mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 19 Apr 2024

219 papers

  1. UnifiedRL: A Reinforcement Learning Algorithm Tailored for Multi-Task Fusion in Large-Scale Recommender SystemsOffline RL and imitation learning from data → Decision transformers and sequence modeling +1
  2. The Instruction Hierarchy: Training LLMs to Prioritize Privileged InstructionsLLM safety and security → Prompt injection and agent security
  3. Privacy-Preserving Debiasing using Data Augmentation and Machine UnlearningLLM safety and security → Machine unlearning
  4. CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language ModelsLLM safety and security → Prompt injection and agent security
  5. Beyond Self-Consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer StagingLLM reasoning → Clinical and biomedical applications
  6. Deep Learning-based Text-in-Image WatermarkingLLM safety and security → Watermarking generated content and models
  7. DISC: Latent Diffusion Models with Self-Distillation from Separated Conditions for Prostate Cancer GradingDiffusion models → Medical imaging and segmentation
  8. MoVA: Adapting Mixture of Vision Experts to Multimodal ContextMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  9. Analysis of Classifier-Free Guidance Weight SchedulersDiffusion models → Diffusion foundations and sampling
  10. Mapping Social Choice Theory to RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  11. PhysDreamer: Physics-Based Interaction with 3D Objects via Video GenerationWorld models → Latent predictive world models
  12. Groma: Localized Visual Tokenization for Grounding Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  13. RadRotator: 3D Rotation of Radiographs with Diffusion ModelsDiffusion models → Medical imaging and segmentation
  14. Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  15. Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMsLLM reasoning → Reasoning benchmarks and evaluation
  16. Cross-modal Diffusion Modelling for Super-resolved Spatial TranscriptomicsDiffusion models → Medical imaging and segmentation
  17. Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive ReasoningLLM reasoning → Multimodal reasoning +1
  18. Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion ModellingDiffusion models → Diffusion foundations and sampling
  19. MM-PhyRLHF: Reinforcement Learning Framework for Multimodal Physics Question-AnsweringLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment +1
  20. Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution ImagesLLM safety and security → Machine unlearning
  21. Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion ModelsDiffusion models → Medical imaging and segmentation
  22. R3L: Relative Representations for Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  23. Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language ModelsLLM safety and security → Prompt injection and agent security
  24. Robust CLIP-Based Detector for Exposing Diffusion Model-Generated ImagesDiffusion models → Image generation, text-to-image and editing
  25. ConCLVD: Controllable Chinese Landscape Video Generation via Diffusion ModelDiffusion models → Video generation
  26. MCM: Multi-condition Motion Synthesis FrameworkDiffusion models → Video generation
  27. Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  28. FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  29. How Does the Textual Information Affect the Retrieval of Multimodal In-Context Learning?Multimodal LLMs / vision-language models → Document understanding and multimodal RAG
  30. LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing PoisoningLLM safety and security → Backdoor and data poisoning attacks
  31. Towards Logically Consistent Language Models via Probabilistic ReasoningLLM reasoning → Test-time compute and efficient thinking
  32. ECOR: Explainable CLIP for Object RecognitionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  33. Generative Modelling with High-Order Langevin DynamicsDiffusion models → Diffusion foundations and sampling
  34. TextSquare: Scaling up Text-Centric Visual Instruction TuningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  35. Defending against Data Poisoning Attacks in Federated Learning via User EliminationLLM safety and security → Federated unlearning and poisoning
  36. Generating Test Scenarios from NL Requirements using Retrieval-Augmented LLMs: An Industrial StudyRetrieval-augmented generation → RAG pipeline design and evaluation
  37. Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman EquationDeep reinforcement learning methods → Deep RL algorithms and representations
  38. AutoScraper: A Progressive Understanding Web Agent for Web Scraper GenerationLLM agents and tool use → Web, search, and research agents
  39. Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?LLM reasoning → Reasoning benchmarks and evaluation
  40. Dynamic Temperature Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  41. Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language ModelMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  42. Detecting Out-Of-Distribution Earth Observation Images with Diffusion ModelsDiffusion models → Inverse problems and image restoration
