mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 30 Jan 2023

220 papers

  1. Multi-modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense ReasoningLLM reasoning → Multimodal reasoning +1
  2. Incorporating Recurrent Reinforcement Learning into Model Predictive Control for Adaptive Control in Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
  3. Understanding Self-Distillation in the Presence of Label NoiseKnowledge distillation → General knowledge distillation methods
  4. ArchiSound: Audio Generation with DiffusionDiffusion models → Audio, speech and music
  5. Extracting Training Data from Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  6. Optimal Decision Tree Policies for Markov Decision ProcessesOffline RL and imitation learning from data → Offline RL algorithms
  7. STEEL: Singularity-aware Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  8. Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation PoliciesOffline RL and imitation learning from data → Real-world robot offline RL
  9. Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical DistillationKnowledge distillation → Speech and audio distillation
  10. Hierarchical Imitation Learning with Vector Quantized ModelsOffline RL and imitation learning from data → Imitation learning methods
  11. GALIP: Generative Adversarial CLIPs for Text-to-Image SynthesisDiffusion models → Image generation, text-to-image and editing
  12. ERA-Solver: Error-Robust Adams Solver for Fast Sampling of Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
  13. On student-teacher deviations in distillation: does it pay to disobey?Knowledge distillation → General knowledge distillation methods
  14. PromptMix: Text-to-image diffusion models enhance the performance of lightweight networksDiffusion models → Image generation, text-to-image and editing
  15. Guiding Online Reinforcement Learning with Action-Free Offline PretrainingOffline RL and imitation learning from data → Offline RL algorithms
  16. Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and ToxicityLLM safety and security → Prompt injection and agent security
  17. Direct Preference-based Policy Optimization without Reward ModelingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  18. FractalAD: A simple industrial anomaly detection method using fractal anomaly generation and backbone knowledge distillationKnowledge distillation → Detection and dense prediction distillation
  19. Specializing Smaller Language Models towards Multi-Step ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  20. Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  21. GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion RestorationDiffusion models → Inverse problems and image restoration
  22. Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion ModelsDiffusion models → Audio, speech and music
  23. REPLUG: Retrieval-Augmented Black-Box Language ModelsRetrieval-augmented generation → Generation and context integration
  24. MAKE: Vision-Language Pre-training based Product Retrieval in Taobao SearchMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  25. Knowledge Distillation ≈ Label Smoothing: Fact or Fallacy?Knowledge distillation → General knowledge distillation methods
  26. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  27. Chebyshev distances associated to the second members of systems of Max-product/Lukasiewicz Fuzzy relational equations
  28. ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text
  29. CSDN: Combing Shallow and Deep Networks for Accurate Real-time Segmentation of High-definition Intravascular Ultrasound Images
  30. DAFD: Domain Adaptation via Feature Disentanglement for Image Classification
  31. The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learning
  32. A Bias-Accuracy-Privacy Trilemma for Statistical Estimation
  33. Neural Operator: Is data all you need to model the world? An insight into the paradigm of data-driven scientific ML
  34. Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference
  35. On the Complexity of Enumerating Prime Implicants from Decision-DNNF Circuits
  36. A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback
  37. V2N Service Scaling with Deep Reinforcement Learning
  38. Fairness and Accuracy under Domain Generalization
  39. ParticleSeg3D: A Scalable Out-of-the-Box Deep Learning Segmentation Solution for Individual Particle Characterization from Micro CT Images in Mineral Processing and Recycling
  40. Proxy-based Zero-Shot Entity Linking by Effective Candidate Retrieval
  41. Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization
  42. Alternating Updates for Efficient Transformers
  43. Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics
  44. Variational sparse inverse Cholesky approximation for latent Gaussian processes via double Kullback-Leibler minimization
  45. LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization
  46. Adaptive Machine Translation with Large Language Models
  47. Overcoming Simplicity Bias in Deep Networks using a Feature Sieve
  48. On the Statistical Benefits of Temporal Difference Learning
  49. Team Plan Recognition: A Review of the State of the Art
  50. MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning
  51. Learning Coordination Policies over Heterogeneous Graphs for Human-Robot Teams via Recurrent Neural Schedule Propagation
  52. Distributed Swarm Intelligence
  53. Near Optimal Private and Robust Linear Regression
  54. Probabilistic Neural Data Fusion for Learning from an Arbitrary Number of Multi-fidelity Data Sets
  55. Structure Learning and Parameter Estimation for Graphical Models via Penalized Maximum Likelihood Methods
  56. Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems
  57. Temporal Consistency Loss for Physics-Informed Neural Networks
  58. Emergence of Maps in the Memories of Blind Navigation Agents
  59. Deep Monocular Hazard Detection for Safe Small Body Landing
  60. Meta-Learning Adaptive Loss Functions
  61. Conversational Automated Program Repair
  62. Mono-STAR: Mono-camera Scene-level Tracking and Reconstruction
  63. Policy Gradient with Tree Expansion
  64. Streaming Anomaly Detection
  65. Unlocking Slot Attention by Changing Optimal Transport Costs
  66. Looped Transformers as Programmable Computers
  67. Adaptive Computation with Elastic Input Sequence
