Search Results for author:
Found 408 papers, 183 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.
Tracing Human Stress from Physiological Signals using UWB Radar
Experimental results show that the proposed DST method significantly outperforms all the baselines in terms of tracing human stress states.
Task-agnostic Pre-training and Task-guided Fine-tuning for Versatile Diffusion Planner
To address these challenges, we aim to develop a versatile diffusion planner that can leverage large-scale inferior data that contains task-agnostic sub-optimal trajectories, with the ability to fast adapt to specific tasks.
Offline Signature Verification Based on Feature Disentangling Aided Variational Autoencoder
First, genuine signatures and skilled forgeries are highly similar in their appearances, resulting in a small inter-class distance.
MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective.
Ranked #1 on
Causal Discovery in Video Reasoning
on MECD
Investigating Layer Importance in Large Language Models
In this study, we advance the understanding of LLM by investigating the significance of individual layers in LLMs.
Axial Attention Transformer Networks: A New Frontier in Breast Cancer Detection
This paper delves into the challenges and advancements in the field of medical image segmentation, particularly focusing on breast cancer diagnosis.
Efficient Fine-Tuning of Large Language Models for Automated Medical Documentation
Scientific research indicates that for every hour spent in direct patient care, physicians spend nearly two additional hours on administrative tasks, particularly on electronic health records (EHRs) and desk work.
Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data
Large language models (LLMs) have shown considerable success in a range of domain-specific tasks, especially after fine-tuning.
Q-value Regularized Decision ConvFormer for Offline Reinforcement Learning
However, due to the inconsistency between the sampled returns within a single trajectory and the optimal returns across multiple trajectories, it is challenging to set an expected return to output the optimal action and stitch together suboptimal trajectories.
Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?
By analyzing the linkage between membership inference vulnerability and data importance, we demonstrate that sample characteristics can be integrated into membership metrics by introducing sample-specific criteria, therefore enhancing the membership inference performance.
SPDiffusion: Semantic Protection Diffusion for Multi-concept Text-to-image Generation
We found that attribute confusion occurs when a certain region of the latent features attend to multiple or incorrect prompt tokens.
Membership Inference Attacks Against In-Context Learning
Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL).
Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution
This study takes an initial step in investigating the evolution of text-to-image models from the perspectives of safety, bias, and authenticity.
EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUs
Specifically, EMHI provides synchronized stereo images from downward-sloping cameras on the headset and IMU data from body-worn sensors, along with pose annotations in SMPL format.
Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders
Despite being prevalent in the general field of Natural Language Processing (NLP), pre-trained language models inherently carry privacy and copyright concerns due to their nature of training on large-scale web-scraped data.
BadMerging: Backdoor Attacks Against Model Merging
Considering that a merged model may incorporate tasks from different domains, BadMerging can jointly compromise the tasks provided by the adversary (on-task attack) and other contributors (off-task attack) and solve the corresponding unique challenges with novel attack designs.
Membership Inference Attack Against Masked Image Modeling
Masked Image Modeling (MIM) has achieved significant success in the realm of self-supervised learning (SSL) for visual recognition.
Model Hijacking Attack in Federated Learning
Machine learning (ML), driven by prominent paradigms such as centralized and federated learning, has made significant progress in various critical applications ranging from autonomous driving to face recognition.
Sustainable Diffusion-based Incentive Mechanism for Generative AI-driven Digital Twins in Industrial Cyber-Physical Systems
Industrial Cyber-Physical Systems (ICPSs) are an integral component of modern manufacturing and industries.
Vera Verto: Multimodal Hijacking Attack
A recent attack in this domain is the model hijacking attack, whereby an adversary hijacks a victim model to implement their own -- possibly malicious -- hijacking tasks.
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
Through attacks on implemented and deployable agents in multi-agent scenarios, we accentuate the realistic risks associated with these vulnerabilities.
GradCraft: Elevating Multi-task Recommendations through Holistic Gradient Crafting
GradCraft ensures the concurrent achievement of appropriate magnitude balance and global direction balance, aligning with the inherent characteristics of recommendation scenarios.
Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
This paper investigates Who's Harry Potter (WHP), a pioneering yet insufficiently understood method for LLM unlearning.
SeqMIA: Sequential-Metric Based Membership Inference Attack
Building upon this signal, we introduce a novel attack method called Sequential-metric based Membership Inference Attack (SeqMIA).
Towards Understanding Unsafe Video Generation
With the labeled information and the corresponding prompts, we created the first dataset of unsafe videos generated by VGMs.
ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization
It is a fine-tuning framework designed to allow the model owner to regulate ICL behavior on different data.
Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
SOS! Soft Prompt Attack Against Open-Source Large Language Models
In this work, we present a new training time attack, SOS, which is designed to be low in computational demand and does not require clean data or modification of the model weights, thereby maintaining the model's utility intact.
Movable Antenna-enabled RIS-aided Integrated Sensing and Communication
In this paper, we investigate a movable antenna (MA)-aided integrated sensing and communication (ISAC) system, where a reconfigurable intelligent surface (RIS) is employed to enhance wireless communication and sensing performance in dead zones.
VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs
One understudied capability in VLMs is visual spatial planning -- the ability to comprehend the spatial arrangements of objects and devise action plans to achieve desired outcomes in visual scenes.
Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks
Specifically, we query the model to generate a fallacious yet deceptively real procedure for the harmful behavior.
ProgressGym: Alignment with a Millennium of Moral Progress
Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users.
Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
We cast the dynamics learning as an auto-regressive sequence modeling problem over discrete tokens by leveraging the expressive Transformer architecture, in order to model complex local dynamics across different agents and provide accurate and consistent long-term imaginations.
Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based Recommendation
However, we find these methods encounter significant challenges: 1) amplification bias -- where standard length normalization inflates scores for items containing tokens with generation probabilities close to 1 (termed ghost tokens), and 2) homogeneity issue -- generating multiple similar or repetitive items for a user.
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Bi-level optimization (BO) has become a fundamental mathematical framework for addressing hierarchical machine learning problems.
Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphs
Protein representation learning aims to learn informative protein embeddings capable of addressing crucial biological questions, such as protein function prediction.
Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments
Upon input claims, RAFTS starts with evidence retrieval, where we design a retrieval pipeline to collect and re-rank relevant documents from verifiable sources.
Multiple Prior Representation Learning for Self-Supervised Monocular Depth Estimation via Hybrid Transformer
To address these challenges, we introduce a novel self-supervised monocular depth estimation model that leverages multiple priors to bolster representation capabilities across spatial, context, and semantic dimensions.
APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation
Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples.
Towards Unsupervised Speech Recognition Without Pronunciation Models
Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
To achieve both goals, a mainstream class of LLM unlearning methods introduces an optimization framework with a combination of two objectives - maximizing the prediction loss on the forget documents while minimizing that on the retain documents, which suffers from two challenges, degenerated output and catastrophic forgetting.
A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation
To address this problem, a popular class of methods utilize the LLM's self-consistencies in its beliefs in a set of logically related augmented statements generated by the LLM, which does not require external knowledge databases and can work with both white-box and black-box LLMs.
Methodology and Real-World Applications of Dynamic Uncertain Causality Graph for Clinical Diagnosis with Explainability and Invariance
After verifications, the 46 DUCG models were applied in the real-world in China.
Text-like Encoding of Collaborative Information in Large Language Models for Recommendation
BinLLM converts collaborative embeddings from external models into binary sequences -- a specific text format that LLMs can understand and operate on directly, facilitating the direct usage of collaborative information in text-like format by LLMs.
Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild.
Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction
From the examiner perspective, we define four evaluation tasks for error identification and correction along with a new dataset with annotated error types and steps.
Voice Jailbreak Attacks Against GPT-4o
This resistance is primarily due to GPT-4o's internal safeguards and the difficulty of adapting text jailbreak prompts to voice mode.
FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs).
