mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 6 Oct 2022

229 papers

  1. Novel View Synthesis with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  2. ReAct: Synergizing Reasoning and Acting in Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  3. Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead AdaptationEnd-to-end autonomous driving → Reinforcement learning for driving
  4. Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language ModelsEfficient LLM inference and serving → Prompt and context compression
  5. On Distillation of Guided Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  6. A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  7. Language Models are Multilingual Chain-of-Thought ReasonersLLM reasoning → Mathematical reasoning
  8. MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and TextRetrieval-augmented generation → Multimodal RAG
  9. Flow Matching for Generative ModelingWorld models → Video-generation world models and simulators +1
  10. Join-Chain Network: A Logical Reasoning View of the Multi-head Attention in TransformerLLM reasoning → Reasoning benchmarks and evaluation
  11. On Optimal Learning Under Targeted Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
  12. Teaching Neural Module Networks to Do ArithmeticLLM reasoning → Mathematical reasoning
  13. Probabilistic partition of unity networks for high-dimensional regression problemsMixture-of-experts → MoE theory and gating functions
  14. A Logic for Expressing Log-Precision TransformersLLM reasoning → Prompting and chain-of-thought reasoning
  15. Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  16. Learning to Reason With Relational AbstractionsLLM reasoning → Mathematical reasoning
  17. Forecasting Bitcoin volatility spikes from whale transactions and CryptoQuant data using Synthesizer Transformer models
  18. Low-Thrust Orbital Transfer using Dynamics-Agnostic Reinforcement Learning
  19. Incorporating High-Frequency Weather Data into Consumption Expenditure Predictions
  20. Detecting Emerging Technologies in Artificial Intelligence Scientific Ecosystem Using an Indicator-based Model
  21. Bayesian Nonlocal Operator Regression (BNOR): A Data-Driven Learning Framework of Nonlocal Models with Uncertainty Quantification
  22. Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning
  23. Digital Asset Valuation: A Study on Domain Names, Email Addresses, and NFTs
  24. Knowledge Tracing for Complex Problem Solving: Granular Rank-Based Tensor Factorization
  25. ECG for high-throughput screening of multiple diseases: Proof-of-concept using multi-diagnosis deep learning from population-based datasets
  26. Domain-Specific Word Embeddings with Structure Prediction
  27. Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design
  28. Deep Learning Mixture-of-Experts Approach for Cytotoxic Edema Assessment in Infants and Children
  29. Critical Learning Periods for Multisensory Integration in Deep Networks
  30. Exploration via Planning for Information about the Optimal Trajectory
  31. Single Image Super-Resolution Based on Capsule Neural Networks
  32. Dual-Stage Deeply Supervised Attention-based Convolutional Neural Networks for Mandibular Canal Segmentation in CBCT Scans
  33. An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era
  34. From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible ML
  35. A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs
  36. STSyn: Speeding Up Local SGD with Straggler-Tolerant Synchronization
  37. LGTBIDS: Layer-wise Graph Theory Based Intrusion Detection System in Beyond 5G
  38. Fairness in generative modeling
  39. Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
  40. Spiking neural networks for nonlinear regression
  41. Adversarial Lagrangian Integrated Contrastive Embedding for Limited Size Datasets
  42. Considerations for Task Allocation in Human-Robot Teams
  43. Interpreting County Level COVID-19 Infection and Feature Sensitivity using Deep Learning Time Series Models
  44. Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation
  45. Damage Control During Domain Adaptation for Transducer Based Automatic Speech Recognition
  46. Network Intrusion Detection System in a Light Bulb
  47. Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints
  48. Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup
  49. HealthE: Classifying Entities in Online Textual Health Advice
  50. Improving Large-scale Paraphrase Acquisition and Generation
  51. Dominance-based Rough Set Approach, basic ideas and main trends
  52. NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies
  53. PQLM -- Multilingual Decentralized Portable Quantum Language Model for Privacy Protection
  54. Self-Supervised Monocular Depth Underwater
  55. Synthetic Dataset Generation for Privacy-Preserving Machine Learning
  56. Enabling Deep Learning on Edge Devices
  57. FocalUNETR: A Focal Transformer for Boundary-aware Segmentation of CT Images
