Papers

New on arXiv

Sat 14 Sep 2024

144 papers

Enhancing EEG Signal Generation through a Hybrid Approach Integrating Reinforcement Learning and Diffusion ModelsDiffusion models → Medical imaging and segmentation
IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-WebMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Block-Attention for Efficient PrefillingRetrieval-augmented generation → Generation and context integration
Synergistic Simulations: Multi-Agent Problem Solving with Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
Thinking Before Speaking: A Role-playing Model with MindsetLLM reasoning → Reasoning benchmarks and evaluation
ASFT: Aligned Supervised Fine-Tuning through Absolute LikelihoodLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model WatermarkingLLM safety and security → Watermarking generated content and models
On the limits of agency in agent-based modelsLLM agents and tool use → Social simulation and multi-agent debate
Autonomous Goal Detection and Cessation in Reinforcement Learning: A Case Study on Source Term EstimationDeep reinforcement learning methods → Deep RL algorithms and representations
Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning TokensOffline RL and imitation learning from data → Decision transformers and sequence modeling
One missing piece in Vision and Language: A Survey on Comics UnderstandingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Integrating Deep Unfolding with Direct Diffusion Bridges for Computed Tomography ReconstructionDiffusion models → Medical imaging and segmentation
Real-world Adversarial Defense against Patch Attacks based on Diffusion ModelDiffusion models → Robustness, privacy and adversarial aspects
Towards Diverse and Efficient Audio Captioning via Diffusion ModelsDiffusion models → Audio, speech and music
Integrated Multi-Level Knowledge Distillation for Enhanced Speaker VerificationKnowledge distillation → Speech and audio distillation
Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLMMultimodal LLMs / vision-language models → Video understanding with MLLMs
Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved IntelligibilityKnowledge distillation → Speech and audio distillation
E1 TTS: Simple and Fast Non-Autoregressive TTSDiffusion models → Audio, speech and music
Schr"odinger Bridge Flow for Unpaired Data TranslationDiffusion models → Diffusion foundations and sampling
Enhancing Decision-Making for LLM Agents via Step-Level Q-Value ModelsLLM agents and tool use → Reinforcement learning for LLM agents
Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super ResolutionState-space sequence models (S4, Mamba) → Speech and audio SSMs
ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant GenerationDiffusion models → Audio, speech and music
ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided DiffusionDiffusion models → Diffusion and flow policies for robotics
Infrared and Visible Image Fusion with Hierarchical Human PerceptionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Language Models "Grok" to CopyRetrieval-augmented generation → Generation and context integration
Visuo-Tactile Zero-Shot Object Recognition with Vision-Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge TypesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Unleash LLMs Potential for Sequential Recommendation by Coordinating Dual Dynamic Index MechanismLLM reasoning → LLM reasoning for recommendation
Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent TransformerLLM reasoning → Prompting and chain-of-thought reasoning
Computer Vision Intelligence Test Modeling and Generation: A Case Study on Smart OCR
Multiscale fusion enhanced spiking neural network for invasive BCI neural signal decoding
Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospects
AI in Food Marketing from Personalized Recommendations to Predictive Analytics: Comparing Traditional Advertising Techniques with AI-Driven Strategies
Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare
From Text to Multimodality: Exploring the Evolution and Impact of Large Language Models in Medical Practice
Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and English
Multimodal Power Outage Prediction for Rapid Disaster Response and Resource Allocation
A Multitask VAE for Time Series Preprocessing and Prediction of Blood Glucose Level
StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?
SEA-ViT: Sea Surface Currents Forecasting Using Vision Transformer and GRU-Based Spatio-Temporal Covariance Modeling
SEE: Semantically Aligned EEG-to-Text Translation
Increasing the Value of Information During Planning in Uncertain Environments
Federated Learning with Quantum Computing and Fully Homomorphic Encryption: A Novel Computing Paradigm Shift in Privacy-Preserving ML
Evaluating authenticity and quality of image captions via sentiment and semantic analyses
A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem
Enhancing Printed Circuit Board Defect Detection through Ensemble Learning
ASR Error Correction using Large Language Models
COMFORT: A Continual Fine-Tuning Framework for Foundation Models Targeted at Consumer Healthcare
Multi-Microphone and Multi-Modal Emotion Recognition in Reverberant Environment
MANGO: Learning Disentangled Image Transformation Manifolds with Grouped Operators
Deep Fast Machine Learning Utils: A Python Library for Streamlined Machine Learning Prototyping
VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications
Using Synthetic Data to Mitigate Unfairness and Preserve Privacy in Collaborative Machine Learning
An Augmentation-based Model Re-adaptation Framework for Robust Image Segmentation
Enhancing Skin Disease Diagnosis: Interpretable Visual Concept Discovery with SAM
Deep Learning Under Siege: Identifying Security Vulnerabilities and Risk Mitigation Strategies
Explaining Deep Learning Embeddings for Speech Emotion Recognition by Predicting Interpretable Acoustic Features
Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models
ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration
Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language
Synthetic4Health: Generating Annotated Synthetic Clinical Letters
Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation
Hacking, The Lazy Way: LLM Augmented Pentesting
Evaluating probabilistic and data-driven inference models for fiber-coupled NV-diamond temperature sensors
Enumerating Minimal Unsatisfiable Cores of LTLf formulas
Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model
Neumann Series-based Neural Operator for Solving Inverse Medium Problem
MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry
From FDG to PSMA: A Hitchhiker's Guide to Multitracer, Multicenter Lesion Segmentation in PET/CT Imaging
MALADY: Multiclass Active Learning with Auction Dynamics on Graphs
Learning to enhance multi-legged robot on rugged landscapes
Hyperedge Representations with Hypergraph Wavelets: Applications to Spatial Transcriptomics
Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI
Measuring the Influence of Incorrect Code on Test Generation
TX-Gen: Multi-Objective Optimization for Sparse Counterfactual Explanations for Time-Series Classification
Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision
On the Generalizability of Foundation Models for Crop Type Mapping
MulCPred: Learning Multi-modal Concepts for Explainable Pedestrian Action Prediction
KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition
PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotion
Detecting Looted Archaeological Sites from Satellite Image Time Series
Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrieval
NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection
Distributed Clustering based on Distributional Kernel
Enhancing LLM Problem Solving with REAP: Reflection, Explicit Problem Deconstruction, and Advanced Prompting
Weather Prediction Using CNN-LSTM for Time Series Analysis: A Case Study on Delhi Temperature Data
Constructive Approach to Bidirectional Influence between Qualia Structure and Language Emergence
Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations
AI-Driven Virtual Teacher for Enhanced Educational Efficiency: Leveraging Large Pretrain Models for Autonomous Error Analysis and Correction
Topological Eigenvalue Theorems for Tensor Analysis in Multi-Modal Data Fusion
Tran-GCN: A Transformer-Enhanced Graph Convolutional Network for Person Re-Identification in Monitoring Videos
Estimating Neural Orientation Distribution Fields on High Resolution Diffusion MRI Scans
AMBER -- Advanced SegFormer for Multi-Band Image Segmentation: an application to Hyperspectral Imaging
LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach
Text Prompt is Not Enough: Sound Event Enhanced Prompt Adapter for Target Style Audio Generation
Prevailing Research Areas for Music AI in the Era of Foundation Models
BM2: Coupled Schr"odinger Bridge Matching
WeatherReal: A Benchmark Based on In-Situ Observations for Evaluating Weather Models
MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI

All 144