  68. Polynomial Preconditioning for Gradient Methods
  69. Robust empirical risk minimization via Newton's method
  70. Audio-Visual Segmentation with Semantics
  71. Accurate Gaze Estimation using an Active-gaze Morphable Model
  72. Learning Control from Raw Position Measurements
  73. Shape-aware Text-driven Layered Video Editing
  74. Improved machine learning algorithm for predicting ground state properties
  75. ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
  76. SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition
  77. Advancing Radiograph Representation Learning with Masked Record Modeling
  78. Protein Representation Learning via Knowledge Enhanced Primary Structure Modeling
  79. Convolutional Neural Network-Based Automatic Classification of Colorectal and Prostate Tumor Biopsies Using Multispectral Imagery: System Development Study
  80. Self-Compressing Neural Networks
  81. Consistency Regularisation in Varying Contexts and Feature Perturbations for Semi-Supervised Semantic Segmentation of Histology Images
  82. A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
  83. Towards the Linear Algebra Based Taxonomy of XAI Explanations
  84. Contrastive Meta-Learning for Partially Observable Few-Shot Learning
  85. Falsification of Internal and External Validity in Observational Studies via Conditional Moment Restrictions
  86. Standardized CycleGAN training for unsupervised stain adaptation in invasive carcinoma classification for breast histopathology
  87. LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain
  88. Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification
  89. Doubly Optimal No-Regret Learning in Monotone Games
  90. A Fully-Automated Framework Integrating Gaussian Process Regression and Bayesian Optimization to Design Pin-Fins
  91. Benchmarking optimality of time series classification methods in distinguishing diffusions
  92. Generalization on the Unseen, Logic Reasoning and Degree Curriculum
  93. Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models
  94. Prediction of Customer Churn in Banking Industry
  95. CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy
  96. Language-Driven Anchors for Zero-Shot Adversarial Robustness
  97. Optimal Approximation Complexity of High-Dimensional Functions with Neural Networks
  98. Action Capsules: Human Skeleton Action Recognition
  99. Can an AI Win Ghana's National Science and Maths Quiz? An AI Grand Challenge for Education
  100. Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces II: non-compact symmetric spaces
All 220
  1. Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation
  2. Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off
  3. PaCaNet: A Study on CycleGAN with Transfer Learning for Diversifying Fused Chinese Painting and Calligraphy
  4. STAIR: Learning Sparse Text and Image Representation in Grounded Tokens
  5. A Human Word Association based model for topic detection in social networks
  6. Operator Fusion in XLA: Analysis and Evaluation
  7. Zero-One Laws of Graph Neural Networks
  8. The Secret of Metaphor on Expressing Stronger Emotion
  9. Representation biases in sentence transformers
  10. Federated Learning for Water Consumption Forecasting in Smart Cities
  11. BSSAD: Towards A Novel Bayesian State-Space Approach for Anomaly Detection in Multivariate Time Series
  12. On the Efficacy of Metrics to Describe Adversarial Attacks
  13. DELTA: degradation-free fully test-time adaptation
  14. Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods
  15. FedFA: Federated Feature Augmentation
  16. Benchmarking Robustness to Adversarial Image Obfuscations
  17. The Optimal Choice of Hypothesis Is the Weakest, Not the Shortest
  18. MOSAIC, acomparison framework for machine learning models
  19. Integrating Earth Observation Data into Causal Inference: Challenges and Opportunities
  20. ContCommRTD: A Distributed Content-based Misinformation-aware Community Detection System for Real-Time Disaster Reporting
  21. Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scene
  22. Quantifying Context Mixing in Transformers
  23. Using n-aksaras to model Sanskrit and Sanskrit-adjacent texts
  24. Improving Adversarial Transferability with Scheduled Step Size and Dual Example
  25. Hierarchical learning, forecasting coherent spatio-temporal individual and aggregated building loads
  26. Quadratic Matrix Factorization with Applications to Manifold Learning
  27. Unraveling Privacy Risks of Individual Fairness in Graph Neural Networks
  28. Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs
  29. Factors that affect Camera based Self-Monitoring of Vitals in the Wild
  30. Refined Regret for Adversarial MDPs with Linear Function Approximation
  31. Data-driven soiling detection in PV modules
  32. Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?
  33. Active Learning for Multilingual Semantic Parser
  34. Curvature Filtrations for Graph Generative Model Evaluation
  35. Long Short-Term Memory Neural Network for Temperature Prediction in Laser Powder Bed Additive Manufacturing
  36. DepGraph: Towards Any Structural Pruning
  37. Identifying Adversarially Attackable and Robust Samples
  38. Deep learning numerical methods for high-dimensional fully nonlinear PIDEs and coupled FBSDEs with jumps
  39. Formalizing Piecewise Affine Activation Functions of Neural Networks in Coq
  40. Half of an image is enough for quality assessment
  41. Modelling the performance of delivery vehicles across urban micro-regions to accelerate the transition to cargo-bike logistics
  42. Extremal Domain Translation with Neural Optimal Transport
  43. Approximating DTW with a convolutional neural network on EEG data
  44. A Machine Learning approach for correcting radial velocities using physical observables
  45. On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex
  46. N-Gram Nearest Neighbor Machine Translation
  47. SMDP-Based Dynamic Batching for Efficient Inference on GPU-Based Platforms
  48. Minimalistic Predictions to Schedule Jobs with Online Precedence Constraints
  49. Massively Scaling Heteroscedastic Classifiers
  50. How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification
  51. GE-Blender: Graph-Based Knowledge Enhancement for Blender
  52. Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks
  53. Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?
