mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 29 Oct 2023

140 papers

  1. DiffSpectralNet : Unveiling the Potential of Diffusion Models for Hyperspectral Image ClassificationDiffusion models → Inverse problems and image restoration
  2. Learning to Follow Object-Centric Image Editing Instructions FaithfullyDiffusion models → Image generation, text-to-image and editing
  3. Atom: Low-bit Quantization for Efficient and Accurate LLM ServingEfficient LLM inference and serving → KV cache quantization
  4. Reward Finetuning for Faster and More Accurate Unsupervised Object DiscoveryLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  5. Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  6. Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4VMultimodal LLMs / vision-language models → Medical vision-language models
  7. TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling LikewiseLLM reasoning → Reasoning benchmarks and evaluation
  8. Language Agents with Reinforcement Learning for Strategic Play in the Werewolf GameLLM agents and tool use → Reinforcement learning for LLM agents
  9. Label Poisoning is All You NeedLLM safety and security → Backdoor and data poisoning attacks
  10. Ever Evolving Evaluator (EV3): Towards Flexible and Reliable Meta-Optimization for Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  11. Towards Generalized Multi-stage Clustering: Multi-view Self-distillationKnowledge distillation → General knowledge distillation methods
  12. MUST: A Multilingual Student-Teacher Learning approach for low-resource speech recognitionKnowledge distillation → Speech and audio distillation
  13. SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts ModelsMixture-of-experts → Efficient MoE training and inference systems
  14. Comparison of Microservice Call Rate Predictions for Replication in the Cloud
  15. FLORIDA: Fake-looking Real Images Dataset
  16. Variational Autoencoders for Noise Reduction in Industrial LLRF Systems
  17. CrossEAI: Using Explainable AI to generate better bounding boxes for Chest X-ray images
  18. AMIR: Automated MisInformation Rebuttal -- A COVID-19 Vaccination Datasets based Recommendation System
  19. Improved Motor Imagery Classification Using Adaptive Spatial Filters Based on Particle Swarm Optimization Algorithm
  20. Enhancing Motor Imagery Decoding in Brain Computer Interfaces using Riemann Tangent Space Mapping and Cross Frequency Coupling
  21. Emergence of Grid-like Representations by Training Recurrent Networks with Conformal Normalization
  22. 3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets
  23. Fast Trainable Projection for Robust Fine-Tuning
  24. From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude
  25. JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation
  26. Robustifying Language Models with Test-Time Adaptation
  27. Predicting recovery following stroke: deep learning, multimodal data and feature selection using explainable AI
  28. BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping
  29. Rare Event Probability Learning by Normalizing Flows
  30. The Power of Explainability in Forecast-Informed Deep Learning Models for Flood Mitigation
  31. RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulation
  32. Transfer Learning in Transformer-Based Demand Forecasting For Home Energy Management System
  33. Poisoning Retrieval Corpora by Injecting Adversarial Passages
  34. Real-World Implementation of Reinforcement Learning Based Energy Coordination for a Cluster of Households
  35. BERT Lost Patience Won't Be Robust to Adversarial Slowdown
  36. MAG-GNN: Reinforcement Learning Boosted Graph Neural Network
  37. Backward and Forward Inference in Interacting Independent-Cascade Processes: A Scalable and Convergent Message-Passing Approach
  38. Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning
  39. Women Wearing Lipstick: Measuring the Bias Between an Object and Its Related Gender
  40. Unified Representation for Non-compositional and Compositional Expressions
  41. Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations
  42. Good Tools are Half the Work: Tool Usage in Deep Learning Projects
  43. Three Dogmas, a Puzzle and its Solution
  44. Out-of-distribution Object Detection through Bayesian Uncertainty Estimation
  45. Dynamic V2X Autonomous Perception from Road-to-Vehicle Vision
  46. Efficient IoT Inference via Context-Awareness
  47. Dynamic Task and Weight Prioritization Curriculum Learning for Multimodal Imagery
  48. PACuna: Automated Fine-Tuning of Language Models for Particle Accelerators
  49. Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
  50. Web3 Meets AI Marketplace: Exploring Opportunities, Analyzing Challenges, and Suggesting Solutions
  51. Bridging the gap: Towards an Expanded Toolkit for AI-driven Decision-Making in the Public Sector
  52. Pushdown Layers: Encoding Recursive Structure in Transformer Language Models
  53. Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention
  54. Bespoke Solvers for Generative Flow Models
  55. Efficient Cluster Selection for Personalized Federated Learning: A Multi-Armed Bandit Approach
  56. Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming
  57. Gauge-optimal approximate learning for small data classification problems
  58. Evaluating LLP Methods: Challenges and Approaches
  59. Apple Tasting: Combinatorial Dimensions and Minimax Rates
  60. Feature Aggregation in Joint Sound Classification and Localization Neural Networks
  61. A multi-modal table tennis robot system
  62. TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
  63. Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression
  64. A Unique Training Strategy to Enhance Language Models Capabilities for Health Mention Detection from Social Media Content
  65. MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
