mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 25 Apr 2023

215 papers

  1. SAFE: Machine Unlearning With Shard GraphsLLM safety and security → Machine unlearning
  2. Diffusion Probabilistic Model Based Accurate and High-Degree-of-Freedom Metasurface Inverse DesignDiffusion models → Flow matching, time series and science
  3. Stable and low-precision training for large-scale vision-language modelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  4. Answering Questions by Meta-Reasoning over Multiple Chains of ThoughtLLM reasoning → Knowledge- and tool-augmented reasoning
  5. Towards Theoretical Understanding of Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
  6. The Score-Difference Flow for Implicit Generative ModelingDiffusion models → Diffusion foundations and sampling
  7. Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantificationDiffusion models → Flow matching, time series and science
  8. What can online reinforcement learning with function approximation benefit from general coverage conditions?Offline RL and imitation learning from data → Offline RL algorithms
  9. Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  10. Zero-shot Transfer Learning of Driving Policy via Socially Adversarial Traffic FlowEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  11. Class Attention Transfer Based Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  12. State Spaces Aren't Enough: Machine Translation Needs AttentionState-space sequence models (S4, Mamba) → Core SSM architectures for language
  13. Bayesian Optimization Meets Self-DistillationKnowledge distillation → General knowledge distillation methods
  14. CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular SynthesisDiffusion models → Flow matching, time series and science
  15. Exploring Compositional Visual Generation with Latent Classifier GuidanceDiffusion models → Diffusion foundations and sampling
  16. Patch Diffusion: Faster and More Data-Efficient Training of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  17. GlyphDiffusion: Text Generation as Image GenerationDiffusion models → Image generation, text-to-image and editing
  18. Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning ApproachOffline RL and imitation learning from data → Imitation learning methods
  19. Leveraging Human Feedback to Evolve and Discover Novel Emergent Behaviors in Robot Swarms
  20. NUANCE: Near Ultrasound Attack On Networked Communication Environments
  21. Curriculum Modeling the Dependence among Targets with Multi-task Learning for Financial Marketing
  22. Vision-based Target Pose Estimation with Multiple Markers for the Perching of UAVs
  23. An Audit Framework for Adopting AI-Nudging on Children
  24. What's in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models through User-Provided Names in CAD Files
  25. When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability
  26. Lane Change Intention Recognition and Vehicle Status Prediction for Autonomous Vehicles
  27. Connector 0.5: A unified framework for graph representation learning
  28. Towards Reliable Colorectal Cancer Polyps Classification via Vision Based Tactile Sensing and Confidence-Calibrated Neural Networks
  29. Towards Explainable and Safe Conversational Agents for Mental Health: A Survey
  30. Onboard Science Instrument Autonomy for the Detection of Microscopy Biosignatures on the Ocean Worlds Life Surveyor
  31. TABLET: Learning From Instructions For Tabular Data
  32. AI-assisted coding: Experiments with GPT-4
  33. Sample-Specific Debiasing for Better Image-Text Models
  34. Sebis at SemEval-2023 Task 7: A Joint System for Natural Language Inference and Evidence Retrieval from Clinical Trial Reports
  35. Robust Non-Linear Feedback Coding via Power-Constrained Deep Learning
  36. Dynamic Datasets and Market Environments for Financial Reinforcement Learning
  37. LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization
  38. Towards Compute-Optimal Transfer Learning
  39. HDR or SDR? A Subjective and Objective Study of Scaled and Compressed Videos
  40. Autoencoder-based Radio Frequency Interference Mitigation For SMAP Passive Radiometer
  41. HDR-ChipQA: No-Reference Quality Assessment on High Dynamic Range Videos
  42. LumiGAN: Unconditional Generation of Relightable 3D Human Faces
  43. Roll-Drop: accounting for observation noise with a single parameter
  44. Modeling Spoken Information Queries for Virtual Assistants: Open Problems, Challenges and Opportunities
  45. Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection
  46. Self-Supervised Multi-Object Tracking For Autonomous Driving From Consistency Across Timescales
  47. T Cell Receptor Protein Sequences and Sparse Coding: A Novel Approach to Cancer Classification
  48. Self-Supervised Temporal Analysis of Spatiotemporal Data
  49. Optimal and exact recovery on the general nonuniform Hypergraph Stochastic Block Model
  50. The Update-Equivalence Framework for Decision-Time Planning
  51. MEDNC: Multi-ensemble deep neural network for COVID-19 diagnosis
  52. LAST: Scalable Lattice-Based Speech Modelling in JAX
  53. Directed Chain Generative Adversarial Networks
  54. Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining
  55. Precision Spectroscopy of Fast, Hot Exotic Isotopes Using Machine Learning Assisted Event-by-Event Doppler Correction
  56. Application of Transformers for Nonlinear Channel Compensation in Optical Systems
  57. AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction
  58. BO-ICP: Initialization of Iterative Closest Point Based on Bayesian Optimization
  59. Federated Deep Reinforcement Learning for THz-Beam Search with Limited CSI
  60. Time-Selective RNN for Device-Free Multi-Room Human Presence Detection Using WiFi CSI
  61. Attention-Enhanced Deep Learning for Device-Free Through-the-Wall Presence Detection Using Indoor WiFi Systems
  62. LSTM-based Load Forecasting Robustness Against Noise Injection Attack in Microgrid
  63. HyMo: Vulnerability Detection in Smart Contracts using a Novel Multi-Modal Hybrid Model
  64. Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient
  65. Making Video Quality Assessment Models Robust to Bit Depth
  66. Model Extraction Attacks Against Reinforcement Learning Based Controllers
  67. Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations
  68. Organizational Governance of Emerging Technologies: AI Adoption in Healthcare
  69. iMixer: hierarchical Hopfield network implies an invertible, implicit and iterative MLP-Mixer
