mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 5 Apr 2024

178 papers

  1. DiffuseMix: Label-Preserving Data Augmentation with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  2. Conditional diffusion models for downscaling and bias correction of Earth system model precipitationDiffusion models → Flow matching, time series and science
  3. Best Response ShapingDeep reinforcement learning methods → RL for games and combinatorial optimization
  4. Exploring Autonomous Agents through the Lens of Large Language Models: A ReviewLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. Fine-Tuning, Quantization, and LLMs: Navigating Unintended OutcomesLLM safety and security → Safety alignment, refusal and guardrails
  6. Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal InputsDiffusion models → 3D, point cloud and scene generation
  7. Why does the two-timescale Q-learning converge to different mean field solutions? A unified convergence analysisDeep reinforcement learning methods → RL for games and combinatorial optimization
  8. Pixel-wise RL on Diffusion Models: Reinforcement Learning from Rich FeedbackDiffusion models → Diffusion and flow policies for robotics +2
  9. Suppressing Modulation Instability with Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  10. Sigma: Siamese Mamba Network for Multi-Modal Semantic SegmentationState-space sequence models (S4, Mamba) → Vision Mamba backbones
  11. Watermark-based Attribution of AI-Generated ContentLLM safety and security → Watermarking generated content and models
  12. Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control ResolutionDeep reinforcement learning methods → RL theory and sample complexity
  13. Identity Decoupling for Multi-Subject Personalization of Text-to-Image ModelsDiffusion models → Image generation, text-to-image and editing
  14. GroundCocoa: A Benchmark for Evaluating Compositional & Conditional Reasoning in Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  15. Continual Policy Distillation of Reinforcement Learning-based Controllers for Soft Robotic In-Hand ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  16. Enhancing IoT Intelligence: A Transformer-based Reinforcement Learning MethodologyDeep reinforcement learning methods → RL for energy, networks and operations
  17. Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated LearningLLM safety and security → Federated unlearning and poisoning
  18. Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical ReportDeep reinforcement learning methods → RL for energy, networks and operations
  19. ROPO: Robust Preference Optimization for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  20. Dynamic Prompt Optimizing for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  21. Label Propagation for Zero-shot Classification with Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  22. Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step GenerationDiffusion models → Diffusion foundations and sampling
  23. Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question AnsweringLLM reasoning → Multimodal reasoning
  24. Demonstration Guided Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  25. Can only LLMs do Reasoning?: Potential of Small Language Models in Task PlanningLLM reasoning → Spatial and embodied reasoning
  26. A proximal policy optimization based intelligent home solar managementDeep reinforcement learning methods → RL for energy, networks and operations
  27. SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language ModelsLLM reasoning → Mathematical reasoning
  28. FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward SkippingEfficient LLM inference and serving → Speculative decoding
  29. Verifiable by Design: Aligning Language Models to Quote from Pre-Training DataLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  30. Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data HeterogeneityMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  31. AI Royalties -- an IP Framework to Compensate Artists & IP Holders for AI-Generated Content
  32. Spectral Image Data Fusion for Multisource Data Augmentation
  33. LookUp3D: Data-Driven 3D Scanning
  34. Influence based explainability of brain tumors segmentation in multimodal Magnetic Resonance Imaging
  35. Statistical Mechanics and Artificial Neural Networks: Principles, Models, and Applications
  36. Using GANs for De Novo Protein Design Targeting Microglial IL-3Rα to Inhibit Alzheimer's Progression
  37. Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response
  38. Physically recurrent neural network for rate and path-dependent heterogeneous materials in a finite strain framework
  39. Advanced simulation-based predictive modelling for solar irradiance sensor farms
  40. Transportation mode recognition based on low-rate acceleration and location signals with an attention-based multiple-instance learning network
  41. Lossless and Near-Lossless Compression for Foundation Models
  42. Multi-Task Learning as enabler for General-Purpose AI-native RAN
  43. Lightweight Geometric Deep Learning for Molecular Modelling in Catalyst Discovery
  44. Effects of Different Prompts on the Quality of GPT-4 Responses to Dementia Care Questions
