Papers

New on arXiv

Sun 30 Jun 2024

114 papers

Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect SimulatorsOffline RL and imitation learning from data → Offline RL algorithms +1
Model-Free Active Exploration in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Diffusion Models and Representation Learning: A SurveyDiffusion models → Diffusion foundations and sampling
Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical ReasoningLLM reasoning → Mathematical reasoning +1
Chest-Diffusion: A Light-Weight Text-to-Image Model for Report-to-CXR GenerationDiffusion models → Medical imaging and segmentation
Posterior Sampling with Denoising Oracles via Tilted TransportDiffusion models → Inverse problems and image restoration
Disentangled Representations for Causal CognitionDeep reinforcement learning methods → Deep RL algorithms and representations
Diffusion Models for Offline Multi-agent Reinforcement Learning with Safety ConstraintsDiffusion models → Diffusion and flow policies for robotics +1
LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
Generative prediction of flow fields around an obstacle using the diffusion modelDiffusion models → Flow matching, time series and science
Model-based Offline Reinforcement Learning with Lower Expectile Q-LearningOffline RL and imitation learning from data → Offline RL algorithms
BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models PersonalizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Safe Reinforcement Learning for Power System Control: A ReviewDeep reinforcement learning methods → RL for energy, networks and operations
Chain-of-Knowledge: Integrating Knowledge Reasoning into Large Language Models by Learning from Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without ReconstructionDeep reinforcement learning methods → RL for robot locomotion and manipulation
CAMON: Cooperative Agents for Multi-Object Navigation with LLM-based ConversationsLLM agents and tool use → General LLM agent frameworks and benchmarks
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based ModelsDiffusion models → Diffusion and flow policies for robotics +2
Consistency Purification: Effective and Efficient Diffusion Purification towards Certified RobustnessDiffusion models → Diffusion foundations and sampling
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box OptimizationDiffusion models → Diffusion foundations and sampling
GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual ProbingMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated SchedulesMixture-of-experts → Efficient MoE training and inference systems
Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
OxonFair: A Flexible Toolkit for Algorithmic Fairness
"I understand why I got this grade": Automatic Short Answer Grading with Feedback
Understanding Transformers via N-gram Statistics
Large Language Models for Behavioral Economics: Internal Validity and Elicitation of Mental Models
Evaluation of Bias Towards Medical Professionals in Large Language Models
Causality-driven Sequence Segmentation for Enhancing Multiphase Industrial Process Data Analysis and Soft Sensing
Actionable Cyber Threat Intelligence using Knowledge Graphs and Large Language Models
A Deep Generative Framework for Joint Households and Individuals Population Synthesis
NeurIPS 2024 ML4CFD Competition: Harnessing Machine Learning for Computational Fluid Dynamics in Airfoil Design
BADM: Batch ADMM for Deep Learning
ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks
LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes
Learning Dual Transformers for All-In-One Image Restoration from a Frequency Perspective
Commute Graph Neural Networks
SAFE: a SAR Feature Extractor based on self-supervised learning and masked Siamese ViTs
Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learning
A Unified Approach to Extract Interpretable Rules from Tree Ensembles via Integer Programming
MUSE-Net: Missingness-aware mUlti-branching Self-attention Encoder for Irregular Longitudinal Electronic Health Records
Towards Robust Speech Representation Learning for Thousands of Languages
DroBoost: An Intelligent Score and Model Boosting Method for Drone Detection
NAIST Simultaneous Speech Translation System for IWSLT 2024
Image Classification for Snow Detection to Improve Pedestrian Safety
Kernel Neural Operators (KNOs) for Scalable, Memory-efficient, Geometrically-flexible Operator Learning
