Search Results for author:
Found 105 papers, 38 papers with code
Knowledge-Guided Paraphrase Identification
We propose to mine outline knowledge of concepts related to given sentences from Wikipedia via BM25 model.
Capturing the Content of a Document through Complex Event Identification
We address this task as a pipeline, first predicting whether two granular events mentioned in the text belong to the same complex event, independently of their position in the text, and then using this to cluster them into complex events.
RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios
We introduce RESIN-11, a new schema-guided event extraction&prediction framework that can be applied to a large variety of newsworthy scenarios.
BLINK: Multimodal Large Language Models Can See but Not Perceive
We introduce Blink, a new benchmark for multimodal language models (LLMs) that focuses on core visual perception abilities not found in other evaluations.
Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection
We present categorizations of the identified glitch tokens and symptoms exhibited by LLMs when interacting with glitch tokens.
Mask-ControlNet: Higher-Quality Image Generation with An Additional Mask Prompt
Then, the object images are employed as additional prompts to facilitate the diffusion model to better understand the relationship between foreground and background regions during image generation.
A Distributionally Robust Model Predictive Control for Static and Dynamic Uncertainties in Smart Grids
The distinctive contribution of this paper lies in its holistic approach to both static and dynamic uncertainties in smart grids.
Stochastic Gradient Langevin Unlearning
Our approach achieves a similar utility under the same privacy constraint while using $2\%$ and $10\%$ of the gradient computations compared with the state-of-the-art gradient-based approximate unlearning methods for mini-batch and full-batch settings, respectively.
Subequivariant Reinforcement Learning Framework for Coordinated Motion Control
Effective coordination is crucial for motion control with reinforcement learning, especially as the complexity of agents and their motions increases.
DL2Fence: Integrating Deep Learning and Frame Fusion for Enhanced Detection and Localization of Refined Denial-of-Service in Large-Scale NoCs
This study introduces a refined Flooding Injection Rate-adjustable Denial-of-Service (DoS) model for Network-on-Chips (NoCs) and more importantly presents DL2Fence, a novel framework utilizing Deep Learning (DL) and Frame Fusion (2F) for DoS detection and localization.
NNCTC: Physical Layer Cross-Technology Communication via Neural Networks
In this work, we present NNCTC, a Neural-Network-based Cross-Technology Communication framework inspired by the adaptability of trainable neural models in wireless communications.
Logic Rules as Explanations for Legal Case Retrieval
In this paper, we address the issue of using logic rules to explain the results from legal case retrieval.
PRSA: Prompt Reverse Stealing Attacks against Large Language Models
In the mutation phase, we propose a prompt attention algorithm based on differential feedback to capture these critical features for effectively inferring the target prompts.
$C^3$: Confidence Calibration Model Cascade for Inference-Efficient Cross-Lingual Natural Language Understanding
Existing model cascade methods seek to enhance inference efficiency by greedily selecting the lightest model capable of processing the current input from a variety of models, based on model confidence scores.
OMGEval: An Open Multilingual Generative Evaluation Benchmark for Large Language Models
We evaluate several representative multilingual LLMs on the proposed OMGEval, which we believe will provide a valuable reference for the community to further understand and improve the multilingual capability of LLMs.
BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering
Retrieval-augmented Large Language Models (LLMs) offer substantial benefits in enhancing performance across knowledge-intensive scenarios.
Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
To further exploit the capabilities of bootstrapping, we investigate and adjust the training order of data, which yields improved performance of the model.
Multi-Center Fetal Brain Tissue Annotation (FeTA) Challenge 2022 Results
The FeTA Challenge 2022 was able to successfully evaluate and advance generalizability of multi-class fetal brain tissue segmentation algorithms for MRI and it continues to benchmark new algorithms.
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset
Different from previous works that simply translate English instructions, we consider both the language-specific and language-agnostic abilities of LLMs.
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
We propose Langevin unlearning, an unlearning framework based on noisy gradient descent with privacy guarantees for approximate unlearning problems.
Beyond Fidelity: Explaining Vulnerability Localization of Learning-based Detectors
Vulnerability detectors based on deep learning (DL) models have proven their effectiveness in recent years.
Digger: Detecting Copyright Content Mis-usage in Large Language Model Training
In this paper, we introduce a detailed framework designed to detect and assess the presence of content from potentially copyrighted books within the training datasets of LLMs.
Enhancing Medical Task Performance in GPT-4V: A Comprehensive Study on Prompt Engineering Strategies
OpenAI's latest large vision-language model (LVLM), GPT-4V(ision), has piqued considerable interest for its potential in medical applications.
SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masks
Segment Anything Model (SAM) has achieved impressive results for natural image segmentation with input prompts such as points and bounding boxes.
Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey
After carefully examining these studies, we designed a taxonomy of pitfalls in LM4Code research and conducted a systematic study to summarize the issues, implications, current solutions, and challenges of different pitfalls for LM4Code systems.
Adapt Anything: Tailor Any Image Classifiers across Domains And Categories Using Text-to-Image Diffusion Models
Such a one-for-all adaptation paradigm allows us to adapt anything in the world using only one text-to-image generator as well as the corresponding unlabeled target data.
On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
Focusing on per-instance differential privacy (pDP), our framework elucidates the potential privacy leakage for each data point in a given training dataset, offering insights into data preprocessing to reduce privacy risks of the synthetic dataset generation via DDMs.
SAM-Med3D
These issues can hardly be addressed by fine-tuning SAM on medical data because the original 2D structure of SAM neglects 3D spatial information.
DIG-MILP: a Deep Instance Generator for Mixed-Integer Linear Programming with Feasibility Guarantee
Mixed-integer linear programming (MILP) stands as a notable NP-hard problem pivotal to numerous crucial industrial applications.
Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendation
Existing HIN-based recommender systems operate under the assumption of centralized storage and model training.
Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes
The color component is estimated from aligned multi-exposure images, while the structure one is generated through a structure-focused network that is supervised by the color component and an input reference (\eg, medium-exposure) image.
Towards Poisoning Fair Representations
Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female.
Learning to Recover for Safe Reinforcement Learning
Safety controllers is widely used to achieve safe reinforcement learning.
Channel Reciprocity Attacks Using Intelligent Surfaces with Non-Diagonal Phase Shifts
While reconfigurable intelligent surface (RIS) technology has been shown to provide numerous benefits to wireless systems, in the hands of an adversary such technology can also be used to disrupt communication links.
Are Large Language Models Really Robust to Word-Level Perturbations?
Notably, we are surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted.
GLAD: Content-aware Dynamic Graphs For Log Anomaly Detection
Subsequently, GLAD utilizes a temporal-attentive graph edge anomaly detection model for identifying anomalous relations in these dynamic log graphs.
Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty
Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples.
Ranked #6 on
Open Information Extraction
on OIE2016
A-Eval: A Benchmark for Cross-Dataset Evaluation of Abdominal Multi-Organ Segmentation
To address these questions, we introduce A-Eval, a benchmark for the cross-dataset Evaluation ('Eval') of Abdominal ('A') multi-organ segmentation.
SAM-Med2D
To bridge this gap, we introduce SAM-Med2D, the most comprehensive studies on applying SAM to medical 2D images.
Large Language Models for Software Engineering: A Systematic Literature Review
Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages.
Versatile Face Animator: Driving Arbitrary 3D Facial Avatar in RGBD Space
Creating realistic 3D facial animation is crucial for various applications in the movie production and gaming industry, especially with the burgeoning demand in the metaverse.
LIVABLE: Exploring Long-Tailed Classification of Software Vulnerability Types
(2) adaptive re-weighting module, which adjusts the learning weights for different types according to the training epochs and numbers of associated samples by a novel training loss.
Prompt Injection attack against LLM-integrated Applications
We deploy HouYi on 36 actual LLM-integrated applications and discern 31 applications susceptible to prompt injection.
DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model
Multilingual self-supervised speech representation models have greatly enhanced the speech recognition performance for low-resource languages, and the compression of these huge models has also become a crucial prerequisite for their industrial application.
Task-Agnostic Structured Pruning of Speech Representation Models
Self-supervised pre-trained models such as Wav2vec2, Hubert, and WavLM have been shown to significantly improve many speech tasks.
Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey
In this article, we present a comprehensive survey on domain specification techniques for large language models, an emerging direction critical for large language model applications.
Whisper-KDQ: A Lightweight Whisper via Guided Knowledge Distillation and Quantization for Efficient ASR
Due to the rapid development of computing hardware resources and the dramatic growth of data, pre-trained models in speech recognition, such as Whisper, have significantly improved the performance of speech recognition tasks.
Glocal Energy-based Learning for Few-Shot Open-Set Recognition
Few-shot open-set recognition (FSOR) is a challenging task of great practical value.
STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-training
However, the state-of-the-art models for medical image segmentation are still small-scale, with their parameters only in the tens of millions.