  70. Injecting structural hints: Using language models to study inductive biases in language learning
  71. GULP: Solar-Powered Smart Garbage Segregation Bins with SMS Notification and Machine Learning Image Processing
  72. Optimizing Deep Learning Models For Raspberry Pi
  73. VeML: An End-to-End Machine Learning Lifecycle for Large-scale and High-dimensional Data
  74. DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection
  75. CompletionFormer: Depth Completion with Convolutions and Vision Transformers
  76. Bake off redux: a review and experimental evaluation of recent time series classification algorithms
  77. A Strong and Reproducible Object Detector with Only Public Datasets
  78. Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images
  79. Face Feature Visualisation of Single Morphing Attack Detection
  80. Certifying Ensembles: A General Certification Theory with S-Lipschitzness
  81. DuETT: Dual Event Time Transformer for Electronic Health Records
  82. Subsample Ridge Ensembles: Equivalences and Generalized Cross-Validation
  83. Flickr-PAD: New Face High-Resolution Presentation Attack Detection Database
  84. Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art
  85. Unstructured and structured data: Can we have the best of both worlds with large language models?
  86. The Potential of Visual ChatGPT For Remote Sensing
  87. PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling
  88. Evaluating Inter-Bilingual Semantic Parsing for Indian Languages
  89. Centralized control for multi-agent RL in a complex Real-Time-Strategy game
  90. On the Generalization of Learned Structured Representations
  91. Segment anything, from space?
  92. AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
  93. Multi-Scale Feature Fusion using Parallel-Attention Block for COVID-19 Chest X-ray Diagnosis
  94. Quantifying the Effect of Image Similarity on Diabetic Foot Ulcer Classification
  95. Measuring Massive Multitask Chinese Understanding
  96. Rubik's Optical Neural Networks: Multi-task Learning with Physics-aware Rotation Architecture
  97. Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11
  98. GMNLP at SemEval-2023 Task 12: Sentiment Analysis with Phylogeny-Based Adapters
  99. Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning
  100. Escaping the sentence-level paradigm in machine translation
All 215
  1. A Closer Look at Reward Decomposition for High-Level Robotic Explanations
  2. Nondeterministic Stacks in Neural Networks
  3. Asymptotic Behaviors and Phase Transitions in Projected Stochastic Approximation: A Jump Diffusion Approach
  4. Latent Traversals in Generative Models as Potential Flows
  5. User-Centric Federated Learning: Trading off Wireless Resources for Personalization
  6. Quantum Gaussian Process Regression for Bayesian Optimization
  7. Discovering Graph Generation Algorithms
  8. Blockchain-based Federated Learning with Secure Aggregation in Trusted Execution Environment for Internet-of-Things
  9. Out-of-distribution Evidence-aware Fake News Detection via Dual Adversarial Debiasing
  10. Proximal Curriculum for Reinforcement Learning Agents
  11. Evaluation of Parameter-based Attacks against Embedded Neural Networks with Laser Injection
  12. Alternating Local Enumeration (TnALE): Solving Tensor Network Structure Search with Fewer Evaluations
  13. Binary stochasticity enabled highly efficient neuromorphic deep learning achieves better-than-software accuracy
  14. Unpaired Image Translation to Mitigate Domain Shift in Liquid Argon Time Projection Chamber Detector Responses
  15. What Causes Exceptions in Machine Learning Applications? Mining Machine Learning-Related Stack Traces on Stack Overflow
  16. Retinal Vessel Segmentation via a Multi-resolution Contextual Network and Adversarial Learning
  17. Adaptive Services Function Chain Orchestration For Digital Health Twin Use Cases: Heuristic-boosted Q-Learning Approach
  18. Depth-Relative Self Attention for Monocular Depth Estimation
  19. NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset
  20. (Local) Differential Privacy has NO Disparate Impact on Fairness