  54. Deep networks for system identification: a Survey
  55. M3FAS: An Accurate and Robust MultiModal Mobile Face Anti-Spoofing System
  56. YOLO-based Object Detection in Industry 4.0 Fischertechnik Model Environment
  57. Evaluating COVID-19 vaccine allocation policies using Bayesian m-top exploration
  58. Transferring Multiple Policies to Hotstart Reinforcement Learning in an Air Compressor Management Problem
  59. SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
  60. Crawling the Internal Knowledge-Base of Language Models
  61. The Hidden Power of Pure 16-bit Floating-Point Neural Networks
  62. EDSA-Ensemble: an Event Detection Sentiment Analysis Ensemble Architecture
  63. Planning Multiple Epidemic Interventions with Reinforcement Learning
  64. Behavioural Reports of Multi-Stage Malware
  65. Eye Image-based Algorithms to Estimate Percentage Closure of Eye and Saccadic Ratio for Alertness Detection
  66. Reliable Federated Disentangling Network for Non-IID Domain Feature
  67. Rendering the Directional TSDF for Tracking and Multi-Sensor Registration with Point-To-Plane Scale ICP
  68. Equivariant Architectures for Learning in Deep Weight Spaces
  69. Reassessing feature-based Android malware detection in a contemporary context
  70. PAC-Bayesian Soft Actor-Critic Learning
  71. Compression, Generalization and Learning
  72. Causality-based CTR Prediction using Graph Neural Networks
  73. Efficient Node Selection in Private Personalized Decentralized Learning
  74. PointSmile: Point Self-supervised Learning via Curriculum Mutual Information
  75. On Second-Order Scoring Rules for Epistemic Uncertainty Quantification
  76. Response-act Guided Reinforced Dialogue Generation for Mental Health Counseling
  77. Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transport
  78. Automatic Intersection Management in Mixed Traffic Using Reinforcement Learning and Graph Neural Networks
  79. Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features
  80. UzbekTagger: The rule-based POS tagger for Uzbek language
  81. Machine Learning with High-Cardinality Categorical Features in Actuarial Applications
  82. KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation
  83. Robust Meta Learning for Image based tasks
  84. Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels
  85. Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production
  86. Image Contrast Enhancement using Fuzzy Technique with Parameter Determination using Metaheuristics
  87. Distributed Stochastic Optimization under a General Variance Condition
  88. Optimal Decision Trees For Interpretable Clustering with Constraints (Extended Version)
  89. A deep-learning search for technosignatures of 820 nearby stars
  90. NeSyFOLD: Neurosymbolic Framework for Interpretable Image Classification
  91. Solving High-Dimensional PDEs with Latent Spectral Models
  92. SingSong: Generating musical accompaniments from singing
  93. Zero-shot Clarifying Question Generation for Conversational Search
  94. Complex Critical Points of Deep Linear Neural Networks
  95. Convergence of uncertainty estimates in Ensemble and Bayesian sparse model discovery
  96. Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval
  97. Adversarial Style Augmentation for Domain Generalization
  98. Exploring the Constructicon: Linguistic Analysis of a Computational CxG
  99. Reweighted Interacting Langevin Diffusions: an Accelerated Sampling Methodfor Optimization
  100. Lateralized Learning for Multi-Class Visual Classification Tasks
  101. Exploring Image Augmentations for Siamese Representation Learning with Chest X-Rays
  102. Learning the Kalman Filter with Fine-Grained Sample Complexity
  103. FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscation
  104. ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning
  105. Regularized Weight Aggregation in Networked Federated Learning for Glioblastoma Segmentation
  106. Active Sequential Two-Sample Testing
  107. RREx-BoT: Remote Referring Expressions with a Bag of Tricks
  108. AudioEar: Single-View Ear Reconstruction for Personalized Spatial Audio
  109. SSR-TA: Sequence to Sequence based expert recurrent recommendation for ticket automation
  110. Evaluating Neuron Interpretation Methods of NLP Models
  111. Traffic Prediction in Cellular Networks using Graph Neural Networks
  112. Do We Really Need Graph Neural Networks for Traffic Forecasting?
  113. Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents
  114. Bagging Provides Assumption-free Stability
  115. Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining
  116. Adversarial Attacks on Adversarial Bandits
  117. A theory of continuous generative flow networks
  118. Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning
  119. Ensemble Learning for Fusion of Multiview Vision with Occlusion and Missing Information: Framework and Evaluations with Real-World Data and Applications in Driver Hand Activity Recognition
  120. RGB Arabic Alphabets Sign Language Dataset