Search Results for author:
Found 414 papers, 157 papers with code
Membership Inference Attacks on Sequence Models
Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information.
A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement
It is promising to design a single model that can suppress various distortions and improve speech quality, i. e., universal speech enhancement (USE).
Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models
To address this, we propose \textbf{LightD}, a novel framework that generates natural adversarial samples for VLP models via semantically guided relighting.
Generalizable Heuristic Generation Through Large Language Models with Meta-Optimization
Heuristic design with large language models (LLMs) has emerged as a promising approach for tackling combinatorial optimization problems (COPs).
Reinforcement Speculative Decoding for Fast Ranking
Although speculative decoding (SD) methods can be a remedy with verification at different positions, they face challenges in ranking systems due to their left-to-right decoding paradigm.
A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning
Recent advancements in deep models have highlighted the need for intelligent systems that combine continual learning (CL) for knowledge acquisition with machine unlearning (MU) for data removal, forming the Continual Learning-Unlearning (CLU) paradigm.
Table-R1: Region-based Reinforcement Learning for Table Understanding
Tables present unique challenges for language models due to their structured row-column interactions, necessitating specialized approaches for effective comprehension.
RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
Existing benchmarks for evaluating mathematical reasoning in large language models (LLMs) rely primarily on competition problems, formal proofs, or artificially challenging questions -- failing to capture the nature of mathematics encountered in actual research environments.
Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity
Human preference plays a crucial role in the refinement of large language models (LLMs).
SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache
Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more accurate and context-aware reasoning.
BMMDetect: A Multimodal Deep Learning Framework for Comprehensive Biomedical Misconduct Detection
Academic misconduct detection in biomedical research remains challenging due to algorithmic narrowness in existing methods and fragmented analytical pipelines.
Clustering with Communication: A Variational Framework for Single Cell Representation Learning
Single-cell RNA sequencing (scRNA-seq) has revealed complex cellular heterogeneity, but recent studies emphasize that understanding biological function also requires modeling cell-cell communication (CCC), the signaling interactions mediated by ligand-receptor pairs that coordinate cellular behavior.
Holmes: Automated Fact Check with Large Language Models
The rise of Internet connectivity has accelerated the spread of disinformation, threatening societal trust, decision-making, and national security.
Enhancing New-item Fairness in Dynamic Recommender Systems
In addition, FairAgent introduces a novel reward mechanism for recommendation tailored to the characteristics of DRSs, which consists of three components: 1) a new-item exploration reward to promote the exposure of dynamically introduced new-items, 2) a fairness reward to adapt to users' personalized fairness requirements for new-items, and 3) an accuracy reward which leverages users' dynamic feedback to enhance recommendation accuracy.
Inception: Jailbreak the Memory Mechanism of Text-to-Image Generation Systems
Different from previous attacks that fuse the unsafe target prompt into one ultimate adversarial prompt, which can be easily detected or may generate non-unsafe images due to under- or over-optimization, we propose Inception, the first multi-turn jailbreak attack against the memory mechanism in real-world text-to-image generation systems.
Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
To quantify these dynamic anomalies, we first introduce DAA-I, which treats the tokens' attention maps as spatially independent and measures dynamic feature using the Frobenius norm.
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
MetaMolGen: A Neural Graph Motif Generation Model for De Novo Molecular Design
Molecular generation plays an important role in drug discovery and materials science, especially in data-scarce scenarios where traditional generative models often struggle to achieve satisfactory conditional generalization.
Mask Image Watermarking
MaskMark has two variants: (1) MaskMark-D, which supports global watermark embedding, watermark localization, and local watermark extraction for applications such as tamper detection; (2) MaskMark-ED, which focuses on local watermark embedding and extraction, offering enhanced robustness in small regions to support fine-grined image protection.
The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
For example, while all jailbreaks we tested bypass guardrails in models aligned to refuse to answer math, this comes at the expense of a drop of up to 92% in accuracy.
Ray-Based Characterization of the AMPLE Model from 0.85 to 5 GHz
In this paper, we characterize the adaptive multiple path loss exponent (AMPLE) radio propagation model under urban macrocell (UMa) and urban microcell (UMi) scenarios from 0. 85-5 GHz using Ranplan Professional.
Distilling Textual Priors from LLM to Efficient Image Fusion
The distilled network, requiring only 10% of the parameters and inference time of the teacher network, retains 90% of its performance and outperforms existing SOTA methods.
BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
Box-supervised instance segmentation methods aim to achieve instance segmentation with only box annotations.
Clean Image May be Dangerous: Data Poisoning Attacks Against Deep Hashing
It is worth noting that these attacks typically involve altering the query images, which is not a practical concern in real-world scenarios.
Surgical Action Planning with Large Language Models
Large Language Models (LLMs) show promise in understanding surgical video content but remain underexplored for predictive decision-making in SAP, as they focus mainly on retrospective analysis.