  21. Lessons Learned from a Citizen Science Project for Natural Language Processing
  22. A New Information Theory of Certainty for Machine Learning
  23. Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks
  24. A optimization framework for herbal prescription planning based on deep reinforcement learning
  25. A Novel Dual of Shannon Information and Weighting Scheme
  26. On the Use of Singular Value Decomposition as a Clutter Filter for Ultrasound Flow Imaging
  27. Loss- and Reward-Weighting for Efficient Distributed Reinforcement Learning
  28. Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
  29. Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games
  30. QuantProb: Generalizing Probabilities along with Predictions for a Pre-trained Classifier
  31. Test-Time Adaptation with Perturbation Consistency Learning
  32. Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies
  33. Centrality-Based Node Feature Augmentation for Robust Network Alignment
  34. Blockchain Large Language Models
  35. Inverting the Imaging Process by Learning an Implicit Camera Model
  36. Deep learning based Auto Tuning for Database Management System
  37. Local Implicit Ray Function for Generalizable Radiance Field Representation
  38. NPRL: Nightly Profile Representation Learning for Early Sepsis Onset Prediction in ICU Trauma Patients
  39. CitePrompt: Using Prompts to Identify Citation Intent in Scientific Papers
  40. Morphological Classification of Extragalactic Radio Sources Using Gradient Boosting Methods
  41. Eye tracking guided deep multiple instance learning with dual cross-attention for fundus disease detection
  42. Lyapunov-Stable Deep Equilibrium Models
  43. What does BERT learn about prosody?
  44. Empowering Wildlife Guardians: An Equitable Digital Stewardship and Reward System for Biodiversity Conservation using Deep Learning and 3/4G Camera Traps
  45. Deep Learning Framework for the Design of Orbital Angular Momentum Generators Enabled by Leaky-wave Holograms
  46. Phylo2Vec: a vector representation for binary trees
  47. On the Computation of Meaning, Language Models and Incomprehensible Horrors
  48. Exploring the Mutual Influence between Self-Supervised Single-Frame and Multi-Frame Depth Estimation
  49. Docmarking: Real-Time Screen-Cam Robust Document Image Watermarking
  50. Differential Privacy via Distributionally Robust Optimization
  51. Communication-Constrained Bandits under Additive Gaussian Noise
  52. Compressing Sentence Representation with maximum Coding Rate Reduction
  53. Patch-based 3D Natural Scene Generation from a Single Example
  54. Disagreement amongst counterfactual explanations: How transparency can be deceptive
  55. Dynamic Video Frame Interpolation with integrated Difficulty Pre-Assessment
  56. A Multi-Task Approach to Robust Deep Reinforcement Learning for Resource Allocation
  57. Partially Observable Mean Field Multi-Agent Reinforcement Learning Based on Graph-Attention
  58. Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur
  59. Learned Collusion
  60. Change detection needs change information: improving deep 3D point cloud change detection
  61. Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation
  62. Pseudo Labels Refinement with Intra-camera Similarity for Unsupervised Person Re-identification
  63. PUNR: Pre-training with User Behavior Modeling for News Recommendation
  64. Explain like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation
  65. Spatiotemporal Graph Convolutional Recurrent Neural Network Model for Citywide Air Pollution Forecasting
  66. Shape-Net: Room Layout Estimation from Panoramic Images Robust to Occlusion using Knowledge Distillation with 3D Shapes as Additional Inputs
  67. Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures
  68. Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
  69. Genetically-inspired convective heat transfer enhancement in a turbulent boundary layer
  70. Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint
  71. STM-UNet: An Efficient U-shaped Architecture Based on Swin Transformer and Multi-scale MLP for Medical Image Segmentation