Exploring a Physics-Informed Decision Transformer for Distribution System Restoration: Methodology and Performance Analysis
Towards Shutdownable Agents via Stochastic Choice
Controlling Face's Frame generation in StyleGAN's latent space operations: Modifying faces to deceive our memory
InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation
Enhancing Travel Decision-Making: A Contrastive Learning Approach for Personalized Review Rankings in Accommodations
Towards Faster Matrix Diagonalization with Graph Isomorphism Networks and the AlphaZero Framework
Harnessing Quantum Support Vector Machines for Cross-Domain Classification of Quantum States
Structured and Balanced Multi-Component and Multi-Layer Neural Networks
Characterizing Stereotypical Bias from Privacy-preserving Pre-Training
Improving the performance of Stein variational inference through extreme sparsification of physically-constrained neural network models
Improved Graph-based semi-supervised learning Schemes
Analysis of Modern Computer Vision Models for Blood Cell Classification
Self-consistent Deep Geometric Learning for Heterogeneous Multi-source Spatial Point Data Prediction
A Comparative Study of Quality Evaluation Methods for Text Summarization
PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph
LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization
Engineering an Efficient Object Tracker for Non-Linear Motion
Quantum Circuit Synthesis and Compilation Optimization: Overview and Prospects
Large Language Models Struggle in Token-Level Clinical Named Entity Recognition
D-CDLF: Decomposition of Common and Distinctive Latent Factors for Multi-view High-dimensional Data
A Whole-Process Certifiably Robust Aggregation Method Against Backdoor Attacks in Federated Learning
ASPS: Augmented Segment Anything Model for Polyp Segmentation
Learning System Dynamics without Forgetting
Directly Handling Missing Data in Linear Discriminant Analysis for Enhancing Classification Accuracy and Interpretability
Heterogeneous Graph Contrastive Learning with Spectral Augmentation
Sum-of-norms regularized Nonnegative Matrix Factorization
Scaling Technology Acceptance Analysis with Large Language Model (LLM) Annotation Systems
NourishNet: Proactive Severity State Forecasting of Food Commodity Prices for Global Warning Systems
CaFNet: A Confidence-Driven Framework for Radar Camera Depth Estimation
Graph in Graph Neural Network
Learning Formal Mathematics From Intrinsic Motivation
Multi-Task Learning for Affect Analysis
A Narrative Review of Image Processing Techniques Related to Prostate Ultrasound
Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation
TEAL: New Selection Strategy for Small Buffers in Experience Replay Class Incremental Learning
Establishing Deep InfoMax as an effective self-supervised learning methodology in materials informatics
HRDE: Retrieval-Augmented Large Language Models for Chinese Health Rumor Detection and Explainability
Resolving Variable Respiratory Motion From Unsorted 4D Computed Tomography
SCMIL: Sparse Context-aware Multiple Instance Learning for Predicting Cancer Survival Probability Distribution in Whole Slide Images
Multi-Agent Training for Pommerman: Curriculum Learning and Population-based Self-Play Approach
Improving Real-Time Music Accompaniment Separation with MMDenseNet
Particle Semi-Implicit Variational Inference
LegalTurk Optimized BERT for Multi-Label Text Classification and NER
Clusterpath Gaussian Graphical Modeling
NeuroNAS: Enhancing Efficiency of Neuromorphic In-Memory Computing for Intelligent Mobile Agents through Hardware-Aware Spiking Neural Architecture Search
A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacy
DP-MLM: Differentially Private Text Rewriting Using Masked Language Models
Tarsier: Recipes for Training and Evaluating Large Video Description Models
TrialBench: Multi-Modal Artificial Intelligence-Ready Clinical Trial Datasets
DADEE: Well-calibrated uncertainty quantification in neural networks for barriers-based robot safety
GC-Bench: An Open and Unified Benchmark for Graph Condensation
Learning Granularity-Aware Affordances from Human-Object Interaction for Tool-Based Functional Dexterous Grasping
A Linear Programming Enhanced Genetic Algorithm for Hyperparameter Tuning in Machine Learning
ESGNN: Towards Equivariant Scene Graph Neural Network for 3D Scene Understanding

All 114