mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 1 Mar 2024

229 papers

  1. ATP: Enabling Fast LLM Serving via Attention on Top Principal KeysEfficient LLM inference and serving → KV cache optimization
  2. Peacock: A Family of Arabic Multimodal Large Language Models and BenchmarksMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  3. A Case for Validation Buffer in Pessimistic Actor-CriticDeep reinforcement learning methods → RL theory and sample complexity
  4. A Holistic Power Optimization Approach for Microgrid Control Based on Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  5. Leveraging Prompt-Based Large Language Models: Predicting Pandemic Health Decisions and Outcomes Through Social Media LanguageLLM reasoning → Clinical and biomedical applications
  6. On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and GamesDeep reinforcement learning methods → Deep RL algorithms and representations
  7. SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social NavigationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  8. LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA SystemsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  9. MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination DetectionSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  10. Differentially Private Knowledge Distillation via Synthetic Text GenerationKnowledge distillation → Federated, robust and private distillation
  11. Scale-free Adversarial Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  12. PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  13. Crimson: Empowering Strategic Reasoning in Cybersecurity through Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  14. Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss LandscapesLLM safety and security → Jailbreaking
  15. Point Cloud Mamba: Point Cloud Learning via State Space ModelState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  16. AtP*: An efficient and scalable method for localizing LLM behaviour to componentsMechanistic interpretability → Activation steering methods
  17. Self-Consistent Decoding for More Factual Open ResponsesLLM reasoning → Test-time compute and efficient thinking
  18. Playing NetHack with LLMs: Potential & Limitations as Zero-Shot AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  19. Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence RateDeep reinforcement learning methods → RL theory and sample complexity
  20. Snapshot Reinforcement Learning: Leveraging Prior Trajectories for EfficiencyDeep reinforcement learning methods → Deep RL algorithms and representations
  21. Diff-Plugin: Revitalizing Details for Diffusion-based Low-level TasksDiffusion models → Image generation, text-to-image and editing
  22. Rethinking cluster-conditioned diffusion models for label-free image synthesisDiffusion models → Diffusion foundations and sampling
  23. EfficientZero V2: Mastering Discrete and Continuous Control with Limited DataWorld models → Latent dynamics models and model-based RL +1
  24. Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and BenchmarkingOffline RL and imitation learning from data → Imitation learning methods
  25. Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  26. Learning and Leveraging World Models in Visual Representation LearningWorld models → Latent predictive world models
  27. An Ordinal Diffusion Model for Generating Medical Images with Different Severity LevelsDiffusion models → Medical imaging and segmentation
  28. Safe Hybrid-Action Reinforcement Learning-Based Decision and Control for Discretionary Lane ChangeDeep reinforcement learning methods → RL for autonomous driving and traffic
  29. LoMOE: Localized Multi-Object Editing via Multi-DiffusionDiffusion models → Image generation, text-to-image and editing
  30. Hierarchical Indexing for Retrieval-Augmented Opinion SummarizationRetrieval-augmented generation → RAG pipeline design and evaluation
  31. HALC: Object Hallucination Reduction via Adaptive Focal-Contrast DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  32. Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A SurveyDeep reinforcement learning methods → Adversarial robustness and RL in finance
  33. Rethinking Tokenization: Crafting Better Tokenizers for Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  34. Provably Robust DPO: Aligning Language Models with Noisy FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  35. Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  36. Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual ReasoningLLM reasoning → Multimodal reasoning
  37. Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language ModelsSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  38. Deep Reinforcement Learning for Solving Management Problems: Towards A Large Management ModeDeep reinforcement learning methods → RL for energy, networks and operations
  39. Enhancing Jailbreak Attacks with Diversity GuidanceLLM safety and security → Jailbreaking
  40. Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  41. Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-trainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  42. Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  43. Robust Policy Learning via Offline Skill DiffusionDiffusion models → Diffusion and flow policies for robotics +1
  44. Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at ScaleDeep reinforcement learning methods → RL theory and sample complexity
  45. Multi-modal Attribute Prompting for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  46. Improving Socratic Question Generation using Data Augmentation and Preference OptimizationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  47. Multi-modal Heart Failure Risk Estimation based on Short ECG and Sampled Long-Term HRV