Echo disappears: momentum term structure and cyclic information in turnover
We extract cyclic information in turnover and find it can explain the momentum echo.
Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
Deep neural networks are proven to be vulnerable to backdoor attacks.
HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargeting
We present a simple yet effective method for skeleton-free motion retargeting.
SimFair: A Unified Framework for Fairness-Aware Multi-Label Classification
This new framework utilizes data that have similar labels when estimating fairness on a particular label group for better stability, and can unify DP and EOp.
Unsupervised Learning for Combinatorial Optimization Needs Meta-Learning
With this observation, we propose a new objective of unsupervised learning for CO where the goal of learning is to search for good initialization for future problem instances rather than give direct solutions.
Resampling Sensitivity of High-Dimensional PCA
Let $ \mathbf{v} $ and $ \mathbf{v}^{[k]} $ denote the principal components of $ \mathbf{X} $ and $ \mathbf{X}^{[k]} $.
Generic Temporal Reasoning with Differential Analysis and Explanation
Temporal reasoning is the task of predicting temporal relations of event pairs.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
Exploring Vanilla U-Net for Lesion Segmentation from Whole-body FDG-PET/CT Scans
The combination of PET-based metabolic and CT-based anatomic information can contribute to better tumor segmentation results.
Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models
Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world.
Zero-Shot On-the-Fly Event Schema Induction
The answers to these questions can be found by collecting many documents on the complex event of interest, extracting relevant information, and analyzing it.
Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction
In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives.
Ranked #3 on
Temporal Relation Classification
on MATRES
Are All Steps Equally Important? Benchmarking Essentiality Detection of Events
In this paper, we address this gap by examining the extent to which current models comprehend the essentiality of step events in relation to a goal event.
An evaluation of U-Net in Renal Structure Segmentation
Renal structure segmentation from computed tomography angiography~(CTA) is essential for many computer-assisted renal cancer treatment applications.
Gaze Estimation Approach Using Deep Differential Residual Network
We propose a differential residual model (DRNet) combined with a new loss function to make use of the difference information of two eye images.
Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation
Using machine learning to solve combinatorial optimization (CO) problems is challenging, especially when the data is unlabeled.
The THUEE System Description for the IARPA OpenASR21 Challenge
For the Constrained training condition, we construct our basic ASR system based on the standard hybrid architecture.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving
One main reason that impedes the development of truly reliably self-driving systems is the lack of public datasets for evaluating the performance of object detectors on corner cases.
Towards Efficient Data-Centric Robust Machine Learning with Noise-based Augmentation
The data-centric machine learning aims to find effective ways to build appropriate datasets which can improve the performance of AI models.
Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition
To solve the problem, we propose a multi-modality feature fusion network to combine the modalities of the skeleton sequence and RGB frame instead of the RGB video, as the key information contained by the combination of skeleton sequence and RGB frame is close to that of the skeleton sequence and RGB video.
Random Graph Matching in Geometric Models: the Case of Complete Graphs
This paper studies the problem of matching two complete graphs with edge weights correlated through latent geometries, extending a recent line of research on random graph matching with independent edge weights to geometric models.
Numerical Demonstration of Multiple Actuator Constraint Enforcement Algorithm for a Molten Salt Loop
In this work, we focus on the specific problem of optimal control during autonomous operation.
Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesis
Due to such huge differences between different styles, it is necessary to incorporate the talking style into audio-driven talking face synthesis framework.
BCDR: Betweenness Centrality-based Distance Resampling for Graph Shortest Distance Embedding
Second, we perform Distance Resampling (DR) from original walk paths before maximum likelihood optimization instead of the PMI-based optimization and prove that this strategy preserves distance relation with respect to any calibrated node via steering optimization objective to reconstruct a global distance matrix.
Learning Constraints and Descriptive Segmentation for Subevent Detection
The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes.
Multimodal Emergent Fake News Detection via Meta Neural Process Networks
The experimental results show our proposed MetaFEND model can detect fake news on never-seen events effectively and outperform the state-of-the-art methods.
RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System
We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities (speech, text, image and video).
DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection
The core of the attack is a neural conditional branch constructed with a trigger detector and several operators and injected into the victim model as a malicious payload.
An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications
In contrast, faults related to the deployment of DL models on mobile devices (named as deployment faults of mobile DL apps) have not been well studied.
Unsupervised Label-aware Event Trigger and Argument Classification
Rather than relying on annotated data, our model matches the semantics of identified events with those of event type labels.
