mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 16 Feb 2023

197 papers

  1. Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic DimensionDiffusion models → Image generation, text-to-image and editing
  2. LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  3. What A Situated Language-Using Agent Must be Able to Do: A Top-Down AnalysisLLM agents and tool use → General LLM agent frameworks and benchmarks
  4. Pretraining Language Models with Human PreferencesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  5. Dual RL: Unification and New Methods for Reinforcement and Imitation LearningOffline RL and imitation learning from data → Offline RL algorithms
  6. Text-driven Visual Synthesis with Latent Diffusion PriorDiffusion models → Image generation, text-to-image and editing
  7. LEVER: Learning to Verify Language-to-Code Generation with ExecutionLLM reasoning → Reasoning for agents, planning and code
  8. ST-MFNet Mini: Knowledge Distillation-Driven Frame InterpolationKnowledge distillation → General knowledge distillation methods
  9. T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  10. LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  11. Boundary Guided Learning-Free Semantic Control with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  12. Retrieval-augmented Image CaptioningRetrieval-augmented generation → Multimodal RAG
  13. DIFUSCO: Graph-based Diffusion Solvers for Combinatorial OptimizationDiffusion models → Diffusion foundations and sampling
  14. Aligning Language Models with Preferences through f-divergence MinimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  15. Cross Modal Distillation for Flood Extent MappingKnowledge distillation → Detection and dense prediction distillation
  16. Learning From Biased Soft LabelsKnowledge distillation → General knowledge distillation methods
  17. Empirical Investigation of Neural Symbolic Reasoning StrategiesLLM reasoning → Reasoning benchmarks and evaluation
  18. MultiDiffusion: Fusing Diffusion Paths for Controlled Image GenerationDiffusion models → Image generation, text-to-image and editing
  19. Fuzzy Knowledge Distillation from High-Order TSK to Low-Order TSKKnowledge distillation → General knowledge distillation methods
  20. Object-centric Learning with Cyclic Walks between Parts and WholeLLM reasoning → Multimodal reasoning
  21. AI Risk Skepticism, A Comprehensive Survey
  22. Gaussian Switch Sampling: A Second Order Approach to Active Learning
  23. GLUECons: A Generic Benchmark for Learning Under Constraints
  24. Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers
  25. Distributed Learning in Heterogeneous Environment: federated learning with adaptive aggregation and computation reduction
  26. Generalization algorithm of multimodal pre-training model based on graph-text self-supervised training
  27. Dynamic Named Entity Recognition
  28. A Generative Adversarial Network for Climate Tipping Point Discovery (TIP-GAN)
  29. SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry
  30. E2E Spoken Entity Extraction for Virtual Agents
  31. Stabilising and accelerating light gated recurrent units for automatic speech recognition
  32. Bridge the Gap between Language models and Tabular Understanding
  33. Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production
  34. Rejecting Cognitivism: Computational Phenomenology for Deep Learning
  35. Empathetic AI for Empowering Resilience in Games
  36. Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification
  37. Fashion Image Retrieval with Multi-Granular Alignment
  38. Physics-based parameterized neural ordinary differential equations: prediction of laser ignition in a rocket combustor
  39. InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis
  40. A Hybrid Chimp Optimization Algorithm and Generalized Normal Distribution Algorithm with Opposition-Based Learning Strategy for Solving Data Clustering Problems
  41. Distances for Markov Chains, and Their Differentiation
  42. SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detection
  43. Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning
  44. Robust expected improvement for Bayesian optimization
  45. Intrinsic and extrinsic deep learning on manifolds
  46. Using Explainable AI to Cross-Validate Socio-economic Disparities Among Covid-19 Patient Mortality
  47. On the Role of Memory in Robust Opinion Dynamics
  48. Frequency-domain Learning for Volumetric-based 3D Data Perception
  49. TransUPR: A Transformer-based Uncertain Point Refiner for LiDAR Point Cloud Semantic Segmentation
  50. Syntactic Structure Processing in the Brain while Listening
  51. MM Algorithms to Estimate Parameters in Continuous-time Markov Chains
  52. JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
  53. Online Learning Guided Curvature Approximation: A Quasi-Newton Method with Global Non-Asymptotic Superlinear Convergence
