mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 4 May 2023

235 papers

  1. Seeing is Believing: Brain-Inspired Modular Training for Mechanistic InterpretabilityMechanistic interpretability → Circuits and mechanistic analysis
  2. Diffusion Explainer: Visual Explanation for Text-to-image Stable DiffusionDiffusion models → Image generation, text-to-image and editing
  3. VideoOFA: Two-Stage Pre-Training for Video-to-Text GenerationLLM reasoning → Multimodal reasoning
  4. Smaller3d: Smaller Models for 3D Semantic Segmentation Using Minkowski Engine and Knowledge Distillation MethodsKnowledge distillation → Detection and dense prediction distillation
  5. Programming-by-Demonstration for Long-Horizon Robot TasksOffline RL and imitation learning from data → Robot learning from demonstration
  6. Federated Ensemble-Directed Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  7. Confidence-Based Skill Reproduction Through Perturbation AnalysisOffline RL and imitation learning from data → Robot learning from demonstration
  8. Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human SupervisionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  9. Masked Trajectory Models for Prediction, Representation, and ControlOffline RL and imitation learning from data → Decision transformers and sequence modeling
  10. An automatically discovered chain-of-thought prompt generalizes to novel models and datasetsLLM reasoning → Prompting and chain-of-thought reasoning
  11. Explainable Reinforcement Learning via a Causal World ModelWorld models → World models for language agents
  12. Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with UncertaintyKnowledge distillation → General knowledge distillation methods
  13. CCIL: Context-conditioned imitation learning for urban drivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  14. How to Enhance Causal Discrimination of Utterances: A Case on Affective ReasoningLLM reasoning → Causal reasoning in LLMs
  15. High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data SamplingKnowledge distillation → General knowledge distillation methods
  16. Multimodal-driven Talking Face Generation via a Unified Diffusion-based GeneratorDiffusion models → Audio, speech and music
  17. LayoutDM: Transformer-based Diffusion Model for Layout GenerationDiffusion models → Image generation, text-to-image and editing
  18. Faithful Question Answering with Monte-Carlo PlanningLLM reasoning → Knowledge- and tool-augmented reasoning
  19. Can LLMs Capture Human Preferences?LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  20. Meta-Learning Enabled Score-Based Generative Model for 1.5T-Like Image Reconstruction from 0.5T MRIDiffusion models → Medical imaging and segmentation
  21. Personalized Abstractive Summarization by Tri-agent Generation PipelineLLM agents and tool use → Agent memory systems
  22. FR-Net:A Light-weight FFT Residual Net For Gaze Estimation
  23. Late-Binding Scholarship in the Age of AI: Navigating Legal and Normative Challenges of a New Form of Knowledge Production
  24. A Comparative Study of GAN-Generated Handwriting Images and MNIST Images using t-SNE Visualization
  25. Analysis of Visual Question Answering Algorithms with attention model
  26. An Imitation Learning Based Algorithm Enabling Priori Knowledge Transfer in Modern Electricity Markets for Bayesian Nash Equilibrium Estimation
  27. How to Use Reinforcement Learning to Facilitate Future Electricity Market Design? Part 2: Method and Applications
  28. Optimizing Drug Design by Merging Generative AI With Active Learning Frameworks
  29. Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimization
  30. Conversational Semantic Parsing using Dynamic Context Graphs
  31. DomainInv: Domain Invariant Fine Tuning and Adversarial Label Correction For QA Domain Adaptation
  32. Hardware Acceleration of Explainable Artificial Intelligence
  33. Fuzzy Gene Selection and Cancer Classification Based on Deep Learning Model
  34. Causal Policy Gradient for Whole-Body Mobile Manipulation
  35. Revisiting Table Detection Datasets for Visually Rich Documents
  36. Multi-grained Hypergraph Interest Modeling for Conversational Recommendation
  37. The Application of Affective Measures in Text-based Emotion Aware Recommender Systems
  38. Tuning Traditional Language Processing Approaches for Pashto Text Classification
  39. Stackelberg Games for Learning Emergent Behaviors During Competitive Autocurricula
  40. ChatGPT and Works Scholarly: Best Practices and Legal Pitfalls in Writing with AI
  41. Training Is Everything: Artificial Intelligence, Copyright, and Fair Training
  42. Governance of the AI, by the AI, and for the AI
  43. Leveraging BERT Language Model for Arabic Long Document Classification
  44. Black-box Prompt Tuning with Subspace Learning
  45. Few-shot Domain-Adaptive Visually-fused Event Detection from Text
  46. SI-LSTM: Speaker Hybrid Long-short Term Memory and Cross Modal Attention for Emotion Recognition in Conversation
  47. Automatic Prompt Optimization with "Gradient Descent" and Beam Search
  48. LLM2Loss: Leveraging Language Models for Explainable Model Diagnostics
  49. AttentionViz: A Global View of Transformer Attention
  50. Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages
  51. Enhancing Pashto Text Classification using Language Processing Techniques for Single And Multi-Label Analysis
  52. Employing Hybrid Deep Neural Networks on Dari Speech
  53. Emulation Learning for Neuromimetic Systems
  54. Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing
  55. Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition
  56. A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes
  57. G-MATT: Single-step Retrosynthesis Prediction using Molecular Grammar Tree Transformer
  58. Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching
  59. CAMEL: Co-Designing AI Models and Embedded DRAMs for Efficient On-Device Learning
  60. Influence of various text embeddings on clustering performance in NLP
  61. Contrastive losses as generalized models of global epistasis
  62. The Role of Global and Local Context in Named Entity Recognition
  63. Chain-of-Skills: A Configurable Model for Open-domain Question Answering
  64. Multimodal Understanding Through Correlation Maximization and Minimization
  65. Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations
  66. Calibrating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation
  67. Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
  68. HAISTA-NET: Human Assisted Instance Segmentation Through Attention
  69. Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks
  70. Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainability
  71. A Bootstrap Algorithm for Fast Supervised Learning
  72. Unsupervised anomaly localization in high-resolution breast scans using deep pluralistic image completion
  73. Curating corpora with classifiers: A case study of clean energy sentiment online
  74. Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation
  75. Explaining dark matter halo density profiles with neural networks
  76. Neuro-symbolic model for cantilever beams damage detection
  77. ZipIt! Merging Models from Different Tasks without Training
  78. Tracking through Containers and Occluders in the Wild
  79. Controllable Visual-Tactile Synthesis
  80. NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds
  81. Personalize Segment Anything Model with One Shot
  82. OctFormer: Octree-based Transformers for 3D Point Clouds
  83. Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization
  84. Are VAEs Bad at Reconstructing Molecular Graphs?
  85. TUVF: Learning Generalizable Texture UV Radiance Fields
  86. SuperNOVA: Design Strategies and Opportunities for Interactive Visualization in Computational Notebooks
  87. 3D Reconstruction of Objects in Hands without Real World 3D Supervision
  88. Contrastive Mean Teacher for Domain Adaptive Object Detectors
  89. What changes when you randomly choose BPE merge operations? Not much
  90. NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads
  91. Panda LLM: Training Data and Evaluation for Open-Sourced Chinese Instruction-Following Large Language Models
  92. Improving Code Example Recommendations on Informal Documentation Using BERT and Query-Aware LSH: A Comparative Study
  93. Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence
  94. NatCS: Eliciting Natural Customer Support Dialogues
  95. Evaluating Post-hoc Interpretability with Intrinsic Interpretability
  96. OSDaR23: Open Sensor Data for Rail 2023
  97. When Do Neural Nets Outperform Boosted Trees on Tabular Data?
  98. Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition
  99. Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations
  100. SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data
All 235
  1. Adversarially-Guided Portrait Matting
  2. ExeKGLib: Knowledge Graphs-Empowered Machine Learning Analytics
  3. FUSegNet: A Deep Convolutional Neural Network for Foot Ulcer Segmentation
  4. Majorizing Measures, Codes, and Information
  5. Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality
  6. Rethinking Population-assisted Off-policy Reinforcement Learning
  7. Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training
  8. End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders
  9. Image Captioners Sometimes Tell More Than Images They See
  10. Piecewise Normalizing Flows
  11. Forward-Forward Contrastive Learning
  12. Recent Advances in the Foundations and Applications of Unbiased Learning to Rank
  13. UPDExplainer: an Interpretable Transformer-based Framework for Urban Physical Disorder Detection Using Street View Imagery
  14. Aligning Bird-Eye View Representation of Point Cloud Sequences using Scene Flow
  15. Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning
  16. Additive Class Distinction Maps using Branched-GANs
  17. FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization
  18. APR: Online Distant Point Cloud Registration Through Aggregated Point Cloud Reconstruction
  19. Neuromorphic Sensing for Yawn Detection in Driver Drowsiness
  20. Input Layer Binarization with Bit-Plane Encoding
  21. Simple Noisy Environment Augmentation for Reinforcement Learning
  22. Trainability barriers and opportunities in quantum generative modeling
  23. The AI generation gap: Are Gen Z students more interested in adopting generative AI such as ChatGPT in teaching and learning than their Gen X and Millennial Generation teachers?