  45. Sentiment analysis and random forest to classify LLM versus human source applied to Scientific Texts
  46. Taxonomy and Analysis of Sensitive User Queries in Generative AI Search
  47. Implicit Assimilation of Sparse In Situ Data for Dense & Global Storm Surge Forecasting
  48. Physics Event Classification Using Large Language Models
  49. Implicit Bias of AdamW: ℓ_∞ Norm Constrained Optimization
  50. Vision transformers in domain adaptation and domain generalization: a study of robustness
  51. Bounding Causal Effects with Leaky Instruments
  52. Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation
  53. Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations
  54. AI Knowledge and Reasoning: Emulating Expert Creativity in Scientific Research
  55. Robust Few-Shot Ensemble Learning with Focal Diversity-Based Pruning
  56. PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos
  57. Bayesian Additive Regression Networks
  58. PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
  59. The NES Video-Music Database: A Dataset of Symbolic Video Game Music Paired with Gameplay Videos
  60. Dynamic Switch Layers For Unsupervised Learning
  61. Low-Rank Robust Subspace Tensor Clustering for Metro Passenger Flow Modeling
  62. Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer
  63. Generating Synthetic Ground Truth Distributions for Multi-step Trajectory Prediction using Probabilistic Composite B'ezier Curves
  64. Analyzing Participants' Engagement during Online Meetings Using Unsupervised Remote Photoplethysmography with Behavioral Features
  65. Counting Like Transformers: Compiling Temporal Counting Logic Into Softmax Transformers
  66. Mining Potentially Explanatory Patterns via Partial Solutions
  67. LOSS-SLAM: Lightweight Open-Set Semantic Simultaneous Localization and Mapping
  68. ClickDiffusion: Harnessing LLMs for Interactive Precise Image Editing
  69. ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks
  70. Deciphering Political Entity Sentiment in News with Large Language Models: Zero-Shot and Few-Shot Strategies
  71. Prompt Public Large Language Models to Synthesize Data for Private On-device Applications
  72. Assisting humans in complex comparisons: automated information comparison at scale
  73. Koala: Key frame-conditioned long video-LLM
  74. A Repository for Formal Contexts
  75. Scope Ambiguities in Large Language Models
  76. Hypothesis Generation with Large Language Models
  77. SpatialTracker: Tracking Any 2D Pixels in 3D Space
  78. Robust Depth Enhancement via Polarization Prompt Fusion Tuning
  79. DeepLINK-T: deep learning inference for time series data using knockoffs and LSTM
  80. Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
  81. Faraday: Synthetic Smart Meter Generator for the smart grid
  82. JobFormer: Skill-Aware Job Recommendation with Semantic-Enhanced Transformer
  83. Half-Space Feature Learning in Neural Networks
  84. A Real-time Anomaly Detection Using Convolutional Autoencoder with Dynamic Threshold
  85. Visual Knowledge in the Big Model Era: Retrospect and Prospect
  86. AuditGPT: Auditing Smart Contracts with ChatGPT
  87. Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)
  88. Evaluating Adversarial Robustness: A Comparison Of FGSM, Carlini-Wagner Attacks, And The Role of Distillation as Defense Mechanism
  89. Fast Diffeomorphic Image Registration using Patch based Fully Convolutional Networks
  90. Physical Property Understanding from Language-Embedded Feature Fields
  91. Dynamic Conditional Optimal Transport through Simulation-Free Flows
  92. player2vec: A Language Modeling Approach to Understand Player Behavior in Games
  93. Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
  94. Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation
  95. Twins in rotational spectroscopy: Does a rotational spectrum uniquely identify a molecule?
  96. Active Causal Learning for Decoding Chemical Complexities with Targeted Interventions
  97. How Lexical is Bilingual Lexicon Induction?
  98. Multi-modal perception for soft robotic interactions using generative models
  99. Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation
  100. Robust Gaussian Splatting
All 178
  1. Social Skill Training with Large Language Models
  2. Deep-learning Segmentation of Small Volumes in CT images for Radiotherapy Treatment Planning
  3. Exploring Probabilistic Models for Semi-supervised Learning
  4. Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection
  5. SCAResNet: A ResNet Variant Optimized for Tiny Object Detection in Transmission and Distribution Towers
  6. H3DFact: Heterogeneous 3D Integrated CIM for Factorization with Holographic Perceptual Representations
  7. Do Sentence Transformers Learn Quasi-Geospatial Concepts from General Text?
  8. Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model
  9. Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval
  10. Noisy Label Processing for Classification: A Survey
  11. MarsSeg: Mars Surface Semantic Segmentation with Multi-level Extractor and Connector
  12. Context-Aware Aerial Object Detection: Leveraging Inter-Object and Background Relationships
  13. Generalizable Temperature Nowcasting with Physics-Constrained RNNs for Predictive Maintenance of Wind Turbine Components
