mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 31 Jan 2024

231 papers

  1. Decentralized Covert Routing in Heterogeneous Networks Using Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  2. RAG-Fusion: a New Take on Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  3. An Early Categorization of Prompt Injection Attacks on Large Language ModelsLLM safety and security → Prompt injection and agent security
  4. MoDE: A Mixture-of-Experts Model with Mutual Distillation among the ExpertsMixture-of-experts → MoE theory and gating functions
  5. Beyond Inserting: Learning Identity Embedding for Semantic-Fidelity Personalized Diffusion GenerationDiffusion models → Image generation, text-to-image and editing
  6. Dataset Condensation Driven Machine UnlearningLLM safety and security → Machine unlearning
  7. De-identification is not enough: a comparison between de-identified and synthetic clinical notesLLM safety and security → Membership inference attacks
  8. Behind the Myth of Exploration in Policy GradientsDeep reinforcement learning methods → RL theory and sample complexity
  9. Large Language Models for Mathematical Reasoning: Progresses and ChallengesLLM reasoning → Mathematical reasoning
  10. A Reinforcement Learning Based Controller to Minimize Forces on the Crutches of a Lower-Limb ExoskeletonDeep reinforcement learning methods → RL for robot locomotion and manipulation
  11. Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy LearningDeep reinforcement learning methods → RL training of language and agent models
  12. EPSD: Early Pruning with Self-Distillation for Efficient Model CompressionKnowledge distillation → General knowledge distillation methods
  13. Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion EstimatorsDiffusion models → Image generation, text-to-image and editing
  14. KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache QuantizationEfficient LLM inference and serving → KV cache quantization
  15. RAPTOR: Recursive Abstractive Processing for Tree-Organized RetrievalRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  16. LongAlign: A Recipe for Long Context Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  17. Enhancing End-to-End Multi-Task Dialogue Systems: A Study on Intrinsic Motivation Reinforcement Learning Algorithms for Improved Training and AdaptabilityDeep reinforcement learning methods → RL training of language and agent models
  18. On Prompt-Driven Safeguarding for Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  19. Causal Coordinated Concurrent Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  20. From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection InformationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  21. Circuit Partitioning for Multi-Core Quantum Architectures with Deep Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
  22. Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein DistancesDiffusion models → Diffusion foundations and sampling
  23. Attention Graph for Multi-Robot Social Navigation with Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  24. On Tractability, Complexity, and Mixed-Integer Convex Programming Representability of Distributionally Favorable OptimizationDeep reinforcement learning methods → RL theory and sample complexity
  25. I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBenchLLM reasoning → Reasoning benchmarks and evaluation
  26. Graph Attention-based Reinforcement Learning for Trajectory Design and Resource Assignment in Multi-UAV Assisted CommunicationDeep reinforcement learning methods → RL for robot navigation and UAV control
  27. AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction ErrorDiffusion models → Image generation, text-to-image and editing
  28. Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity AnalysisMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  29. Simplifying Latent Dynamics with Softly State-Invariant World ModelsWorld models → Latent predictive world models
  30. A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC GuaranteesDeep reinforcement learning methods → RL theory and sample complexity
  31. SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language modelsLLM agents and tool use → Reinforcement learning for LLM agents
  32. Enhancing Large Language Model with Decomposed Reasoning for Emotion Cause Pair ExtractionLLM reasoning → Audio-language model reasoning
  33. Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with TransformerOffline RL and imitation learning from data → Robot manipulation imitation learning
  34. Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  35. ReSLLM: Large Language Models are Strong Resource Selectors for Federated SearchRetrieval-augmented generation → Generation and context integration
  36. BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving SystemsEfficient LLM inference and serving → Serving systems and request scheduling
  37. Spatial-and-Frequency-aware Restoration method for Images based on Diffusion ModelsDiffusion models → Inverse problems and image restoration
  38. Topology-Aware Latent Diffusion for 3D Shape GenerationDiffusion models → 3D, point cloud and scene generation
