mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sat 21 Oct 2023

86 papers

  1. When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical ApplicationsMixture-of-experts → Medical and biomedical MoE
  2. Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  3. CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual EnhancementMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  4. Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChainLLM reasoning → Reasoning for agents, planning and code
  5. Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion ModelsDiffusion models → Audio, speech and music
  6. Fast Diffusion GAN Model for Symbolic Music Generation Controlled by EmotionsDiffusion models → Audio, speech and music
  7. Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMsSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  8. Cold Diffusion on the Replay Buffer: Learning to Plan from Known Good StatesOffline RL and imitation learning from data → Robot manipulation imitation learning
  9. A Robust Adversary Detection-Deactivation Method for Metaverse-oriented Collaborative Deep Learning
  10. AITA Generating Moral Judgements of the Crowd with Reasoning
  11. Application of deep and reinforcement learning to boundary control problems
  12. Optimal Batched Best Arm Identification
  13. Ask To The Point: Open-Domain Entity-Centric Question Generation
  14. Structural generalization in COGS: Supertagging is (almost) all you need
  15. Sentiment Analysis Across Multiple African Languages: A Current Benchmark
  16. Finite-context Indexing of Restricted Output Space for NLP Models Facing Noisy Input
  17. On the Transferability of Visually Grounded PCFGs
  18. Zero-shot Learning of Individualized Task Contrast Prediction from Resting-state Functional Connectomes
  19. Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications
  20. Stabilizing reinforcement learning control: A modular framework for optimizing over all stable behavior
  21. DispersioNET: Joint Inversion of Rayleigh-Wave Multimode Phase Velocity Dispersion Curves using Convolutional Neural Networks
  22. Leveraging Knowledge Graphs for Orphan Entity Allocation in Resume Processing
  23. Learning Reward for Physical Skills using Large Language Model
  24. MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation
  25. A Specialized Semismooth Newton Method for Kernel-Based Optimal Transport
  26. Adaptive, Doubly Optimal No-Regret Learning in Strongly Monotone and Exp-Concave Games with Gradient Feedback
  27. Graph Neural Networks and Applied Linear Algebra
  28. Unleashing Modified Deep Learning Models in Efficient COVID19 Detection
  29. To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders
  30. Ladder Bottom-up Convolutional Bidirectional Variational Autoencoder for Image Translation of Dotted Arabic Expiration Dates
  31. Counterfactual Prediction Under Selective Confounding
  32. Concept-based Anomaly Detection in Retail Stores for Automatic Correction using Mobile Robots
  33. On the Neural Tangent Kernel of Equilibrium Models
  34. Code-Switching with Word Senses for Pretraining in Neural Machine Translation
  35. MeaeQ: Mount Model Extraction Attacks with Efficient Queries
  36. Training Image Derivatives: Increased Accuracy and Universal Robustness
  37. On discretisation drift and smoothness regularisation in neural network training
  38. Tree Prompting: Efficient Task Adaptation without Fine-Tuning
  39. Analysing State-Backed Propaganda Websites: a New Dataset and Linguistic Study
  40. LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions
  41. GASCOM: Graph-based Attentive Semantic Context Modeling for Online Conversation Understanding
  42. Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation
  43. You Only Condense Once: Two Rules for Pruning Condensed Datasets
  44. Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series
  45. One is More: Diverse Perspectives within a Single Network for Efficient DRL
  46. Leveraging Complementary Attention maps in vision transformers for OCT image analysis
  47. Toward Stronger Textual Attack Detectors
  48. Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models
  49. Emulating the Human Mind: A Neural-symbolic Link Prediction Model with Fast and Slow Reasoning and Filtered Rules
  50. On Bilingual Lexicon Induction with Large Language Models
  51. A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification
  52. GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4
  53. HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models
  54. Filling the Missing: Exploring Generative AI for Enhanced Federated Learning over Heterogeneous Mobile Edge Devices
  55. Continual Invariant Risk Minimization
  56. ASBART:Accelerated Soft Bayes Additive Regression Trees
  57. Automatic Pronunciation Assessment -- A Review
  58. Distributed Linear Regression with Compositional Covariates
  59. Transfer Learning for Kernel-based Regression
  60. Linguistically Motivated Sign Language Segmentation
  61. Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment
  62. Competitive Ensembling Teacher-Student Framework for Semi-Supervised Left Atrium MRI Segmentation
  63. Towards dialogue based, computer aided software requirements elicitation
  64. Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMS
  65. Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces
  66. Approximate Implication for Probabilistic Graphical Models
  67. Toward Generative Data Augmentation for Traffic Classification
  68. Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
  69. Equivariant Map and Agent Geometry for Autonomous Driving Motion Prediction
  70. Southern Ocean Dynamics Under Climate Change: New Knowledge Through Physics-Guided Machine Learning
  71. Values, Ethics, Morals? On the Use of Moral Concepts in NLP Research
  72. Pre-Training on Large-Scale Generated Docking Conformations with HelixDock to Unlock the Potential of Protein-ligand Structure Prediction Models
  73. Learning Motion Refinement for Unsupervised Face Animation
  74. Exploring Driving Behavior for Autonomous Vehicles Based on Gramian Angular Field Vision Transformer
  75. Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights
  76. Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
  77. RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization
  78. The Hidden Adversarial Vulnerabilities of Medical Federated Learning
  79. Specify Robust Causal Representation from Mixed Observations
  80. COVIDFakeExplainer: An Explainable Machine Learning based Web Application for Detecting COVID-19 Fake News
  81. Towards a General Framework for Continual Learning with Pre-training
  82. Nonlinear Filtering with Brenier Optimal Transport Maps
  83. Multimodal Transformer Using Cross-Channel attention for Object Detection in Remote Sensing Images
  84. Fast Approximation of Similarity Graphs with Kernel Density Estimation
  85. RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning
  86. Distributionally Robust Optimization with Bias and Variance Reduction