Towards Invisible Backdoor Attack on Text-to-Image Diffusion Model
Backdoor attacks targeting text-to-image diffusion models have advanced rapidly, enabling attackers to implant malicious triggers into these models to manipulate their outputs.
WarmFed: Federated Learning with Warm-Start for Globalization and Personalization Via Personalized Diffusion Models
In contrast to FL, Personalized federated learning aims at serving for each client in achieving persoanlized model.
Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks
As speech translation (ST) systems become increasingly prevalent, understanding their vulnerabilities is crucial for ensuring robust and reliable communication.
RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multi-Scale Receptive Fields and Foreground Focus Mechanism
Challenges in remote sensing object detection (RSOD), such as high inter-class similarity, imbalanced foreground-background distribution, and the small size of objects in remote sensing images significantly hinder detection accuracy.
RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers
The Diffusion Transformer plays a pivotal role in advancing text-to-image and text-to-video generation, owing primarily to its inherent scalability.
CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
We evaluate Corba on two widely-used LLM-MASs, namely, AutoGen and Camel across various topologies and commercial models.
Does Training with Synthetic Data Truly Protect Privacy?
As synthetic data becomes increasingly popular in machine learning tasks, numerous methods--without formal differential privacy guarantees--use synthetic data for training.
Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs).
Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings.
Converting Transformers into DGNNs Form
Recent advances in deep learning have established Transformer architectures as the predominant modeling paradigm.
Ranked #3 on
Long-range modeling
on LRA
VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
Artificial Intelligence Generated Content (AIGC) has advanced significantly, particularly with the development of video generation models such as text-to-video (T2V) models and image-to-video (I2V) models.
Pre-train and Fine-tune: Recommenders as Large Models
We first propose the theory of the information bottleneck for fine-tuning and present an explanation for the fine-tuning technique in recommenders.
The First Indoor Pathloss Radio Map Prediction Challenge
To encourage further research and to facilitate fair comparisons in the development of deep learning-based radio propagation models, in the less explored case of directional radio signal emissions in indoor propagation environments, we have launched the ICASSP 2025 First Indoor Pathloss Radio Map Prediction Challenge.
Energy Consumption Reduction for UAV Trajectory Training : A Transfer Learning Approach
The advent of 6G technology demands flexible, scalable wireless architectures to support ultra-low latency, high connectivity, and high device density.
Normalize Then Propagate: Efficient Homophilous Regularization for Few-shot Semi-Supervised Node Classification
In this paper, we first analyze the restrictions of GNNs generalization from the perspective of supervision signals in the context of few-shot semi-supervised node classification.
Decision Transformers for RIS-Assisted Systems with Diffusion Model-Based Channel Acquisition
Reconfigurable intelligent surfaces (RISs) have been recognized as a revolutionary technology for future wireless networks.
Three-dimensional attention Transformer for state evaluation in real-time strategy games
Situation assessment in Real-Time Strategy (RTS) games is crucial for understanding decision-making in complex adversarial environments.
Online Reinforcement Learning-Based Dynamic Adaptive Evaluation Function for Real-Time Strategy Tasks
Building on traditional static evaluation functions, the method employs gradient descent in online reinforcement learning to update weights dynamically, incorporating weight decay techniques to ensure stability.
Face Forgery Video Detection via Temporal Forgery Cue Unraveling
Then, we devise a future guide module to unravel inconsistency cues by iteratively aggregating historical anomaly cues and gradually propagating them into future frames.
Video-Bench: Human-Aligned Video Generation Benchmark
This benchmark represents the first attempt to systematically leverage MLLMs across all dimensions relevant to video generation assessment in generative models.
AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised Learning
To tackle these gaps, we introduce AVF-MAE++, a series audio-visual MAE designed to explore the impact of scaling on AVFA with a focus on advanced correlation modeling.
M$^3$oralBench: A MultiModal Moral Benchmark for LVLMs
To bridge this gap, we introduce M$^3$oralBench, the first MultiModal Moral Benchmark for LVLMs.
EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
Removing unwanted concepts from large-scale text-to-image (T2I) diffusion models while maintaining their overall generative quality remains an open challenge.
Multi-P$^2$A: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models
Multi-P$^2$A covers 26 categories of personal privacy, 15 categories of trade secrets, and 18 categories of state secrets, totaling 31, 962 samples.
VSFormer: Value and Shape-Aware Transformer with Prior-Enhanced Self-Attention for Multivariate Time Series Classification
Additionally, the recent success of Transformer models has inspired many studies.
Multi-Granularity Open Intent Classification via Adaptive Granular-Ball Decision Boundary
To tackle these issues, we propose a Multi-granularity Open intent classification method via adaptive Granular-Ball decision boundary (MOGB).
