mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 23 Mar 2023

242 papers

  1. ChatGPT for Shaping the Future of Dentistry: The Potential of Multi-Modal Large Language ModelMultimodal LLMs / vision-language models → Medical vision-language models
  2. Detecting Backdoors in Pre-trained EncodersLLM safety and security → Backdoor and data poisoning attacks
  3. End-to-End Diffusion Latent Optimization Improves Classifier GuidanceDiffusion models → Diffusion foundations and sampling
  4. Adaptive Similarity Bootstrapping for Self-Distillation based Representation LearningKnowledge distillation → General knowledge distillation methods
  5. Efficient Symbolic Reasoning for Neural-Network VerificationLLM reasoning → Reasoning benchmarks and evaluation
  6. Ablating Concepts in Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  7. Persistent Nature: A Generative Model of Unbounded 3D WorldsWorld models → Video-generation world models and simulators
  8. Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 CompetitionLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  9. A Closer Look at Model Adaptation using Feature Distortion and Simplicity BiasMechanistic interpretability → Sparse autoencoder training and evaluation
  10. ReVersion: Diffusion-Based Relation Inversion from ImagesDiffusion models → Image generation, text-to-image and editing
  11. Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  12. On the Utility of Koopman Operator Theory in Learning Dexterous Manipulation SkillsOffline RL and imitation learning from data → Robot manipulation imitation learning
  13. Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video GeneratorsDiffusion models → Video generation
  14. Medical diffusion on a budget: Textual Inversion for medical image generationDiffusion models → Medical imaging and segmentation
  15. Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defenseLLM safety and security → Watermarking generated content and models
  16. DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from VideosDiffusion models → 3D, point cloud and scene generation
  17. A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIDiffusion models → Audio, speech and music
  18. Visual-Language Prompt Tuning with Knowledge-guided Context OptimizationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  19. A Simple and Generic Framework for Feature Distillation via Channel-wise TransformationKnowledge distillation → General knowledge distillation methods
  20. MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  21. Retrieval-Augmented Classification with Decoupled RepresentationRetrieval-augmented generation → Generation and context integration
  22. DiffPattern: Layout Pattern Generation via Discrete DiffusionDiffusion models → Image generation, text-to-image and editing
  23. Open-Vocabulary Object Detection using Pseudo Caption LabelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  24. Controllable Inversion of Black-Box Face Recognition Models via DiffusionDiffusion models → Image generation, text-to-image and editing
  25. From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft LabelsKnowledge distillation → General knowledge distillation methods
  26. Automatic Generation of Labeled Data for Video-Based Human Pose Analysis via NLP applied to YouTube Subtitles
  27. Secure Federated Learning for Cognitive Radio Sensing
  28. An embedding for EEG signals learned using a triplet loss
  29. IoT trust and reputation: a survey and taxonomy
  30. Neuro-Symbolic Execution of Generic Source Code
  31. Federated Learning for Metaverse: A Survey
  32. Severity classification of ground-glass opacity via 2-D convolutional neural network and lung CT scans: a 3-day exploration
  33. A Novel Patent Similarity Measurement Methodology: Semantic Distance and Technological Distance
  34. Dialogue-to-Video Retrieval
  35. Judicial Intelligent Assistant System: Extracting Events from Divorce Cases to Detect Disputes for the Judge
  36. A Gold Standard Dataset for the Reviewer Assignment Problem
  37. Explaining Exchange Rate Forecasts with Macroeconomic Fundamentals Using Interpretive Machine Learning
  38. A Deliberation-based Joint Acoustic and Text Decoder
  39. Predicting the Future of the CMS Detector: Crystal Radiation Damage and Machine Learning at the LHC
  40. Physics Symbolic Learner for Discovering Ground-Motion Models Via NGA-West2 Database
  41. High Fidelity Image Synthesis With Deep VAEs In Latent Space
  42. Low-frequency Image Deep Steganography: Manipulate the Frequency Distribution to Hide Secrets with Tenacious Robustness
  43. Decision-aid or Controller? Steering Human Decision Makers with Algorithms
  44. Adaptive Multi-scale Online Likelihood Network for AI-assisted Interactive Segmentation
  45. Learning and generalization of compositional representations of visual scenes
  46. OFA2: A Multi-Objective Perspective for the Once-for-All Neural Architecture Search