  58. Compositional Generalisation with Structured Reordering and Fertility Layers
  59. A ResNet is All You Need? Modeling A Strong Baseline for Detecting Referable Diabetic Retinopathy in Fundus Images
  60. Probabilistic Model Incorporating Auxiliary Covariates to Control FDR
  61. Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes
  62. CoGrasp: 6-DoF Grasp Generation for Human-Robot Collaboration
  63. Gastrointestinal Disorder Detection with a Transformer Based Approach
  64. FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training
  65. A Theory of Dynamic Benchmarks
  66. InfoOT: Information Maximizing Optimal Transport
  67. Brief Introduction to Contrastive Learning Pretext Tasks for Visual Representation
  68. Neural Volumetric Mesh Generator
  69. Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles
  70. Comparison of Missing Data Imputation Methods using the Framingham Heart study dataset
  71. Integrative Imaging Informatics for Cancer Research: Workflow Automation for Neuro-oncology (I3CR-WANO)
  72. Towards Out-of-Distribution Adversarial Robustness
  73. Deep Inventory Management
  74. On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processing
  75. Temporal Spatial Decomposition and Fusion Network for Time Series Forecasting
  76. GBSVM: Granular-ball Support Vector Machine
  77. Evaluating k-NN in the Classification of Data Streams with Concept Drift
  78. Unsupervised confidence for LiDAR depth maps and applications
  79. MaPLe: Multi-modal Prompt Learning
  80. Content-Based Search for Deep Generative Models
  81. SimPer: Simple Self-Supervised Learning of Periodic Targets
  82. CLIP model is an Efficient Continual Learner
  83. IR-MCL: Implicit Representation-Based Online Global Localization
  84. Real-World Robot Learning with Masked Visual Pre-training
  85. Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
  86. Distributionally Adaptive Meta Reinforcement Learning
  87. Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content!
  88. Ambiguous Images With Human Judgments for Robust Visual Event Classification
  89. Accelerated Single-Call Methods for Constrained Min-Max Optimization
  90. VIMA: General Robot Manipulation with Multimodal Prompts
  91. Edge-Varying Fourier Graph Networks for Multivariate Time Series Forecasting
  92. Adaptive Ranking-based Sample Selection for Weakly Supervised Class-imbalanced Text Classification
  93. Iterative Vision-and-Language Navigation
  94. Explainable Verbal Deception Detection using Transformers
  95. Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering
  96. IJCB 2022 Mobile Behavioral Biometrics Competition (MobileB2C)
  97. Toxicity in Multilingual Machine Translation at Scale
  98. PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks
  99. InferES : A Natural Language Inference Corpus for Spanish Featuring Negation-Based Contrastive and Adversarial Examples
  100. Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal Prediction
All 229
  1. Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal
  2. Reinforcement Learning with Large Action Spaces for Neural Machine Translation
  3. ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
  4. State-of-the-art generalisation research in NLP: A taxonomy and review
  5. Conditional Feature Importance for Mixed Data
  6. Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
  7. Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding
  8. Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video
  9. Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph
  10. Learning many-body Hamiltonians with Heisenberg-limited scaling
  11. Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt
  12. Detecting Narrative Elements in Informational Text
  13. Explanations as Programs in Probabilistic Logic Programming
  14. Measuring Fine-Grained Semantic Equivalence with Abstract Meaning Representation
  15. Uncovering the Structural Fairness in Graph Contrastive Learning
  16. Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems
  17. XDGAN: Multi-Modal 3D Shape Generation in 2D Space
  18. To Softmax, or not to Softmax: that is the question when applying Active Learning for Transformer Models
  19. MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentation
  20. ThoraX-PriorNet: A Novel Attention-Based Architecture Using Anatomical Prior Probability Maps for Thoracic Disease Classification
  21. Expander Graph Propagation
  22. Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks
  23. Compressed Vision for Efficient Video Understanding
  24. COVID-19 Detection Using Segmentation, Region Extraction and Classification Pipeline
  25. Cross-Modality Domain Adaptation for Freespace Detection: A Simple yet Effective Baseline
  26. SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data
  27. The Lie Derivative for Measuring Learned Equivariance
  28. Fault Diagnosis using eXplainable AI: a Transfer Learning-based Approach for Rotating Machinery exploiting Augmented Synthetic Data
