Papers

New on arXiv

Sat 31 Aug 2024

106 papers

BreachSeek: A Multi-Agent Automated Penetration TesterLLM agents and tool use → Agent threats, guardrails and governance
HSF: Defending against Jailbreak Attacks with Hidden State FilteringLLM safety and security → Jailbreaking
TSO: Self-Training with Scaled Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
Sparse Mamba: Introducing Controllability, Observability, And Stability To Structural State Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Compositional 3D-aware Video Generation with LLM DirectorDiffusion models → Video generation
Learning to Ask: When LLM Agents Meet Unclear InstructionLLM agents and tool use → Tool learning and function calling
FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language ModelMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
How Does Diverse Interpretability of Textual Prompts Impact Medical Vision-Language Zero-Shot Tasks?Multimodal LLMs / vision-language models → Medical vision-language models
RevCD -- Reversed Conditional Diffusion for Generalized Zero-Shot LearningDiffusion models → Image generation, text-to-image and editing
GenAI-powered Multi-Agent Paradigm for Smart Urban Mobility: Opportunities and Challenges for Integrating Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) with Intelligent Transportation SystemsRetrieval-augmented generation → Agentic RAG, agents and memory +1
Accurate Compression of Text-to-Image Diffusion Models via Vector QuantizationDiffusion models → Diffusion foundations and sampling
Is Difficulty Calibration All We Need? Towards More Practical Membership Inference AttacksLLM safety and security → Membership inference attacks
Robust off-policy Reinforcement Learning via Soft Constrained AdversaryDeep reinforcement learning methods → Adversarial robustness and RL in finance
iToT: An Interactive System for Customized Tree-of-Thought GenerationLLM reasoning → Prompting and chain-of-thought reasoning
A Hybrid Transformer-Mamba Network for Single Image DerainingState-space sequence models (S4, Mamba) → Vision Mamba backbones
Rethinking Backdoor Detection Evaluation for Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
Towards understanding Diffusion Models (on Graphs)Diffusion models → Flow matching, time series and science
YA-TA: Towards Personalized Question-Answering Teaching Assistants using Instructor-Student Dual Retrieval-augmented Knowledge FusionRetrieval-augmented generation → Agentic RAG, agents and memory
Aligning Medical Images with General Knowledge from Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
Foundations of Multivariate Distributional Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Training-Free Sketch-Guided Diffusion with Latent OptimizationDiffusion models → Image generation, text-to-image and editing
StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language ModelsLLM reasoning → Audio-language model reasoning +1
OpenRANet: Neuralized Spectrum Access by Joint Subcarrier and Power Allocation with Optimization-based Deep Learning
CyberNFTs: Conceptualizing a decentralized and reward-driven intrusion detection system with ML
Fairness in Survival Analysis with Distributionally Robust Optimization
The potential functions of an international institution for AI safety. Insights from adjacent policy areas and recent trends
Learning Co-Speech Gesture Representations in Dialogue through Contrastive Learning: An Intrinsic Evaluation
Ethical Challenges in Computer Vision: Ensuring Privacy and Mitigating Bias in Publicly Available Datasets
Slug Mobile: Test-Bench for RL Testing
Identifying Factors to Help Improve Existing Decomposition-Based PMI Estimation Methods
Evaluating the Performance of Large Language Models in Competitive Programming: A Multi-Year, Multi-Grade Analysis
Post-mastoidectomy Surface Multi-View Synthesis from a Single Microscopy Image
Machine Learning Framework for High-Resolution Air Temperature Downscaling Using LiDAR-Derived Urban Morphological Features
CoRA: Optimizing Low-Rank Adaptation with Common Subspace of Large Language Models
Two-Stage Hierarchical and Explainable Feature Selection Framework for Dimensionality Reduction in Sleep Staging
Using Deep Learning to Design High Aspect Ratio Fusion Devices
Comparative Analysis of Modality Fusion Approaches for Audio-Visual Person Identification and Verification
Multi-Task Combinatorial Bandits for Budget Allocation
Multi-Output Distributional Fairness via Post-Processing
Digit Recognition using Multimodal Spiking Neural Networks
Testing and Evaluation of Large Language Models: Correctness, Non-Toxicity, and Fairness