RepFace: Refining Closed-Set Noise with Progressive Label Correction for Face Recognition
However, face recognition performance is heavily affected by the label noise, especially closed-set noise.
Active Large Language Model-based Knowledge Distillation for Session-based Recommendation
Knowledge distillation (KD)-based methods can alleviate these issues by transferring the knowledge to a small student, which trains a student based on the predictions of a cumbersome teacher.
SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution
For extraction, the process is reversed: the watermarked image is inverted back to the initial watermarked noise via DDIM Inversion, from which the embedded watermark is extracted.
CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder
Singing Voice Synthesis (SVS) aims to generate singing voices of high fidelity and expressiveness.
Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging.
FaceTracer: Unveiling Source Identities from Swapped Face Images and Videos for Fraud Prevention
Face-swapping techniques have advanced rapidly with the evolution of deep learning, leading to widespread use and growing concerns about potential misuse, especially in cases of fraud.
MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents
We validate our method on both digital and physical level, \ie, nuImage and manually captured real scenes, where both statistical and visual results prove that our MAGIC is powerful and effectively for attacking wide-used object detection systems.
Reinforcement Learning Enhanced LLMs: A Survey
This paper surveys research in the rapidly growing field of enhancing large language models (LLMs) with reinforcement learning (RL), a technique that enables LLMs to improve their performance by receiving feedback in the form of rewards based on the quality of their outputs, allowing them to generate more accurate, coherent, and contextually appropriate responses.
Physics-informed Deep Learning for Muscle Force Prediction with Unlabeled sEMG Signals
To achieve this, the Hill muscle model-based forward dynamics is embedded into the deep neural network as the additional loss to further regulate the behavior of the deep neural network.
MRP-LLM: Multitask Reflective Large Language Models for Privacy-Preserving Next POI Recommendation
The Neighbor Preference Retrieval Module retrieves and summarizes the preferences of similar users from the KB to obtain collaborative signals.
MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images
Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches.
Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
The rapid development of Artificial Intelligence (AI) has revolutionized numerous fields, with large language models (LLMs) and computer vision (CV) systems driving advancements in natural language understanding and visual processing, respectively.
CA-MoE: Channel-Adapted MoE for Incremental Weather Forecasting
Atmospheric science is intricately connected with other fields, e. g., geography and aerospace.
From ChebNet to ChebGibbsNet
Different polynomial bases, such as Bernstein, Chebyshev, and monomial basis, have various convergence rates that will affect the error in polynomial interpolation.
SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
In this paper, we present the first approach to generate scene-coherent typographic adversarial attacks that mislead advanced LVLMs while maintaining visual naturalness through the capability of the LLM-based agent.
Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense
Ensemble everything everywhere is a defense to adversarial examples that was recently proposed to make image classifiers robust.
Enhancing Low Dose Computed Tomography Images Using Consistency Training Techniques
This is combined with a sinusoidal curriculum that enhances the learning of the trajectory between the noise distribution and the posterior distribution of interest, allowing High Noise Improved Consistency Training (HN-iCT) to be trained in a supervised fashion.
Semantic or Covariate? A Study on the Intractable Case of Out-of-Distribution Detection
The primary goal of out-of-distribution (OOD) detection tasks is to identify inputs with semantic shifts, i. e., if samples from novel classes are absent in the in-distribution (ID) dataset used for training, we should reject these OOD samples rather than misclassifying them into existing ID classes.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Spider: Any-to-Many Multimodal LLM
To address this limitation, we introduce Spider, a novel efficient Any-to-Many Modalities Generation (AMMG) framework, which can generate an arbitrary combination of modalities 'Text + Xs', such as Text + {Image and Audio and Video}.
Advancing Sustainability via Recommender Systems: A Survey
Human behavioral patterns and consumption paradigms have emerged as pivotal determinants in environmental degradation and climate change, with quotidian decisions pertaining to transportation, energy utilization, and resource consumption collectively precipitating substantial ecological impacts.
Confidence Aware Learning for Reliable Face Anti-spoofing
The prediction confidence for each sample is subsequently assessed using the Mahalanobis distance between the sample and the Gaussians for the "known data".
Learning to Handle Complex Constraints for Vehicle Routing Problems
Vehicle Routing Problems (VRPs) can model many real-world scenarios and often involve complex constraints.
DEAN: Deactivating the Coupled Neurons to Mitigate Fairness-Privacy Conflicts in Large Language Models
Extensive experimental results demonstrate that DEAN eliminates the trade-off phenomenon and significantly improves LLMs' fairness and privacy awareness simultaneously, \eg improving Qwen-2-7B-Instruct's fairness awareness by 12. 2\% and privacy awareness by 14. 0\%.
SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
However, in this paper, we examine the merged model's representation distribution and uncover a critical issue of "representation bias".
