Papers

New on arXiv

Sun 3 Nov 2024

151 papers

Poison Attacks and Adversarial Prompts Against an Informed University Virtual AssistantLLM safety and security → Prompt injection and agent security
Learning World Models for Unconstrained Goal NavigationWorld models → Latent dynamics models and model-based RL +1
Data Extraction Attacks in Retrieval-Augmented Generation via BackdoorsRetrieval-augmented generation → Privacy and security of RAG +1
UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Optical Flow Representation Alignment Mamba Diffusion Model for Medical Video GenerationDiffusion models → Medical imaging and segmentation +1
EcoAct: Economic Agent Determines When to Register What ActionLLM agents and tool use → General LLM agent frameworks and benchmarks
Denoising Diffusions with Optimal Transport: Localization, Curvature, and Multi-Scale ComplexityDiffusion models → Diffusion foundations and sampling
RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question AnsweringMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
BiT-MamSleep: Bidirectional Temporal Mamba for EEG Sleep StagingState-space sequence models (S4, Mamba) → Physiological signal modeling
HC3L-Diff: Hybrid conditional latent diffusion with high frequency enhancement for CBCT-to-CT synthesisDiffusion models → Medical imaging and segmentation
Conditional Controllable Image FusionDiffusion models → Image generation, text-to-image and editing
Addressing Failures in Robotics using Vision-Based Language Models (VLMs) and Behavior Trees (BT)Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
SQL Injection Jailbreak: A Structural Disaster of Large Language ModelsLLM safety and security → Jailbreaking
Statistical guarantees for denoising reflected diffusion modelsDiffusion models → Diffusion foundations and sampling
Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level AlignmentKnowledge distillation → General knowledge distillation methods
Towards Small Object Editing: A Benchmark Dataset and A Training-Free ApproachDiffusion models → Image generation, text-to-image and editing
Diversity Progress for Goal Selection in Discriminability-Motivated RLDeep reinforcement learning methods → Deep RL algorithms and representations
Integration of Large Vision Language Models for Efficient Post-disaster Damage Assessment and ReportingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Sample-Efficient Alignment for LLMsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering BenchmarkMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
DPCL-Diff: The Temporal Knowledge Graph Reasoning Based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive LearningDiffusion models → Discrete and text diffusion
Facet-Aware Multi-Head Mixture-of-Experts Model for Sequential RecommendationMixture-of-experts → MoE for recommender systems
Deep Reinforcement Learning for Optimizing Inverter Control: Fixed and Adaptive Gain Tuning Strategies for Power System StabilityDeep reinforcement learning methods → RL for energy, networks and operations
A Visual Question Answering Method for SAR Ship: Breaking the Requirement for Multimodal Dataset Construction and Model Fine-TuningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
Learning Hidden Subgoals under Temporal Ordering Constraints in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
MambaReg: Mamba-Based Disentangled Convolutional Sparse Coding for Unsupervised Deformable Multi-Modal Image RegistrationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System
A Multi-Modal Unsupervised Machine Learning Approach for Biomedical Signal Processing in CPR
Unexploited Information Value in Human-AI Collaboration
A Machine Learning based Hybrid Receiver for 5G NR PRACH
Equitable Length of Stay Prediction for Patients with Learning Disabilities and Multiple Long-term Conditions Using Machine Learning
Guiding Genetic Programming with Graph Neural Networks
Hierarchical Sentiment Analysis Framework for Hate Speech Detection: Implementing Binary and Multiclass Classification Strategy
Undermining Image and Text Classification Algorithms Using Adversarial Attacks
Machine Learning Innovations in CPR: A Comprehensive Survey on Enhanced Resuscitation Techniques
A Course Intelligence Platform for Higher Education: Lessons from AI-Assisted Course Evaluation
Graph-based Confidence Calibration for Large Language Models
Super-Resolution without High-Resolution Labels for Black Hole Simulations
Goal-Oriented Semantic Communication for Wireless Visual Question Answering
High-performance automated abstract screening with large language model ensembles
Assessing Superposition-Targeted Coverage Criteria for Quantum Neural Networks
Chronic Obstructive Pulmonary Disease Prediction Using Deep Convolutional Network
Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models
WiCV@CVPR2024: The Thirteenth Women In Computer Vision Workshop at the Annual CVPR Conference
1st-Order Magic: Analysis of Sharpness-Aware Minimization
Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation
Large-Scale Multirobot Coverage Path Planning on Grids With Path Deconfliction
Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups
Symmetry Adapted Residual Neural Network Diabatization: Conical Intersections in Aniline Photodissociation
Conformal Risk Minimization with Variance Reduction
Co-clustering for Federated Recommender System
Reducing Biases in Record Matching Through Scores Calibration
ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Driving
Autoformulation of Mathematical Optimization Models Using LLMs
Robust Neural Processes for Noisy Data
MamT4: Multi-view Attention Networks for Mammography Cancer Classification
GraphXForm: Graph transformer for computer-aided molecular design
Unlocking the Theory Behind Scaling 1-Bit Neural Networks
Sing-On-Your-Beat: Simple Text-Controllable Accompaniment Generations
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration
Diagnosing Medical Datasets with Training Dynamics
Optimizing Gastrointestinal Diagnostics: A CNN-Based Model for VCE Image Classification
Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers
Achieving Domain-Independent Certified Robustness via Knowledge Continuity
Quantum Rationale-Aware Graph Contrastive Learning for Jet Discrimination
Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics
Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework
Leveraging Microservices Architecture for Dynamic Pricing in the Travel Industry: Algorithms, Scalability, and Impact on Revenue and Customer Satisfaction
Multiclass Transductive Online Learning
Energy-Aware FPGA Implementation of Spiking Neural Network with LIF Neurons
Counterfactual explainability and analysis of variance
PreCM: The Padding-based Rotation Equivariant Convolution Mode for Semantic Segmentation
FilterNet: Harnessing Frequency Filters for Time Series Forecasting
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labels
Ontology Population using LLMs
Stochastic Communication Avoidance for Recommendation Systems
Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM
GITSR: Graph Interaction Transformer-based Scene Representation for Multi Vehicle Collaborative Decision-making
Large Language Model Supply Chain: Open Problems From the Security Perspective
DreamPolish: Domain Score Distillation With Progressive Geometry Generation
Graph Fourier Neural ODEs: Modeling Spatial-temporal Multi-scales in Molecular Dynamics
OSAD: Open-Set Aircraft Detection in SAR Images
Strategic Conformal Prediction
High-Fidelity Virtual Try-on with Large-Scale Unpaired Learning
One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection
Trustworthy Federated Learning: Privacy, Security, and Beyond
Federated Learning Clients Clustering with Adaptation to Data Drifts
Flexible Coded Distributed Convolution Computing for Enhanced Straggler Resilience and Numerical Stability in Distributed CNNs
Explainable Clustering of Mixture Models
DELE: Deductive EL++ Embeddings for Knowledge Base Completion
Online Graph Topology Learning via Time-Vertex Adaptive Filters: From Theory to Cardiac Fibrillation
ParseCaps: An Interpretable Parsing Capsule Network for Medical Image Diagnosis
Are LLMs good pragmatic speakers?
Adaptive Conformal Inference by Particle Filtering under Hidden Markov Models
Learning to Communicate Through Implicit Communication Channels
Analysis of regularized federated learning

All 151