  47. Mordecai 3: A Neural Geoparser and Event Geocoder
  48. Clustering based on Mixtures of Sparse Gaussian Processes
  49. Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data
  50. Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment
  51. Presenting Multiagent Challenges in Team Sports Analytics
  52. Policy Evaluation in Distributional LQR
  53. NEWTON: Neural View-Centric Mapping for On-the-Fly Large-Scale SLAM
  54. Efficient Neural Architecture Search for Emotion Recognition
  55. Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild
  56. Adversarial Robustness and Feature Impact Analysis for Driver Drowsiness Detection
  57. Planning as Theorem Proving with Heuristics
  58. Efficient and Direct Inference of Heart Rate Variability using Both Signal Processing and Machine Learning
  59. PPG-based Heart Rate Estimation with Efficient Sensor Sampling and Learning Models
  60. Associated Random Neural Networks for Collective Classification of Nodes in Botnet Attacks
  61. NOPE: Novel Object Pose Estimation from a Single Image
  62. Artificial-intelligence-based molecular classification of diffuse gliomas using rapid, label-free optical imaging
  63. Multi-Antenna Dual-Blind Deconvolution for Joint Radar-Communications via SoMAN Minimization
  64. Stochastic Submodular Bandits with Delayed Composite Anonymous Bandit Feedback
  65. Scaled Quantization for the Vision Transformer
  66. Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages
  67. Une comparaison des algorithmes d'apprentissage pour la survie avec donn'ees manquantes
  68. On the Efficacy of Generalization Error Prediction Scoring Functions
  69. SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates
  70. Inheriting Bayer's Legacy-Joint Remosaicing and Denoising for Quad Bayer Image Sensor
  71. Return of the RNN: Residual Recurrent Networks for Invertible Sentence Embeddings
  72. TinyML: Tools, Applications, Challenges, and Future Research Directions
  73. Extracting real estate values of rental apartment floor plans using graph convolutional networks
  74. AI Models Close to your Chest: Robust Federated Learning Strategies for Multi-site CT
  75. Enhancing Embedding Representations of Biomedical Data using Logic Knowledge
  76. Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains
  77. Skip Connections in Spiking Neural Networks: An Analysis of Their Effect on Network Training
  78. Learning unidirectional coupling using echo-state network
  79. MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation
  80. Collaboration Helps Camera Overtake LiDAR in 3D Detection
  81. Enhancing Unsupervised Speech Recognition with Diffusion GANs
  82. Learning and Verification of Task Structure in Instructional Videos
  83. Three ways to improve feature alignment for open vocabulary detection
  84. SAOR: Single-View Articulated Object Reconstruction
  85. Neural Preset for Color Style Transfer
  86. MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
  87. Position-Guided Point Cloud Panoptic Segmentation Transformer
  88. DreamBooth3D: Subject-Driven Text-to-3D Generation
  89. The Quantization Model of Neural Scaling
  90. A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition
  91. ReBotNet: Fast Real-time Video Enhancement
  92. Chordal Averaging on Flag Manifolds and Its Applications
  93. TriPlaneNet: An Encoder for EG3D Inversion
  94. The effectiveness of MAE pre-pretraining for billion-scale pretraining
  95. Attention! Dynamic Epistemic Logic Models of (In)attentive Agents
  96. Boosting Reinforcement Learning and Planning with Demonstrations: A Survey
  97. NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations
  98. TactoFind: A Tactile Only System for Object Retrieval
  99. IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation
  100. TransPoser: Transformer as an Optimizer for Joint Object Shape and Pose Estimation
All 242
  1. Egocentric Audio-Visual Object Localization
  2. Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric
  3. Optimization Dynamics of Equivariant and Augmented Neural Networks
  4. CoBIT: A Contrastive Bi-directional Image-Text Generation Model
  5. Human Behavior in the Time of COVID-19: Learning from Big Data
  6. Development and validation of a natural language processing algorithm to pseudonymize documents in the context of a clinical data warehouse
  7. Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes
  8. CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not
  9. Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective
  10. Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimation
  11. GiveMeLabeledIssues: An Open Source Issue Recommendation System
  12. Low-Light Image Enhancement by Learning Contrastive Representations in Spatial and Frequency Domains
  13. Adaptive Endpointing with Deep Contextual Multi-armed Bandits