  24. Masked Structural Growth for 2x Faster Language Model Pre-training
  25. Hierarchical Transformer for Scalable Graph Learning
  26. CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing
  27. ReMask: A Robust Information-Masking Approach for Domain Counterfactual Generation
  28. Maximum Causal Entropy Inverse Constrained Reinforcement Learning
  29. Impossibility of Depth Reduction in Explainable Clustering
  30. MEDIC: A Multimodal Empathy Dataset in Counseling
  31. Comparison of retinal regions-of-interest imaged by OCT for the classification of intermediate AMD
  32. Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation
  33. Noise-Resistant Multimodal Transformer for Emotion Recognition
  34. MTLSegFormer: Multi-task Learning with Transformers for Semantic Segmentation in Precision Agriculture
  35. Interpretable Sentence Representation with Variational Autoencoders and Attention
  36. The Elephant in the Room: Analyzing the Presence of Big Tech in Natural Language Processing Research
  37. Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning
  38. BranchNorm: Robustly Scaling Extremely Deep Transformers
  39. A Momentum-Incorporated Non-Negative Latent Factorization of Tensors Model for Dynamic Network Representation
  40. Interpretable Regional Descriptors: Hyperbox-Based Local Explanations
  41. Unified Model Learning for Various Neural Machine Translation
  42. Efficient Personalized Federated Learning via Sparse Model-Adaptation
  43. Spatial and Modal Optimal Transport for Fast Cross-Modal MRI Reconstruction
  44. The Politics of Language Choice: How the Russian-Ukrainian War Influences Ukrainians' Language Use on Twitter
  45. Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer
  46. VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets
  47. Multi-Modality Deep Network for JPEG Artifacts Reduction
  48. Disentangled Contrastive Collaborative Filtering
  49. Multi-Domain Learning From Insufficient Annotations
  50. Floaters No More: Radiance Field Gradient Scaling for Improved Near-Camera Training
  51. A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects
  52. A computational framework for human values
  53. Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation
  54. Age-Invariant Face Embedding using the Wasserstein Distance
  55. Incremental 3D Semantic Scene Graph Prediction from RGB Sequences
  56. Human Values in Multiagent Systems
  57. Weakly-supervised Micro- and Macro-expression Spotting Based on Multi-level Consistency
  58. Can Fair Federated Learning reduce the need for Personalisation?
  59. Using Spatio-Temporal Dual-Stream Network with Self-Supervised Learning for Lung Tumor Classification on Radial Probe Endobronchial Ultrasound Video
  60. An Asynchronous Updating Reinforcement Learning Framework for Task-oriented Dialog System
  61. Using interpretable boosting algorithms for modeling environmental and agricultural data
  62. DECICE: Device-Edge-Cloud Intelligent Collaboration Framework
  63. In-situ Anomaly Detection in Additive Manufacturing with Graph Neural Networks
  64. Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning
  65. PGB: A PubMed Graph Benchmark for Heterogeneous Network Representation Learning
  66. Big Data and Large Numbers. Interpreting Zipf's Law
  67. Neighboring Words Affect Human Interpretation of Saliency Explanations
  68. Caption Anything: Interactive Image Description with Diverse Multimodal Controls
  69. Modelling Spatio-Temporal Interactions For Compositional Action Recognition
  70. LatentAugment: Dynamically Optimized Latent Probabilities of Data Augmentation
  71. Learning Language-Specific Layers for Multilingual Machine Translation
  72. Impact Study of Numerical Discretization Accuracy on Parameter Reconstructions and Model Parameter Distributions
  73. Expanding Synthetic Real-World Degradations for Blind Video Super Resolution
  74. On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
  75. Point2Tree(P2T) -- framework for parameter tuning of semantic and instance segmentation used with mobile laser scanning data in coniferous forest
  76. A Constrained BA Algorithm for Rate-Distortion and Distortion-Rate Functions
  77. Edge-aware Consistent Stereo Video Depth Estimation
  78. Neuralizer: General Neuroimage Analysis without Re-Training
  79. Towards Causal Representation Learning and Deconfounding from Indefinite Data
