Papers

New on arXiv

Thu 14 Nov 2024

226 papers

Edge Caching Optimization with PPO and Transfer Learning for Dynamic EnvironmentsDeep reinforcement learning methods → RL for energy, networks and operations
To bootstrap or to rollout? An optimal and adaptive interpolationDeep reinforcement learning methods → RL theory and sample complexity
Iterative Batch Reinforcement Learning via Safe Diversified Model-based Policy SearchOffline RL and imitation learning from data → Offline RL algorithms +1
Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Adaptive Decoding via Latent Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer FrameworkRetrieval-augmented generation → RAG pipeline design and evaluation
Adopting RAG for LLM-Aided Future Vehicle DesignRetrieval-augmented generation → RAG pipeline design and evaluation
Prompting the Unseen: Detecting Hidden Backdoors in Black-Box ModelsLLM safety and security → Backdoor and data poisoning attacks
FlowNav: Combining Flow Matching and Depth Priors for Efficient NavigationDiffusion models → Diffusion and flow policies for robotics
Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based AgentsLLM agents and tool use → Agent threats, guardrails and governance
Golden Noise for Diffusion Models: A Learning FrameworkDiffusion models → Diffusion foundations and sampling
DiffRoad: Realistic and Diverse Road Scenario Generation for Autonomous Vehicle TestingDiffusion models → Diffusion and flow policies for robotics
Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment +1
Spider: Any-to-Many Multimodal LLMMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
A survey of probabilistic generative frameworks for molecular simulationsDiffusion models → Flow matching, time series and science
When Mamba Meets xLSTM: An Efficient and Precise Method with the xLSTM-VMUNet Model for Skin lesion SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Multi-scale Generative Modeling for Fast SamplingDiffusion models → Diffusion foundations and sampling
Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
EEG-Based Speech Decoding: A Novel Approach Using Multi-Kernel Ensemble Diffusion ModelsDiffusion models → Medical imaging and segmentation
LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language InterpretationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
LLV-FSR: Exploiting Large Language-Vision Prior for Face Super-resolutionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Cross-Modal Consistency in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Jailbreak Attacks and Defenses against Multimodal Generative Models: A SurveyLLM safety and security → Vision-language and text-to-image safety
Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question AnsweringRetrieval-augmented generation → Medical and biomedical RAG
SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AISynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
Enhancing reinforcement learning for population setpoint tracking in co-culturesDeep reinforcement learning methods → RL for energy, networks and operations
Advancing Diffusion Models: Alias-Free Resampling and Enhanced Rotational EquivarianceDiffusion models → Diffusion foundations and sampling
Innate-Values-driven Reinforcement Learning based Cognitive ModelingDeep reinforcement learning methods → RL training of language and agent models
VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot ManipulationDiffusion models → Diffusion and flow policies for robotics
DROJ: A Prompt-Driven Attack against Large Language ModelsLLM safety and security → Jailbreaking
Reducing Reasoning Costs: The Path of Optimization for Chain of Thought via Sparse Attention MechanismLLM reasoning → Prompting and chain-of-thought reasoning
Effective Mitigations for Systemic Risks from General-Purpose AI
Semantic, Orthographic, and Phonological Biases in Humans' Wordle Gameplay
Volume Rendering of Human Hand Anatomy
MFP3D: Monocular Food Portion Estimation Leveraging 3D Point Clouds
AI-Spectra: A Visual Dashboard for Model Multiplicity to Enhance Informed and Transparent Decision-Making
Biometrics in Extended Reality: A Review
The Future of Skill: What Is It to Be Skilled at Work?
Artificial Intelligence for Infectious Disease Prediction and Prevention: A Comprehensive Review
Self-Supervised Radio Pre-training: Toward Foundational Models for Spectrogram Learning
Towards a Fairer Non-negative Matrix Factorization