  14. SC-MIL: Supervised Contrastive Multiple Instance Learning for Imbalanced Classification in Pathology
  15. MSFA-Frequency-Aware Transformer for Hyperspectral Images Demosaicing
  16. Optimization and Optimizers for Adversarial Robustness
  17. Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation
  18. Zero-guidance Segmentation Using Zero Segment Labels
  19. Xplainer: From X-Ray Observations to Explainable Zero-Shot Diagnosis
  20. Compositional Zero-Shot Domain Transfer with Text-to-Text Models
  21. Planning for Manipulation among Movable Objects: Deciding Which Objects Go Where, in What Order, and How
  22. Plug-and-Play Regulators for Image-Text Matching
  23. FS-Real: Towards Real-World Cross-Device Federated Learning
  24. POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery
  25. Planning for Complex Non-prehensile Manipulation Among Movable Objects by Interleaving Multi-Agent Pathfinding and Physics-Based Simulation
  26. DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph
  27. Increasing Textual Context Size Boosts Medical Image-Text Matching
  28. Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides through Variational Autoencoder Based Image Compression
  29. Logistic Regression Equivalence: A Framework for Comparing Logistic Regression Models Across Populations
  30. Decentralized Adversarial Training over Graphs
  31. DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices
  32. Deep Generative Multi-Agent Imitation Model as a Computational Benchmark for Evaluating Human Performance in Complex Interactive Tasks: A Case Study in Football
  33. QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulation
  34. SwissBERT: The Multilingual Language Model for Switzerland
  35. The Innovation Paradox: Concept Space Expansion with Diminishing Originality and the Promise of Creative AI
  36. Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective
  37. Improving Generalization with Domain Convex Game
  38. Considerations on the Evaluation of Biometric Quality Assessment Algorithms
  39. LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms
  40. Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration
  41. GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering
  42. Improved Anisotropic Gaussian Filters
  43. SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field
  44. TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision
  45. Frame-Level Multi-Label Playing Technique Detection Using Multi-Scale Network and Self-Attention Mechanism
  46. Disguise without Disruption: Utility-Preserving Face De-Identification
  47. A Bag-of-Prototypes Representation for Dataset-Level Applications
  48. CrOC: Cross-View Online Clustering for Dense Visual Representation Learning
  49. 6D Object Pose Estimation from Approximate 3D Models for Orbital Robotics
  50. Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World
  51. Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylization
  52. Enriching Neural Network Training Dataset to Improve Worst-Case Performance Guarantees
  53. Confidence-Aware and Self-Supervised Image Anomaly Localisation
  54. Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels
  55. Explore the Power of Synthetic Data on Few-shot Object Detection
  56. Parameter-Efficient Sparse Retrievers and Rerankers using Adapters
  57. Fairness-guided Few-shot Prompting for Large Language Models
  58. A Case Study on AI Engineering Practices: Developing an Autonomous Stock Trading System
  59. Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs
  60. Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learning
  61. Confidence-Driven Deep Learning Framework for Early Detection of Knee Osteoarthritis
  62. First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning
  63. Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection
  64. VADER: Video Alignment Differencing and Retrieval
  65. Mechanism Design for Ad Auctions with Display Prices
  66. Extended High Utility Pattern Mining: An Answer Set Programming Based Framework and Applications
  67. Marching-Primitives: Shape Abstraction from Signed Distance Function
  68. ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding
  69. CMG-Net: An End-to-End Contact-Based Multi-Finger Dexterous Grasping Network
  70. It is all Connected: A New Graph Formulation for Spatio-Temporal Forecasting
  71. Enhancement of theColor Image Compression Using a New Algorithm based on Discrete Hermite Wavelet Transform
  72. 3D-POP -- An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion capture
  73. Design Patterns for AI-based Systems: A Multivocal Literature Review and Pattern Repository
  74. An elementary belief function logic
  75. Take 5: Interpretable Image Classification with a Handful of Features
  76. Improvement of Color Image Analysis Using a New Hybrid Face Recognition Algorithm based on Discrete Wavelets and Chebyshev Polynomials
  77. Adiabatic replay for continual learning
