mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 31 Mar 2022

201 papers

  1. Data-augmented cross-lingual synthesis in a teacher-student frameworkKnowledge distillation → Speech and audio distillation
  2. Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?LLM reasoning → Multimodal reasoning +1
  3. BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal TransformersWorld models → World models for autonomous driving
  4. A Closer Look at Rehearsal-Free Continual LearningKnowledge distillation → Distillation for continual learning
  5. Generating High Fidelity Data from Low-density Regions using Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  6. kNN-NER: Named Entity Recognition with Nearest Neighbor SearchRetrieval-augmented generation → Generation and context integration
  7. Speech Enhancement with Score-Based Generative Models in the Complex STFT DomainDiffusion models → Audio, speech and music
  8. Equivariant Diffusion for Molecule Generation in 3DDiffusion models → Flow matching, time series and science
  9. Self-distillation Augmented Masked Autoencoders for Histopathological Image ClassificationKnowledge distillation → Distillation for medical imaging
  10. Towards Driving-Oriented Metric for Lane Detection ModelsEnd-to-end autonomous driving → VLMs for autonomous driving
  11. TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  12. SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral ShapingDiffusion models → Audio, speech and music
  13. Scaling Language Model Size in Cross-Device Federated Learning
  14. Generative Pre-Trained Transformers for Biologically Inspired Design
  15. TropeTwist: Trope-based Narrative Structure Generation
  16. Leveraging pre-trained language models for conversational information seeking from text
  17. Optimize Deep Learning Models for Prediction of Gene Mutations Using Unsupervised Clustering
  18. Deep Learning for Spectral Filling in Radio Frequency Applications
  19. Criacc~ao e aplicacc~ao de ferramenta para auxiliar no ensino de algoritmos e programacc~ao de computadores
  20. Bayesian Image Super-Resolution with Deep Modeling of Image Statistics
  21. Universal Lymph Node Detection in T2 MRI using Neural Networks
  22. Maze Learning using a Hyperdimensional Predictive Processing Cognitive Architecture
  23. 1-D CNN based Acoustic Scene Classification via Reducing Layer-wise Dimensionality
  24. Model Predictive Control for Fluid Human-to-Robot Handovers
  25. Real-Time and Robust 3D Object Detection Within Road-Side LiDARs Using Domain Adaptation
  26. VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition
  27. Perceptual Quality Assessment of UGC Gaming Videos
  28. GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing
  29. Synthesis of Stabilizing Recurrent Equilibrium Network Controllers
  30. Visual-Tactile Multimodality for Following Deformable Linear Objects Using Reinforcement Learning
  31. A Survey of Robust 3D Object Detection Methods in Point Clouds
  32. Scalable Whitebox Attacks on Tree-based Models
  33. Dynamic Multimodal Fusion
  34. TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization
  35. Tooth Instance Segmentation on Panoramic Dental Radiographs Using U-Nets and Morphological Processing
  36. Efficient Maximal Coding Rate Reduction by Variational Forms
  37. Automatic Classification of Alzheimer's Disease using brain MRI data and deep Convolutional Neural Networks
  38. rfPhen2Gen: A machine learning based association study of brain imaging phenotypes to genotypes
  39. SimPO: Simultaneous Prediction and Optimization
  40. SELFIES and the future of molecular string representations
  41. Digitizing Historical Balance Sheet Data: A Practitioner's Guide
  42. AKF-SR: Adaptive Kalman Filtering-based Successor Representation
  43. Efficient Active Learning with Abstention
  44. A Statistical Decision-Theoretical Perspective on the Two-Stage Approach to Parameter Estimation
  45. Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets
  46. Improving Adversarial Transferability via Neuron Attribution-Based Attacks
  47. Data Sampling Affects the Complexity of Online SGD over Dependent Data
  48. Graph-based Active Learning for Semi-supervised Classification of SAR Data
  49. Bringing Old Films Back to Life
  50. DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools
  51. Exploring Visual Prompts for Adapting Large-Scale Models
  52. FindIt: Generalized Localization with Natural Language Queries
  53. MyStyle: A Personalized Generative Prior
  54. TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
  55. A 23 MW data centre is all you need
  56. Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis
  57. R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis
  58. Modeling Long-Term Memory and Temporal Attention Shifts for Video Salient Object Ranking with a New Benchmark
  59. Continuous Scene Representations for Embodied AI
  60. ImpDet: Exploring Implicit Fields for 3D Object Detection
  61. Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions
  62. Performative Power
  63. A Baseline Readability Model for Cebuano
  64. SimVQA: Exploring Simulated Environments for Visual Question Answering
  65. Improved Relation Networks for End-to-End Speaker Verification and Identification
  66. On the probability-quality paradox in language generation