REEF: Representation Encoding Fingerprints for Large Language Models
Therefore, model owners and third parties need to identify whether a suspect model is a subsequent development of the victim model.
SiFiSinger: A High-Fidelity End-to-End Singing Voice Synthesizer based on Source-filter Model
This paper presents an advanced end-to-end singing voice synthesis (SVS) system based on the source-filter mechanism that directly translates lyrical and melodic cues into expressive and high-fidelity human-like singing.
Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
In this paper, we introduce SIREN, a novel methodology to proactively trace unauthorized data usage in black-box personalized text-to-image diffusion models.
Wireless-Friendly Window Position Optimization for RIS-Aided Outdoor-to-Indoor Networks based on Multi-Modal Large Language Model
This paper aims to simultaneously optimize indoor wireless and daylight performance by adjusting the positions of windows and the beam directions of window-deployed reconfigurable intelligent surfaces (RISs) for RIS-aided outdoor-to-indoor (O2I) networks utilizing large language models (LLM) as optimizers.
Collaboration! Towards Robust Neural Methods for Routing Problems
Given a neural VRP method, we adversarially train multiple models in a collaborative manner to synergistically promote robustness against attacks, while boosting standard generalization on clean instances.
Multiscale Latent Diffusion Model for Enhanced Feature Extraction from Medical Images
In response to these challenges, we propose LTDiff++, a multiscale latent diffusion model designed to enhance feature extraction in medical imaging.
Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
We argue that this approach is fundamentally unsound: to provide convincing evidence, the data creator needs to demonstrate that their attack has a low false positive rate, i. e., that the attack's output is unlikely under the null hypothesis that the model was not trained on the target data.
Face Forgery Detection with Elaborate Backbone
Specifically, we analyze the crucial contributions of backbones with different configurations in FFD task and propose leveraging the ViT network with self-supervised learning on real-face datasets to pre-train a backbone, equipping it with superior facial representation capabilities.
Mean Age of Information in Partial Offloading Mobile Edge Computing Networks
The results show that by jointly optimising the COR and TGR, the partial offloading scheme outperforms the local and remote computing schemes in terms of the MAoI, which can be improved by up to 51% and 61%, respectively.
LiSenNet: Lightweight Sub-band and Dual-Path Modeling for Real-Time Speech Enhancement
Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility.
Geometry-Constrained EEG Channel Selection for Brain-Assisted Speech Enhancement
Brain-assisted speech enhancement (BASE) aims to extract the target speaker in complex multi-talker scenarios using electroencephalogram (EEG) signals as an assistive modality, as the auditory attention of the listener can be decoded from electroneurographic signals of the brain.
A Lightweight and Real-Time Binaural Speech Enhancement Model with Spatial Cues Preservation
Binaural speech enhancement (BSE) aims to jointly improve the speech quality and intelligibility of noisy signals received by hearing devices and preserve the spatial cues of the target for natural listening.
InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference
Several cost-effective solutions leverage host memory or SSDs to reduce storage costs for offline inference scenarios and improve the throughput.
Spindle: Efficient Distributed Training of Multi-Task Large Models via Wavefront Scheduling
Recent foundation models are capable of handling multiple tasks and multiple data modalities with the unified base model structure and several specialized model components.
Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusion
Multi-modal image fusion integrates complementary information from different modalities to produce enhanced and informative images.
Optimal Dispatch Strategy for a Multi-microgrid Cooperative Alliance Using a Two-Stage Pricing Mechanism
To coordinate resources among multi-level stakeholders and enhance the integration of electric vehicles (EVs) into multi-microgrids, this study proposes an optimal dispatch strategy within a multi-microgrid cooperative alliance using a nuanced two-stage pricing mechanism.
LCM-SVC: Latent Diffusion Model Based Singing Voice Conversion with Inference Acceleration via Latent Consistency Distillation
We achieved one-step or few-step inference while maintaining the high performance by distilling a pre-trained LDM based SVC model, which had the advantages of timbre decoupling and sound quality.
Empowering Wireless Network Applications with Deep Learning-based Radio Propagation Models
The efficient deployment and operation of any wireless communication ecosystem rely on knowledge of the received signal quality over the target coverage area.
Non-Homophilic Graph Pre-Training and Prompt Learning
In particular, many real-world graphs are non-homophilic, not strictly or uniformly homophilic with mixing homophilic and heterophilic patterns, exhibiting varying non-homophilic characteristics across graphs and nodes.
GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models
By offering a realistic assessment and tailored reduction of gender biases, we hope that our GenderCARE can represent a significant step towards achieving fairness and equity in LLMs.
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
Model merging is an efficient empowerment technique in the machine learning community that does not require the collection of raw training data and does not require expensive computation.