  72. A Bi-fidelity DeepONet Approach for Modeling Uncertain and Degrading Hysteretic Systems
  73. Performance Evaluation of Regression Models in Predicting the Cost of Medical Insurance
  74. Adaptive Path-Memory Network for Temporal Knowledge Graph Reasoning
  75. Is deep learning a useful tool for the pure mathematician?
  76. Application of Segment Anything Model for Civil Infrastructure Defect Assessment
  77. Detection of Pavement Cracks by Deep Learning Models of Transformer and UNet
  78. MMRDN: Consistent Representation for Multi-View Manipulation Relationship Detection in Object-Stacked Scenes
  79. Unsupervised Synthetic Image Refinement via Contrastive Learning and Consistent Semantic-Structural Constraints
  80. ContrastMotion: Self-supervised Scene Motion Learning for Large-Scale LiDAR Point Clouds
  81. MF-NeRF: Memory Efficient NeRF with Mixed-Feature Hash Table
  82. Unsupervised Discovery of Extreme Weather Events Using Universal Representations of Emergent Organization
  83. Learning imaging mechanism directly from optical microscopy observations
  84. Real-time Safety Assessment of Dynamic Systems in Non-stationary Environments: A Review of Methods and Techniques
  85. Learning Trajectories are Generalization Indicators
  86. Harnessing Deep Learning and HPC Kernels via High-Level Loop and Tensor Abstractions on CPU Architectures
  87. Fairness and Bias in Truth Discovery Algorithms: An Experimental Analysis
  88. Learnable Pillar-based Re-ranking for Image-Text Retrieval
  89. KINLP at SemEval-2023 Task 12: Kinyarwanda Tweet Sentiment Analysis
  90. Performance Optimization using Multimodal Modeling and Heterogeneous GNN
  91. Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks
  92. AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation
  93. Empirical Evaluation of ChatGPT on Requirements Information Retrieval Under Zero-Shot Setting
  94. TCR: Short Video Title Generation and Cover Selection with Attention Refinement
  95. SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge
  96. Combining Adversaries with Anti-adversaries in Training
  97. COUPA: An Industrial Recommender System for Online to Offline Service Platforms
  98. Object Semantics Give Us the Depth We Need: Multi-task Approach to Aerial Depth Completion
  99. Efficient Bayesian inference using physics-informed invertible neural networks for inverse problems
  100. Text-guided Eyeglasses Manipulation with Spatial Constraints
  101. GARCIA: Powering Representations of Long-tail Query with Multi-granularity Contrastive Learning
  102. Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders
  103. Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMM
  104. SEA: A Spatially Explicit Architecture for Multi-Agent Reinforcement Learning
  105. Improved Trust in Human-Robot Collaboration with ChatGPT
  106. CIMLA: Interpretable AI for inference of differential causal networks
  107. A New Inexact Proximal Linear Algorithm with Adaptive Stopping Criteria for Robust Phase Retrieval
  108. Hint-Aug: Drawing Hints from Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning
  109. IMUPoser: Full-Body Pose Estimation using IMUs in Phones, Watches, and Earbuds
  110. Semantic Compression With Large Language Models
  111. Fulfilling Formal Specifications ASAP by Model-free Reinforcement Learning
  112. Learning Task-Specific Strategies for Accelerated MRI
  113. Generalized Bayesian Additive Regression Trees: Theory and Software
  114. CNN-Assisted Steganography -- Integrating Machine Learning with Established Steganographic Techniques
  115. The cross-sectional stock return predictions via quantum neural network and tensor network