mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 20 Oct 2022

229 papers

  1. Graphically Structured Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  2. Large Language Models Can Self-ImproveLLM reasoning → Test-time compute and efficient thinking +1
  3. New data poison attacks on machine learning classifiers for mobile exfiltrationLLM safety and security → Backdoor and data poisoning attacks
  4. Learning and Retrieval from Prior Data for Skill-based Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  5. DiffEdit: Diffusion-based semantic image editing with mask guidanceDiffusion models → Image generation, text-to-image and editing
  6. VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal PriorsOffline RL and imitation learning from data → Robot manipulation imitation learning
  7. Proof of Unlearning: Definitions and InstantiationLLM safety and security → Machine unlearning
  8. MoCoDA: Model-based Counterfactual Data AugmentationOffline RL and imitation learning from data → Offline RL algorithms
  9. Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning TransformersLLM reasoning → Reasoning benchmarks and evaluation
  10. Robust Imitation via Mirror Descent Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
  11. Toward Multiple Specialty Learners for Explaining GNNs via Online Knowledge DistillationKnowledge distillation → Graph neural network distillation
  12. Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive LearningLLM safety and security → Backdoor and data poisoning attacks
  13. Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID ScenarioLLM safety and security → Federated unlearning and poisoning
  14. Representation Learning with Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  15. Task Phasing: Automated Curriculum Learning from DemonstrationsOffline RL and imitation learning from data → Inverse reinforcement learning
  16. Diffusion Models already have a Semantic Latent SpaceDiffusion models → Diffusion foundations and sampling
  17. Combining Neuro-Evolution of Augmenting Topologies with Convolutional Neural Networks
  18. Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity
  19. Fine-Grained Session Recommendations in E-commerce using Deep Reinforcement Learning
  20. AugCSE: Contrastive Sentence Embedding with Diverse Augmentations
  21. Chaos Theory and Adversarial Robustness
  22. A Complete Recipe for Bayesian Knowledge Transfer: Object Tracking
  23. Analysing Training-Data Leakage from Gradients through Linear Systems and Gradient Matching
  24. GeoAI at ACM SIGSPATIAL: The New Frontier of Geospatial Artificial Intelligence Research
  25. Deep-Learning-Based Precipitation Nowcasting with Ground Weather Station Data and Radar Data
  26. End-to-End Context-Aided Unicity Matching for Person Re-identification
  27. DIICAN: Dual Time-scale State-Coupled Co-estimation of SOC, SOH and RUL for Lithium-Ion Batteries
  28. JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking
  29. Improving Semi-supervised End-to-end Automatic Speech Recognition using CycleGAN and Inter-domain Losses
  30. HesScale: Scalable Computation of Hessian Diagonals
  31. Slippage-robust Gaze Tracking for Near-eye Display
  32. Using Large Language Models to Enhance Programming Error Messages
  33. Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?
