mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 14 Jun 2023

217 papers

  1. EM-Network: Oracle Guided Self-distillation for Sequence LearningKnowledge distillation → Speech and audio distillation
  2. Katakomba: Tools and Benchmarks for Data-Driven NetHackOffline RL and imitation learning from data → Offline RL algorithms
  3. InfoDiffusion: Representation Learning Using Information Maximizing Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  4. VidEdit: Zero-Shot and Spatially Aware Text-Driven Video EditingDiffusion models → Video generation
  5. Norm-guided latent space exploration for text-to-image generationDiffusion models → Image generation, text-to-image and editing
  6. World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. Toward Grounded Commonsense ReasoningLLM reasoning → Spatial and embodied reasoning
  8. Language to Rewards for Robotic Skill SynthesisLLM reasoning → Spatial and embodied reasoning
  9. Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image SynthesisDiffusion models → Image generation, text-to-image and editing
  10. Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized SettingsMixture-of-experts → Federated mixture-of-experts
  11. MiniLLM: On-Policy Distillation of Large Language ModelsKnowledge distillation → Knowledge distillation for LLMs
  12. Variance-Preserving-Based Interpolation Diffusion Models for Speech EnhancementDiffusion models → Audio, speech and music
  13. Probabilistic Regular Tree Priors for Scientific Symbolic ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  14. DiffuDetox: A Mixed Diffusion Model for Text DetoxificationDiffusion models → Robustness, privacy and adversarial aspects
  15. PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry GenerationDiffusion models → Discrete and text diffusion
  16. Provably Efficient Offline Reinforcement Learning with Perturbed Data SourcesOffline RL and imitation learning from data → Offline RL algorithms
  17. Multi-target Backdoor Attacks for Code Pre-trained ModelsLLM safety and security → Backdoor and data poisoning attacks
  18. On the Robustness of Latent Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  19. Data Augmentation for Seizure Prediction with Generative Diffusion ModelDiffusion models → Medical imaging and segmentation
  20. GBSD: Generative Bokeh with Stage DiffusionDiffusion models → 3D, point cloud and scene generation
  21. Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned GenerationDiffusion models → Image generation, text-to-image and editing
  22. Curricular Subgoals for Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
  23. CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape ExplorationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  24. Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
  25. Is there a Trojan! : Literature survey and critical evaluation of the latest ML based modern intrusion detection systems in IoT environments
  26. Deep Policy Gradient Methods in Commodity Markets
  27. Unconventional Cognitive Intelligent Robotic Control: Quantum Soft Computing Approach in Human Being Emotion Estimation -- QCOptKB Toolkit Application
  28. M2Hub: Unlocking the Potential of Machine Learning for Materials Discovery
  29. The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks
  30. Neural ShDF: Reviving an Efficient and Consistent Mesh Segmentation Method
  31. Towards social generative AI for education: theory, practices and ethics
  32. Revealing the structure of language model capabilities
  33. The Ontology for Agents, Systems and Integration of Services: OASIS version 2
  34. MUBen: Benchmarking the Uncertainty of Molecular Representation Models
  35. Generate to Understand for Representation
  36. Feeding control and water quality monitoring in aquaculture systems: Opportunities and challenges
  37. GenORM: Generalizable One-shot Rope Manipulation with Parameter-Aware Policy
  38. SAFER: Situation Aware Facial Emotion Recognition
  39. Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series
  40. Fault Detection in Induction Motors using Functional Dimensionality Reduction Methods
  41. TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting
  42. A Simple Data Augmentation for Feature Distribution Skewed Federated Learning
  43. Density-Aware Reinforcement Learning to Optimise Energy Efficiency in UAV-Assisted Networks
  44. HOSSnet: an Efficient Physics-Guided Neural Network for Simulating Crack Propagation
  45. Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability
  46. MMD-FUSE: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting
  47. Generalizable One-shot Neural Head Avatar
  48. Causal Discovery from Time Series with Hybrids of Constraint-Based and Noise-Based Algorithms
  49. Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information
  50. Recipes for Sequential Pre-training of Multilingual Encoder and Seq2Seq Models
  51. ClimSim-Online: A Large Multi-scale Dataset and Framework for Hybrid ML-physics Climate Emulation
  52. Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer
  53. Improving Selective Visual Question Answering by Learning from Your Peers
  54. Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reports
  55. Multi-Object Manipulation via Object-Centric Neural Scattering Functions
  56. MetaML: Automating Customizable Cross-Stage Design-Flow for Deep Learning Acceleration
  57. PLAN: Variance-Aware Private Mean Estimation
  58. High-performance deep spiking neural networks with 0.3 spikes per neuron
  59. Investigation of the Challenges of Underwater-Visual-Monocular-SLAM
  60. LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation
  61. WavPool: A New Block for Deep Neural Networks
  62. Continuous Learning Based Novelty Aware Emotion Recognition System
  63. EPIC Fields: Marrying 3D Geometry and Video Understanding
  64. Towards trustworthy seizure onset detection using workflow notes
