Search Results for author:
Found 349 papers, 157 papers with code
Dual Attention Model for Citation Recommendation with Analyses on Explainability of Attention Mechanisms and Qualitative Experiments
A neural network model is designed to maximize the similarity between the embedding of the three inputs (local context words, section headers, and structural contexts) and the target citation appearing in the context.
Integrating Encyclopedic Knowledge into Neural Language Models
Neural models have recently shown big improvements in the performance of phrase-based machine translation.
Large Language Models Can Plan Your Travels Rigorously with Formal Verification Tools
We evaluate our framework with TravelPlanner and achieve a success rate of 97%.
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns.
Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models
This paper studies the relationship between the surface form of a mathematical problem and its solvability by large language models.
Exact and Efficient Unlearning for Large Language Model-based Recommendation
The evolving paradigm of Large Language Model-based Recom- mendation (LLMRec) customizes Large Language Models (LLMs) through parameter-efficient fine-tuning (PEFT) using recommenda- tion data.
RULER: What's the Real Context Size of Your Long-Context Language Models?
Despite achieving nearly perfect accuracy in the vanilla NIAH test, all models exhibit large performance drops as the context length increases.
Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation
The proliferation of online misinformation has posed significant threats to public interest.
Beamforming Design for Double-Active-RIS-aided Communication Systems with Inter-Excitation
Due to the signal amplification capability of active RISs, the mutual influence between active RISs, which is termed as the "inter-excitation" effect, cannot be ignored.
Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models
Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks.
The 2nd Workshop on Recommendation with Generative Models
The rise of generative models has driven significant advancements in recommender systems, leaving unique opportunities for enhancing users' personalized recommendations.
HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations
It is especially challenging to achieve real-time human motion tracking on a standalone VR Head-Mounted Display (HMD) such as Meta Quest and PICO.
DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalization
With the recent advance of vision-language models (VLMs), viewed as natural source models, the cross-domain task changes to directly adapt the pre-trained source model to arbitrary target domains equipped with prior domain knowledge, and we name this task Adaptive Domain Generalization (ADG).
A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods
Automatic Text Summarization (ATS), utilizing Natural Language Processing (NLP) algorithms, aims to create concise and accurate summaries, thereby significantly reducing the human effort required in processing large volumes of text.
Lower-Left Partial AUC: An Effective and Efficient Optimization Metric for Recommendation
Compared to AUC, LLPAUC considers only the partial area under the ROC curve in the Lower-Left corner to push the optimization focus on Top-K. We provide theoretical validation of the correlation between LLPAUC and Top-K ranking metrics and demonstrate its robustness to noisy user feedback.
Enhancing Long-Term Recommendation with Bi-level Learnable Large Language Model Planning
To achieve this, we propose a Bi-level Learnable LLM Planner framework, which combines macro-learning and micro-learning through a hierarchical mechanism.
Prospect Personalized Recommendation on Large Language Model-based Agent Platform
Additionally, we prospect the evolution of Rec4Agentverse and conceptualize it into three stages based on the enhancement of the interaction and information exchange among Agent Items, Agent Recommender, and the user.
An Efficient MLP-based Point-guided Segmentation Network for Ore Images with Ambiguous Boundary
The precise segmentation of ore images is critical to the successful execution of the beneficiation process.
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content.
FlexHB: a More Efficient and Flexible Framework for Hyperparameter Optimization
Comprehensive study on FlexHB shows that (1) our fine-grained fidelity method considerably enhances the efficiency of searching optimal configurations, (2) our FlexBand framework (self-adaptive allocation of SH brackets, and global ranking of configurations in both current and past SH procedures) grants the algorithm with more flexibility and improves the anytime performance.
Reconfigurable Intelligent Surface assisted Integrated Communication, Sensing, and Computation Systems
To address the formulated non-convex problem, we propose an algorithm based on the block coordinate descent (BCD) method to decouple the original problem into two subproblems, where the computational and beamforming settings are optimized alternately.
VGMShield: Mitigating Misuse of Video Generative Models
Together with fake video detection and tracing, our multi-faceted set of solutions can effectively mitigate misuse of video generative models.
Prompt Stealing Attacks Against Large Language Models
Our proposed prompt stealing attack aims to steal these well-designed prompts based on the generated answers.
Are LLM-based Evaluators Confusing NLG Quality Criteria?