  34. Sparse Dynamical Features generation, application to Parkinson's Disease diagnosis
  35. SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages
  36. LOT: Layer-wise Orthogonal Training on Improving ℓ2 Certified Robustness
  37. Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve
  38. Boosting Natural Language Generation from Instructions with Meta-Learning
  39. Generalized Reciprocal Perspective
  40. Searching for a higher power in the human evaluation of MT
  41. Tag-Set-Sequence Learning for Generating Question-Answer Pairs
  42. Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes
  43. 3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows
  44. gSuite: A Flexible and Framework Independent Benchmark Suite for Graph Neural Network Inference on GPUs
  45. The VolcTrans System for WMT22 Multilingual Machine Translation Task
  46. Identifying Human Strategies for Generating Word-Level Adversarial Examples
  47. Photo-realistic 360 Head Avatars in the Wild
  48. XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection
  49. Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization
  50. Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
  51. Deep Learning for Diagonal Earlobe Crease Detection
  52. Model-based Lifelong Reinforcement Learning with Bayesian Exploration
  53. Global Convergence of Direct Policy Search for State-Feedback H_∞ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential
  54. LiBeamsNet: AUV Velocity Vector Estimation in Situations of Limited DVL Beam Measurements
  55. Rethinking Learning Approaches for Long-Term Action Anticipation
  56. Dense Paraphrasing for Textual Enrichment
  57. Local SGD in Overparameterized Linear Regression
  58. Low-Rank Representations Towards Classification Problem of Complex Networks
  59. Finding Dataset Shortcuts with Grammar Induction
  60. Learning Attention Propagation for Compositional Zero-Shot Learning
  61. H4VDM: H.264 Video Device Matching
  62. Transferring learned patterns from ground-based field imagery to predict UAV-based imagery for crop and weed semantic segmentation in precision crop farming
  63. Object Goal Navigation Based on Semantics and RGB Ego View
  64. ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing
  65. An Improved Algorithm for Clustered Federated Learning
  66. CONSISTENT: Open-Ended Question Generation From News Articles
  67. DNN-ForwardTesting: A New Trading Strategy Validation using Statistical Timeseries Analysis and Deep Neural Networks
  68. Theoretical analysis of deep neural networks for temporally dependent observations
  69. Unsupervised Text Deidentification
  70. Composing Ensembles of Pre-trained Models via Iterative Consensus
  71. Learning Sample Reweighting for Accuracy and Adversarial Robustness
  72. Communication breakdown: On the low mutual intelligibility between human and neural captioning
  73. Overexposure Mask Fusion: Generalizable Reverse ISP Multi-Step Refinement
  74. Multimodal Neural Network For Demand Forecasting
  75. Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models
  76. Machine-Learning Compression for Particle Physics Discoveries
  77. A Methodology for the Prediction of Drug Target Interaction using CDK Descriptors
  78. Improving aircraft performance using machine learning: a review
  79. VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling
  80. Choose Your Lenses: Flaws in Gender Bias Evaluation
  81. i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?
  82. G2NetPL: Generic Game-Theoretic Network for Partial-Label Image Classification
  83. ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications
  84. Multi-View Guided Multi-View Stereo
  85. Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
  86. Self-Supervised Learning via Maximum Entropy Coding
  87. Breaking Bad: A Dataset for Geometric Fracture and Reassembly
  88. MixMask: Revisiting Masking Strategy for Siamese ConvNets
  89. Global Convergence of SGD On Two Layer Neural Nets
  90. Bagging in overparameterized learning: Risk characterization and risk monotonization
  91. How can a Radar Mask its Cognition?
  92. Snapshot of Algebraic Vision
  93. Augmentative Topology Agents For Open-Ended Learning
  94. Cell tracking for live-cell microscopy using an activity-prioritized assignment strategy
  95. Revisiting Le Cam's Equation: Exact Minimax Rates over Convex Density Classes
  96. Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario
  97. GPR-Net: Multi-view Layout Estimation via a Geometry-aware Panorama Registration Network
  98. Scaling Instruction-Finetuned Language Models
  99. Similarity of Neural Architectures using Adversarial Attack Transferability
  100. Self-Supervised Learning with Masked Image Modeling for Teeth Numbering, Detection of Dental Restorations, and Instance Segmentation in Dental Panoramic Radiographs
All 229
  1. Learning Rationalizable Equilibria in Multiplayer Games