  39. Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation dataMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  40. Head and Neck Tumor Segmentation from [18F]F-FDG PET/CT Images Based on 3D Diffusion ModelDiffusion models → Medical imaging and segmentation
  41. Diffusion Model Compression for Image-to-Image TranslationDiffusion models → Image generation, text-to-image and editing
  42. Game-Theoretic Unlearnable Example GeneratorLLM safety and security → Backdoor and data poisoning attacks
  43. Dynamic Model Switching for Improved Accuracy in Machine Learning
  44. Ontologia para monitorar a deficiencia mental em seus d'eficts no processamento da informacc~ao por decl'inio cognitivo e evitar agress~oes psicol'ogicas e f'isicas em ambientes educacionais com ajuda da I.A*
  45. MOD-CL: Multi-label Object Detection with Constrained Loss
  46. Large Scale Generative AI Text Applied to Sports and Music
  47. ConSmax: Hardware-Friendly Alternative Softmax with Learnable Parameters
  48. A Comparative Study of Conventional and Tripolar EEG for High-Performance Reach-to-Grasp BCI Systems
  49. Wavelet Analysis of Noninvasive EEG Signals Discriminates Complex and Natural Grasp Types
  50. iMove: Exploring Bio-impedance Sensing for Fitness Activity Recognition
  51. Multimodal Action Quality Assessment
  52. Uncertainty-Aware Explainable Recommendation with Large Language Models
  53. Heterophily-Aware Fair Recommendation using Graph Convolutional Networks
  54. LLM Voting: Human Choices and AI Collective Decision Making
  55. LLMs Simulate Big Five Personality Traits: Further Evidence
  56. Real Sparks of Artificial Intelligence and the Importance of Inner Interpretability
  57. Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees
  58. Screening method for early dementia using sound objects as voice biomarkers
  59. Privacy and Security Implications of Cloud-Based AI Services : A Survey
  60. EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks
  61. Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replay
  62. Capacity Constraint Analysis Using Object Detection for Smart Manufacturing
  63. Spectral Norm of Convolutional Layers with Circular and Zero Paddings
  64. CNN-FL for Biotechnology Industry Empowered by Internet-of-BioNano Things and Digital Twins
  65. Positional Encoding Helps Recurrent Neural Networks Handle a Large Vocabulary
  66. Exploring the limits of decoder-only models trained on public speech recognition corpora
  67. Can Generative AI Support Patients' & Caregivers' Informational Needs? Towards Task-Centric Evaluation Of AI Systems
  68. Learning Label Hierarchy with Supervised Contrastive Learning
  69. Geometry aware 3D generation from in-the-wild images in ImageNet
  70. Uncover the nature of overlapping community in cities
  71. FedCore: Straggler-Free Federated Learning with Distributed Coresets
  72. MP-SL: Multihop Parallel Split Learning
  73. Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Data
  74. An Experiment on Feature Selection using Logistic Regression
  75. Determination of Trace Organic Contaminant Concentration via Machine Classification of Surface-Enhanced Raman Spectra
  76. Distance and Collision Probability Estimation from Gaussian Surface Models
  77. Adversarial Quantum Machine Learning: An Information-Theoretic Generalization Analysis
  78. Weakly-Supervised Detection of Bone Lesions in CT
  79. Continuous Treatment Effects with Surrogate Outcomes
  80. Improving Object Detection Quality in Football Through Super-Resolution Techniques
  81. Emergency Department Decision Support using Clinical Pseudo-notes
  82. Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
  83. Fully Data-Driven Model for Increasing Sampling Rate Frequency of Seismic Data using Super-Resolution Generative Adversarial Networks
  84. Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss
  85. The Impact of Language Adapters in Cross-Lingual Transfer for NLU
  86. Making a Long Story Short in Conversation Modeling
  87. Decomposable Submodular Maximization in Federated Setting
  88. Multimodal Neurodegenerative Disease Subtyping Explained by ChatGPT
  89. CMRNext: Camera to LiDAR Matching in the Wild for Localization and Extrinsic Calibration
  90. Real-time Traffic Object Detection for Autonomous Driving
  91. Common Sense Reasoning for Deepfake Detection
  92. Comparing Template-based and Template-free Language Model Probing
  93. Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM
  94. Deep Neural Networks: A Formulation Via Non-Archimedean Analysis
  95. ChIRAAG: ChatGPT Informed Rapid and Automated Assertion Generation
  96. Episodic-free Task Selection for Few-shot Learning
  97. SCAPE: Searching Conceptual Architecture Prompts using Evolution
  98. Retrosynthesis prediction enhanced by in-silico reaction data augmentation
  99. Modeling Access Differences to Reduce Disparity in Resource Allocation
  100. Binding Touch to Everything: Learning Unified Multimodal Tactile Representations
All 231
  1. Improved Scene Landmark Detection for Camera Localization
  2. CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting
  3. Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?