Some prior work has shown that LLMs perform well in NLG evaluation for different tasks.
Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection
The complexity of food semantic attributes further makes it more difficult for current ZSD methods to distinguish various food categories.
Rapid Adoption, Hidden Risks: The Dual Impact of Large Language Model Customization
The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs.
PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Preference Alignment
Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task.
Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention.
Comprehensive Assessment of Jailbreak Attacks Against LLMs
Some jailbreak prompt datasets, available from the Internet, can also achieve high attack success rates on many LLMs, such as ChatGLM3, GPT-3. 5, and PaLM2.
Conversation Reconstruction Attack Against GPT Models
We then introduce two advanced attacks aimed at better reconstructing previous conversations, specifically the UNR attack and the PBU attack.
GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models
Our system of different roles will leverage this knowledge graph to generate new jailbreaks, which have proved effective in inducing LLMs to generate unethical or guideline-violating responses.
Secure Wireless Communication in Active RIS-Assisted DFRC System
This work considers a dual-functional radar and communication (DFRC) system with an active reconfigurable intelligent surface (RIS) and a potential eavesdropper.
A Concise but Effective Network for Image Guided Depth Completion in Autonomous Driving
Depth completion is a crucial task in autonomous driving, aiming to convert a sparse depth map into a dense depth prediction.
Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion
Table question answering is a popular task that assesses a model's ability to understand and interact with structured data.
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline
This study explores the vulnerabilities associated with copyright protection in DMs by introducing a backdoor data poisoning attack (SilentBadDiffusion) against text-to-image diffusion models.
Preliminary Study on Incremental Learning for Large Language Model-based Recommender Systems
Rather than directly dismissing the role of incremental learning, we ascribe this lack of anticipated performance improvement to the mismatch between the LLM4Recarchitecture and incremental learning: LLM4Rec employs a single adaptation module for learning recommendation, hampering its ability to simultaneously capture long-term and short-term user preferences in the incremental learning context.
FAKEPCD: Fake Point Cloud Detection via Source Attribution
Take the open-world attribution as an example, FAKEPCD attributes point clouds to known sources with an accuracy of 0. 82-0. 98 and to unknown sources with an accuracy of 0. 73-1. 00.
LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting
Through meta-learning techniques, LabelCraft effectively addresses the bi-level optimization hurdle posed by the recommender and labeling models, enabling the automatic acquisition of intricate label generation mechanisms. Extensive experiments on real-world datasets corroborate LabelCraft's excellence across varied operational metrics, encompassing usage time, user engagement, and retention.
Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis
Our framework comprises two core modules: collaborative step mining and frame-to-step alignment.
Polyper: Boundary Sensitive Polyp Segmentation
We present a new boundary sensitive framework for polyp segmentation, called Polyper.
RdimKD: Generic Distillation Paradigm by Dimensionality Reduction
Knowledge Distillation (KD) emerges as one of the most promising compression technologies to run advanced deep neural networks on resource-limited devices.
Spatial-wise Dynamic Distillation for MLP-like Efficient Visual Fault Detection of Freight Trains
Existing modeling shortcomings of spatial invariance and pooling layers in conventional CNNs often ignore the neglect of crucial global information, resulting in error localization for fault objection tasks of freight trains.
Correcting Diffusion Generation through Resampling
Despite diffusion models' superior capabilities in modeling complex distributions, there are still non-trivial distributional discrepancies between generated and ground-truth images, which has resulted in several notable problems in image generation, including missing object errors in text-to-image generation and low image quality.
From Beginner to Expert: Modeling Medical Knowledge into General LLMs
(3) Specifically for multi-choice questions in the medical domain, we propose a novel Verification-of-Choice approach for prompting engineering, which significantly enhances the reasoning ability of LLMs.
VIoTGPT: Learning to Schedule Vision Tools towards Intelligent Video Internet of Things
Video Internet of Things (VIoT) has shown full potential in collecting an unprecedented volume of video data.
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling
Uncertainty decomposition refers to the task of decomposing the total uncertainty of a model into data (aleatoric) uncertainty, resulting from the inherent complexity or ambiguity of the data, and model (epistemic) uncertainty, resulting from the lack of knowledge in the model.
Efficient Segmentation with Texture in Ore Images Based on Box-supervised Approach
At the same time, the ore distribution is stacked, and it is difficult to identify the complete features.