  2. Transcending Scaling Laws with 0.1% Extra Compute
  3. Solving Reasoning Tasks with a Slot Transformer
  4. TTTFlow: Unsupervised Test-Time Training with Normalizing Flow
  5. Physics-informed Deep Diffusion MRI Reconstruction with Synthetic Data: Break Training Data Bottleneck in Artificial Intelligence
  6. Transformer-based Action recognition in hand-object interacting scenarios
  7. On Representations of Mean-Field Variational Inference
  8. Transformer-based Global 3D Hand Pose Estimation in Two Hands Manipulating Objects Scenarios
  9. Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces
  10. Meeting Decision Tracker: Making Meeting Minutes with De-Contextualized Utterances
  11. On Feature Learning in the Presence of Spurious Correlations
  12. Deep conditional transformation models for survival analysis
  13. Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
  14. Network Synthetic Interventions: A Causal Framework for Panel Data Under Network Interference
  15. A Survey on Over-the-Air Computation
  16. Hypernetworks in Meta-Reinforcement Learning
  17. SS-VAERR: Self-Supervised Apparent Emotional Reaction Recognition from Video
  18. Play It Back: Iterative Attention for Audio Recognition
  19. Improving Data Quality with Training Dynamics of Gradient Boosting Decision Trees
  20. A Study of Scalarisation Techniques for Multi-Objective QUBO Solving
  21. Image-Text Retrieval with Binary and Continuous Label Supervision
  22. A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture
  23. Dynamic selection of p-norm in linear adaptive filtering via online kernel-based reinforcement learning
  24. The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)
  25. Tele-Knowledge Pre-training for Fault Analysis
  26. Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts
  27. Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videos
  28. Tighter PAC-Bayes Generalisation Bounds by Leveraging Example Difficulty
  29. DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection
  30. TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition
  31. Causal Structural Hypothesis Testing and Data Generation Models
  32. In-Vehicle Interface Adaptation to Environment-Induced Cognitive Workload
  33. Inference from Real-World Sparse Measurements
  34. RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control
  35. Safe Policy Improvement in Constrained Markov Decision Processes
  36. A note on diffusion limits for stochastic gradient descent
  37. Evidence > Intuition: Transferability Estimation for Encoder Selection
  38. Neural ODEs as Feedback Policies for Nonlinear Optimal Control
  39. Attacking Motion Estimation with Adversarial Snow
  40. Context-driven Visual Object Recognition based on Knowledge Graphs
  41. Comparing Machine Learning Techniques for Alfalfa Biomass Yield Prediction
  42. Learning-Augmented Private Algorithms for Multiple Quantile Release
  43. Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation
  44. YOWO-Plus: An Incremental Improvement
  45. Modelling and Explaining Legal Case-based Reasoners through Classifiers
  46. PalGAN: Image Colorization with Palette Generative Adversarial Networks
  47. Removing grid structure in angle-resolved photoemission spectra via deep learning method
  48. Controller-Guided Partial Label Consistency Regularization with Unlabeled Data
  49. Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN
  50. Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions
  51. Towards Better Guided Attention and Human Knowledge Insertion in Deep Convolutional Neural Networks
  52. Overlapping Community Detection using Dynamic Dilated Aggregation in Deep Residual GCN
  53. Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem
  54. Coordinates Are NOT Lonely -- Codebook Prior Helps Implicit Neural 3D Representations
  55. Content-based Graph Privacy Advisor
  56. Pre-training Language Models with Deterministic Factual Knowledge
  57. Graph Neural Networks with Trainable Adjacency Matrices for Fault Diagnosis on Multivariate Sensor Data
  58. From Modelling to Understanding Children's Behaviour in the Context of Robotics and Social Artificial Intelligence
  59. VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection
  60. Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
  61. Machine Learning for K-adaptability in Two-stage Robust Optimization
  62. Transformer-based Entity Typing in Knowledge Graphs
  63. Reproducibility of the Methods in Medical Imaging with Deep Learning
  64. General Image Descriptors for Open World Image Retrieval using ViT CLIP
  65. Sensor interoperability and fusion in signature verification: A case study using tablet PC
  66. Trust Region Policy Optimization with Optimal Transport Discrepancies: Duality and Algorithm for Continuous Actions
  67. On-line signature verification using Tablet PC