  29. Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners
  30. Few-shot Generation of Personalized Neural Surrogates for Cardiac Simulation via Bayesian Meta-Learning
  31. Designing a Robust Low-Level Agnostic Controller for a Quadrotor with Actor-Critic Reinforcement Learning
  32. POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique
  33. Are word boundaries useful for unsupervised language learning?
  34. Video Referring Expression Comprehension via Transformer with Content-aware Query
  35. Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
  36. VLSNR:Vision-Linguistics Coordination Time Sequence-aware News Recommendation
  37. BootAug: Boosting Text Augmentation via Hybrid Instance Filtering Framework
  38. Communication-Efficient and Drift-Robust Federated Learning via Elastic Net
  39. Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks
  40. A Review of Uncertainty Calibration in Pretrained Object Detectors
  41. Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering
  42. Data-Driven Meets Navigation: Concepts, Models, and Experimental Validation
  43. Generative Entity Typing with Curriculum Learning
  44. Biological neurons act as generalization filters in reservoir computing
  45. CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
  46. Federated Boosted Decision Trees with Differential Privacy
  47. Joint Entropy Search for Multi-objective Bayesian Optimization
  48. Multiview Contextual Commonsense Inference: A New Dataset and Task
  49. A Distributional Lens for Multi-Aspect Controllable Text Generation
  50. Scaling up Stochastic Gradient Descent for Non-convex Optimisation
  51. Binding Language Models in Symbolic Languages
  52. Text-driven Video Prediction
  53. Causal Inference for Chatting Handoff
  54. Time Will Change Things: An Empirical Study on Dynamic Language Understanding in Social Media Classification
  55. Anomaly detection using data depth: multivariate case
  56. Evaluating the Impact of COVID-19 Vaccination in the United Kingdom: A Gaussian Process Approach
  57. XDoc: Unified Pre-training for Cross-Format Document Understanding
  58. Are Synonym Substitution Attacks Really Synonym Substitution Attacks?
  59. CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection
  60. Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection
  61. Heterogeneous Treatment Effect Estimation for Observational Data using Model-based Forests
  62. Robust Double-Encoder Network for RGB-D Panoptic Segmentation
  63. Matching Text and Audio Embeddings: Exploring Transfer-learning Strategies for Language-based Audio Retrieval
  64. KnowledgeShovel: An AI-in-the-Loop Document Annotation System for Scientific Knowledge Base Construction
  65. Melody Infilling with User-Provided Structural Context
  66. Effective Self-supervised Pre-training on Low-compute Networks without Distillation
  67. A Review of Multilingualism in and for Ontologies
  68. Just ClozE! A Novel Framework for Evaluating the Factual Consistency Faster in Abstractive Summarization
  69. Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding
  70. Hypernetwork approach to Bayesian MAML
  71. Why Should I Choose You? AutoXAI: A Framework for Selecting and Tuning eXplainable AI Solutions
  72. FloatingFusion: Depth from ToF and Image-stabilized Stereo Cameras
  73. Paging with Succinct Predictions
  74. Modelling Commonsense Properties using Pre-Trained Bi-Encoders
  75. Artificial virtuous agents in a multiagent tragedy of the commons
  76. Distilling Task-specific Logical Rules from Large Pre-trained Models
  77. AutoQC: Automated Synthesis of Quantum Circuits Using Neural Network
  78. Vision Transformer Based Model for Describing a Set of Images as a Story
  79. CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization
  80. Audio-Visual Face Reenactment
  81. Meta Reinforcement Learning for Optimal Design of Legged Robots