  54. For Generated Text, Is NLI-Neutral Text the Best Text?
  55. Foundation Models for Natural Language Processing -- Pre-trained Language Models Integrating Media
  56. Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers
  57. A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
  58. Generative Adversarial Networks for Malware Detection: a Survey
  59. Infinite Action Contextual Bandits with Reusable Data Exhaust
  60. THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression
  61. Federated Learning as a Network Effects Game
  62. Learning with Rejection for Abstractive Text Summarization
  63. 3D-aware Conditional Image Synthesis
  64. The Scope of Multicalibration: Characterizing Multicalibration via Property Elicitation
  65. PersonNeRF: Personalized Reconstruction from Photo Collections
  66. Auditing large language models: a three-layered approach
  67. FOSI: Hybrid First and Second Order Optimization
  68. Local-to-Global Information Communication for Real-Time Semantic Segmentation Network Search
  69. Tools for Landscape Analysis of Optimisation Problems in Procedural Content Generation for Games
  70. Kernelized Back-Projection Networks for Blind Super Resolution
  71. Counting Carbon: A Survey of Factors Influencing the Emissions of Machine Learning
  72. Efficient 3D Object Reconstruction using Visual Transformers
  73. Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators
  74. Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data
  75. Evaluating and Improving the Coreference Capabilities of Machine Translation Models
  76. GP CC-OPF: Gaussian Process based optimization tool for Chance-Constrained Optimal Power Flow
  77. Assisting Human Decisions in Document Matching
  78. Graph Neural Networks over the Air for Decentralized Tasks in Wireless Networks
  79. Trieste: Efficiently Exploring The Depths of Black-box Functions with TensorFlow
  80. On marginal feature attributions of tree-based models
  81. Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies
  82. From Contextual Data to Newsvendor Decisions: On the Actual Performance of Data-Driven Algorithms
  83. Generative AI-empowered Simulation for Autonomous Driving in Vehicular Mixed Reality Metaverses
  84. A Bayesian Perspective for Determinant Minimization Based Robust Structured Matrix Factorizatio
  85. Temporal Graph Neural Networks for Irregular Data
  86. On the Limit Performance of Floating Gossip
  87. Explicit Diffusion of Gaussian Mixture Model Based Image Priors
  88. Entity Aware Modelling: A Survey
  89. Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks
  90. Adaptive Selective Sampling for Online Prediction with Experts
  91. Fast evaluation of spherical harmonics with sphericart
  92. Efficiency 360: Efficient Vision Transformers
  93. Defect Transfer GAN: Diverse Defect Synthesis for Data Augmentation
  94. Conversation Style Transfer using Few-Shot Learning
  95. A Survey on Event-based News Narrative Extraction
  96. The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems
  97. Linear Bandits with Memory: from Rotting to Rising
  98. Cluster-based Deep Ensemble Learning for Emotion Classification in Internet Memes
  99. NUAA-QMUL-AIIT at Memotion 3: Multi-modal Fusion with Squeeze-and-Excitation for Internet Meme Emotion Analysis
  100. Introduction to Presentation Attacks in Signature Biometrics and Recent Advances
All 197
  1. The ADMM-PINNs Algorithmic Framework for Nonsmooth PDE-Constrained Optimization: A Deep Learning Approach
  2. Deterministic Nonsmooth Nonconvex Optimization
  3. Unleashing the Potential of Acquisition Functions in High-Dimensional Bayesian Optimization
  4. Navya3DSeg -- Navya 3D Semantic Segmentation Dataset & split generation for autonomous vehicles
  5. Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective
  6. Theory and Implementation of Complex-Valued Neural Networks
  7. ClaPIM: Scalable Sequence CLAssification using Processing-In-Memory
  8. Robust Human Motion Forecasting using Transformer-based Model
  9. Revisiting Hidden Representations in Transfer Learning for Medical Imaging
  10. Detecting Clouds in Multispectral Satellite Images Using Quantum-Kernel Support Vector Machines
  11. SyreaNet: A Physically Guided Underwater Image Enhancement Framework Integrating Synthetic and Real Images
  12. Knowledge-augmented Graph Machine Learning for Drug Discovery: A Survey
  13. HE-MAN -- Homomorphically Encrypted MAchine learning with oNnx models
  14. Tragic and Comical Networks. Clustering Dramatic Genres According to Structural Properties
  15. On the Effect of Adversarial Training Against Invariance-based Adversarial Examples
  16. Self-supervised Guided Hypergraph Feature Propagation for Semi-supervised Classification with Missing Node Features
  17. New Insights on Relieving Task-Recency Bias for Online Class Incremental Learning
  18. Tuning computer vision models with task rewards
  19. Learning-Based Adaptive User Selection in Millimeter Wave Hybrid Beamforming Systems
  20. A Cloud-based Deep Learning Framework for Early Detection of Pushing at Crowded Event Entrances
  21. 3M3D: Multi-view, Multi-path, Multi-representation for 3D Object Detection
  22. Improving Spoken Language Identification with Map-Mix
  23. Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Tracking
  24. Visible-Infrared Person Re-Identification via Patch-Mixed Cross-Modality Learning