FacialPulse: An Efficient RNN-based Depression Detection via Temporal Facial Landmarks
Depression is a prevalent mental health disorder that significantly impacts individuals' lives and well-being.
The Crowd in MOOCs: A Study of Learning Patterns at Scale
The increasing availability of learning activity data in Massive Open Online Courses (MOOCs) enables us to conduct a large-scale analysis of learners' learning behavior.
Training-Free Large Model Priors for Multiple-in-One Image Restoration
To address this issue, we propose Large Model Driven Image Restoration framework (LMDIR), a novel multiple-in-one image restoration paradigm that leverages the generic priors from large multi-modal language models (MMLMs) and the pretrained diffusion models.
The Better Angels of Machine Personality: How Personality Relates to LLM Safety
In this paper, we discover that LLMs' personality traits are closely related to their safety abilities, i. e., toxicity, privacy, and fairness, based on the reliable MBTI-M scale.
RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL
Large language models (LLMs) with in-context learning have significantly improved the performance of text-to-SQL task.
T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
In this paper, for the first time, we propose a comprehensive defense method named T2IShield to detect, localize, and mitigate such attacks.
The USTC-NERCSLIP Systems for The ICMC-ASR Challenge
This report describes the submitted system to the In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) challenge, which considers the ASR task with multi-speaker overlapping and Mandarin accent dynamics in the ICMC case.
Complementary Fusion of Deep Network and Tree Model for ETA Prediction
Estimated time of arrival (ETA) is a very important factor in the transportation system.
Decision Transformer for IRS-Assisted Systems with Diffusion-Driven Generative Channels
In this paper, we propose a novel diffusion-decision transformer (D2T) architecture to optimize the beamforming strategies for intelligent reflecting surface (IRS)-assisted multiple-input single-output (MISO) communication systems.
Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs
Currently many benchmarks have been proposed to evaluate the perception ability of the Large Vision-Language Models (LVLMs).
Evaluating the Quality of Hallucination Benchmarks for Large Vision-Language Models
Furthermore, based on the results of our quality measurement, we construct a High-Quality Hallucination Benchmark (HQH) for LVLMs, which demonstrates superior reliability and validity under our HQM framework.
Blind Baselines Beat Membership Inference Attacks for Foundation Models
Membership inference (MI) attacks try to determine if a data sample was used to train a machine learning model.
Similarity-aware Syncretic Latent Diffusion Model for Medical Image Translation with Representation Learning
Typical conditional diffusion models commonly generate images with guidance of segmentation labels for medical modal transformation.
VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
The emergence of Large Vision-Language Models (LVLMs) marks significant strides towards achieving general artificial intelligence.
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute malicious tasks.
Textual Unlearning Gives a False Sense of Unlearning
Language Models (LMs) are prone to ''memorizing'' training data, including substantial sensitive user information.
Multimodal Radiomics Model for Predicting Gold Nanoparticles Accumulation in Mouse Tumors
For each tumor in the test set, the radiomics signature predicted gold nanoparticle uptake.
Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
In this paper, we construct a benchmark named Incremental Shift OOD (IS-OOD) to address the issue, in which we divide the test samples into subsets with different semantic and covariate shift degrees relative to the ID dataset.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Refining Self-Supervised Learnt Speech Representation using Brain Activations
It was shown in literature that speech representations extracted by self-supervised pre-trained models exhibit similarities with brain activations of human for speech perception and fine-tuning speech representation models on downstream tasks can further improve the similarity.
LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance
We pretrain a variational autoencoder structure using the noted open-source So-VITS-SVC project based on the VITS framework, which is then used for the LDM training.
Anonymization Prompt Learning for Facial Privacy-Preserving Text-to-Image Generation
Specifically, we train a learnable prompt prefix for text-to-image diffusion models, which forces the model to generate anonymized facial identities, even when prompted to produce images of specific individuals.
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
Additionally, we introduce three large-scale red-teaming datasets for studying the safety risks associated with text-to-image models.
Unlearning during Learning: An Efficient Federated Machine Unlearning Method
To facilitate the implementation of the right to be forgotten, the concept of federated machine unlearning (FMU) has also emerged.
Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography
To further explore the risk in AD systems and the transferability of practical threats, we propose to leverage typographic attacks against AD systems relying on the decision-making capabilities of Vision-LLMs.
BIMM: Brain Inspired Masked Modeling for Video Representation Learning
The visual pathway of human brain includes two sub-pathways, ie, the ventral pathway and the dorsal pathway, which focus on object identification and dynamic information modeling, respectively.
Image to Pseudo-Episode: Boosting Few-Shot Segmentation by Unlabeled Data
Few-shot segmentation (FSS) aims to train a model which can segment the object from novel classes with a few labeled samples.
Cross-Domain Continual Learning via CLAMP
To this end, this article proposes a cross-domain CL approach making possible to deploy a single model in such environments without additional labelling costs.
