Search Results for author:
Found 90 papers, 33 papers with code
Practical Poisoning Attacks on Neural Networks
Importantly, we show that the effectiveness of BlackCard can be intuitively guaranteed by a set of analytical reasoning and observations, through exploiting an essential characteristic of gradient-descent optimization which is pervasively adopted in DNN models.
Assessing the Utility of Large Language Models for Phenotype-Driven Gene Prioritization in Rare Genetic Disorder Diagnosis
A similar increasing trend was observed for the task completion rate, with complicated prompts more likely to increase task completeness in models smaller than GPT-4.
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.
Clifford Group Equivariant Simplicial Message Passing Networks
Experimental results show that our method is able to outperform both equivariant and simplicial graph neural networks on a variety of geometric tasks.
Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
In terms of the AMG mode, Hi-SAM segments text stroke foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing.
Ranked #1 on
Hierarchical Text Segmentation
on HierText
PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models
In recent times, a plethora of Large Code Generation Models (LCGMs) have been proposed, showcasing significant potential in assisting developers with complex programming tasks.
The stability and instability of the language control network: a longitudinal resting-state functional magnetic resonance imaging study
These findings provide preliminary evidence of the coexistence of stability and instability in the language control network.
Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study
We observe that these methods generally improve the uncertainty awareness of CodeLlama, with increased calibration quality and higher uncertainty estimation~(UE) precision.
Multimodal Machine Learning Combining Facial Images and Clinical Texts Improves Diagnosis of Rare Genetic Diseases
Individuals with suspected rare genetic disorders often undergo multiple clinical evaluations, imaging studies, laboratory tests and genetic tests, to find a possible answer over a prolonged period of multiple years.
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety consideration?
Generative Input: Towards Next-Generation Input Methods Paradigm
The results demonstrate that we have achieved state-of-the-art performance for the first time in the Full-mode Key-sequence to Characters(FK2C) task.
1DFormer: a Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Tracking
For temporal modeling, we propose a recurrent token mixing mechanism, an axis-landmark-positional embedding mechanism, as well as a confidence-enhanced multi-head attention mechanism to adaptively and robustly embed long-term landmark dynamics into their 1D representations; for structure modeling, we design intra-group and inter-group structure modeling mechanisms to encode the component-level as well as global-level facial structure patterns as a refinement for the 1D representations of landmarks through token communications in the spatial dimension via 1D convolutional layers.
Untying the Reversal Curse via Bidirectional Language Model Editing
A new evaluation metric of reversibility is introduced, and a benchmark dubbed as Bidirectional Assessment for Knowledge Editing (BAKE) is constructed to evaluate the reversibility of edited models in recalling knowledge in the reverse direction of editing.
Distantly-Supervised Joint Entity and Relation Extraction with Noise-Robust Learning
However, existing research primarily addresses only one type of noise, thereby limiting the effectiveness of noise reduction.
RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models
Recent advancements in language models (LMs) have gained substantial attentions on their capability to generate human-like responses.
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.
RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics
This process ensures the scheduling framework's compatibility with MIMONet and maximizes efficiency.
R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics
These components collaboratively tackle the trade-offs in on-device DRL training, improving timing and algorithm performance while minimizing the risk of out-of-memory (OOM) errors.
4D Myocardium Reconstruction with Decoupled Motion and Shape Model
Estimating the shape and motion state of the myocardium is essential in diagnosing cardiovascular diseases. However, cine magnetic resonance (CMR) imaging is dominated by 2D slices, whose large slice spacing challenges inter-slice shape reconstruction and motion acquisition. To address this problem, we propose a 4D reconstruction method that decouples motion and shape, which can predict the inter-/intra- shape and motion estimation from a given sparse point cloud sequence obtained from limited slices.
Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT
We hypothesize that large language models (LLMs) based on the transformer architecture can enable automated detection of clinical phenotype terms, including terms not documented in the HPO.