  48. ClickTree: A Tree-based Method for Predicting Math Students' Performance Based on Clickstream Data
  49. Machine Learning Predicts Upper Secondary Education Dropout as Early as the End of Primary School
  50. Beyond Beats: A Recipe to Song Popularity? A machine learning approach
  51. Sketching the Heat Kernel: Using Gaussian Processes to Embed Data
  52. Can Interpretability Layouts Influence Human Perception of Offensive Sentences?
  53. Identify Critical Nodes in Complex Network with Large Language Models
  54. Reservoir Computing Using Measurement-Controlled Quantum Dynamics
  55. Federated Learning via Lattice Joint Source-Channel Coding
  56. Autonomous Strike UAVs for Counterterrorism Missions: Challenges and Preliminary Solutions
  57. Policy Optimization for PDE Control with a Warm Start
  58. FlaKat: A Machine Learning-Based Categorization Framework for Flaky Tests
  59. Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
  60. Distributional Dataset Distillation with Subtask Decomposition
  61. Predictions from language models for multiple-choice tasks are not robust under variation of scoring methods
  62. Formulation Comparison for Timeline Construction using LLMs
  63. Merging Text Transformer Models from Different Initializations
  64. Even-Ifs From If-Onlys: Are the Best Semi-Factual Explanations Found Using Counterfactuals As Guides?
  65. Joint Spatial-Temporal Calibration for Camera and Global Pose Sensor
  66. Equipment Health Assessment: Time Series Analysis for Wind Turbine Performance
  67. Motif distribution and function of sparse deep neural networks
  68. Binary Gaussian Copula Synthesis: an LLM-powered data augmentation framework for early dialysis prediction in chronic kidney disease
  69. Tree-Regularized Tabular Embeddings
  70. Data Science Education in Undergraduate Physics: Lessons Learned from a Community of Practice
  71. Resolution of Simpson's paradox via the common cause principle
  72. AutoRD: An Automatic and End-to-End System for Rare Disease Knowledge Graph Construction Based on Ontologies-enhanced Large Language Models