Comprehensive Assessment of Toxicity in ChatGPT
Moderating offensive, hateful, and toxic language has always been an important but challenging topic in the domain of safe use in NLP.
A New Fine-grained Alignment Method for Image-text Matching
For this purpose, we introduce the Cross-Modal Prominent Fragments Enhancement Aligning Network(CPFEAN), which achieves improved retrieval accuracy by diminishing the participation of irrelevant regions during alignment and relatively increasing the alignment similarity of prominent words.
Revitalizing Legacy Video Content: Deinterlacing with Bidirectional Information Propagation
Our proposed method supports bidirectional spatio-temporal information propagation across multiple scales to leverage information in both space and time.
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
Several membership inference attacks (MIAs) have been proposed to exhibit the privacy vulnerability of generative models by classifying a query image as a training dataset member or nonmember.
CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation
In pursuit of superior recommendations for both cold and warm start scenarios, we introduce CoLLM, an innovative LLMRec methodology that seamlessly incorporates collaborative information into LLMs for recommendation.
From Generative AI to Generative Internet of Things: Fundamentals, Framework, and Outlooks
Generative Artificial Intelligence (GAI) possesses the capabilities of generating realistic data and facilitating advanced decision-making.
DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification
Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming and the augmented samples lack diversity.
Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning
Large Language Models (LLMs) are powerful tools for natural language processing, enabling novel applications and user experiences.
A Comprehensive Study of Privacy Risks in Curriculum Learning
Training a machine learning model with data following a meaningful order, i. e., from easy to hard, has been proven to be effective in accelerating the training process and achieving better model performance.
LGL-BCI: A Lightweight Geometric Learning Framework for Motor Imagery-Based Brain-Computer Interfaces
The efficiency, assessed on two public EEG datasets and two real-world EEG devices, significantly outperforms the state-of-the-art solution in accuracy ($82. 54\%$ versus $62. 22\%$) with fewer parameters (64. 9M compared to 183. 7M).
Prompt Backdoors in Visual Prompt Learning
Specifically, the VPPTaaS provider optimizes a visual prompt given downstream data, and downstream users can use this prompt together with the large pre-trained model for prediction.
Audio-Visual Neural Syntax Acquisition
We study phrase structure induction from visually-grounded speech.
Composite Backdoor Attacks Against Large Language Models
Such a Composite Backdoor Attack (CBA) is shown to be stealthier than implanting the same multiple trigger keys in only a single component.
AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
Feature attribution explains neural network outputs by identifying relevant input features.
SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection
To tackle this, we propose the Semantic Separable Diffusion Synthesizer (SeeDS) framework for Zero-Shot Food Detection (ZSFD).
Ranked #1 on
Generalized Zero-Shot Object Detection
on MS-COCO
A Chat About Boring Problems: Studying GPT-based text normalization
Through this new framework, we can identify strengths and weaknesses of GPT-based TN, opening opportunities for future work.
When Large Language Models Meet Citation: A Survey
Such information could be incorporated into LLMs pre-training and improve the text representation in LLMs.
On Copyright Risks of Text-to-Image Diffusion Models
Specifically, we introduce a data generation pipeline to systematically produce data for studying copyright in diffusion models.
Efficient Real-time Path Planning with Self-evolving Particle Swarm Optimization in Dynamic Scenarios
Particle Swarm Optimization (PSO) has demonstrated efficacy in addressing static path planning problems.
A Dual-Perspective Approach to Evaluating Feature Attribution Methods
We apply these metrics to mainstream attribution methods, offering a novel lens through which to analyze and compare feature attribution methods.
A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems
As the focus on Large Language Models (LLMs) in the field of recommendation intensifies, the optimization of LLMs for recommendation purposes (referred to as LLM4Rec) assumes a crucial role in augmenting their effectiveness in providing recommendations.
SAM Meets Robotic Surgery: An Empirical Study on Generalization, Robustness and Adaptation
Our extensive evaluation results reveal that although SAM shows remarkable zero-shot generalization ability with bounding box prompts, it struggles to segment the whole instrument with point-based prompts and unprompted settings.
Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation
Efficient RGB-D semantic segmentation has received considerable attention in mobile robots, which plays a vital role in analyzing and recognizing environmental information.
