个义类的先秦汉语词网。本文还通过与古梵语词网的跨语言对比, 尝试分析这两种古老语言在词汇上的共性和差异, 初步验证先秦词网的有效性。”
Manga Generation via Layout-controllable Diffusion
However, there are few studies on generating multi-panel Manga (Japanese comics) solely based on plain text.
Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition
Moreover, existing methods for ambiguous actions often overemphasize local details, resulting in the loss of crucial global context, which further complicates the task of differentiating ambiguous actions.
3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting
The creation of 3D scenes has traditionally been both labor-intensive and costly, requiring designers to meticulously configure 3D assets and environments.
DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration
Recent advancements in Large Language Models (LLMs) have opened new avenues for accelerating drug discovery processes.
D$^3$epth: Self-Supervised Depth Estimation with Dynamic Mask in Dynamic Scenes
First, within the self-supervised framework, we design a reprojection constraint to identify regions likely to contain dynamic objects, allowing the construction of a dynamic mask that mitigates their impact at the loss level.
GWQ: Gradient-Aware Weight Quantization for Large Language Models
Compared to current quantization methods, GWQ can be applied to multiple language models and achieves lower PPL on the WikiText2 and C4 dataset.
Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law
To address this issue, we propose an efficient law article recommendation approach utilizing a Knowledge Graph (KG) and a Large Language Model (LLM).
On metric choice in dimension reduction for Fréchet regression
Fr\'echet regression is becoming a mainstay in modern data analysis for analyzing non-traditional data types belonging to general metric spaces.
Depth Matters: Exploring Deep Interactions of RGB-D for Semantic Segmentation in Traffic Scenes
RGB-D has gradually become a crucial data source for understanding complex scenes in assisted driving.
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
In the limiting model, the first attention layer acts as a $\mathit{copier}$, copying past tokens within a given window to each position, and the feed-forward network with normalization acts as a $\mathit{selector}$ that generates a feature vector by only looking at informationally relevant parents from the window.
Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods
This estimator effectively solves the multi-step reasoning problem by aggregating a posterior distribution inferred from the demonstration examples in the prompt.
Practical Marketplace Optimization at Uber Using Causally-Informed Machine Learning
Budget allocation of marketplace levers, such as incentives for drivers and promotions for riders, has long been a technical and business challenge at Uber; understanding lever budget changes' impact and estimating cost efficiency to achieve predefined budgets is crucial, with the goal of optimal allocations that maximize business value; we introduce an end-to-end machine learning and optimization procedure to automate budget decision-making for cities, relying on feature store, model training and serving, optimizers, and backtesting; proposing state-of-the-art deep learning (DL) estimator based on S-Learner and a novel tensor B-Spline regression model, we solve high-dimensional optimization with ADMM and primal-dual interior point convex optimization, substantially improving Uber's resource allocation efficiency.
Fintech and MSEs Innovation: an Empirical Analysis
Employing a comprehensive survey of micro and small enterprises (MSEs) and the Digital Financial Inclusion Index in China, this study investigates the influence of fintech on MSE innovation empirically.
Why does in-context learning fail sometimes? Evaluating in-context learning on open and closed questions
This effect is especially visible for open questions and questions of high difficulty or novelty.
Contractual Reinforcement Learning: Pulling Arms with Invisible Hands
The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection.
From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems
In this work, from a theoretical lens, we aim to understand why large language model (LLM) empowered agents are able to solve decision-making problems in the physical world.
Digital finance, Bargaining Power and Gender Wage Gap
The proliferation of internet technology has catalyzed the rapid development of digital finance, significantly impacting the optimization of resource allocation in China and exerting a substantial and enduring influence on the structure of employment and income distribution.
Fermat Number Transform Based Chromatic Dispersion Compensation and Adaptive Equalization Algorithm
By introducing the Fermat number transform into chromatic dispersion compensation and adaptive equalization, the computational complexity has been reduced by 68% compared with the con? ventional implementation.
A minimal model of boosting and waning iin a recurrent seasonal epidemic
We propose a model of the immunity to a cyclical epidemic disease taking account not only of seasonal boosts during the infectious season, but also of residual immunity remaining from one season to the next.
Salient Sparse Visual Odometry With Pose-Only Supervision
Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs.
Implicit Regularization of Gradient Flow on One-Layer Softmax Attention
Under a separability assumption on the data, we show that when gradient flow achieves the minimal loss value, it further implicitly minimizes the nuclear norm of the product of the key and query weight matrices.
Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality
In addition, we prove that an interesting "task allocation" phenomenon emerges during the gradient flow dynamics, where each attention head focuses on solving a single task of the multi-task model.
Cooperative Learning with Gaussian Processes for Euler-Lagrange Systems Tracking Control under Switching Topologies
This work presents an innovative learning-based approach to tackle the tracking control problem of Euler-Lagrange multi-agent systems with partially unknown dynamics operating under switching communication topologies.
Context Matters: Data-Efficient Augmentation of Large Language Models for Scientific Applications
In this paper, we explore the challenges inherent to Large Language Models (LLMs) like GPT-4, particularly their propensity for hallucinations, logic mistakes, and incorrect conclusions when tasked with answering complex questions.
Actions Speak What You Want: Provably Sample-Efficient Reinforcement Learning of the Quantal Stackelberg Equilibrium from Strategic Feedbacks
The goal of the leader is to find her optimal policy, which yields the optimal expected total return, by interacting with the follower and learning from data.