  66. A Few-Shot Learning Focused Survey on Recent Named Entity Recognition and Relation Classification Methods
  67. Object-centric architectures enable efficient causal representation learning
  68. Datasets and Benchmarks for Nanophotonic Structure and Parametric Design Simulations
  69. Exploring the Emotional Landscape of Music: An Analysis of Valence Trends and Genre Variations in Spotify Music Data
  70. Differentially Private Permutation Tests
  71. On Linear Separation Capacity of Self-Supervised Representation Learning
  72. Machine Learning for the identification of phase-transitions in interacting agent-based systems: a Desai-Zwanzig example
  73. Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors
  74. Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
  75. ArBanking77: Intent Detection Neural Model and a New Dataset in Modern and Dialectical Arabic
  76. SALMA: Arabic Sense-Annotated Corpus and WSD Benchmarks
  77. An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits
  78. FPGAN-Control: A Controllable Fingerprint Generator for Training with Synthetic Data
  79. Optimization Landscape of Policy Gradient Methods for Discrete-time Static Output Feedback
  80. Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction
  81. Behavior Alignment via Reward Function Optimization
  82. Kernel-based Joint Multiple Graph Learning and Clustering of Graph Signals
  83. Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation
  84. DynPoint: Dynamic Neural Point For View Synthesis
  85. Bipartite Graph Pre-training for Unsupervised Extractive Summarization with Graph Convolutional Auto-Encoders
  86. A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning
  87. Path Analysis for Effective Fault Localization in Deep Neural Networks
  88. Controllable Group Choreography using Contrastive Diffusion
  89. DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding
  90. Blacksmith: Fast Adversarial Training of Vision Transformers via a Mixture of Single-step and Multi-step Methods
  91. EtiCor: Corpus for Analyzing LLMs for Etiquettes
  92. TRIAGE: Characterizing and auditing training data for improved regression
  93. Analyzing Vision Transformers for Image Classification in Class Embedding Space
  94. Spacecraft Autonomous Decision-Planning for Collision Avoidance: a Reinforcement Learning Approach
  95. LLMs and Finetuning: Benchmarking cross-domain performance for hate speech detection
  96. AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
  97. End-to-End Autoregressive Retrieval via Bootstrapping for Smart Reply Systems
  98. Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
  99. Mask Propagation for Efficient Video Semantic Segmentation
  100. TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression
All 140
  1. Customize StyleGAN with One Hand Sketch
  2. Multi-Path Long-Term Vessel Trajectories Forecasting with Probabilistic Feature Fusion for Problem Shifting
  3. Video Frame Interpolation with Many-to-many Splatting and Spatial Selective Refinement
  4. S2F-NER: Exploring Sequence-to-Forest Generation for Complex Entity Recognition
  5. Machine Learning Algorithms to Predict Chess960 Result and Develop Opening Themes
  6. The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomes
  7. Adversarial Examples Are Not Real Features
  8. Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data
  9. Self Attention with Temporal Prior: Can We Learn More from Arrow of Time?
  10. Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning
  11. A transfer learning approach with convolutional neural network for Face Mask Detection
  12. CHAIN: Exploring Global-Local Spatio-Temporal Information for Improved Self-Supervised Video Hashing
  13. Remaining useful life prediction of Lithium-ion batteries using spatio-temporal multimodal attention networks
  14. QWID: Quantized Weed Identification Deep neural network
  15. Improving Multi-Person Pose Tracking with A Confidence Network
  16. Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
  17. Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach
  18. TivNe-SLAM: Dynamic Mapping and Tracking via Time-Varying Neural Radiance Fields
  19. Debiasing Algorithm through Model Adaptation
  20. Sentence Bag Graph Formulation for Biomedical Distant Supervision Relation Extraction
  21. InstanT: Semi-supervised Learning with Instance-dependent Thresholds
  22. Estimating the Rate-Distortion Function by Wasserstein Gradient Descent
  23. Topological, or Non-topological? A Deep Learning Based Prediction
  24. Stacking the Odds: Transformer-Based Ensemble for AI-Generated Text Detection
  25. Identifiable Contrastive Learning with Automatic Feature Importance Discovery
  26. Multi-task deep learning for large-scale building detail extraction from high-resolution satellite imagery
  27. Differentiable DG with Neural Operator Source Term Correction
  28. Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity
  29. D2NO: Efficient Handling of Heterogeneous Input Function Spaces with Distributed Deep Neural Operators
  30. Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes
  31. A foundational neural operator that continuously learns without forgetting
  32. Simple and Asymmetric Graph Contrastive Learning without Augmentations
  33. Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks
  34. Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition
  35. HDMNet: A Hierarchical Matching Network with Double Attention for Large-scale Outdoor LiDAR Point Cloud Registration
  36. Correlation Aware Sparsified Mean Estimation Using Random Projection
  37. Prompt-Engineering and Transformer-based Question Generation and Evaluation
  38. Counterfactually Probing Language Identity in Multilingual Models
  39. Peer-to-Peer Deep Learning for Beyond-5G IoT
  40. Bayes beats Cross Validation: Efficient and Accurate Ridge Regression via Expectation Maximization