Deep Autoencoders for Unsupervised Anomaly Detection in Wildfire Prediction
FedRewind: Rewinding Continual Model Exchange for Decentralized Federated Learning
OneNet: A Channel-Wise 1D Convolutional U-Net
Real-time Adapting Routing (RAR): Improving Efficiency Through Continuous Learning in Software Powered by Layered Foundation Models
A Benchmark for Long-Form Medical Question Answering
The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases
Evaluating Gender Bias in Large Language Models
Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting
Advancing Stroke Risk Prediction Using a Multi-modal Foundation Model
Towards Scalable Newborn Screening: Automated General Movement Assessment in Uncontrolled Settings
WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarking
Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition
Can Features for Phishing URL Detection Be Trusted Across Diverse Datasets? A Case Study with Explainable AI
Evaluating Loss Landscapes from a Topology Perspective
Fair Resource Allocation in Weakly Coupled Markov Decision Processes
Modeling human decomposition: a Bayesian approach
Video Denoising in Fluorescence Guided Surgery
Reinforced Disentanglers on Random Unitary Circuits
Combining Machine Learning Defenses without Conflicts
Beyond Static Tools: Evaluating Large Language Models for Cryptographic Misuse Detection
Deep Learning for Fetal Inflammatory Response Diagnosis in the Umbilical Cord
NACNet: A Histology Context-aware Transformer Graph Convolution Network for Predicting Treatment Response to Neoadjuvant Chemotherapy in Triple Negative Breast Cancer
Evaluating the Predictive Capacity of ChatGPT for Academic Peer Review Outcomes Across Multiple Platforms
Partial Multi-View Clustering via Meta-Learning and Contrastive Feature Alignment
Analyzing the AI Nudification Application Ecosystem
RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering
Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations
SureMap: Simultaneous Mean Estimation for Single-Task and Multi-Task Disaggregated Evaluation
Physics-informed neural networks (PINNs) for numerical model error approximation and superresolution
Spatio-Temporal Jump Model for Urban Thermal Comfort Monitoring
Towards Neural Foundation Models for Vision: Aligning EEG, MEG, and fMRI Representations for Decoding, Encoding, and Modality Conversion
Early-Scheduled Handover Preparation in 5G NR Millimeter-Wave Systems
NFRs in Medical Imaging
MagicQuill: An Intelligent Interactive Image Editing System
On the Surprising Effectiveness of Attention Transfer for Vision Transformers
A Bayesian Optimization Approach to Machine Translation Reranking
CropCraft: Complete Structural Characterization of Crop Plants From Images
Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge
Squeezed Attention: Accelerating Long Context Length LLM Inference
Conditional regression for the Nonlinear Single-Variable Model
Towards a Classification of Open-Source ML Models and Datasets for Software Engineering
NeuralDEM -- Real-time Simulation of Industrial Particulate Flows
Med-Bot: An AI-Powered Assistant to Provide Accurate and Reliable Medical Information
How do Machine Learning Models Change?
Neural Operators Can Play Dynamic Stackelberg Games
On the Limits of Language Generation: Trade-Offs Between Hallucination and Mode Collapse
MCCE: Missingness-aware Causal Concept Explainer
Counterfactual Uncertainty Quantification of Factual Estimand of Efficacy from Before-and-After Treatment Repeated Measures Randomized Controlled Trials
One-Shot Manipulation Strategy Learning by Making Contact Analogies
Local deployment of large-scale music AI models on commodity hardware
Vision-based Manipulation of Transparent Plastic Bags in Industrial Setups
MICCAI-CDMRI 2023 QuantConn Challenge Findings on Achieving Robust Quantitative Connectivity through Harmonized Preprocessing of Diffusion MRI
Task-Aligned Tool Recommendation for Large Language Models
The Moral Foundations Weibo Corpus
Local-Global Attention: An Adaptive Mechanism for Multi-Scale Feature Integration
Accelerating Knowledge Graph and Ontology Engineering with Large Language Models
Latency Optimization in LEO Satellite Communications with Hybrid Beam Pattern and Interference Control
Assessing the Performance of the DINOv2 Self-supervised Learning Vision Transformer Model for the Segmentation of the Left Atrium from MRI Images
LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

All 226