What Are You Trying to Do? Semantic Typing of Event Processes
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given anevent process, attempts to infer free-form typelabels describing (i) the type of action made bythe process and (ii) the type of object the pro-cess seeks to affect.
Analogous Process Structure Induction for Sub-event Sequence Prediction
Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its components into (soft) event categories.
"What Are You Trying to Do?" Semantic Typing of Event Processes
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given an event process, attempts to infer free-form type labels describing (i) the type of action made by the process and (ii) the type of object the process seeks to affect.
Joint Constrained Learning for Event-Event Relation Extraction
Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other.
Visualizing the Finer Cluster Structure of Large-Scale and High-Dimensional Data
Dimension reduction and visualization of high-dimensional data have become very important research topics because of the rapid growth of large databases in data science.
Beyond the Virus: A First Look at Coronavirus-themed Mobile Malware
To facilitate future research, we have publicly released all the well-labelled COVID-19 themed apps (and malware) to the research community.
Cryptography and Security
Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
Neuromorphic data, recording frameless spike events, have attracted considerable attention for the spatiotemporal information components and the event-driven processing fashion.
Ranked #11 on
Gesture Recognition
on DVS128 Gesture
Understanding Challenges in Deploying Deep Learning Based Software: An Empirical Study
Deep learning (DL) becomes increasingly pervasive, being used in a wide range of software applications.
Software Engineering
Lightrec: A memory and search-efficient recommender system
On top of such a structure, LightRec will have an item represented as additive composition of B codewords, which are optimally selected from each of the codebooks.
REGNet: REgion-based Grasp Network for End-to-end Grasp Detection in Point Clouds
Reliable robotic grasping in unstructured environments is a crucial but challenging task.
Robotics
Context-Aware Conversation Thread Detection in Multi-Party Chat
In multi-party chat, it is common for multiple conversations to occur concurrently, leading to intermingled conversation threads in chat logs.
Do Multi-hop Readers Dream of Reasoning Chains?
General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i. e. the ability to reason with information collected from multiple passages to derive the answer.
Out-of-Domain Detection for Low-Resource Text Classification Tasks
Out-of-domain (OOD) detection for low-resource text classification is a realistic but understudied task.
EVulHunter: Detecting Fake Transfer Vulnerabilities for EOSIO's Smart Contracts at Webassembly-level
Unfortunately, current tools are web-application oriented and cannot be applied to EOSIO WebAssembly code directly, which makes it more difficult to detect vulnerabilities from those smart contracts.
Cryptography and Security
Binarized Collaborative Filtering with Distilling Graph Convolutional Networks
Then we distill the ranking information derived from GCN into binarized collaborative filtering, which makes use of binary representation to improve the efficiency of online recommendation.
Group Chat Ecology in Enterprise Instant Messaging: How Employees Collaborate Through Multi-User Chat Channels on Slack
We cross-referenced 117 project teams and their team-based Slack channels and identified 57 teams that appeared in both datasets, then we built a regression model to reveal the relationship between these group communication styles and the project team performance.
Nearest-Neighbor Neural Networks for Geostatistics
We propose a more flexible spatial prediction method based on the Nearest-Neighbor Neural Network (4N) process that embeds deep learning into a geostatistical model.
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers
Most approaches to extraction multiple relations from a paragraph require multiple passes over the paragraph.
Ranked #19 on
Relation Extraction
on SemEval-2010 Task-8
Estimating 6D Pose From Localizing Designated Surface Keypoints
In this paper, we present an accurate yet effective solution for 6D pose estimation from an RGB image.
Ranked #17 on
6D Pose Estimation using RGB
on LineMOD
The Trace Criterion for Kernel Bandwidth Selection for Support Vector Data Description
Support vector data description (SVDD) is a popular anomaly detection technique.
DOLORES: Deep Contextualized Knowledge Graph Embeddings
We introduce a new method DOLORES for learning knowledge graph embeddings that effectively captures contextual cues and dependencies among entities and relations.
Diverse Few-Shot Text Classification with Multiple Metrics
We study few-shot learning in natural language domains.
Pose Flow: Efficient Online Pose Tracking
Multi-person articulated pose tracking in unconstrained videos is an important while challenging problem.
Ranked #9 on
Pose Tracking
on PoseTrack2017
(using extra training data)
Fast Incremental SVDD Learning Algorithm with the Gaussian Kernel
Each iteration involves only the existing support vectors and the new data point.
Robust Task Clustering for Deep Many-Task Learning
We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario.