  67. Analyzing Wrap-Up Effects through an Information-Theoretic Lens
  68. Adversarial Examples in Random Neural Networks with General Activations
  69. Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy
  70. CatIss: An Intelligent Tool for Categorizing Issues Reports using Transformers
  71. Learning from many trajectories
  72. Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion
  73. Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech
  74. Scaling Up Models and Data with textttt5x and textttseqio
  75. 3D Equivariant Graph Implicit Functions
  76. On the Evaluation of NLP-based Models for Software Engineering
  77. Quantum open system identification via global optimization: Optimally accurate Markovian models of open systems from time-series data
  78. Preventing Over-Smoothing for Hypergraph Neural Networks
  79. Adaptive Mean-Residue Loss for Robust Facial Age Estimation
  80. Predicting extreme events from data using deep machine learning: when and where
  81. An energy-based deep splitting method for the nonlinear filtering problem
  82. Perceptual Contrast Stretching on Target Feature for Speech Enhancement
  83. Online Learning for Traffic Routing under Unknown Preferences
  84. AEGNN: Asynchronous Event-based Graph Neural Networks
  85. Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors
  86. Neural Q-learning for solving PDEs
  87. Doubly-Robust Estimation for Correcting Position-Bias in Click Feedback for Unbiased Learning to Rank
  88. Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data
  89. Impact of Environmental Noise on Alzheimer's Disease Detection from Speech: Should You Let a Baby Cry?
  90. A Rich Recipe Representation as Plan to Support Expressive Multi Modal Queries on Recipe Content and Preparation Process
  91. PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model
  92. Quantum-Aided Meta-Learning for Bayesian Binary Neural Networks via Born Machines
  93. RobIn: A Robust Interpretable Deep Network for Schizophrenia Diagnosis
  94. Interpretation of Black Box NLP Models: A Survey
  95. Scientific and Technological Text Knowledge Extraction Method of based on Word Mixing and GRU
  96. Deep Hyperspectral Unmixing using Transformer Network
  97. Manipulation of oral cancer speech using neural articulatory synthesis
  98. Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes
  99. CADG: A Model Based on Cross Attention for Domain Generalization
  100. Cross-modal Learning of Graph Representations using Radar Point Cloud for Long-Range Gesture Recognition
All 201
  1. Wind Farm Layout Optimisation using Set Based Multi-objective Bayesian Optimisation
  2. Certified machine learning: A posteriori error estimation for physics-informed neural networks
  3. BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection
  4. IITD-DBAI: Multi-Stage Retrieval with Pseudo-Relevance Feedback and Query Reformulation
  5. Partial Coupling of Optimal Transport for Spoken Language Identification
  6. Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verification
  7. Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
  8. Differentially Private Federated Learning via Reconfigurable Intelligent Surface
  9. Flat-topped Probability Density Functions for Mixture Models
  10. CTA-RNN: Channel and Temporal-wise Attention RNN Leveraging Pre-trained ASR Embeddings for Speech Emotion Recognition
  11. Logit Normalization for Long-tail Object Detection
  12. DeepFry: Identifying Vocal Fry Using Deep Neural Networks
  13. A Temporal Learning Approach to Inpainting Endoscopic Specularities and Its effect on Image Correspondence
  14. A Temporal-oriented Broadcast ResNet for COVID-19 Detection
  15. It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
  16. Conditional Autoregressors are Interpretable Classifiers
  17. SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategy
  18. Measuring hand use in the home after cervical spinal cord injury using egocentric video
  19. Message Passing Neural Networks for Hypergraphs
  20. Acoustic-Net: A Novel Neural Network for Sound Localization and Quantification
  21. Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition
  22. Human Instance Segmentation and Tracking via Data Association and Single-stage Detector
  23. PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations
  24. An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer
  25. Multimodal Fusion Transformer for Remote Sensing Image Classification
  26. Semantic Pose Verification for Outdoor Visual Localization with Self-supervised Contrastive Learning
  27. A data-driven approach for the closure of RANS models by the divergence of the Reynolds Stress Tensor
  28. A unified theory of learning
  29. Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs
  30. Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs
  31. HiFi-VC: High Quality ASR-Based Voice Conversion
  32. Learning from few examples with nonlinear feature maps
  33. Contributions to interframe coding
  34. Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond
  35. WavThruVec: Latent speech representation as intermediate features for neural speech synthesis
  36. Neural Architecture Search for Speech Emotion Recognition
  37. Applying PBL in the Development and Modeling of kinematics for Robotic Manipulators with Interdisciplinarity between Computer-Assisted Project, Robotics, and Microcontrollers