Data Augmentation for Image Classification using Generative AI
Large Language Models-Enabled Digital Twins for Precision Medicine in Rare Gynecological Tumors
Incremental Open-set Domain Adaptation
Post-OCR Text Correction for Bulgarian Historical Documents
EraseDraw: Learning to Draw Step-by-Step via Erasing Objects from Images
Mapping earth mounds from space
Plant detection from ultra high resolution remote sensing images: A Semantic Segmentation approach based on fuzzy loss
Streamlining Forest Wildfire Surveillance: AI-Enhanced UAVs Utilizing the FLAME Aerial Video Dataset for Lightweight and Efficient Monitoring
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
DAP: Diffusion-based Affordance Prediction for Multi-modality Storage
Evaluation of Prosumer Networks for Peak Load Management in Iran: A Distributed Contextual Stochastic Optimization Approach
Geospatial foundation models for image analysis: evaluating and enhancing NASA-IBM Prithvi's domain adaptability
Rapid Gyroscope Calibration: A Deep Learning Approach
TrackSSM: A General Motion Predictor by State-Space Model
Multi-scale Multi-instance Visual Sound Localization and Segmentation
Advancing Machine Learning in Industry 4.0: Benchmark Framework for Rare-event Prediction in Chemical Processes
Statistics of punctuation in experimental literature -- the remarkable case of "Finnegans Wake" by James Joyce
Simbanex: Similarity-based Exploration of IEEE VIS Publications
Studying the Effects of Self-Attention on SAR Automatic Target Recognition
Gradient-Free Method for Heavily Constrained Nonconvex Optimization
Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
LangPose: Language-Aligned Motion for Robust 3D Human Pose Estimation
PSLF: A PID Controller-incorporated Second-order Latent Factor Analysis Model for Recommender System
The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcripts
Separation of Body and Background in Radiological Images. A Practical Python Code
Breaking Down Financial News Impact: A Novel AI Approach with Geometric Hypergraphs
Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations
Learning linear acyclic causal model including Gaussian noise using ancestral relationships
With Good MT There is No Need For End-to-End: A Case for Translate-then-Summarize Cross-lingual Summarization
Multi-label Zero-Shot Audio Classification with Temporal Attention
An Enhanced Batch Query Architecture in Real-time Recommendation
COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation
Self-supervised Fusarium Head Blight Detection with Hyperspectral Image and Feature Mining
Lyapunov Neural ODE State-Feedback Control Policies
Density Adaptive Attention-based Speech Network: Enhancing Feature Understanding for Mental Health Disorders
A method for detecting dead fish on large water surfaces based on improved YOLOv10
3D Gaussian Splatting for Large-scale Surface Reconstruction from Aerial Images
First Competition on Presentation Attack Detection on ID Card
An Empirical Study on Information Extraction using Large Language Models
UDGS-SLAM : UniDepth Assisted Gaussian Splatting for Monocular SLAM
Predicting Femicide in Veracruz: A Fuzzy Logic Approach with the Expanded MFM-FEM-VER-CP-2024 Model
Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models
Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technology
RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning
Does Alignment Tuning Really Break LLMs' Internal Confidence?
ToddlerAct: A Toddler Action Recognition Dataset for Gross Motor Development Assessment
Chatting Up Attachment: Using LLMs to Predict Adult Bonds
SMAFormer: Synergistic Multi-Attention Transformer for Medical Image Segmentation
PS-StyleGAN: Illustrative Portrait Sketching using Attention-Based Style Adaptation
EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System
AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation
Fish Tracking Challenge 2024: A Multi-Object Tracking Competition with Sweetfish Schooling Data
GSpect: Spectral Filtering for Cross-Scale Graph Classification
Evaluating the Effectiveness of Large Language Models in Representing and Understanding Movement Trajectories
WikiCausal: Corpus and Evaluation Framework for Causal Knowledge Graph Construction
GMFL-Net: A Global Multi-geometric Feature Learning Network for Repetitive Action Counting
Demo: FedCampus: A Real-world Privacy-preserving Mobile Application for Smart Campus via Federated Learning & Analytics
From Prediction to Application: Language Model-based Code Knowledge Tracing with Domain Adaptive Pre-Training and Automatic Feedback System with Pedagogical Prompting for Comprehensive Programming Education

All 106