Ranked #57 on
Semantic Segmentation
on NYU Depth v2
You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
We find that prompt learning achieves around 10\% improvement in the toxicity classification task compared to the baselines, while for the toxic span detection task we find better performance to the best baseline (0. 643 vs. 0. 640 in terms of $F_1$-score).
Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audio
We propose CONF-TSASR, a non-autoregressive end-to-end time-frequency domain architecture for single-channel target-speaker automatic speech recognition (TS-ASR).
Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing
In this paper, we discover a new attack strategy against LLM APIs, namely the prompt abstraction attack.
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
The misuse of large language models (LLMs) has garnered significant attention from the general public and LLM vendors.
Learning to Select the Relevant History Turns in Conversational Question Answering
In this paper, we propose a framework, DHS-ConvQA (Dynamic History Selection in Conversational Question Answering), that first generates the context and question entities for all the history turns, which are then pruned on the basis of similarity they share in common with the question at hand.
Blockchain-empowered Federated Learning for Healthcare Metaverses: User-centric Incentive Mechanism with Optimal Data Freshness
Given the revolutionary role of metaverses, healthcare metaverses are emerging as a transformative force, creating intelligent healthcare systems that offer immersive and personalized services.
FATRER: Full-Attention Topic Regularizer for Accurate and Robust Conversational Emotion Recognition
This paper concentrates on the understanding of interlocutors' emotions evoked in conversational utterances.
Ranked #17 on
Emotion Recognition in Conversation
on IEMOCAP
Certified Robustness for Large Language Models with Self-Denoising
This largely falls into the study of certified robust LLMs, i. e., all predictions of LLM are certified to be correct in a local region around the input.
Separate-and-Aggregate: A Transformer-based Patch Refinement Model for Knowledge Graph Completion
Previous KGC methods typically represent knowledge graph entities and relations as trainable continuous embeddings and fuse the embeddings of the entity $h$ (or $t$) and relation $r$ into hidden representations of query $(h, r, ?
AI For Global Climate Cooperation 2023 Competition Proceedings
On the other hand, an interdisciplinary panel of human experts in law, policy, sociology, economics and environmental science, evaluated the solutions qualitatively.
Recommendation Unlearning via Influence Function
In this work, we propose an Influence Function-based Recommendation Unlearning (IFRU) framework, which efficiently updates the model without retraining by estimating the influence of the unusable data on the model via the influence function.
Efficient Visual Fault Detection for Freight Train Braking System via Heterogeneous Self Distillation in the Wild
Efficient visual fault detection of freight trains is a critical part of ensuring the safe operation of railways under the restricted hardware environment.
Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework
With the proliferation of short video applications, the significance of short video recommendations has vastly increased.
Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning
Despite the impressive performance recently achieved by automatic speech recognition (ASR), we observe two primary challenges that hinder its broader applications: (1) The difficulty of introducing scalability into the model to support more languages with limited training, inference, and storage overhead; (2) The low-resource adaptation ability that enables effective low-resource adaptation while avoiding over-fitting and catastrophic forgetting issues.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Generated Graph Detection
Graph generative models become increasingly effective for data distribution approximation and data augmentation.
Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis
In particular, to help the watermark survive the subject-driven synthesis, we incorporate the synthesis process in learning GenWatermark by fine-tuning the detector with synthesized images for a specific subject.
AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers
Rather than using LLMs to directly plan task sub-goals, we instead perform few-shot translation from natural language task descriptions to an intermediate task representation that can then be consumed by a TAMP algorithm to jointly solve the task and motion plan.
S$^2$ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation
Furthermore, to produce reliable mixed pseudo labels, which enhance the effectiveness of ensemble learning, we introduce a novel adaptive pixel-wise fusion technique based on the entropy guidance from the spatial and spectral branches.
Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer
In this work, we propose a novel end-to-end wind power forecasting model named Hierarchical Spatial-Temporal Transformer Network (HSTTN) to address the long-term WPF problems.
Epistemic Graph: A Plug-And-Play Module For Hybrid Representation Learning
In this paper, a novel Epistemic Graph Layer (EGLayer) is introduced to enable hybrid learning, enhancing the exchange of information between deep features and a structured knowledge graph.
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
Such attacks can be easily affected by retraining on downstream tasks and with different prompting strategies, limiting the transferability of backdoor attacks.
CUEING: a lightweight model to Capture hUman attEntion In driviNG
Discrepancies in decision-making between Autonomous Driving Systems (ADS) and human drivers underscore the need for intuitive human gaze predictors to bridge this gap, thereby improving user trust and experience.
Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models
Our evaluation result shows that 24% of the generated images using DreamBooth are hateful meme variants that present the features of the original hateful meme and the target individual/community; these generated images are comparable to hateful meme variants collected from the real world.
MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learning
As such, MetaAdapt can learn how to adapt the misinformation detection model and exploit the source data for improved performance in the target domain.
UMDFood: Vision-language models boost food composition compilation
Nutrition information is crucial in precision nutrition and the food industry.
Two-in-One: A Model Hijacking Attack Against Text Generation Models
In this work, we broaden the scope of this attack to include text generation and classification models, hence showing its broader applicability.
Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation
The remarkable achievements of Large Language Models (LLMs) have led to the emergence of a novel recommendation paradigm -- Recommendation via LLM (RecLLM).
NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models
Then, we finetune T5 models on the lifted versions (i. e., the specific Atomic Propositions (AP) are hidden) of the NL and TL.
Faster OreFSDet : A Lightweight and Effective Few-shot Object Detector for Ore Images
For the ore particle size detection, obtaining a sizable amount of high-quality ore labeled data is time-consuming and expensive.
TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
We have demonstrated that the proposed TALLRec framework can significantly enhance the recommendation capabilities of LLMs in the movie and book domains, even with a limited dataset of fewer than 100 samples.
SAM Meets Robotic Surgery: An Empirical Study in Robustness Perspective
In this empirical study, we investigate the robustness and zero-shot generalizability of the SAM in the domain of robotic surgery in various settings of (i) prompted vs. unprompted; (ii) bounding box vs. points-based prompt; (iii) generalization under corruptions and perturbations with five severity levels; and (iv) state-of-the-art supervised model vs. SAM.
Prediction then Correction: An Abductive Prediction Correction Method for Sequential Recommendation
To improve the accuracy of these models, some researchers have attempted to simulate human analogical reasoning to correct predictions for testing data by drawing analogies with the prediction errors of similar training data.
Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation
However, such a manner inevitably learns unstable feature interactions, i. e., the ones that exhibit strong correlations in historical data but generalize poorly for future serving.
In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT
In this paper, we perform the first large-scale measurement of ChatGPT's reliability in the generic QA scenario with a carefully curated set of 5, 695 questions across ten datasets and eight domains.
Improving Neural Radiance Fields with Depth-aware Optimization for Novel View Synthesis
Through these explicit constraints and the implicit constraint from NeRF, our method improves the view synthesis as well as the 3D-scene geometry performance of NeRF at the same time.
Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis
We then impose spatial attention control by combining the attention over the entire text description and that over the local description of the particular object in the corresponding pixel region of that object.
Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models
COPAINT also uses the Bayesian framework to jointly modify both revealed and unrevealed regions, but approximates the posterior distribution in a way that allows the errors to gradually drop to zero throughout the denoising steps, thus strongly penalizing any mismatches with the reference image.
FACE-AUDITOR: Data Auditing in Facial Recognition Systems
Few-shot-based facial recognition systems have gained increasing attention due to their scalability and ability to work with a few face images during the model deployment phase.
MGTBench: Benchmarking Machine-Generated Text Detection
Extensive evaluations on public datasets with curated texts generated by various powerful LLMs such as ChatGPT-turbo and Claude demonstrate the effectiveness of different detection methods.
Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation
To fully exploit information with event streams to detect objects, a dual-memory aggregation network (DMANet) is proposed to leverage both long and short memory along event streams to aggregate effective information for object detection.
A Generative Model for Digital Camera Noise Synthesis
To this end, we propose an effective generative model which utilizes clean features as guidance followed by noise injections into the network.
From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need
In this sense, we propose SeMap, a more effective mapping using the semantic alignment between the pre-trained model's knowledge and the downstream task.
EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
Predicting the binding sites of the target proteins plays a fundamental role in drug discovery.
A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Given the simplicity and effectiveness of the attack method, our study indicates scientific plots indeed constitute a valid side channel for model information stealing attacks.
Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network
At first, a top-n selection strategy is proposed to provide pseudo-labels for public data, and use pseudo-labels to guide the training of the cGAN.
Prompt Stealing Attacks Against Text-to-Image Generation Models
In this paper, we perform the first study on understanding the threat of a novel attack, namely prompt stealing attack, which aims to steal prompts from generated images by text-to-image generation models.