  43. Pre-trained Vision-Language Models Learn Discoverable Visual ConceptsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  44. F2FLDM: Latent Diffusion Models with Histopathology Pre-Trained Embeddings for Unpaired Frozen Section to FFPE TranslationDiffusion models → Medical imaging and segmentation
  45. Data-Incremental Continual Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  46. FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource AllocationDeep reinforcement learning methods → RL for energy, networks and operations
  47. QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoringEfficient LLM inference and serving → Serving systems and request scheduling
  48. Continuous-time Risk-sensitive Reinforcement Learning via Quadratic Variation PenaltyDeep reinforcement learning methods → RL theory and sample complexity
  49. Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  50. Random Network Distillation Based Deep Reinforcement Learning for AGV Path PlanningDeep reinforcement learning methods → RL for robot navigation and UAV control
  51. Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  52. Reinforcement Learning Approach for Integrating Compressed Contexts into Knowledge GraphsDeep reinforcement learning methods → RL training of language and agent models
  53. Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQLRetrieval-augmented generation → RAG robustness and adaptive retrieval
  54. TopoLedgerBERT: Topological Learning of Ledger Description Embeddings using Siamese BERT-Networks
  55. Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank
  56. Learning Object Semantic Similarity with Self-Supervision
  57. Low-Rank Online Dynamic Assortment with Dual Contextual Information
  58. Large Language Models for Next Point-of-Interest Recommendation
  59. Leveraging Intra-modal and Inter-modal Interaction for Multi-Modal Entity Alignment
  60. Self-Supervised Learning for User Localization
  61. Can a Machine be Conscious? Towards Universal Criteria for Machine Consciousness
  62. Unmasking the Role of Remote Sensors in Comfort, Energy and Demand Response
  63. Leveraging Visibility Graphs for Enhanced Arrhythmia Classification with Graph Convolutional Networks
  64. A Weight-aware-based Multi-source Unsupervised Domain Adaptation Method for Human Motion Intention Recognition
  65. Investigating Resource-efficient Neutron/Gamma Classification ML Models Targeting eFPGAs
  66. Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures
  67. DeeperHistReg: Robust Whole Slide Images Registration Framework
  68. KATO: Knowledge Alignment and Transfer for Transistor Sizing of Different Design and Technology
  69. On the Temperature of Machine Learning Systems
  70. Machine Learning-Guided Design of Non-Reciprocal and Asymmetric Elastic Chiral Metamaterials
  71. STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
  72. An economically-consistent discrete choice model with flexible utility specification based on artificial neural networks
  73. Heterogeneous Subgraph Transformer for Fake News Detection
  74. Unlocking Robust Segmentation Across All Age Groups via Continual Learning
  75. Spectral Convolutional Conditional Neural Processes
  76. Course-Skill Atlas: A national longitudinal dataset of skills taught in U.S. higher education curricula
  77. Equivariant Imaging for Self-supervised Hyperspectral Image Inpainting
  78. Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring
  79. Transformer Based Planning in the Observation Space with Applications to Trick Taking Card Games
  80. BACS: Background Aware Continual Semantic Segmentation
  81. Multiclass ROC
  82. DeepFake-O-Meter v2.0: An Open Platform for DeepFake Detection
  83. Decentralized Coordination of Distributed Energy Resources through Local Energy Markets and Deep Reinforcement Learning
  84. Explainable AI for Fair Sepsis Mortality Predictive Model
  85. From Model Performance to Claim: How a Change of Focus in Machine Learning Replicability Can Help Bridge the Responsibility Gap
  86. On-board classification of underwater images using hybrid classical-quantum CNN based method
  87. Towards Robust Real-Time Hardware-based Mobile Malware Detection using Multiple Instance Learning Formulation
  88. RegWSI: Whole Slide Image Registration using Combined Deep Feature- and Intensity-Based Methods: Winner of the ACROBAT 2023 Challenge
  89. Automatic Cranial Defect Reconstruction with Self-Supervised Deep Deformable Masked Autoencoders
  90. On-Demand Earth System Data Cubes
  91. Multi Class Depression Detection Through Tweets using Artificial Intelligence
  92. ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Images
  93. Single-sample image-fusion upsampling of fluorescence lifetime images
  94. DensePANet: An improved generative adversarial network for photoacoustic tomography image reconstruction from sparse data
  95. Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks
  96. Endmember Extraction from Hyperspectral Images Using Self-Dictionary Approach with Linear Programming
  97. Reducing Redundant Computation in Multi-Agent Coordination through Locally Centralized Execution
  98. Unified Scene Representation and Reconstruction for 3D Large Language Models
  99. Data Alignment for Zero-Shot Concept Generation in Dermatology AI
  100. LaPA: Latent Prompt Assist Model For Medical Visual Question Answering
All 219
  1. Sample Design Engineering: An Empirical Study of What Makes Good Downstream Fine-Tuning Samples for LLMs
  2. When Life gives you LLMs, make LLM-ADE: Large Language Models with Adaptive Data Engineering
  3. BANF: Band-limited Neural Fields for Levels of Detail Reconstruction
  4. Stronger Random Baselines for In-Context Learning
  5. Optimizing Calibration by Gaining Aware of Prediction Correctness
  6. A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting
  7. Towards Robust Ferrous Scrap Material Classification with Deep Learning and Conformal Prediction
  8. Nuclei Instance Segmentation of Cryosectioned H&E Stained Histological Images using Triple U-Net Architecture
  9. Eye-tracking in Mixed Reality for Diagnosis of Neurodegenerative Diseases
  10. TRNet: Two-level Refinement Network leveraging Speech Enhancement for Noise Robust Speech Emotion Recognition
  11. FineRec:Exploring Fine-grained Sequential Recommendation
  12. Disentangling ID and Modality Effects for Session-based Recommendation
  13. Scalable Data Assimilation with Message Passing
  14. Improving Pediatric Pneumonia Diagnosis with Adult Chest X-ray Images Utilizing Contrastive Learning and Embedding Similarity
  15. Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction
  16. Next Generation Loss Function for Image Classification
  17. Purposer: Putting Human Motion Generation in Context
  18. MAiDE-up: Multilingual Deception Detection of GPT-generated Hotel Reviews
  19. Cross-cultural Inspiration Detection and Analysis in Real and LLM-generated Social Media Data
  20. The Positivity of the Neural Tangent Kernel
  21. A Hybrid Generative and Discriminative PointNet on Unordered Point Sets
  22. Probabilistic Numeric SMC Sampling for Bayesian Nonlinear System Identification in Continuous Time
  23. Large Language Models for Networking: Workflow, Advances and Challenges
  24. Training-and-Prompt-Free General Painterly Harmonization via Zero-Shot Disentenglement on Style and Content References
  25. Bayesian Co-navigation: Dynamic Designing of the Materials Digital Twins via Active Learning
  26. Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning
  27. A Machine Learning-Based Error Mitigation Approach For Reliable Software Development On IBM'S Quantum Computers
  28. Learn2Talk: 3D Talking Face Learns from 2D Talking Face
  29. 3D Multi-frame Fusion for Video Stabilization
  30. A Large-scale Medical Visual Task Adaptation Benchmark
  31. LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency
  32. A Guide to Feature Importance Methods for Scientific Inference
  33. Weakly Supervised LiDAR Semantic Segmentation via Scatter Image Annotation
  34. Language-Driven Active Learning for Diverse Open-Set 3D Object Detection
  35. CaBaFL: Asynchronous Federated Learning via Hierarchical Cache and Feature Balance
  36. KoReA-SFL: Knowledge Replay-based Split Federated Learning Against Catastrophic Forgetting
  37. TartuNLP @ SIGTYP 2024 Shared Task: Adapting XLM-RoBERTa for Ancient and Historical Languages
  38. Explainable Deepfake Video Detection using Convolutional Neural Network and CapsuleNet
  39. COIN: Counterfactual inpainting for weakly supervised semantic segmentation for medical images
  40. LiMe: a Latin Corpus of Late Medieval Criminal Sentences
  41. An Evaluation Benchmark for Adverse Drug Event Prediction from Clinical Trial Results
  42. MAexp: A Generic Platform for RL-based Multi-Agent Exploration
  43. Unveiling the Ambiguity in Neural Inverse Rendering: A Parameter Compensation Analysis
  44. Enhancing Counterfactual Explanation Search with Diffusion Distance and Directional Coherence
  45. Linearly-evolved Transformer for Pan-sharpening
  46. Enhancing Interval Type-2 Fuzzy Logic Systems: Learning for Precision and Prediction Intervals
  47. Zadeh's Type-2 Fuzzy Logic Systems: Precision and High-Quality Prediction Intervals
  48. A Point-Based Approach to Efficient LiDAR Multi-Task Perception
  49. MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model
  50. Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning
  51. REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking
  52. Contrastive Gaussian Clustering: Weakly Supervised 3D Scene Segmentation
  53. Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting
  54. EfficientGS: Streamlining Gaussian Splatting for Large-Scale High-Resolution Scene Representation
  55. Camera Agnostic Two-Head Network for Ego-Lane Inference
  56. MixLight: Borrowing the Best of both Spherical Harmonics and Gaussian Models
  57. Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
  58. How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law