LMVD: A Large-Scale Multimodal Vlog Dataset for Depression Detection in the Wild
Depression can significantly impact many aspects of an individual's life, including their personal and social functioning, academic and work performance, and overall quality of life.
When LLMs Meet Cybersecurity: A Systematic Literature Review
The rapid development of large language models (LLMs) has opened new avenues across various fields, including cybersecurity, which faces an evolving threat landscape and demand for innovative technologies.
MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
Learning to solve vehicle routing problems (VRPs) has garnered much attention.
Evaluations of Machine Learning Privacy Defenses are Misleading
Empirical defenses for machine learning privacy forgo the provable guarantees of differential privacy in the hope of achieving higher utility while resisting realistic adversaries.
Dual Expert Distillation Network for Generalized Zero-Shot Learning
Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation.
ID-Animator: Zero-Shot Identity-Preserving Human Video Generation
In this study, we present \textbf{ID-Animator}, a zero-shot human-video generation approach that can perform personalized video generation given a single reference facial image without further training.
High Noise Scheduling is a Must
The results show that the polynomial noise distribution outperforms the model trained with log-normal noise distribution, yielding a 33. 54 FID score after 100, 000 training steps with constant discretization steps.
Decision Transformers for Wireless Communications: A New Paradigm of Resource Management
By leveraging the power of DT models learned over offline datasets, the proposed architecture is expected to achieve rapid convergence with many fewer training epochs and higher performance in new scenarios with different state and action spaces, compared with DRL.
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
In this work, we investigate a more practical and universal attack that does not require the presence of a target model and demonstrate that the high-dimensional text embedding space inherently contains NSFW concepts that can be exploited to generate harmful images.
How memories are stored in the brain: the declarative memory model
The ability to form memories is a basic feature of learning and accumulating knowledge.
RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict
Furthermore, we construct RU22Fact, a novel multilingual explainable fact-checking dataset on the Russia-Ukraine conflict in 2022 of 16K samples, each containing real-world claims, optimized evidence, and referenced explanation.
Re2LLM: Reflective Reinforcement Large Language Model for Session-based Recommendation
However, the former methods struggle with optimal prompts to elicit the correct reasoning of LLMs due to the lack of task-specific feedback, leading to unsatisfactory recommendations.
DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
Federated learning (FL) has emerged as a powerful paradigm for learning from decentralized data, and federated domain generalization further considers the test dataset (target domain) is absent from the decentralized training data (source domains).
DiffClass: Diffusion-Based Class Incremental Learning
On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data.
RSAM-Seg: A SAM-based Approach with Prior Knowledge Integration for Remote Sensing Image Semantic Segmentation
While the direct application of SAM to remote sensing image segmentation tasks does not yield satisfactory results, we propose RSAM-Seg, which stands for Remote Sensing SAM with Semantic Segmentation, as a tailored modification of SAM for the remote sensing field and eliminates the need for manual intervention to provide prompts.
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
This research provides an initial exploration of trustworthiness modeling during LLM pre-training, seeking to unveil new insights and spur further developments in the field.
Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging
Log parsing, which entails transforming raw log messages into structured templates, constitutes a critical phase in the automation of log analytics.
Model X-ray:Detecting Backdoored Models via Decision Boundary
By accessing the model to obtain hard labels, we construct decision boundaries within the convex combination of three samples.
FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computing
However, the resulting model still consumes a large amount of GPU memory.
Pan-Mamba: Effective pan-sharpening with State Space Model
To the best of our knowledge, this work is the first attempt in exploring the potential of the Mamba model and establishes a new frontier in the pan-sharpening techniques.
Towards Cross-Domain Continual Learning
In this work, we introduce a novel approach called Cross-Domain Continual Learning (CDCL) that addresses the limitations of being limited to single supervised domains.
SIBO: A Simple Booster for Parameter-Efficient Fine-Tuning
Fine-tuning all parameters of large language models (LLMs) necessitates substantial computational power and extended time.
Large Language Model with Graph Convolution for Recommendation
To adapt text-based LLMs with structured graphs, We use the LLM as an aggregator in graph processing, allowing it to understand graph-based information step by step.
Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
Recent Meta-learning for Black-Box Optimization (MetaBBO) methods harness neural networks to meta-learn configurations of traditional black-box optimizers.
PRIME: Protect Your Videos From Malicious Editing
With the development of generative models, the quality of generated content keeps increasing.
Multi-granularity Correspondence Learning from Long-term Noisy Videos
Existing video-language studies mainly focus on learning short video clips, leaving long-term temporal dependencies rarely explored due to over-high computational cost of modeling long videos.
Action Segmentation
Long Video Retrieval (Background Removed)
+2
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
Multi-modal Large Language Models (MLLMs) have shown impressive abilities in generating reasonable responses with respect to multi-modal contents.