  25. A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold
  26. Parallax-Tolerant Unsupervised Deep Image Stitching
  27. A method for incremental discovery of financial event types based on anomaly detection
  28. Counterfactual Reasoning for Bias Evaluation and Detection in a Fairness under Unawareness setting
  29. Deep learning based surrogate modeling for thermal plume prediction of groundwater heat pumps
  30. Un mod`ele de base de connaissances terminologiques
  31. OPT: One-shot Pose-Controllable Talking Head Generation
  32. Frugal day-ahead forecasting of multiple local electricity loads by aggregating adaptive models
  33. LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation
  34. Reimagining Demand-Side Management with Mean Field Learning
  35. WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks
  36. Singular Value Representation: A New Graph Perspective On Neural Networks
  37. The logic behind desirable sets of things, and its filter representation
  38. A numerical approximation method for the Fisher-Rao distance between multivariate normal distributions
  39. The Inadequacy of Shapley Values for Explainability
  40. Counterfactual Fair Opportunity: Measuring Decision Model Fairness with Counterfactual Reasoning
  41. Human-Centered Responsible Artificial Intelligence: Current & Future Trends
  42. Research on road object detection algorithm based on improved YOLOX
  43. Reanalyzing L2 Preposition Learning with Bayesian Mixed Effects and a Pretrained Language Model
  44. URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation
  45. CluCDD:Contrastive Dialogue Disentanglement via Clustering
  46. Learning-based solutions to nonlinear hyperbolic PDEs: Empirical insights on generalization errors
  47. Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?
  48. Auto-Parallelizing Large Models with Rhino: A Systematic Approach on Production AI Platform
  49. Model-Based Decentralized Policy Optimization
  50. ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations
  51. A weighted subspace exponential kernel for support tensor machines
  52. Personalized Audio Quality Preference Prediction
  53. Neighbor Based Enhancement for the Long-Tail Ranking Problem in Video Rank Models
  54. A Review of Uncertainty Estimation and its Application in Medical Imaging
  55. User Response in Ad Auctions: An MDP Formulation of Long-Term Revenue Optimization
  56. Towards Efficient Visual Adaption via Structural Re-parameterization
  57. A Neural PDE Solver with Temporal Stencil Modeling
  58. Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition
  59. New √n-consistent, numerically stable higher-order influence function estimators
  60. PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement
  61. Product Question Answering in E-Commerce: A Survey
  62. Do We Still Need Clinical Language Models?
  63. QTrojan: A Circuit Backdoor Against Quantum Neural Networks
  64. TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement
  65. Understanding the Distillation Process from Deep Generative Models to Tractable Probabilistic Circuits
  66. Learning Multi-Object Positional Relationships via Emergent Communication
  67. Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization
  68. Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation
  69. Group Fairness with Uncertainty in Sensitive Attributes
  70. Local Causal Discovery for Estimating Causal Effects
  71. LabelPrompt: Effective Prompt-based Learning for Relation Classification
  72. Masking and Mixing Adversarial Training
  73. MINOTAUR: Multi-task Video Grounding From Multimodal Queries
  74. Fossil Image Identification using Deep Learning Ensembles of Data Augmented Multiviews
  75. A Geometric Reduction Approach for Identity Testing of Reversible Markov Chains
  76. Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution
  77. Spectral 3D Computer Vision -- A Review
  78. Hierarchical Cross-modal Transformer for RGB-D Salient Object Detection
  79. Graph Adversarial Immunization for Certifiable Robustness
  80. Positive-unlabeled learning for binary and multi-class cell detection in histopathology images with incomplete annotations
  81. Improved Discretization Analysis for Underdamped Langevin Monte Carlo
  82. Robust Mid-Pass Filtering Graph Convolutional Networks
  83. TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation
  84. Continuous Remote Sensing Image Super-Resolution based on Context Interaction in Implicit Function Space
  85. Balancing Privacy Protection and Interpretability in Federated Learning
  86. GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks
  87. Fourier Analysis Meets Runtime Analysis: Precise Runtimes on Plateaus
  88. Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking
  89. Preventing Discriminatory Decision-making in Evolving Data Streams
  90. Individual Fairness under Uncertainty
  91. Equilibrium of Data Markets with Externality
  92. Vision-Based Terrain Relative Navigation on High-Altitude Balloon and Sub-Orbital Rocket
  93. With Shared Microexponents, A Little Shifting Goes a Long Way
  94. Slapo: A Schedule Language for Progressive Optimization of Large Deep Learning Model Training
  95. Deep Learning Enhanced Realized GARCH
  96. Learning Density-Based Correlated Equilibria for Markov Games
  97. cGAN-Based High Dimensional IMU Sensor Data Generation for Enhanced Human Activity Recognition in Therapeutic Activities