Adaptive Parameter Estimation under Finite Excitation
And it is given that the theoretical analysis of the proposed method in stability and robustness.
Image Quality-aware Diagnosis via Meta-knowledge Co-embedding
Medical images usually suffer from image degradation in clinical practice, leading to decreased performance of deep learning-based models.
Unsupervised detection of small hyperreflective features in ultrahigh resolution optical coherence tomography
Recent advances in optical coherence tomography such as the development of high speed ultrahigh resolution scanners and corresponding signal processing techniques may reveal new potential biomarkers in retinal diseases.
A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations
We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data.
VDDT: Improving Vessel Detection with Deformable Transfomer
In this paper, we use Deformable DETR as the baseline model and modify it on top of that.
Ranked #1 on
Vessel Detection
on Vessel detection Dateset
Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model
Such a problem is modeled as a Stackelberg game between the principal and the agent, where the principal announces a scoring rule that specifies the payment, and then the agent then chooses an effort level that maximizes her own profit and reports the information.
Retinal blood flow speed quantification at the capillary level using temporal autocorrelation fitting OCTA
Optical coherence tomography angiography (OCTA) can visualize vasculature structures, but provides limited information about the blood flow speeds.
DiP: Learning Discriminative Implicit Parts for Person Re-Identification
In person re-identification (ReID) tasks, many works explore the learning of part features to improve the performance over global image features.
Ranked #2 on
Person Re-Identification
on CUHK03 detected
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
A Spatiotemporal Model for Precise and Efficient Fully-automatic 3D Motion Correction in OCT
Optical coherence tomography (OCT) is a micrometer-scale, volumetric imaging modality that has become a clinical standard in ophthalmology.
The planted XY model: thermodynamics and inference
We derive the replica symmetric (RS) phase diagram in the temperature, ferromagnetic bias plane using the approximate message passing (AMP) algorithm and its state evolution (SE).
Few-shot Forgery Detection via Guided Adversarial Interpolation
Notably, our method is also validated to be robust to choices of majority and minority forgery approaches.
X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation
2) Squeeze Stage: X-Learner condenses the model to a reasonable size and learns the universal and generalizable representation for various tasks transferring.
Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic
Specifically, we consider a version of AC where the actor and critic are represented by overparameterized two-layer neural networks and are updated with two-timescale learning rates.
INTERN: A New Learning Paradigm Towards General Vision
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.
Video Temporal Relationship Mining for Data-Efficient Person Re-identification
This paper is a technical report to our submission to the ICCV 2021 VIPriors Re-identification Challenge.
ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
To counter this emerging threat, we construct the ForgeryNet dataset, an extremely large face forgery dataset with unified annotations in image- and video-level data across four tasks: 1) Image Forgery Classification, including two-way (real / fake), three-way (real / fake with identity-replaced forgery approaches / fake with identity-remained forgery approaches), and n-way (real and 15 respective forgery approaches) classification.
Probing $μ$eV ALPs with future LHAASO observation of AGN $γ$-ray spectra
For $g_{a\gamma}\gtrsim 2\times$$10^{-11} \rm GeV^{-1}$ with $m_{a}\lesssim0. 5\,\mu$eV, the flux at around 100\, TeV predicted by the ALP model can be enhanced more than an order of magnitude than that from the standard absorption, and could be detected by LHAASO.
High Energy Astrophysical Phenomena Cosmology and Nongalactic Astrophysics High Energy Physics - Phenomenology
Market Design for Tradable Mobility Credits
Further, it is more robust in the presence of forecasting errors and non-recurrent events due to the adaptiveness of the market.
Maximum a posteriori signal recovery for optical coherence tomography angiography image generation and denoising
Optical coherence tomography angiography (OCTA) is a novel and clinically promising imaging modality to image retinal and sub-retinal vasculature.
RANDOM MASK: Towards Robust Convolutional Neural Networks
We next investigate the adversarial examples which 'fool' a CNN with Random Mask.
1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020.
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context.
Ranked #2 on
Action Recognition
on AVA v2.1
Defective Convolutional Networks
Robustness of convolutional neural networks (CNNs) has gained in importance on account of adversarial examples, i. e., inputs added as well-designed perturbations that are imperceptible to humans but can cause the model to predict incorrectly.
Defective Convolutional Layers Learn Robust CNNs
We first show that predictions made by the defective CNN are less dependent on textural information, but more on shape information, and further find that adversarial examples generated by the defective CNN appear to have semantic shapes.
Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems
First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks.
A Deep Optimization Approach for Image Deconvolution
In blind image deconvolution, priors are often leveraged to constrain the solution space, so as to alleviate the under-determinacy.
Deep Neural Network Based Hyperspectral Pixel Classification With Factorized Spectral-Spatial Feature Representation
Secondly, in order to utilize the local spatial correlation among pixels, we share the previous subnetwork as a spectral feature extractor for each pixel in a patch of image, after which the spectral features of all pixels in a patch are combined and feeded into the subsequent classification subnetwork.
Spectral Image Visualization Using Generative Adversarial Networks
The adversarial loss pushes our solution to the natural image distribution using a discriminator network that is trained to differentiate between false-color images and natural-color images.
Visualization of Hyperspectral Images Using Moving Least Squares
The matching pixels between a pair of HSI and RGB image can be reused to display other HSIs captured b the same imaging sensor with natural colors.
Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence
Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization).