Adversarial speech for voice privacy protection from Personalized Speech generation
For validation, we employ the open-source pre-trained YourTTS model for speech generation and protect the target speaker's speech in the white-box scenario.
CBVS: A Large-Scale Chinese Image-Text Benchmark for Real-World Short Video Search Scenarios
Differently, video covers in short video search scenarios are presented as user-originated contents that provide important visual summaries of videos.
Ranked #1 on
Image Retrieval
on CBVS
Generalized Face Liveness Detection via De-fake Face Generator
Previous Face Anti-spoofing (FAS) methods face the challenge of generalizing to unseen domains, mainly because most existing FAS datasets are relatively small and lack data diversity.
Collaboratively Self-supervised Video Representation Learning for Action Recognition
Considering the close connection between action recognition and human pose estimation, we design a Collaboratively Self-supervised Video Representation (CSVR) learning framework specific to action recognition by jointly factoring in generative pose prediction and discriminative context matching as pretext tasks.
Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
Specifically, PMG-AFT minimizes the distance between the features of adversarial examples in the target model and those in the pre-trained model, aiming to preserve the generalization features already captured by the pre-trained model.
TeleChat Technical Report
Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe.
Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
Considering that visual information helps to improve speech recognition performance in noisy scenes, in this work we propose a multichannel multi-modal speech self-supervised learning framework AV-wav2vec2, which utilizes video and multichannel audio data as inputs.
Audio-Visual Speech Recognition
Automatic Speech Recognition
+7
Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain
However, current methods often ignore the difference between cell phone RAW images and DSLR camera RGB images, a difference that goes beyond the color matrix and extends to spatial structure due to resolution variations.
Frequency-Adaptive Pan-Sharpening with Mixture of Experts
Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance.
FullLoRA-AT: Efficiently Boosting the Robustness of Pretrained Vision Transformers
In recent years, the Vision Transformer (ViT) model has gradually become mainstream in various computer vision tasks, and the robustness of the model has received increasing attention.
Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement
The attention mechanism has been proven effective on various visual tasks in recent years.
Video Harmonization with Triplet Spatio-Temporal Variation Patterns
Video harmonization is an important and challenging task that aims to obtain visually realistic composite videos by automatically adjusting the foreground's appearance to harmonize with the background.
SAME: Sample Reconstruction against Model Extraction Attacks
While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure.
ParsNets: A Parsimonious Orthogonal and Low-Rank Linear Networks for Zero-Shot Learning
Then, to facilitate the generalization of local linearities, we construct a maximal margin geometry on the learned features by enforcing low-rank constraints on intra-class samples and high-rank constraints on inter-class samples, resulting in orthogonal subspaces for different classes and each subspace lies on a compact manifold.
iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching
We present a method named iComMa to address the 6D camera pose estimation problem in computer vision.
MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing
This enhances masked-based editing in local areas; second, we present a novel distillation strategy: Conditional Distillation on Geometry and Texture (CDGT).
Calibration-free quantitative phase imaging in multi-core fiber endoscopes using end-to-end deep learning
Quantitative phase imaging (QPI) through multi-core fibers (MCFs) has been an emerging in vivo label-free endoscopic imaging modality with minimal invasiveness.
Control Risk for Potential Misuse of Artificial Intelligence in Science
In this study, we aim to raise awareness of the dangers of AI misuse in science, and call for responsible AI development and use in this domain.
Data-Free Hard-Label Robustness Stealing Attack
In response to these identified gaps, we introduce a novel Data-Free Hard-Label Robustness Stealing (DFHL-RS) attack in this paper, which enables the stealing of both model accuracy and robustness by simply querying hard labels of the target model without the help of any natural data.
Singular Regularization with Information Bottleneck Improves Model's Adversarial Robustness
However, these works lack analysis of adversarial information or perturbation, which cannot reveal the mystery of adversarial examples and lose proper interpretation.
FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model
Specifically, we find that the very last few steps of the denoising (i. e., generation) process strongly correspond to the stylistic information of images, and based on this, we propose to augment the latent features of both the foreground and background images with Gaussians for a direct denoising-based harmonization.
Attribute-Aware Representation Rectification for Generalized Zero-Shot Learning
In this paper, we propose a simple yet effective Attribute-Aware Representation Rectification framework for GZSL, dubbed $\mathbf{(AR)^{2}}$, to adaptively rectify the feature extractor to learn novel features while keeping original valuable features.
Sparsity-Driven EEG Channel Selection for Brain-Assisted Speech Enhancement
In this work, we therefore propose a novel end-to-end brain-assisted speech enhancement network (BASEN), which incorporates the listeners' EEG signals and adopts a temporal convolutional network together with a convolutional multi-layer cross attention module to fuse EEG-audio features.