  68. A lower confidence sequence for the changing mean of non-negative right heavy-tailed observations with bounded mean
  69. Super-Resolution and Image Re-projection for Iris Recognition
  70. Pruning by Active Attention Manipulation
  71. PAC-Bayesian Learning of Optimization Algorithms
  72. The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning
  73. Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation
  74. Robust One-Shot Singing Voice Conversion
  75. Iterative collaborative routing among equivariant capsules for transformation-robust capsule networks
  76. Robustcaps: a transformation-robust capsule network for image classification
  77. Standardized Medical Image Classification across Medical Disciplines
  78. Large-batch Optimization for Dense Visual Predictions
  79. Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise
  80. Frequency of Interest-based Noise Attenuation Method to Improve Anomaly Detection Performance
  81. MovieCLIP: Visual Scene Recognition in Movies
  82. Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots
  83. DisC-VC: Disentangled and F0-Controllable Neural Voice Conversion
  84. Vertical Federated Linear Contextual Bandits
  85. How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers
  86. Robust Image Registration with Absent Correspondences in Pre-operative and Follow-up Brain MRI Scans of Diffuse Glioma Patients
  87. Entire Space Counterfactual Learning for Reliable Content Recommendations
  88. PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points
  89. Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble
  90. Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection
  91. DeepRING: Learning Roto-translation Invariant Representation for LiDAR based Place Recognition
  92. A survey on Self Supervised learning approaches for improving Multimodal representation learning
  93. Independence Testing-Based Approach to Causal Discovery under Measurement Error and Linear Non-Gaussian Models
  94. Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks
  95. Single Image Super-Resolution Using Lightweight Networks Based on Swin Transformer
  96. An Attention-Guided and Wavelet-Constrained Generative Adversarial Network for Infrared and Visible Image Fusion
  97. Multi-Granularity Optimization for Non-Autoregressive Translation
  98. Towards Sustainable Self-supervised Learning
  99. SimpleClick: Interactive Image Segmentation with Simple Vision Transformers
  100. Pre-trained Sentence Embeddings for Implicit Discourse Relation Classification
  101. Synthetic Blips: Generalizing Synthetic Controls for Dynamic Treatment Effects
  102. Visual-Semantic Contrastive Alignment for Few-Shot Image Classification
  103. Semi-supervised object detection based on single-stage detector for thighbone fracture localization
  104. Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity
  105. MBTI Personality Prediction for Fictional Characters Using Movie Scripts
  106. A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs
  107. NIFT: Neural Interaction Field and Template for Object Manipulation
  108. Large-scale learning of generalised representations for speaker recognition
  109. RAIS: Robust and Accurate Interactive Segmentation via Continual Learning
  110. PSA-Det3D: Pillar Set Abstraction for 3D object Detection
  111. MGTUNet: An new UNet for colon nuclei instance segmentation and quantification
  112. Improving Segmentation of Breast Ultrasound Images: Semi Automatic Two Pointers Histogram Splitting Technique
  113. Scalable Bayesian Transformed Gaussian Processes
  114. A Multimodal Sensor Fusion Framework Robust to Missing Modalities for Person Recognition
  115. Optimal Settings for Cryptocurrency Trading Pairs
  116. SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy Grading
  117. IDM-Follower: A Model-Informed Deep Learning Method for Long-Sequence Car-Following Trajectory Prediction
  118. Uncertainty Disentanglement with Non-stationary Heteroscedastic Gaussian Processes for Active Learning
  119. Optimization on Manifolds via Graph Gaussian Processes
  120. Geo6D: Geometric Constraints Learning for 6D Pose Estimation
  121. 3D Human Mesh Construction Leveraging Wi-Fi
  122. Non-Iterative Scribble-Supervised Learning with Pacing Pseudo-Masks for Medical Image Segmentation
  123. Discovering Many Diverse Solutions with Bayesian Optimization
  124. Autoencoded sparse Bayesian in-IRT factorization, calibration, and amortized inference for the Work Disability Functional Assessment Battery
  125. Automatic Document Selection for Efficient Encoder Pretraining
  126. ESPNN: A novel electronic stopping power neural-network code built on the IAEA stopping power database. I. Atomic targets
  127. Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?
  128. Causally-guided Regularization of Graph Attention Improves Generalizability
  129. FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information