Backdoor Attacks Against Dataset Distillation
A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset.
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
Robustness evaluation against adversarial examples has become increasingly important to unveil the trustworthiness of the prevailing deep models in natural language processing (NLP).
PromptBoosting: Black-Box Text Classification with Ten Forward Passes
Instead of directly optimizing in prompt space, PromptBoosting obtains a small pool of prompts via a gradient-free approach and then constructs a large pool of weak learners by pairing these prompts with different elements of the LM's output distribution.
Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Backdoor attacks represent one of the major threats to machine learning models.
Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
Based on this finding, we further propose a simple, light-weight image editing algorithm where the mixing weights of the two text embeddings are optimized for style matching and content preservation.
On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning
The dissemination of hateful memes online has adverse effects on social media platforms and the real world.
Mitigating Spurious Correlations for Self-supervised Recommendation
This objective requires to 1) automatically mask spurious features without supervision, and 2) block the negative effect transmission from spurious features to other features during SSL.
Detection of brain activations induced by naturalistic stimuli in a pseudo model-driven way
We evaluated the effectiveness of AINS with both statistical and predictive analyses on individual differences in sex and intelligence quotient (IQ), based on the four movie fMRI runs included in the Human Connectome Project dataset.
Visual Fault Detection of Multi-scale Key Components in Freight Trains
Fault detection for key components in the braking system of freight trains is critical for ensuring railway transportation safety.
BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance
We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25. 1x speedup and 20. 2x storage-saving on edge hardware.
Learning to Learn Domain-invariant Parameters for Domain Generalization
Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice.
SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency
To bridge the gap between the reference points of salient queries and Transformer detectors, we propose SAlient Point-based DETR (SAP-DETR) by treating object detection as a transformation from salient points to instance objects.
Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
We believe S$^3$-Router has provided a new perspective for practical deployment of speech SSL models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Amplifying Membership Exposure via Data Poisoning
In this paper, we investigate the third type of exploitation of data poisoning - increasing the risks of privacy leakage of benign training samples.
DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models
To tackle this problem, we pioneer a systematic study on the detection and attribution of fake images generated by text-to-image generation models.
Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup
Moreover, we leverage the power of domain adversarial examples to establish an intermediate domain mixup, where the latent representations of the input text from both domains could be mixed during the training process.
Backdoor Attacks in the Supply Chain of Masked Image Modeling
Different from previous work, we are the first to systematically threat modeling on SSL in every phase of the model supply chain, i. e., pre-training, release, and downstream phases.
On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks
In many applications with real-world consequences, it is crucial to develop reliable uncertainty estimation for the predictions made by the AI decision systems.
UnGANable: Defending Against GAN-based Face Manipulation
Extensive experiments on four popular GAN models trained on two benchmark face datasets show that UnGANable achieves remarkable effectiveness and utility performance, and outperforms multiple baseline methods.
Membership Inference Attacks Against Text-to-image Generation Models
The empirical results show that all of the proposed attacks can achieve significant performance, in some cases even close to an accuracy of 1, and thus the corresponding risk is much more severe than that shown by existing membership inference attacks.
Structure-Aware NeRF without Posed Camera via Epipolar Constraint
This two-stage strategy is not convenient to use and degrades the performance because the error in the pose extraction can propagate to the view synthesis.
Data Poisoning Attacks Against Multimodal Encoders
Extensive evaluations on different datasets and model architectures show that all three attacks can achieve significant attack performance while maintaining model utility in both visual and linguistic modalities.
Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation
A standard choice is treating the missing data as negative training samples and estimating interaction likelihood between user-item pairs along with the observed interactions.
Fairness Reprogramming
Specifically, FairReprogram considers the case where models can not be changed and appends to the input a set of perturbations, called the fairness trigger, which is tuned towards the fairness criteria under a min-max formulation.
Predicting Protein-Ligand Binding Affinity via Joint Global-Local Interaction Modeling
The prediction of protein-ligand binding affinity is of great significance for discovering lead compounds in drug research.
Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots
We show that publicly available chatbots are prone to providing toxic responses when fed toxic queries.
On the Privacy Risks of Cell-Based NAS Architectures
Existing studies on neural architecture search (NAS) mainly focus on efficiently and effectively searching for network architectures with better performance.