  65. A Client-server Deep Federated Learning for Cross-domain Surgical Image Segmentation
  66. Off-policy Evaluation in Doubly Inhomogeneous Environments
  67. Integrating machine learning paradigms and mixed-integer model predictive control for irrigation scheduling
  68. What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations
  69. Naeural AI OS -- Decentralized ubiquitous computing MLOps execution engine
  70. Does mBERT understand Romansh? Evaluating word embeddings using word alignment
  71. Iterative self-transfer learning: A general methodology for response time-history prediction based on small dataset
  72. Phase Transitions of Civil Unrest across Countries and Time
  73. A generative artificial intelligence framework based on a molecular diffusion model for the design of metal-organic frameworks for carbon capture
  74. Integrating Uncertainty Awareness into Conformalized Quantile Regression
  75. ICET Online Accuracy Characterization for Geometry-Based Laser Scan Matching
  76. Predicting Real-time Crash Risks during Hurricane Evacuation Using Connected Vehicle Data
  77. Temporally Extended Goal Recognition in Fully Observable Non-Deterministic Domain Models
  78. Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data
  79. Simple Opinion Dynamics for No-Regret Learning
  80. When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants
  81. Radiology-GPT: A Large Language Model for Radiology
  82. Explore In-Context Learning for 3D Point Cloud Understanding
  83. Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations
  84. EMERSK -- Explainable Multimodal Emotion Recognition with Situational Knowledge
  85. Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
  86. Learning to Rank when Grades Matter
  87. OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
  88. SimpleMapping: Real-Time Visual-Inertial Dense Mapping with Deep Multi-View Stereo
  89. Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models
  90. AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn
  91. TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
  92. Predicting Wireless Channel Quality by means of Moving Averages and Regression Models
  93. Vulnerability Assessment of Industrial Control System with an Improved CVSS
  94. High-Dimensional MR Reconstruction Integrating Subspace and Adaptive Generative Models
  95. Graph-Based Matrix Completion Applied to Weather Data
  96. RRSIS: Referring Remote Sensing Image Segmentation
  97. Anticipatory Music Transformer
  98. Multi-class Graph Clustering via Approximated Effective p-Resistance
  99. TomoSAM: a 3D Slicer extension using SAM for tomography segmentation
  100. A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy
All 217
  1. M^2UNet: MetaFormer Multi-scale Upsampling Network for Polyp Segmentation
  2. Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters
  3. TensorKrowch: Smooth integration of tensor networks in machine learning
  4. Heterogeneous Continual Learning
  5. Self-Supervised Polyp Re-Identification in Colonoscopy
  6. Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
  7. Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation
  8. Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data
  9. Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition
  10. Label Noise Robust Image Representation Learning based on Supervised Variational Autoencoders in Remote Sensing
  11. GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image
  12. WizardCoder: Empowering Code Large Language Models with Evol-Instruct
  13. Federated Learning-based Vehicle Trajectory Prediction against Cyberattacks
  14. Reliable Evaluation of Adversarial Transferability
  15. The Universal Law of Generalization Holds for Naturalistic Stimuli
  16. Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach
  17. User Simulation for Evaluating Information Access Systems
  18. An Exploratory Study of Masked Face Recognition with Machine Learning Algorithms
  19. Fine-Tuned but Zero-Shot 3D Shape Sketch View Similarity and Retrieval
  20. Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions
  21. VIBR: Learning View-Invariant Value Functions for Robust Visual Control
  22. SQL2Circuits: Estimating Cardinalities, Execution Times, and Costs for SQL Queries with Quantum Natural Language Processing
  23. Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images
  24. AlbMoRe: A Corpus of Movie Reviews for Sentiment Analysis in Albanian
  25. Measuring and Controlling Divisiveness in Rank Aggregation
  26. Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications
  27. ITALIC: An Italian Intent Classification Dataset
  28. Adaptive Modeling of Satellite-Derived Nighttime Lights Time-Series for Tracking Urban Change Processes Using Machine Learning
  29. Extending CLIP's Image-Text Alignment to Referring Image Segmentation
  30. Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited
  31. A Relaxed Optimization Approach for Adversarial Attacks against Neural Machine Translation Models
  32. Analysis and Approximate Inference of Large Random Kronecker Graphs
  33. Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation
  34. Bandits with Replenishable Knapsacks: the Best of both Worlds
  35. Self-supervised Learning and Graph Classification under Heterophily
  36. Improving Generalization in Meta-Learning via Meta-Gradient Augmentation
  37. A Survey on Blood Pressure Measurement Technologies: Addressing Potential Sources of Bias
  38. Kalman Filter for Online Classification of Non-Stationary Data
  39. Towards Rigorous Design of OoD Detectors
  40. Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems
  41. "Definition Modeling: To model definitions." Generating Definitions With Little to No Semantics
  42. Batches Stabilize the Minimum Norm Risk in High Dimensional Overparameterized Linear Regression
