mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 9 Dec 2023

124 papers

  1. Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  2. Steering Llama 2 via Contrastive Activation AdditionMechanistic interpretability → Activation steering methods
  3. Perceptual Similarity guidance and text guidance optimization for Editing Real Images using Guided Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  4. Context Tuning for Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  5. Iterative Token Evaluation and Refinement for Real-World Super-ResolutionDiffusion models → Inverse problems and image restoration
  6. Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic ReasoningLLM reasoning → Mathematical reasoning
  7. Chain-of-Thought in Neural Code Generation: From and For Lightweight Language ModelsLLM reasoning → Reasoning for agents, planning and code
  8. DPoser: Diffusion Model as Robust 3D Human Pose PriorDiffusion models → 3D, point cloud and scene generation
  9. Stateful Large Language Model Serving with PensieveEfficient LLM inference and serving → KV cache optimization
  10. Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  11. FreeFlow: A Comprehensive Understanding on Diffusion Probabilistic Models via Optimal TransportDiffusion models → Diffusion foundations and sampling
  12. BARET : Balanced Attention based Real image Editing driven by Target-text InversionDiffusion models → Image generation, text-to-image and editing
  13. FLoW3 -- Web3 Empowered Federated LearningLLM safety and security → Federated unlearning and poisoning
  14. Consistency Models for Scalable and Fast Simulation-Based InferenceDiffusion models → Flow matching, time series and science
  15. Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  16. Efficient Quantization Strategies for Latent Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  17. Enhancing Financial Data Visualization for Investment Decision-Making
  18. Two Directions for Clinical Data Generation with Large Language Models: Data-to-Label and Label-to-Data
  19. A Cascaded Neural Network System For Rating Student Performance In Surgical Knot Tying Simulation
  20. Labrador: Exploring the Limits of Masked Language Modeling for Laboratory Data
  21. SAR image segmentation algorithms based on I-divergence-TV model
  22. ALGNet: Attention Light Graph Memory Network for Medical Recommendation System
  23. Annotating sleep states in children from wrist-worn accelerometer data using Machine Learning
  24. Distributional Bellman Operators over Mean Embeddings
  25. Performance of externally validated machine learning models based on histopathology images for the diagnosis, classification, prognosis, or treatment outcome prediction in female breast cancer: A systematic review
  26. Evolving Reservoirs for Meta Reinforcement Learning
  27. Robo360: A 3D Omnispective Multi-Material Robotic Manipulation Dataset
  28. Enhanced E-Commerce Attribute Extraction: Innovating with Decorative Relation Correction and LLAMA 2.0-Based Annotation
  29. Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction
  30. Non-Cartesian Self-Supervised Physics-Driven Deep Learning Reconstruction for Highly-Accelerated Multi-Echo Spiral fMRI
  31. Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC
  32. Unsupervised Multi-modal Feature Alignment for Time Series Representation Learning
  33. GPT-4 and Safety Case Generation: An Exploratory Analysis
  34. The Counterattack of CNNs in Self-Supervised Learning: Larger Kernel Size might be All You Need
  35. Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
  36. NLLG Quarterly arXiv Report 09/23: What are the most influential current AI Papers?
  37. Stellar Spectra Fitting with Amortized Neural Posterior Estimation and nbi
  38. Privacy Preserving Multi-Agent Reinforcement Learning in Supply Chains
  39. Batched Low-Rank Adaptation of Foundation Models
  40. Using Think-Aloud Data to Understand Relations between Self-Regulation Cycle Characteristics and Student Performance in Intelligent Tutoring Systems
  41. Position control of an acoustic cavitation bubble by reinforcement learning
  42. Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers
  43. Relevance Feedback with Brain Signals
  44. CoGS: Controllable Gaussian Splatting
  45. Understanding the Effect of Model Compression on Social Bias in Large Language Models
  46. Optimal Unbiased Randomizers for Regression with Label Differential Privacy
  47. PerfRL: A Small Language Model Framework for Efficient Code Optimization
  48. Spectral methods for Neural Integral Equations
  49. Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity
  50. NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification
  51. Speed Up Federated Learning in Heterogeneous Environment: A Dynamic Tiering Approach
  52. Keyword spotting -- Detecting commands in speech using deep learning
  53. PGDS: Pose-Guidance Deep Supervision for Mitigating Clothes-Changing in Person Re-Identification
  54. Subject-Based Domain Adaptation for Facial Expression Recognition
  55. Redefining Developer Assistance: Through Large Language Models in Software Ecosystem
  56. PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching
  57. Transformer as Linear Expansion of Learngene