  82. CLAD: A Contrastive Learning based Approach for Background Debiasing
  83. The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection
  84. MuS2: A Real-World Benchmark for Sentinel-2 Multi-Image Super-Resolution
  85. Spatial-Temporal Graph Convolutional Gated Recurrent Network for Traffic Forecasting
  86. FedGraph: an Aggregation Method from Graph Perspective
  87. PSVRF: Learning to restore Pitch-Shifted Voice without reference
  88. Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision
  89. Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias
  90. Continuous Diagnosis and Prognosis by Controlling the Update Process of Deep Neural Networks
  91. Embodied Referring Expression for Manipulation Question Answering in Interactive Environment
  92. hyperbox-brain: A Toolbox for Hyperbox-based Machine Learning Algorithms
  93. Block-Structured Optimization for Subgraph Detection in Interdependent Networks
  94. DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation
  95. Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition
  96. Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
  97. Conformal Isometry of Lie Group Representation in Recurrent Network of Grid Cells
  98. DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing
  99. Effective Metaheuristic Based Classifiers for Multiclass Intrusion Detection
  100. Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture
  101. Look Ma, Only 400 Samples! Revisiting the Effectiveness of Automatic N-Gram Rule Generation for Spelling Normalization in Filipino
  102. Orthogonal Nonnegative Matrix Factorization with Sparsity Constraints
  103. A Human Rights-Based Approach to Responsible AI
  104. When not to use machine learning: a perspective on potential and limitations
  105. Vision-Based Defect Classification and Weight Estimation of Rice Kernels
  106. Towards Better Semantic Understanding of Mobile Interfaces
  107. Topological Continual Learning with Wasserstein Distance and Barycenter
  108. Explainable Abuse Detection as Intent Classification and Slot Filling
  109. Learning functional sections in medical conversations: iterative pseudo-labeling and human-in-the-loop approach
  110. Predictive Edge Caching through Deep Mining of Sequential Patterns in User Content Retrievals
  111. Trust in Motion: Capturing Trust Ascendancy in Open-Source Projects using Hybrid AI
  112. Domain Generalization via Contrastive Causal Learning
  113. Learning Algorithms for Intelligent Agents and Mechanisms
  114. Automatic Scene-based Topic Channel Construction System for E-Commerce
  115. Feasibility on Detecting Door Slamming towards Monitoring Early Signs of Domestic Violence
  116. IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks
  117. Geodesic Graph Neural Network for Efficient Graph Representation Learning
  118. Research on the quantity and brightness evolution characteristics of Photospheric Bright Points groups
  119. Data-driven Approaches to Surrogate Machine Learning Model Development
  120. MechRetro is a chemical-mechanism-driven graph learning framework for interpretable retrosynthesis prediction and pathway planning
  121. TensorAnalyzer: Identification of Urban Patterns in Big Cities using Non-Negative Tensor Factorization
  122. Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealing
  123. U3E: Unsupervised and Erasure-based Evidence Extraction for Machine Reading Comprehension
  124. Inference Latency Prediction at the Edge
  125. Dynamic Stochastic Ensemble with Adversarial Robust Lottery Ticket Subnetworks
  126. Generalization Properties of Retrieval-based Models
  127. Digital Twin-Empowered Network Planning for Multi-Tier Computing
  128. Federated Learning with Server Learning: Enhancing Performance for Non-IID Data
  129. Lyapunov Function Consistent Adaptive Network Signal Control with Back Pressure and Reinforcement Learning