Papers

New on arXiv

Sun 3 Mar 2024

131 papers

Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture ModelsDiffusion models → Diffusion foundations and sampling
Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse TasksDeep reinforcement learning methods → Deep RL algorithms and representations
Critical windows: non-asymptotic theory for feature emergence in diffusion modelsDiffusion models → Diffusion foundations and sampling
Towards Comprehensive Vietnamese Retrieval-Augmented Generation and Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
Towards Provable Log Density Policy GradientDeep reinforcement learning methods → RL theory and sample complexity
The Hidden Attention of Mamba ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion ModelsDiffusion models → Flow matching, time series and science
Deep Incremental Model Informed Reinforcement Learning for Continuous Robotic ControlDeep reinforcement learning methods → RL for robot locomotion and manipulation
SCott: Accelerating Diffusion Models with Stochastic Consistency DistillationDiffusion models → Diffusion foundations and sampling
Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image EnhancementDiffusion models → Inverse problems and image restoration
InfiMM-HD: A Leap Forward in High-Resolution Multimodal UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Approximations to the Fisher Information Metric of Deep Generative Models for Out-Of-Distribution DetectionDiffusion models → Medical imaging and segmentation
BronchoCopilot: Towards Autonomous Robotic Bronchoscopy via Multimodal Reinforcement LearningDeep reinforcement learning methods → RL for clinical treatment and surgery
Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine TranslationKnowledge distillation → Knowledge distillation for LLMs
Answerability in Retrieval-Augmented Open-Domain Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
GuardT2I: Defending Text-to-Image Models from Adversarial PromptsLLM safety and security → Vision-language and text-to-image safety
Fine Tuning vs. Retrieval Augmented Generation for Less Popular KnowledgeRetrieval-augmented generation → RAG pipeline design and evaluation
Logit Standardization in Knowledge DistillationKnowledge distillation → General knowledge distillation methods
DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent KeyframesMultimodal LLMs / vision-language models → Video understanding with MLLMs
Barrier Functions Inspired Reward Shaping for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
What Is Missing in Multilingual Visual Reasoning and How to Fix ItLLM reasoning → Multimodal reasoning
CR-LT-KGQA: A Knowledge Graph Question Answering Dataset Requiring Commonsense Reasoning and Long-Tail KnowledgeLLM reasoning → Knowledge- and tool-augmented reasoning
Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
Quantity Matters: Towards Assessing and Mitigating Number Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Structurally Prune Anything: Any Architecture, Any Framework, Any Time
SyllabusQA: A Course Logistics Question Answering Dataset
When SMILES have Language: Drug Classification using Text Classification Methods on Drug SMILES Strings
MATADOR: Automated System-on-Chip Tsetlin Machine Design Generation for Edge Applications
On the stochastics of human and artificial creativity
Exact algorithms and heuristics for capacitated covering salesman problems
Plasmon Resonance Model: Investigation of Analysis of Fake News Diffusion Model with Third Mover Intervention Using Soliton Solution in Non-Complete Information Game under Repeated Dilemma Condition
Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Intervention
Ever-Evolving Memory by Blending and Refining the Past
Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction
Cost-Effective Attention Mechanisms for Low Resource Settings: Necessity & Sufficiency of Linear Transformations
Blue and Green-Mode Energy-Efficient Nanoparticle-Based Chemiresistive Sensor Array Realized by Rapid Ensemble Learning
AIO2: Online Correction of Object Labels for Deep Learning with Incomplete Annotation in Remote Sensing Image Segmentation
Multi-level Product Category Prediction through Text Classification
Application of Neural Ordinary Differential Equations for Tokamak Plasma Dynamics Analysis
SynCode: LLM Generation with Grammar Augmentation
Recent Advances, Applications, and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2023 Symposium
ML4PhySim : Machine Learning for Physical Simulations Challenge (The airfoil design)
Machine Learning vs Deep Learning: The Generalization Problem
Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation
Partial Federated Learning
Real-time respiratory motion forecasting with online learning of recurrent neural networks for accurate targeting in externally guided radiotherapy
A Unified Model Selection Technique for Spectral Clustering Based Motion Segmentation
Can Poverty Be Reduced by Acting on Discrimination? An Agent-based Model for Policy Making
SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos
APISR: Anime Production Inspired Real-World Anime Super-Resolution
Calibrating doubly-robust estimators with unbalanced treatment assignment
Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo
Enhancing Neural Machine Translation of Low-Resource Languages: Corpus Development, Human Evaluation and Explainable AI Architectures
SARD: A Human-AI Collaborative Story Generation
Limits to classification performance by relating Kullback-Leibler divergence to Cohen's Kappa
Small Models are LLM Knowledge Triggers on Medical Tabular Prediction
Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV
ReMatch: Retrieval Enhanced Schema Matching with LLMs
ComTraQ-MPC: Meta-Trained DQN-MPC Integration for Trajectory Tracking with Limited Active Localization Updates
XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition
Transformers for Supervised Online Continual Learning
Self-Supervised Representation Learning with Meta Comprehensive Regularization
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
Hyperspectral Image Analysis in Single-Modal and Multimodal setting using Deep Learning Techniques
Efficient Action Counting with Dynamic Queries
A Hierarchical Federated Learning Approach for the Internet of Things
Mixed Strategy Nash Equilibrium for Crowd Navigation
Fast Ergodic Search with Kernel Functions
Machine learning predicts long-term mortality after acute myocardial infarction using systolic time intervals and routinely collected clinical data
Data-driven local operator finding for reduced-order modelling of plasma systems: II. Application to parametric dynamics
Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey
Data-driven local operator finding for reduced-order modelling of plasma systems: I. Concept and verifications
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images
CDSE-UNet: Enhancing COVID-19 CT Image Segmentation with Canny Edge Detection and Dual-Path SENet Feature Fusion
End-to-End Human Instance Matting
Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics
Extending Complex Logical Queries on Uncertain Knowledge Graphs
Applying Self-supervised Learning to Network Intrusion Detection for Network Flows with Graph Neural Network
Normalizing Flow-based Differentiable Particle Filters
ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis
Regeneration Based Training-free Attribution of Fake Images Generated by Text-to-Image Generative Models
EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation
Infusing Knowledge into Large Language Models with Contextual Prompts
CCC: Color Classified Colorization
Representation Learning on Heterophilic Graph with Directional Neighborhood Attention
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
Tunable correlation retention: A statistical method for generating synthetic data
Is in-domain data beneficial in transfer learning for landmarks detection in x-ray images?
KorMedMCQA: Multi-Choice Question Answering Benchmark for Korean Healthcare Professional Licensing Examinations
Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation
Multiview Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networks
One-Step Multi-View Clustering Based on Transition Probability
Logic Rules as Explanations for Legal Case Retrieval
Controlling Cloze-test Question Item Difficulty with PLM-based Surrogate Models for IRT Assessment
Enhancing Data Provenance and Model Transparency in Federated Learning Systems -- A Database Approach
DUFOMap: Efficient Dynamic Awareness Mapping
3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos
Pyramid Feature Attention Network for Monocular Depth Prediction

All 131