  80. Towards Weakly-Supervised Hate Speech Classification Across Datasets
  81. Conformal Nucleus Sampling
  82. A framework for the emergence and analysis of language in social learning agents
  83. Integrating Psychometrics and Computing Perspectives on Bias and Fairness in Affective Computing: A Case Study of Automated Video Interviews
  84. UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentation
  85. "Oops, Did I Just Say That?" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process
  86. Critical heat flux diagnosis using conditional generative adversarial networks
  87. Semantic-aware Generation of Multi-view Portrait Drawings
  88. Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval
  89. DN at SemEval-2023 Task 12: Low-Resource Language Text Classification via Multilingual Pretrained Language Model Fine-tuning
  90. Re3Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training
  91. Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy
  92. How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning
  93. Semantically Structured Image Compression via Irregular Group-Based Decoupling
  94. On the Expressivity Role of LayerNorm in Transformers' Attention
  95. From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Survey
  96. Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts
  97. Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation
  98. Joint Graph Learning and Model Fitting in Laplacian Regularized Stratified Models
  99. High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning
  100. Unsupervised Domain Adaptation for Neuron Membrane Segmentation based on Structural Features
  101. RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models
  102. Conditional and Residual Methods in Scalable Coding for Humans and Machines
  103. Analyzing Hong Kong's Legal Judgments from a Computational Linguistics point-of-view
  104. Should ChatGPT and Bard Share Revenue with Their Data Providers? A New Business Model for the AI Era
  105. FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
  106. PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits
  107. Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA
  108. Correcting for Interference in Experiments: A Case Study at Douyin
  109. Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder
  110. Cuttlefish: Low-Rank Model Training without All the Tuning
  111. Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization
  112. Point Transformer For Coronary Artery Labeling
  113. Self-Supervised 3D Scene Flow Estimation Guided by Superpoints
  114. Reinforcement Learning with Delayed, Composite, and Partially Anonymous Reward
  115. BitGNN: Unleashing the Performance Potential of Binary Graph Neural Networks on GPUs
  116. ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos
  117. USTC-NELSLIP at SemEval-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex NER
  118. Stimulative Training++: Go Beyond The Performance Limits of Residual Networks
  119. String Diagrams with Factorized Densities
  120. Learning Missing Modal Electronic Health Records with Unified Multi-modal Data Embedding and Modality-Aware Attention
  121. A Cross-direction Task Decoupling Network for Small Logo Detection
  122. AutoML-GPT: Automatic Machine Learning with GPT
  123. Revisiting Graph Contrastive Learning for Anomaly Detection
  124. RCP-RF: A Comprehensive Road-car-pedestrian Risk Management Framework based on Driving Risk Potential Field
  125. Self-Supervised Learning for Organs At Risk and Tumor Segmentation with Uncertainty Quantification
  126. How to Use Reinforcement Learning to Facilitate Future Electricity Market Design? Part 1: A Paradigmatic Theory
  127. Breast Cancer Diagnosis Using Machine Learning Techniques
  128. A new method using deep learning to predict the response to cardiac resynchronization therapy
  129. MLHOps: Machine Learning for Healthcare Operations
  130. Semisupervised regression in latent structure networks on unknown manifolds
  131. Toward the Automated Construction of Probabilistic Knowledge Graphs for the Maritime Domain
  132. Multiplicity Boost Of Transit Signal Classifiers: Validation of 69 New Exoplanets Using The Multiplicity Boost of ExoMiner
  133. The System Model and the User Model: Exploring AI Dashboard Design
  134. Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System
  135. Cognitive Reframing of Negative Thoughts through Human-Language Model Interaction