  38. Domain Adaptation for Sparse-Data Settings: What Do We Gain by Not Using Bert?
  39. Aplicacc~ao de ros como ferramenta de ensino a rob'otica / using ros as a robotics teaching tool
  40. A Character-level Span-based Model for Mandarin Prosodic Structure Prediction
  41. Assessing the risk of re-identification arising from an attack on anonymised data
  42. A Dataset of Images of Public Streetlights with Operational Monitoring using Computer Vision Techniques
  43. MBORE: Multi-objective Bayesian Optimisation by Density-Ratio Estimation
  44. End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps
  45. Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis
  46. Multi-Granularity Alignment Domain Adaptation for Object Detection
  47. CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
  48. Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
  49. A survey of neural models for the automatic analysis of conversation: Towards a better integration of the social sciences
  50. Mutual information estimation for graph convolutional neural networks
  51. A bilingual approach to specialised adjectives through word embeddings in the karstology domain
  52. MPS-NeRF: Generalizable 3D Human Rendering from Multiview Images
  53. An Optimal Control Method to Compute the Most Likely Transition Path for Stochastic Dynamical Systems with Jumps
  54. Ransomware Detection using Process Memory
  55. Memory-Efficient Training of RNN-Transducer with Sampled Softmax
  56. Investigating Modality Bias in Audio Visual Video Parsing
  57. JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech
  58. Revisiting Document Image Dewarping by Grid Regularization
  59. Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset
  60. Speaker Extraction with Co-Speech Gestures Cue
  61. A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings
  62. Point Scene Understanding via Disentangled Instance Mesh Reconstruction
  63. Rethinking Portrait Matting with Privacy Preserving
  64. indic-punct: An automatic punctuation restoration and inverse text normalization framework for Indic languages
  65. Effectiveness of text to speech pseudo labels for forced alignment and cross lingual pretrained models for low resource speech recognition
  66. How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications
  67. Minimum mean-squared error estimation with bandit feedback
  68. BRIO: Bringing Order to Abstractive Summarization
  69. Robust Meta-Reinforcement Learning with Curriculum-Based Task Sampling
  70. Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization
  71. M-MELD: A Multilingual Multi-Party Dataset for Emotion Recognition in Conversations
  72. Ternary and Binary Quantization for Improved Classification
  73. When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning
  74. Deformable Video Transformer
  75. MMER: Multimodal Multi-task Learning for Speech Emotion Recognition
  76. ESGBERT: Language Model to Help with Classification Tasks Related to Companies Environmental, Social, and Governance Practices
  77. Reflection and Rotation Symmetry Detection via Equivariant Learning
  78. Video-Text Representation Learning via Differentiable Weak Temporal Alignment
  79. Weakly Supervised Patch Label Inference Networks for Efficient Pavement Distress Detection and Recognition in the Wild
  80. Misogynistic Meme Detection using Early Fusion Model with Graph Network
  81. A Pixel-based Encryption Method for Privacy-Preserving Deep Learning Models
  82. ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
  83. Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks
  84. An Empirical Study of Language Model Integration for Transducer based Speech Recognition
  85. Bangla hate speech detection on social media using attention-based recurrent neural network
  86. SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks
  87. Learning Decoupling Features Through Orthogonality Regularization
  88. LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints
  89. ReSTR: Convolution-free Referring Image Segmentation Using Transformers
  90. SpatioTemporal Focus for Skeleton-based Action Recognition
  91. CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation
  92. MeMOT: Multi-Object Tracking with Memory
  93. CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR
  94. Exploiting Single-Channel Speech for Multi-Channel End-to-End Speech Recognition: A Comparative Study
  95. Casual 6-DoF: free-viewpoint panorama using a handheld 360 camera
  96. Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models
  97. Personalized Image Aesthetics Assessment with Rich Attributes
  98. An unsupervised cluster-level based method for learning node representations of heterogeneous graphs in scientific papers
  99. How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis
  100. Improving speaker de-identification with functional data analysis of f0 trajectories
  101. Exploiting Explainable Metrics for Augmented SGD