Improving Adversarial Transferability by Stable Diffusion
Various techniques have emerged to enhance the transferability of adversarial attacks for the black-box scenario.
Segue: Side-information Guided Generative Unlearnable Examples for Facial Privacy Protection in Real World
To address these concerns, researchers are actively exploring the concept of ``unlearnable examples", by adding imperceptible perturbation to data in the model training stage, which aims to prevent the model from learning discriminate features of the target face.
Pix2HDR -- A pixel-wise acquisition and deep learning-based synthesis approach for high-speed HDR videos
By combining the versatility of pixel-wise sampling patterns with the strength of deep neural networks at decoding complex scenes, our method greatly enhances the vision system's adaptability and performance in dynamic conditions.
IntentDial: An Intent Graph based Multi-Turn Dialogue System with Reasoning Path Visualization
Intent detection and identification from multi-turn dialogue has become a widely explored technique in conversational agents, for example, voice assistants and intelligent customer services.
Real-Fake: Effective Training Data Synthesis Through Distribution Matching
Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation.
Multiview Transformer: Rethinking Spatial Information in Hyperspectral Image Classification
To aggregate the multiview information, a fully-convolutional SED with a U-shape in spectral dimension is introduced to extract a multiview feature map.
Latent Diffusion Model for Medical Image Standardization and Enhancement
Finally, the decoder uses the transformed latent representation to generate a standardized CT image, providing a more consistent basis for downstream analysis.
PGDQN: Preference-Guided Deep Q-Network
Stochastic exploration is the key to the success of the Deep Q-network (DQN) algorithm.
Warfare:Breaking the Watermark Protection of AI-Generated Content
AI-Generated Content (AIGC) is rapidly expanding, with services using advanced generative models to create realistic images and fluent text.
Cluster-based Method for Eavesdropping Identification and Localization in Optical Links
We propose a cluster-based method to detect and locate eavesdropping events in optical line systems characterized by small power losses.
Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023
Three different structures based on attention-guided feature gathering (AFG) are designed for deep feature fusion.
Understanding Data Augmentation from a Robustness Perspective
In the realm of visual recognition, data augmentation stands out as a pivotal technique to amplify model robustness.
Rep2wav: Noise Robust text-to-speech Using self-supervised representations
Noise-robust TTS models are often trained using the enhanced speech, which thus suffer from speech distortion and background noise that affect the quality of the synthesized speech.
Backdooring Textual Inversion for Concept Censorship
Users can easily download the word embedding from public websites like Civitai and add it to their own stable diffusion model without fine-tuning for personalization.
Patch Is Not All You Need
Vision Transformers have achieved great success in computer visions, delivering exceptional performance across various tasks.
Semantic-Human: Neural Rendering of Humans from Monocular Video with Human Parsing
In this paper, we present Semantic-Human, a novel method that achieves both photorealistic details and viewpoint-consistent human parsing for the neural rendering of humans.
Overlap Bias Matching is Necessary for Point Cloud Registration
Specifically, we propose a plug-and-play Overlap Bias Matching Module (OBMM) comprising two integral components, overlap sampling module and bias prediction module.
Mobile Supply: The Last Piece of Jigsaw of Recommender System
In order to address the problem of pagination trigger mechanism, we propose a completely new module in the pipeline of recommender system named Mobile Supply.
Sampling to Distill: Knowledge Transfer from Open-World Data
Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data.
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
Rethinking Data Distillation: Do Not Overlook Calibration
Neural networks trained on distilled data often produce over-confident output and require correction by calibration methods.
Enhancing Job Recommendation through LLM-based Generative Adversarial Networks
However, directly leveraging LLMs to enhance recommendation results is not a one-size-fits-all solution, as LLMs may suffer from fabricated generation and few-shot problems, which degrade the quality of resume completion.
Our Model Achieves Excellent Performance on MovieLens: What Does it Mean?
First, there are significant differences in user interactions at the different stages when a user interacts with the MovieLens platform.
ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint
We propose a novel Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint (ESMC) and two alternatives: Entire Space Multi-Task Model with Siamese Network (ESMS) and Entire Space Multi-Task Model in Global Domain (ESMG) to address the PSC issue.
Learning Subjective Time-Series Data via Utopia Label Distribution Approximation
In this work, we propose Utopia Label Distribution Approximation (ULDA) for time-series data, which makes the training label distribution closer to real-world but unknown (utopia) label distribution.
Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators
Theoretically, we show the convergence guarantee of the dual regulators.
Using electrical impedance spectroscopy to identify equivalent circuit models of lubricated contacts with complex geometry: in-situ application to mini traction machine
Overall, the proposed method is applicable to general lubricated interfaces for the identification of equivalent circuit models, which in turn facilitates in-situ tribo-contacts with electric impedance measurement of oil film thickness.