  4. Rank Supervised Contrastive Learning for Time Series Classification
  5. Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition
  6. Epidemic Modeling using Hybrid of Time-varying SIRD, Particle Swarm Optimization, and Deep Learning
  7. Multipath parsing in the brain
  8. SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition
  9. Variable selection for Na"ive Bayes classification
  10. Optimizing contrastive learning for cortical folding pattern detection
  11. Paramanu: Compact and Competitive Monolingual Language Models for Low-Resource Morphologically Rich Indian Languages
  12. DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification
  13. Evaluating the Capabilities of LLMs for Supporting Anticipatory Impact Assessment
  14. A cost-sensitive constrained Lasso
  15. Causal Discovery by Kernel Deviance Measures with Heterogeneous Transforms
  16. EEG-GPT: Exploring Capabilities of Large Language Models for EEG Classification and Interpretation
  17. Desiderata for the Context Use of Question Answering Systems
  18. Multilinear Operator Networks
  19. Individual mapping of large polymorphic shrubs in high mountains using satellite images and deep learning
  20. Entity Linking in the Job Market Domain
  21. Understanding polysemanticity in neural networks through coding theory
  22. GUMsley: Evaluating Entity Salience in Summarization for 12 English Genres
  23. MelNet: A Real-Time Deep Learning Algorithm for Object Detection
  24. CONCORD: Towards a DSL for Configurable Graph Code Representation
  25. HyperZ·Z·W Operator Connects Slow-Fast Networks for Full Context Interaction
  26. [Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs
  27. LOCOST: State-Space Models for Long Document Abstractive Summarization
  28. Source-free Domain Adaptive Object Detection in Remote Sensing Images
  29. SNNLP: Energy-Efficient Natural Language Processing Using Spiking Neural Networks
  30. ControlCap: Controllable Region-level Captioning
  31. Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
  32. Revisiting speech segmentation and lexicon learning with better features
  33. Multitask methods for predicting molecular properties from heterogeneous data
  34. Employing Label Models on ChatGPT Answers Improves Legal Text Entailment Performance
  35. ReplaceAnything3D:Text-Guided 3D Scene Editing with Compositional Neural Radiance Fields
  36. Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques
  37. PVLR: Prompt-driven Visual-Linguistic Representation Learning for Multi-Label Image Recognition
  38. VR-based generation of photorealistic synthetic data for training hand-object tracking models
  39. Efficient Subseasonal Weather Forecast using Teleconnection-informed Transformers
  40. Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
  41. Making Sense of Knowledge Intensive Processes: an Oil & Gas Industry Scenario
  42. Manipulating Predictions over Discrete Inputs in Machine Teaching
  43. Probing Language Models' Gesture Understanding for Enhanced Human-AI Interaction
  44. SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition
  45. Instruction-Guided Scene Text Recognition
  46. Explainable Benchmarking for Iterative Optimization Heuristics
  47. Global-Liar: Factuality of LLMs over Time and Geographic Regions
  48. A Cross-View Hierarchical Graph Learning Hypernetwork for Skill Demand-Supply Joint Prediction
  49. Leveraging Swin Transformer for Local-to-Global Weakly Supervised Semantic Segmentation
  50. Neural Machine Translation for Malayalam Paraphrase Generation
  51. A Survey of Pre-trained Language Models for Processing Scientific Text
  52. Privacy-preserving data release leveraging optimal transport and particle gradient descent
  53. Do Object Detection Localization Errors Affect Human Performance and Trust?
  54. Deterministic Computing Power Networking: Architecture, Technologies and Prospects
  55. SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering
  56. Advances in 3D Generation: A Survey
  57. Biospheric AI
  58. SU-SAM: A Simple Unified Framework for Adapting Segment Anything Model in Underperformed Scenes
  59. Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning
  60. M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval
  61. Graph Transformers without Positional Encodings
  62. RADIN: Souping on a Budget
  63. Robustly overfitting latents for flexible neural image compression
  64. SDRDPy: An application to graphically visualize the knowledge obtained with supervised descriptive rule algorithms
  65. Vision-Assisted Digital Twin Creation for mmWave Beam Management
  66. Double InfoGAN for Contrastive Analysis
  67. SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks
  68. Fine-Grained Zero-Shot Learning: Advances, Challenges, and Prospects
  69. Convergence of Expectation-Maximization Algorithm with Mixed-Integer Optimization