Exploring Part-Informed Visual-Language Learning for Person Re-Identification
Recently, visual-language learning has shown great potential in enhancing visual-based person re-identification (ReID).
PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas
Our work introduces a new angle for manipulation in recent multi-agent RL social dilemmas that utilize a unique reward function for incentivization.
How Does Diffusion Influence Pretrained Language Models on Out-of-Distribution Data?
It shows that finetuning PLMs with diffusion degrades the reconstruction ability on OOD data.
MIMONet: Multi-Input Multi-Output On-Device Deep Learning
In this paper, we propose MIMONet, a novel on-device multi-input multi-output (MIMO) DNN framework that achieves high accuracy and on-device efficiency in terms of critical performance metrics such as latency, energy, and memory usage.
DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization
\tool tackles the dynamic nature of DyNNs by introducing a compilation mechanism that redistributes the control and data flow of the original DNN programs during the compilation process.
Weakly Supervised Scene Text Generation for Low-resource Languages
A large number of annotated training images is crucial for training successful scene text recognition models.
JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving
Specially, we construct a Mixture-of-Experts~(MoE) architecture for modeling mathematical text, so as to capture the common mathematical knowledge across tasks.
Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection
LiDAR and Radar are two complementary sensing approaches in that LiDAR specializes in capturing an object's 3D shape while Radar provides longer detection ranges as well as velocity hints.
SlothSpeech: Denial-of-service Attack Against Speech Recognition Models
We show that popular ASR models like Speech2Text model and Whisper model have dynamic computation based on different inputs, causing dynamic efficiency.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation
Given an MPC with a few addressee labels missing, existing methods fail to build a consecutively connected conversation graph, but only a few separate conversation fragments instead.
SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extraction
The proposed encoder is capable of interactively capturing complementary information between features and contextual information, to derive language-agnostic representations for various IE tasks.
Dynamic Transformers Provide a False Sense of Efficiency
Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference.
Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks
The key idea is that the isolation of specific task knowledge to specific masks allows agents to transfer only specific knowledge on-demand, resulting in robust and effective distributed lifelong learning.
GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding
Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention.
TinyML Design Contest for Life-Threatening Ventricular Arrhythmia Detection
This paper concludes with the direction of improvement for the future TinyML design for health monitoring applications.
White-Box Multi-Objective Adversarial Attack on Dialogue Generation
Such language models are, however, vulnerable to various adversarial samples as studied in traditional tasks such as text classification, which inspires our curiosity about their robustness in DG systems.
Uncertainty-Aware Bootstrap Learning for Joint Extraction on Distantly-Supervised Data
To mitigate such impact, we propose uncertainty-aware bootstrap learning, which is motivated by the intuition that the higher uncertainty of an instance, the more likely the model confidence is inconsistent with the ground truths.
DocMAE: Document Image Rectification via Self-supervised Representation Learning
Tremendous efforts have been made on document image rectification, but how to learn effective representation of such distorted images is still under-explored.
VGTS: Visually Guided Text Spotting for Novel Categories in Historical Manuscripts
In the field of historical manuscript research, scholars frequently encounter novel symbols in ancient texts, investing considerable effort in their identification and documentation.
HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures
Moreover, we proposed an encoder-decoder-based hierarchical document structure parsing system (DSPS) to tackle this problem.
Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition
A hard challenge in developing practical face recognition (FR) attacks is due to the black-box nature of the target FR model, i. e., inaccessible gradient and parameter information to attackers.
SEMv2: Table Separation Line Detection Based on Instance Segmentation
Table structure recognition is an indispensable element for enabling machines to comprehend tables.
Masked Images Are Counterfactual Samples for Robust Fine-tuning
In this paper, based on causal analysis of the aforementioned problems, we propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection
In this paper, we take the first step toward the study of adversarial attacks targeted at X-ray prohibited item detection, and reveal the serious threats posed by such attacks in this safety-critical scenario.
The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection
Recent advancements in deploying deep neural networks (DNNs) on resource-constrained devices have generated interest in input-adaptive dynamic neural networks (DyNNs).
Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation
Besides, we also verify that the proposed framework is able to explicitly control the emotion of the animated talking face.
Deep Hashing With Minimal-Distance-Separated Hash Centers
This paper presents an optimization method that finds hash centers with a constraint on the minimal distance between any pair of hash centers, which is non-trivial due to the non-convex nature of the problem.
PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning
To ensure the security of RL agents against malicious backdoors, in this work, we propose the problem of Backdoor Detection in multi-agent RL systems, with the objective of detecting Trojan agents as well as the corresponding potential trigger actions, and further trying to mitigate their bad impact.
Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing
Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders.
Improved Speech Pre-Training with Supervision-Enhanced Acoustic Unit
Speech pre-training has shown great success in learning useful and general latent representations from large-scale unlabeled data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Progressive Multi-Scale Self-Supervised Learning for Speech Recognition
Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information
Multilingual end-to-end models have shown great improvement over monolingual systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition
In this study, a mixture of short-channel distillers (MSD) method is proposed to fully interact the rich hierarchical information in the teacher model and to transfer knowledge to the student model sufficiently and efficiently.
Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation
AV2vec has a student and a teacher module, in which the student performs a masked latent feature regression task using the multimodal target features generated online by the teacher.
Joint Chinese Word Segmentation and Span-based Constituency Parsing
In constituency parsing, span-based decoding is an important direction.
Order-sensitive Neural Constituency Parsing
We propose a novel algorithm that improves on the previous neural span-based CKY decoder for constituency parsing.
DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks
To ensure an AdNN satisfies the performance requirements of resource-constrained applications, it is essential to conduct performance testing to detect IDPBs in the AdNN.
NMTSloth: Understanding and Testing Efficiency Degradation of Neural Machine Translation Systems
Neural Machine Translation (NMT) systems have received much recent attention due to their human-level accuracy.
JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding
Considering the complex nature of mathematical texts, we design a novel curriculum pre-training approach for improving the learning of mathematical PLMs, consisting of both basic and advanced courses.
Learning to Reverse DNNs from AI Programs Automatically
With the privatization deployment of DNNs on edge devices, the security of on-device DNNs has raised significant concern.
NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models
To further understand such efficiency-oriented threats, we propose a new attack approach, NICGSlowDown, to evaluate the efficiency robustness of NICG models.
Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention
To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window.
EREBA: Black-box Energy Testing of Adaptive Neural Networks
The test inputs generated by EREBA can increase the energy consumption of AdNNs by 2, 000% compared to the original inputs.
InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities
Knowledge graph embedding (KGE) models learn the representation of entities and relations in knowledge graphs.
Ranked #4 on
Link Property Prediction
on ogbl-wikikg2
PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning
To ensure the security of RL agents against malicious backdoors, in this work, we propose the problem of Backdoor Detection in a multi-agent competitive reinforcement learning system, with the objective of detecting Trojan agents as well as the corresponding potential trigger actions, and further trying to mitigate their Trojan behavior.
Auto robust relative radiometric normalization via latent change noise modelling
Relative radiometric normalization(RRN) of different satellite images of the same terrain is necessary for change detection, object classification/segmentation, and map-making tasks.
AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis
We approach this problem from the optimization perspective and show that the objective of backdoor detection is bounded by an adversarial objective.
TransSlowDown: Efficiency Attacks on Neural Machine Translation Systems
To further the understanding of such efficiency-oriented threats and raise the community’s concern on the efficiency robustness of NMT systems, we propose a new attack approach, TranSlowDown, to test the efficiency robustness of NMT systems.
NODEAttack: Adversarial Attack on the Energy Consumption of Neural ODEs
Unlike the memory cost, the energy consumption of the Neural ODEs during inference can be adaptive because of the adaptive nature of the ODE solvers.
Automatically eliminating seam lines with Poisson editing in complex relative radiometric normalization mosaicking scenarios
Relative radiometric normalization (RRN) mosaicking among multiple remote sensing images is crucial for the downstream tasks, including map-making, image recognition, semantic segmentation, and change detection.
Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition
Deep neural networks, particularly face recognition models, have been shown to be vulnerable to both digital and physical adversarial examples.
Neural Mean Discrepancy for Efficient Out-of-Distribution Detection
Based upon this observation, we propose a novel metric called Neural Mean Discrepancy (NMD), which compares neural means of the input examples and training data.
SAM-GAN: Self-Attention supporting Multi-stage Generative Adversarial Networks for text-to-image synthesis
With the self-attention mechanism, the model can establish the multi-level dependence of the image and fuse the sentence- and word-level visual-semantic vectors, to improve the quality of the generated image.
PredCoin: Defense against Query-based Hard-label Attack
PredCoin poisons the gradient estimation step, an essential component of most QBHL attacks.
AttackDist: Characterizing Zero-day Adversarial Samples by Counter Attack
We first theoretically clarify under which condition AttackDist can provide a certified detecting performance, then show that a potential application of AttackDist is distinguishing zero-day adversarial examples without knowing the mechanisms of new attacks.
Tensor Completion via Convolutional Sparse Coding Regularization
On the contrary, in the field of signal processing, Convolutional Sparse Coding (CSC) can provide a good representation of the high-frequency component of the image, which is generally associated with the detail component of the data.
CAVA: A Visual Analytics System for Exploratory Columnar Data Augmentation Using Knowledge Graphs
In this paper, we present CAVA, a system that integrates data curation and data augmentation with the traditional data exploration and analysis tasks, enabling information foraging in-situ during analysis.
Deep Partial Updating: Towards Communication Efficient Updating for On-device Inference
Emerging edge intelligence applications require the server to retrain and update deep neural networks deployed on remote edge nodes to leverage newly collected data samples.
PoisHygiene: Detecting and Mitigating Poisoning Attacks in Neural Networks
Being able to detect and mitigate poisoning attacks, typically categorized into backdoor and adversarial poisoning (AP), is critical in enabling safe adoption of DNNs in many application domains.
PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving
We compare PhysGAN with a set of state-of-the-art baseline methods including several of our self-designed ones, which further demonstrate the robustness and efficacy of our approach.
Episodic Training for Domain Generalization
In this paper, we build on this strong baseline by designing an episodic training procedure that trains a single deep network in a way that exposes it to the domain shift that characterises a novel domain at runtime.
Ranked #76 on
Domain Generalization
on PACS
DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems
Furthermore, DeepBillboard is sufficiently robust and resilient for generating physical-world adversarial billboard tests for real-world driving under various weather conditions.
DeepRoad: GAN-based Metamorphic Autonomous Driving System Testing
In this paper, we propose DeepRoad, an unsupervised framework to automatically generate large amounts of accurate driving scenes to test the consistency of DNN-based autonomous driving systems across different scenes.
Software Engineering
BENCHIP: Benchmarking Intelligence Processors
The variety of emerging intelligence processors requires standard benchmarks for fair comparison and system optimization (in both software and hardware).
High-dimensional omics data analysis using a variable screening protocol with prior knowledge integration (SKI)
Results In this study, we proposed an integrative prescreening approach, SKI, for high-throughput data analysis.
Semantic Relation Classification via Hierarchical Recurrent Neural Network with Attention
Semantic relation classification remains a challenge in natural language processing.
Improved Word Embeddings with Implicit Structure Information
Distributed word representation is an efficient method for capturing semantic and syntactic word relations.
Modelling Sentence Pairs with Tree-structured Attentive Encoder
We describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs.
Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
In this paper, we propose a novel neural network structure, namely \emph{feedforward sequential memory networks (FSMN)}, to model long-term dependency in time series without using recurrent feedback.
A Divide-and-Conquer Method for Scalable Low-Rank Latent Matrix Pursuit
To address this issue, we provide a scalable solution for large-scale low-rank latent matrix pursuit by a divide-andconquer method.