Efficient Visual Fault Detection for Freight Train via Neural Architecture Search with Data Volume Robustness
In this work, we propose an efficient NAS-based framework for visual fault detection of freight trains to search for the task-specific detection head with capacities of multi-scale representation.
Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
In this paper, we propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.
Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning
In this paper, we propose a novel representation-based approach to measure the domain gap, where the representation is learned through a contrastive objective by sampling transitions from different domains.
Link Stealing Attacks Against Inductive Graph Neural Networks
This paper fills the gap by conducting a systematic privacy analysis of inductive GNNs through the lens of link stealing attacks, one of the most popular attacks that are specifically designed for GNNs.
UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images
With the advent of text-to-image models and concerns about their misuse, developers are increasingly relying on image safety classifiers to moderate their generated unsafe images.
Fair Recommendations with Limited Sensitive Attributes: A Distributionally Robust Optimization Approach
To this end, we propose Distributionally Robust Fair Optimization (DRFO), which minimizes the worst-case unfairness over all potential probability distributions of missing sensitive attributes instead of the reconstructed one to account for the impact of the reconstruction errors.
Generative AI for Low-Carbon Artificial Intelligence of Things with Large Language Models
In this article, we explore the potential of GAI for carbon emissions reduction and propose a novel GAI-enabled solution for low-carbon AIoT.
WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users
We present a data synthesis pipeline to address this disparity in data collection and subsequently improve pose estimation performance for wheelchair users.
decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points
However, existing quantization schemes suffer from significant accuracy degradation at very low bits, or require some additional computational overhead when deployed, making it difficult to be applied to large-scale applications in industry.
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, almost 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
Furthermore, the results demonstrate that the proposed scheme can enhance the WSR by 30\% compared to scenarios that do not take this effect into account when the maximum amplification gain is 40 dB.
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.
Large Language Models are Learnable Planners for Long-Term Recommendation
To this end, we propose a Bi-level Learnable LLM Planner framework, which consists of a set of LLM instances and breaks down the learning process into macro-learning and micro-learning to learn macro-level guidance and micro-level personalized recommendation policies, respectively.
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.
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.
A Framework of RIS-assisted ICSC User-centric Based Systems: Latency Optimization and Design
To address the formulated non-convex problem in the multi-UE scenario, we decouple the original problem into two subproblems, where the computational and beamforming settings are optimized alternately.
Prompt Stealing Attacks Against Large Language Models
Our proposed prompt stealing attack aims to steal these well-designed prompts based on the generated answers.
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.
Are LLM-based Evaluators Confusing NLG Quality Criteria?
Some prior work has shown that LLMs perform well in NLG evaluation for different tasks.
Instruction Backdoor Attacks Against Customized LLMs
The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs.
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.
PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling
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.
Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models
This attack targets the contents of previous conversations between GPT models and benign users, i. e., the benign users' input contents during their interaction with GPT models.
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 High-performing 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
Our method strategically embeds connections between pieces of copyrighted information and text references in poisoning data while carefully dispersing that information, making the poisoning data inconspicuous when integrated into a clean dataset.
Preliminary Study on Incremental Learning for Large Language Model-based Recommender Systems
Instead of dismissing the role of incremental learning, we attribute the lack of anticipated performance enhancement to a mismatch between the LLM4Rec architecture and incremental learning: LLM4Rec employs a single adaptation module for learning recommendations, limiting 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.
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.
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.
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
We show that, when aleatoric uncertainty arises from ambiguity or under-specification in LLM inputs, this approach makes it possible to factor an (unclarified) LLM's predictions into separate aleatoric and epistemic terms, using a decomposition similar to the one employed by Bayesian neural networks.
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.
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.
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.
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).
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.
Audio-Visual Neural Syntax Acquisition
We study phrase structure induction from visually-grounded speech.
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.
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 #62 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
We hope that our study can facilitate the research community and LLM vendors in promoting safer and regulated LLMs.
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 #22 on
Emotion Recognition in Conversation
on IEMOCAP