Membership Inference Attacks by Exploiting Loss Trajectory
Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset.
Auditing Membership Leakages of Multi-Exit Networks
Furthermore, we propose a hybrid attack that exploits the exit information to improve the performance of existing attacks.
Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models
Finally, we find that data augmentation degrades the performance of existing attacks to a larger extent, and we propose an adaptive attack using augmentation to train shadow and attack models that improve attack performance.
Algorithms of Real-Time Navigation and Control of Autonomous Unmanned Vehicles
In addition, extending the obstacle avoidance algorithms to more competitive situations.
AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N
To facilitate this research, here we introduce RICE-N, a multi-region integrated assessment model that simulates the global climate and economy, and which can be used to design and evaluate the strategic outcomes for different negotiation and agreement frameworks.
Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning
The results show that early stopping can mitigate the membership inference attack, but with the cost of model's utility degradation.
Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion
However, previous works show that state-of-the-art ASV models are seriously vulnerable to voice spoofing attacks, and the recently proposed high-performance spoofing countermeasure (CM) models only focus solely on the standalone anti-spoofing tasks, and ignore the subsequent speaker verification process.
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
For example, on downstream CIFAR-10/100 datasets, we identify double-win matching subnetworks with the standard, fast adversarial, and adversarial pre-training from ImageNet, at 89. 26%/73. 79%, 89. 26%/79. 03%, and 91. 41%/83. 22% sparsity, respectively.
mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation
Concretely, we propose a novel multimodal Medical Transformer (mmFormer) for incomplete multimodal learning with three main components: the hybrid modality-specific encoders that bridge a convolutional encoder and an intra-modal Transformer for both local and global context modeling within each modality; an inter-modal Transformer to build and align the long-range correlations across modalities for modality-invariant features with global semantics corresponding to tumor region; a decoder that performs a progressive up-sampling and fusion with the modality-invariant features to generate robust segmentation.
Ranked #65 on
Semantic Segmentation
on NYU Depth v2
Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images
In this paper, we propose a Decoupled Pyramid Correlation Network (DPC-Net) that exploits attention mechanisms to fully leverage both low- and high-level features embedded in FCN to segment liver tumor.
A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains
In this paper, we propose a lightweight NMS-free framework to achieve real-time detection and high accuracy simultaneously.
Mitigating Hidden Confounding Effects for Causal Recommendation
Towards this goal, we propose a Hidden Confounder Removal (HCR) framework that leverages front-door adjustment to decompose the causal effect into two partial effects, according to the mediators between item features and user feedback.
Multi-scale Attention Flow for Probabilistic Time Series Forecasting
The probability prediction of multivariate time series is a notoriously challenging but practical task.
Addressing Confounding Feature Issue for Causal Recommendation
We demonstrate DCR on the backbone model of neural factorization machine (NFM), showing that DCR leads to more accurate prediction of user preference with small inference time cost.
FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
We propose a novel fairness-aware sequential recommendation task, in which a new metric, interaction fairness, is defined to estimate how recommended items are fairly interacted by users with different protected attribute groups.
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings.
Ranked #13 on
Semantic Textual Similarity
on STS16
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers
Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks.
Finding MNEMON: Reviving Memories of Node Embeddings
Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks.
Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models
One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced.
Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization
First, a non-deterministic WFST outputs all normalization candidates, and then a neural language model picks the best one -- similar to shallow fusion for automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models
We show that WavPrompt is a few-shot learner that can perform speech understanding tasks better than a naive text baseline.
Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition
An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection of texts written in that language without access to any transcribed speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
SpeechSplit 2.0: Unsupervised speech disentanglement for voice conversion Without tuning autoencoder Bottlenecks
SpeechSplit can perform aspect-specific voice conversion by disentangling speech into content, rhythm, pitch, and timbre using multiple autoencoders in an unsupervised manner.
Linking Emergent and Natural Languages via Corpus Transfer
In this work, we propose a novel way to establish such a link by corpus transfer, i. e. pretraining on a corpus of emergent language for downstream natural language tasks, which is in contrast to prior work that directly transfers speaker and listener parameters.
Adversarial Support Alignment
Furthermore, we show that our approach can be viewed as a limit of existing notions of alignment by increasing transportation assignment tolerance.
BiFSMN: Binary Neural Network for Keyword Spotting
Then, to allow the instant and adaptive accuracy-efficiency trade-offs at runtime, we also propose a Thinnable Binarization Architecture to further liberate the acceleration potential of the binarized network from the topology perspective.
Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials
Topological materials present unconventional electronic properties that make them attractive for both basic science and next-generation technological applications.
EVBattery: A Large-Scale Electric Vehicle Dataset for Battery Health and Capacity Estimation
In addition to demonstrating how existing deep learning algorithms can be applied to this task, we further develop an algorithm that exploits the data structure of battery systems.
SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders
Recent research has shown that the machine learning model's copyright is threatened by model stealing attacks, which aim to train a surrogate model to mimic the behavior of a given model.
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images.
Towards Realistic Visual Dubbing with Heterogeneous Sources
The task of few-shot visual dubbing focuses on synchronizing the lip movements with arbitrary speech input for any talking head video.
Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019
Code submissions were executed on hidden tasks, with limited time and computational resources, pushing solutions that get results quickly.
Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation
Encoder-decoder models have been widely used in RGBD semantic segmentation, and most of them are designed via a two-stream network.
Ranked #13 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
Model Stealing Attacks Against Inductive Graph Neural Networks
Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications.
BCORLE($\lambda$): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market
Further, a novel offline reinforcement learning method and an off-policy evaluation algorithm are proposed for policy learning and policy evaluation, respectively.
Recommending Multiple Positive Citations for Manuscript via Content-Dependent Modeling and Multi-Positive Triplet
Third, we propose a dynamic context sampling strategy which captures the ``macro-scoped'' citing intents from a manuscript and empowers the citation embeddings to be content-dependent, which allow the algorithm to further improve the performances.
Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective
In this paper, we provide a comprehensive review for the economic and game theoretic approaches proposed in the literature to design various schemes for stimulating data owners to participate in FL training process.
A Survey of Visual Transformers
Transformer, an attention-based encoder-decoder model, has already revolutionized the field of natural language processing (NLP).
Get a Model! Model Hijacking Attack Against Machine Learning Models
In this work, we propose a new training time attack against computer vision based machine learning models, namely model hijacking attack.
LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image
To further prove the ability of our method, we test it on public dataset MS COCO, and the results show that our LF-YOLO has a outstanding versatility detection performance.
Understanding Interlocking Dynamics of Cooperative Rationalization
The selection mechanism is commonly integrated into the model itself by specifying a two-component cascaded system consisting of a rationale generator, which makes a binary selection of the input features (which is the rationale), and a predictor, which predicts the output based only on the selected features.
Learning Rich Features for Gait Recognition by Integrating Skeletons and Silhouettes
Gait recognition captures gait patterns from the walking sequence of an individual for identification.
Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey
Then, we review a number of applications of MARL to solve emerging issues in future Internet.
Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks
Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks, i. e., an imperceptible perturbation to the input can mislead DNNs trained on clean images into making erroneous predictions.
Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation
To reduce time complexity while improving performance, a sparse representation of global nodes based on noise-free online low-rank representation is used to obtain a global graph at each scale.
A Lightweight and Accurate Recognition Framework for Signs of X-ray Weld Images
Based on SCE module, a narrow network is designed for final weld information recognition.
Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech
In this paper, we study the disentanglement of speaker and language representations in non-autoregressive cross-lingual TTS models from various aspects.
Revisiting IPA-based Cross-lingual Text-to-speech
Experiments show that the way to process the IPA and suprasegmental sequence has a negligible impact on the CL VC performance.
Inference Attacks Against Graph Neural Networks
Second, given a subgraph of interest and the graph embedding, we can determine with high confidence that whether the subgraph is contained in the target graph.
Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
We propose a method to identify features with predictive information in the input domain.
On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
Are end-to-end text-to-speech (TTS) models over-parametrized?
Membership Inference Attacks Against Recommender Systems
In this paper, we make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference.
Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation
Accordingly, a novel formulation for tensor completion and an effective optimization algorithm, called as tensor completion by parallel weighted matrix factorization via tensor train (TWMac-TT), is proposed.
A Unified Transformer-based Framework for Duplex Text Normalization
In addition, we also create a cleaned dataset from the Spoken Wikipedia Corpora for German and report the performance of our systems on the dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Deep Sequence Modeling: Development and Applications in Asset Pricing
We predict asset returns and measure risk premia using a prominent technique from artificial intelligence -- deep sequence modeling.