  59. Food Development through Co-creation with AI: bread with a "taste of love"
  60. decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points
  61. Recurrent Neural Networks for Modelling Gross Primary Production
  62. Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches
  63. Multi-Class Quantum Convolutional Neural Networks
  64. The Solution for the CVPR2024 NICE Image Captioning Challenge
  65. Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer
  66. PATE-TripleGAN: Privacy-Preserving Image Synthesis with Gaussian Differential Privacy
  67. Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works
  68. Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction
  69. Graph Convolutional Network For Semi-supervised Node Classification With Subgraph Sketching
  70. Generalized Few-Shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping via Hybrid Semantic Segmentation Framework
  71. PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering
  72. Improving Prediction Accuracy of Semantic Segmentation Methods Using Convolutional Autoencoder Based Pre-processing Layers
  73. Show and Grasp: Few-shot Semantic Segmentation for Robot Grasping through Zero-shot Foundation Models
  74. Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration
  75. uTRAND: Unsupervised Anomaly Detection in Traffic Trajectories
  76. FedMeS: Personalized Federated Continual Learning Leveraging Local Memory
  77. A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Only
  78. Modeling Multi-Granularity Context Information Flow for Pavement Crack Detection
  79. SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models
  80. Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations
  81. ESC: Evolutionary Stitched Camera Calibration in the Wild
  82. Improving Chinese Character Representation with Formation Tree
  83. Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?
  84. Can LLMs Understand Computer Networks? Towards a Virtual System Administrator
  85. VoxAtnNet: A 3D Point Clouds Convolutional Neural Network for Generalizable Face Presentation Attack Detection
  86. MLSD-GAN -- Generating Strong High Quality Face Morphing Attacks using Latent Semantic Disentanglement
  87. Towards Universal Performance Modeling for Machine Learning Training on Multi-GPU Platforms
  88. Towards Human-centered Proactive Conversational Agents
  89. SOS-1K: A Fine-grained Suicide Risk Classification Dataset for Chinese Social Media Analysis
  90. How Real Is Real? A Human Evaluation Framework for Unrestricted Adversarial Examples
  91. Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation
  92. Cooperative Sentiment Agents for Multimodal Sentiment Analysis
  93. Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming
  94. AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
  95. Transformer-Based Classification Outcome Prediction for Multimodal Stroke Treatment
  96. Breaching the Bottleneck: Evolutionary Transition from Reward-Driven Learning to Reward-Agnostic Domain-Adapted Learning in Neuromodulated Neural Nets
  97. MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction
  98. Efficient infusion of self-supervised representations in Automatic Speech Recognition
  99. A Soft e-Textile Sensor for Enhanced Deep Learning-based Shape Sensing of Soft Continuum Robots
  100. Grasper: A Generalist Pursuer for Pursuit-Evasion Problems
  101. SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformers
  102. DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving
  103. End-to-End Verifiable Decentralized Federated Learning
  104. CORI: CJKV Benchmark with Romanization Integration -- A step towards Cross-lingual Transfer Beyond Textual Scripts
  105. Model Selection and Parameter Estimation of One-Dimensional Gaussian Mixture Models
  106. SA-Attack: Speed-adaptive stealthy adversarial attack on trajectory prediction
  107. Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimization
  108. Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations
  109. ELEV-VISION-SAM: Integrated Vision Language and Foundation Model for Automated Estimation of Building Lowest Floor Elevation
  110. GluMarker: A Novel Predictive Modeling of Glycemic Control Through Digital Biomarkers
  111. A visualization method for data domain changes in CNN networks and the optimization method for selecting thresholds in classification tasks
  112. The phase diagram of kernel interpolation in large dimensions
  113. Integer Programming for Learning Directed Acyclic Graphs from Non-identifiable Gaussian Models
  114. Risk Bounds for Mixture Density Estimation on Compact Domains via the h-Lifted Kullback--Leibler Divergence
  115. iTBLS: A Dataset of Interactive Conversations Over Tabular Information
  116. On the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction
  117. Multi-View Subgraph Neural Networks: Self-Supervised Learning with Scarce Labeled Data
  118. Learning Stable and Passive Neural Differential Equations
  119. RetailOpt: Opt-In, Easy-to-Deploy Trajectory Estimation from Smartphone Motion Data and Retail Facility Information