  14. GNNBENCH: Fair and Productive Benchmarking for Single-GPU GNN System
  15. BEAR: A Unified Framework for Evaluating Relational Knowledge in Causal and Masked Language Models
  16. The Unreasonable Effectiveness Of Early Discarding After One Epoch In Neural Network Hyperparameter Optimization
  17. Large language models as oracles for instantiating ontologies with domain-specific knowledge
  18. SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis
  19. Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo
  20. Hierarchical Neural Additive Models for Interpretable Demand Forecasts
  21. Assessing the quality of information extraction
  22. Does Biomedical Training Lead to Better Medical Performance?
  23. VoicePilot: Harnessing LLMs as Speech Interfaces for Physically Assistive Robots
  24. Fusing Dictionary Learning and Support Vector Machines for Unsupervised Anomaly Detection
  25. Derivative-free tree optimization for complex systems
  26. No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation
  27. Cycle Life Prediction for Lithium-ion Batteries: Machine Learning and More
  28. Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer
  29. Dynamic Risk Assessment Methodology with an LDM-based System for Parking Scenarios
  30. InstructHumans: Editing Animated 3D Human Textures with Instructions
  31. A Dataset for Physical and Abstract Plausibility and Sources of Human Disagreement
  32. Willkommens-Merkel, Chaos-Johnson, and Tore-Klose: Modeling the Evaluative Meaning of German Personal Name Compounds
  33. MM-Gaussian: 3D Gaussian-based Multi-modal Fusion for Localization and Reconstruction in Unbounded Scenes
  34. Framework to generate perfusion map from CT and CTA images in patients with acute ischemic stroke: A longitudinal and cross-sectional study
  35. Good Books are Complex Matters: Gauging Complexity Profiles Across Diverse Categories of Perceived Literary Quality
  36. BuDDIE: A Business Document Dataset for Multi-task Information Extraction
  37. Continual Learning with Weight Interpolation
  38. Approximate UMAP allows for high-rate online visualization of high-dimensional data streams
  39. Finsler-Laplace-Beltrami Operators with Application to Shape Analysis
  40. PHISWID: Physics-Inspired Underwater Image Dataset Synthesized from RGB-D Images
  41. Fast Genetic Algorithm for feature selection -- A qualitative approximation approach
  42. Balancing Progress and Responsibility: A Synthesis of Sustainability Trade-Offs of AI-Based Systems
  43. Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks
  44. Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling
  45. Model Selection with Model Zoo via Graph Learning
  46. Investigating the Robustness of Modelling Decisions for Few-Shot Cross-Topic Stance Detection: A Preregistered Study
  47. ROMA-iQSS: An Objective Alignment Approach via State-Based Value Learning and ROund-Robin Multi-Agent Scheduling
  48. Random Walk in Random Permutation Set Theory
  49. SEME at SemEval-2024 Task 2: Comparing Masked and Generative Language Models on Natural Language Inference for Clinical Trials
  50. Transformers for molecular property prediction: Lessons learned from the past five years
  51. RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications
  52. Re-pseudonymization Strategies for Smart Meter Data Are Not Robust to Deep Learning Profiling Attacks
  53. Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving
  54. Deep Learning for Satellite Image Time Series Analysis: A Review
  55. Real-GDSR: Real-World Guided DSM Super-Resolution via Edge-Enhancing Residual Network
  56. LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation
  57. Learning Correlation Structures for Vision Transformers
  58. Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models
  59. Estimating mixed memberships in multi-layer networks
  60. Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models
  61. Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish
  62. Multi-Task Learning for Lung sound & Lung disease classification
  63. Deep Phase Coded Image Prior
  64. Nonparametric Modern Hopfield Models
  65. VoltaVision: A Transfer Learning model for electronic component classification
  66. Holon: a cybernetic interface for bio-semiotics
  67. KGExplainer: Towards Exploring Connected Subgraph Explanations for Knowledge Graph Completion
  68. Enhancing Breast Cancer Diagnosis in Mammography: Evaluation and Integration of Convolutional Neural Networks and Explainable AI
  69. LiDAR-Guided Cross-Attention Fusion for Hyperspectral Band Selection and Image Classification
  70. A Bi-consolidating Model for Joint Relational Triple Extraction
  71. Wasserstein F-tests for Fr'echet regression on Bures-Wasserstein manifolds
  72. Accurately Classifying Out-Of-Distribution Data in Facial Recognition
  73. Optimizing Convolutional Neural Networks for Identifying Invasive Pollinator Apis Mellifera and Finding a Ligand drug to Protect California's Biodiversity
  74. Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration
  75. Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction
  76. Dimension-free Relaxation Times of Informed MCMC Samplers on Discrete Spaces
  77. Scaling Motion Forecasting Models with Ensemble Distillation
  78. The Low-Degree Hardness of Finding Large Independent Sets in Sparse Random Hypergraphs