  58. Triplet Edge Attention for Algorithmic Reasoning
  59. TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence Processing
  60. Sim-GPT: Text Similarity via GPT Annotated Data
  61. EipFormer: Emphasizing Instance Positions in 3D Instance Segmentation
  62. Not All Data Matters: An End-to-End Adaptive Dataset Pruning Framework for Enhancing Model Performance and Efficiency
  63. Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study
  64. Artificial Intelligence in the automatic coding of interviews on Landscape Quality Objectives. Comparison and case study
  65. Factorized Explainer for Graph Neural Networks
  66. Generative AI for Physical Layer Communications: A Survey
  67. A Review of Hybrid and Ensemble in Deep Learning for Natural Language Processing
  68. Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs
  69. Deeper Understanding of Black-box Predictions via Generalized Influence Functions
  70. Enhancing Medical Specialty Assignment to Patients using NLP Techniques
  71. Better Neural PDE Solvers Through Data-Free Mesh Movers
  72. Conditional Stochastic Interpolation for Generative Learning
  73. Dynamic Adjustment of Matching Radii under the Broadcasting Mode: A Novel Multitask Learning Strategy and Temporal Modeling Approach
  74. Revisiting RIP guarantees for sketching operators on mixture models
  75. R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning
  76. Sparse Variational Student-t Processes
  77. Enhancing the Accuracy of Predictors of Activity Sequences of Business Processes
  78. Improving Parameter Training for VQEs by Sequential Hamiltonian Assembly
  79. Multi-dimensional Fair Federated Learning
  80. D3A-TS: Denoising-Driven Data Augmentation in Time Series
  81. Multi-granularity Causal Structure Learning
  82. A Unified Multi-Phase CT Synthesis and Classification Framework for Kidney Cancer Diagnosis with Incomplete Data
  83. Signatures Meet Dynamic Programming: Generalizing Bellman Equations for Trajectory Following
  84. Federated Causality Learning with Explainable Adaptive Optimization
  85. CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen
  86. KEN: Kernel Extensions using Natural Language
  87. Exploring 3D U-Net Training Configurations and Post-Processing Strategies for the MICCAI 2023 Kidney and Tumor Segmentation Challenge
  88. Reinforcement Neighborhood Selection for Unsupervised Graph Anomaly Detection
  89. You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
  90. Augmenty: A Python Library for Structured Text Augmentation
  91. Isomorphic-Consistent Variational Graph Auto-Encoders for Multi-Level Graph Representation Learning
  92. Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
  93. Poisoning × Evasion: Symbiotic Adversarial Robustness for Graph Neural Networks
  94. History Matters: Temporal Knowledge Editing in Large Language Model
  95. Implicit Steganography Beyond the Constraints of Modality
  96. Using Captum to Explain Generative Language Models
  97. Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification
  98. Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis
  99. Teamwork Dimensions Classification Using BERT
  100. Exploring Sparsity in Graph Transformers
All 124
  1. Exploring the Naturalness of AI-Generated Images
  2. Self Model for Embodied Intelligence: Modeling Full-Body Human Musculoskeletal System and Locomotion Control with Hierarchical Low-Dimensional Representation
  3. Spectroscopy-Guided Discovery of Three-Dimensional Structures of Disordered Materials with Diffusion Models
  4. Fine-Grained Analysis of Team Collaborative Dialogue
  5. Image and Data Mining in Reticular Chemistry Using GPT-4V
  6. Textual Toxicity in Social Media: Understanding the Bangla Toxic Language Expressed in Facebook Comment
  7. On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR
  8. Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation
  9. HumanReg: Self-supervised Non-rigid Registration of Human Point Cloud
  10. STREAMLINE: An Automated Machine Learning Pipeline for Biomedicine Applied to Examine the Utility of Photography-Based Phenotypes for OSA Prediction Across International Sleep Centers
  11. Multi-source domain adaptation for regression
  12. On the calibration of compartmental epidemiological models
  13. Model Evaluation for Domain Identification of Unknown Classes in Open-World Recognition: A Proposal
  14. TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot Image Classification
  15. Domain Adaptation of a State of the Art Text-to-SQL Model: Lessons Learned and Challenges Found
  16. From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos
  17. Rate-Distortion-Perception Theory for Semantic Communication
  18. Enhancing Robustness of Foundation Model Representations under Provenance-related Distribution Shifts
  19. Stochastic Directly-Follows Process Discovery Using Grammatical Inference
  20. Fusing Multiple Algorithms for Heterogeneous Online Learning
  21. FT2TF: First-Person Statement Text-To-Talking Face Generation
  22. Mitigating Nonlinear Algorithmic Bias in Binary Classification
  23. Bauer's Spectral Factorization Method for Low Order Multiwavelet Filter Design
  24. ESPN: Memory-Efficient Multi-Vector Information Retrieval