  78. Defining Quality Requirements for a Trustworthy AI Wildflower Monitoring Platform
  79. Calibrated Out-of-Distribution Detection with a Generic Representation
  80. FedGH: Heterogeneous Federated Learning with Generalized Global Header
  81. Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning
  82. Masked Image Training for Generalizable Deep Image Denoising
  83. Watch Out for the Confusing Faces: Detecting Face Swapping with the Probability Distribution of Face Identification Models
  84. Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations
  85. Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification
  86. Exploring Visual Prompts for Whole Slide Image Classification with Multiple Instance Learning
  87. DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter
  88. RLOR: A Flexible Framework of Deep Reinforcement Learning for Operation Research
  89. AdaCL:Adaptive Continual Learning
  90. A Simple Explanation for the Phase Transition in Large Language Models with List Decoding
  91. Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentation
  92. OCELOT: Overlapped Cell on Tissue Dataset for Histopathology
  93. Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications
  94. MMFormer: Multimodal Transformer Using Multiscale Self-Attention for Remote Sensing Image Classification
  95. PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Clouds
  96. Multi-View Zero-Shot Open Intent Induction from Dialogues: Multi Domain Batch and Proxy Gradient Transfer
  97. CP3: Channel Pruning Plug-in for Point-based Networks
  98. Modeling Entities as Semantic Points for Visual Information Extraction in the Wild
  99. Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent
  100. Orthogonal Annotation Benefits Barely-supervised Medical Image Segmentation
  101. Box-Level Active Detection
  102. Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization
  103. MSAT: Biologically Inspired Multi-Stage Adaptive Threshold for Conversion of Spiking Neural Networks
  104. An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain
  105. CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
  106. Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition
  107. PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circ
  108. Human Guided Ground-truth Generation for Realistic Image Super-resolution
  109. SIEDOB: Semantic Image Editing by Disentangling Object and Background
  110. Predicting the Initial Conditions of the Universe using a Deterministic Neural Network
  111. Reimagining Application User Interface (UI) Design using Deep Learning Methods: Challenges and Opportunities
  112. Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection
  113. Towards Better Dynamic Graph Learning: New Architecture and Unified Library
  114. Top-Down Visual Attention from Analysis by Synthesis
  115. SPeC: A Soft Prompt-Based Calibration on Performance Variability of Large Language Model in Clinical Notes Summarization
  116. Preference-Aware Constrained Multi-Objective Bayesian Optimization
  117. Federated Uncertainty-Aware Aggregation for Fundus Diabetic Retinopathy Staging
  118. Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models
  119. Identifying TBI Physiological States by Clustering Multivariate Clinical Time-Series Data
  120. ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting
  121. MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer
  122. Failure-tolerant Distributed Learning for Anomaly Detection in Wireless Networks
  123. Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention
  124. GesGPT: Speech Gesture Synthesis With Text Parsing from ChatGPT
  125. Semantic Image Attack for Visual Model Diagnosis
  126. MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
  127. Adversarially Contrastive Estimation of Conditional Neural Processes
  128. Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance
  129. Planning Goals for Exploration
  130. Is ChatGPT A Good Keyphrase Generator? A Preliminary Study
  131. Automated Federated Learning in Mobile Edge Networks -- Fast Adaptation and Convergence
  132. FER-former: Multi-modal Transformer for Facial Expression Recognition
  133. Backdoor Defense via Adaptively Splitting Poisoned Dataset
  134. A Survey of Historical Learning: Learning Models with Learning History
  135. Fault Prognosis of Turbofan Engines: Eventual Failure Prediction and Remaining Useful Life Estimation
  136. Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems
  137. NVAutoNet: Fast and Accurate 360circ 3D Visual Perception For Self Driving
  138. Performance Analysis and Evaluation of Cloud Vision Emotion APIs
  139. Uncertainty Calibration for Counterfactual Propensity Estimation in Recommendation
  140. Efficient Meshy Neural Fields for Animatable Human Avatars
  141. Continuous Indeterminate Probability Neural Network
  142. Forecast-Aware Model Driven LSTM