  43. Selective Concept Models: Permitting Stakeholder Customisation at Test-Time
  44. X-Detect: Explainable Adversarial Patch Detection for Object Detectors in Retail
  45. Mediated Multi-Agent Reinforcement Learning
  46. Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement
  47. Building a Corpus for Biomedical Relation Extraction of Species Mentions
  48. LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming
  49. Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning
  50. Scalable Neural-Probabilistic Answer Set Programming
  51. Compatibility of Fairness Metrics with EU Non-Discrimination Laws: Demographic Parity & Conditional Demographic Disparity
  52. Provably Personalized and Robust Federated Learning
  53. Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning
  54. Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
  55. NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification
  56. SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
  57. A semantically enhanced dual encoder for aspect sentiment triplet extraction
  58. Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation
  59. T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing
  60. SaliencyCut: Augmenting Plausible Anomalies for Anomaly Detection
  61. Perceptions and Realities of Text-to-Image Generation
  62. Hierarchical Task Network Planning for Facilitating Cooperative Multi-Agent Reinforcement Learning
  63. Bayesian Non-linear Latent Variable Modeling via Random Fourier Features
  64. UIERL: Internal-External Representation Learning Network for Underwater Image Enhancement
  65. Global-Local Processing in Convolutional Neural Networks
  66. Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction
  67. Research on an improved Conformer end-to-end Speech Recognition Model with R-Drop Structure
  68. Distribution Shift Inversion for Out-of-Distribution Prediction
  69. Early Detection of Late Blight Tomato Disease using Histogram Oriented Gradient based Support Vector Machine
  70. GCformer: An Efficient Framework for Accurate and Scalable Long-Term Multivariate Time Series Forecasting
  71. How to estimate carbon footprint when training deep learning models? A guide and review
  72. Nonparametric regression using over-parameterized shallow ReLU neural networks
  73. Nearly Optimal Algorithms with Sublinear Computational Complexity for Online Kernel Regression
  74. Identification of Energy Management Configuration Concepts from a Set of Pareto-optimal Solutions
  75. Research on Named Entity Recognition in Improved transformer with R-Drop structure
  76. Automated Speaker Independent Visual Speech Recognition: A Comprehensive Survey
  77. A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
  78. Taming Reversible Halftoning via Predictive Luminance
  79. Towards Balanced Active Learning for Multimodal Classification
  80. Pedestrian Recognition with Radar Data-Enhanced Deep Learning Approach Based on Micro-Doppler Signatures
  81. Unifying Large Language Models and Knowledge Graphs: A Roadmap
  82. SaDI: A Self-adaptive Decomposed Interpretable Framework for Electric Load Forecasting under Extreme Events
  83. Efficient Training of Physics-Informed Neural Networks with Direct Grid Refinement Algorithm
  84. A reinforcement learning strategy for p-adaptation in high order solvers
  85. Investigating the dynamics of hand and lips in French Cued Speech using attention mechanisms and CTC-based decoding
  86. A2CiD2: Accelerating Asynchronous Communication in Decentralized Deep Learning
  87. 3-Dimensional Sonic Phase-invariant Echo Localization
  88. Differentially Private Wireless Federated Learning Using Orthogonal Sequences
  89. FRIGATE: Frugal Spatio-temporal Forecasting on Road Networks
  90. TryOnDiffusion: A Tale of Two UNets
  91. C3PS: Context-aware Conditional Cross Pseudo Supervision for Semi-supervised Medical Image Segmentation
  92. A Simple and Scalable Graph Neural Network for Large Directed Graphs
  93. Multiclass Confidence and Localization Calibration for Object Detection
  94. Solar Active Regions Detection Via 2D Circular Kernel Time Series Transformation, Entropy and Machine Learning Approach
  95. LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting
  96. Deblurring Masked Autoencoder is Better Recipe for Ultrasound Image Recognition
  97. MMASD: A Multimodal Dataset for Autism Intervention Analysis
  98. Semi-supervised Cell Recognition under Point Supervision
  99. Maestro: A Gamified Platform for Teaching AI Robustness
  100. OT-Net: A Reusable Neural Optimal Transport Solver
  101. Unbiased Learning of Deep Generative Models with Structured Discrete Representations
  102. Expanding Versatility of Agile Locomotion through Policy Transitions Using Latent State Representation
  103. Contrastive Loss is All You Need to Recover Analogies as Parallel Lines
  104. SMC-UDA: Structure-Modal Constraint for Unsupervised Cross-Domain Renal Segmentation
  105. Uncertainty-Aware Robust Learning on Noisy Graphs
  106. Ball Trajectory Inference from Multi-Agent Sports Contexts Using Set Transformer and Hierarchical Bi-LSTM
  107. Graph Laplacian Learning with Exponential Family Noise
  108. POP: Prompt Of Prompts for Continual Learning
  109. Explainable and Position-Aware Learning in Digital Pathology
  110. Learning on Graphs under Label Noise
  111. Operationalising Representation in Natural Language Processing
  112. Inductive Linear Probing for Few-shot Node Classification
  113. Solving Large-scale Spatial Problems with Convolutional Neural Networks
  114. Assessing the Effectiveness of GPT-3 in Detecting False Political Statements: A Case Study on the LIAR Dataset
  115. Language models are not naysayers: An analysis of language models on negation benchmarks
  116. Contextual Font Recommendations based on User Intent
  117. ZeroForge: Feedforward Text-to-Shape Without 3D Supervision