  70. Regularized Linear Discriminant Analysis Using a Nonlinear Covariance Matrix Estimator
  71. Rapid post-disaster infrastructure damage characterisation enabled by remote sensing and deep learning technologies -- a tiered approach
  72. CauESC: A Causal Aware Model for Emotional Support Conversation
  73. PF-GNN: Differentiable particle filtering based approximation of universal graph representations
  74. Algorithmic Robust Forecast Aggregation
  75. Haris: an Advanced Autonomous Mobile Robot for Smart Parking Assistance
  76. Operator learning without the adjoint
  77. Harnessing Smartwatch Microphone Sensors for Cough Detection and Classification
  78. Hierarchical Bias-Driven Stratification for Interpretable Causal Effect Estimation
  79. Leveraging Human-Machine Interactions for Computer Vision Dataset Quality Enhancement
  80. Towards Physical Plausibility in Neuroevolution Systems
  81. COMET: Contrastive Mean Teacher for Online Source-Free Universal Domain Adaptation
  82. 3D-Plotting Algorithm for Insects using YOLOv5
  83. Prediction of multitasking performance post-longitudinal tDCS via EEG-based functional connectivity and machine learning methods
  84. Aesthetic Preference Prediction in Interior Design: Fuzzy Approach
  85. Predicting suicidal behavior among Indian adults using childhood trauma, mental health questionnaires and machine learning cascade ensembles
  86. WSC+: Enhancing The Winograd Schema Challenge Using Tree-of-Experts
  87. Classification of executive functioning performance post-longitudinal tDCS using functional connectivity and machine learning methods
  88. Unified Physical-Digital Face Attack Detection
  89. Datacube segmentation via Deep Spectral Clustering
  90. Mitigating the Influence of Distractor Tasks in LMs with Prior-Aware Decoding
  91. EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning
  92. Convergence analysis of t-SNE as a gradient flow for point cloud on a manifold
  93. Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain
  94. Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation
  95. Towards the implementation of Industry 4.0: A methodology-based approach oriented to the customer life cycle
  96. Document Structure in Long Document Transformers
  97. An attempt to generate new bridge types from latent space of energy-based model
  98. All Beings Are Equal in Open Set Recognition
  99. A primer on synthetic health data
  100. Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
  101. Navigating the OverKill in Large Language Models
  102. What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis
  103. Generative AI to Generate Test Data Generators
  104. Neighboring Perturbations of Knowledge Editing on Large Language Models
  105. Unveiling the Power of Self-supervision for Multi-view Multi-human Association and Tracking
  106. Graph Multi-Similarity Learning for Molecular Property Prediction
  107. IGCN: Integrative Graph Convolution Networks for patient level insights and biomarker discovery in multi-omics integration
  108. LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement
  109. Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition
  110. Assertion Detection Large Language Model In-context Learning LoRA Fine-tuning
  111. SPECTRUM: Speaker-Enhanced Pre-Training for Long Dialogue Summarization
  112. Local Feature Matching Using Deep Learning: A Survey
  113. Local and Global Contexts for Conversation
  114. Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks
  115. Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion
  116. Graph Contrastive Learning with Cohesive Subgraph Awareness
  117. Scavenging Hyena: Distilling Transformers into Long Convolution Models
  118. Tensor-based process control and monitoring for semiconductor manufacturing with unstable disturbances
  119. Is Registering Raw Tagged-MR Enough for Strain Estimation in the Era of Deep Learning?
  120. Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
  121. Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection
  122. Trainable Fixed-Point Quantization for Deep Learning Acceleration on FPGAs
  123. A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models
  124. Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration
  125. Gradient-Free Score-Based Sampling Methods with Ensembles
  126. PipeNet: Question Answering with Semantic Pruning over Knowledge Graphs
  127. Learning to Stop Cut Generation for Efficient Mixed-Integer Linear Programming
  128. Semantic-Syntactic Discrepancy in Images (SSDI): Learning Meaning and Order of Features from Natural Images
  129. How Useful is Continued Pre-Training for Generative Unsupervised Domain Adaptation?
  130. A PNP ion channel deep learning solver with local neural network and finite element input data
  131. Linguistically Communicating Uncertainty in Patient-Facing Risk Prediction Models