  73. MediSwift: Efficient Sparse Pre-trained Biomedical Language Models
  74. Fine-tuning with Very Large Dropout
  75. Resilience of Entropy Model in Distributed Neural Networks
  76. G3DR: Generative 3D Reconstruction in ImageNet
  77. Transfer Learning for Security: Challenges and Future Directions
  78. An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce
  79. The Algorithm Configuration Problem
  80. VisRec: A Semi-Supervised Approach to Radio Interferometric Data Reconstruction
  81. DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models
  82. End-to-End Graph-Sequential Representation Learning for Accurate Recommendations
  83. Comparing large language models and human programmers for generating programming code
  84. PowerFlowMultiNet: Multigraph Neural Networks for Unbalanced Three-Phase Distribution Systems
  85. A Regularization-based Transfer Learning Method for Information Extraction via Instructed Graph Decoder
  86. Improving Android Malware Detection Through Data Augmentation Using Wasserstein Generative Adversarial Networks
  87. Time-bound Contextual Bio-ID Generation for Minimalist Wearables
  88. Margin Discrepancy-based Adversarial Training for Multi-Domain Text Classification
  89. SEGAA: A Unified Approach to Predicting Age, Gender, and Emotion in Speech
  90. Evaluating and Correcting Performative Effects of Decision Support Systems via Causal Domain Shift
  91. Zero-Shot Topic Classification of Column Headers: Leveraging LLMs for Metadata Enrichment
  92. FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission
  93. CIDGMed: Causal Inference-Driven Medication Recommendation with Enhanced Dual-Granularity Learning
  94. Disaggregated Multi-Tower: Topology-aware Modeling Technique for Efficient Large-Scale Recommendation
  95. Word Order and World Knowledge
  96. Enhancing Protein Predictive Models via Proteins Data Augmentation: A Benchmark and New Directions
  97. Blockchain-empowered Federated Learning: Benefits, Challenges, and Solutions
  98. DFIN-SQL: Integrating Focused Schema with DIN-SQL for Superior Accuracy in Large-Scale Databases
  99. Teach LLMs to Phish: Stealing Private Information from Language Models
  100. Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling
All 229
  1. SoftTiger: A Clinical Foundation Model for Healthcare Workflows
  2. Fast and Efficient Local Search for Genetic Programming Based Loss Function Learning
  3. Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training
  4. A time-stepping deep gradient flow method for option pricing in (rough) diffusion models
  5. Dialect prejudice predicts AI decisions about people's character, employability, and criminality
  6. Can Transformers Capture Spatial Relations between Objects?
  7. Few-Shot Relation Extraction with Hybrid Visual Evidence
  8. Subhomogeneous Deep Equilibrium Models
  9. Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
  10. Rethinking Inductive Biases for Surface Normal Estimation
  11. Defining Expertise: Applications to Treatment Effect Estimation
  12. Toward Autonomous Cooperation in Heterogeneous Nanosatellite Constellations Using Dynamic Graph Neural Networks
  13. Tri-Modal Motion Retrieval by Learning a Joint Embedding Space
  14. Hydra: Computer Vision for Data Quality Monitoring
  15. A Bit of a Problem: Measurement Disparities in Dataset Sizes Across Languages
  16. Know your exceptions: Towards an Ontology of Exceptions in Knowledge Representation
  17. Scalable Learning of Item Response Theory Models
  18. Advancing Additive Manufacturing through Deep Learning: A Comprehensive Review of Current Progress and Future Challenges
  19. Sharp bounds for max-sliced Wasserstein distances
  20. COLON: The largest COlonoscopy LONg sequence public database
  21. Modeling the Quality of Dialogical Explanations
  22. Stability-Certified Learning of Control Systems with Quadratic Nonlinearities
  23. Rethinking The Uniformity Metric in Self-Supervised Learning
  24. Graph Theory and GNNs to Unravel the Topographical Organization of Brain Lesions in Variants of Alzheimer's Disease Progression
  25. Metamorpheus: Interactive, Affective, and Creative Dream Narration Through Metaphorical Visual Storytelling
  26. Region-Adaptive Transform with Segmentation Prior for Image Compression
  27. Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiency
  28. Advancing dermatological diagnosis: Development of a hyperspectral dermatoscope for enhanced skin imaging
  29. Flattening Singular Values of Factorized Convolution for Medical Images
  30. Rethinking Few-shot 3D Point Cloud Semantic Segmentation
  31. Learning Causal Features for Incremental Object Detection
  32. Improving Explicit Spatial Relationships in Text-to-Image Generation through an Automatically Derived Dataset
  33. Generalized User Representations for Transfer Learning
  34. SINDy vs Hard Nonlinearities and Hidden Dynamics: a Benchmarking Study
  35. Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms
  36. IDTrust: Deep Identity Document Quality Detection with Bandpass Filtering
  37. Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
  38. Lincoln's Annotated Spatio-Temporal Strawberry Dataset (LAST-Straw)
  39. Predicting UAV Type: An Exploration of Sampling and Data Augmentation for Time Series Classification
  40. Indirectly Parameterized Concrete Autoencoders
  41. Multi-Task Learning Using Uncertainty to Weigh Losses for Heterogeneous Face Attribute Estimation
  42. Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores
  43. Relaxometry Guided Quantitative Cardiac Magnetic Resonance Image Reconstruction
  44. SURE: SUrvey REcipes for building reliable and robust deep networks
  45. Machine Learning Training Optimization using the Barycentric Correction Procedure
  46. Epsilon-Greedy Thompson Sampling to Bayesian Optimization
  47. VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis
  48. Large Language Models for Simultaneous Named Entity Extraction and Spelling Correction
  49. VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks
  50. ROME: Memorization Insights from Text, Logits and Representation
  51. Surveying the Dead Minds: Historical-Psychological Text Analysis with Contextualized Construct Representation (CCR) for Classical Chinese
  52. PoTeC: A German Naturalistic Eye-tracking-while-reading Corpus
  53. Do Zombies Understand? A Choose-Your-Own-Adventure Exploration of Machine Cognition
  54. Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
  55. A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications
  56. RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
  57. TempCompass: Do Video LLMs Really Understand Videos?
  58. Autonomous Robotic Arm Manipulation for Planetary Missions using Causal Machine Learning
  59. When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability
  60. LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues
  61. Deformable One-shot Face Stylization via DINO Semantic Guidance
  62. Parallel Hyperparameter Optimization Of Spiking Neural Network
  63. Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts
  64. Your Model Is Not Predicting Depression Well And That Is Why: A Case Study of PRIMATE Dataset
  65. Abductive Ego-View Accident Video Understanding for Safe Driving Perception
  66. Deep Learning Computed Tomography based on the Defrise and Clack Algorithm
  67. Validation of ML-UQ calibration statistics using simulated reference values: a sensitivity analysis
  68. LLMs for Targeted Sentiment in News Headlines: Exploring the Descriptive-Prescriptive Dilemma
  69. Data-efficient Event Camera Pre-training via Disentangled Masked Modeling
  70. Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish
  71. Fractal interpolation in the context of prediction accuracy optimization
  72. Spatio-temporal reconstruction of substance dynamics using compressed sensing in multi-spectral magnetic resonance spectroscopic imaging
  73. GLFNET: Global-Local (frequency) Filter Networks for efficient medical image segmentation
  74. List-Mode PET Image Reconstruction Using Dykstra-Like Splitting
  75. TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs
  76. Structured Deep Neural Network-Based Backstepping Trajectory Tracking Control for Lagrangian Systems
  77. HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation
  78. Post-decoder Biasing for End-to-End Speech Recognition of Multi-turn Medical Interview
  79. Exploring the dynamic interplay of cognitive load and emotional arousal by using multimodal measurements: Correlation of pupil diameter and emotional arousal in emotionally engaging tasks
  80. Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy
  81. MS-Net: A Multi-Path Sparse Model for Motion Prediction in Multi-Scenes
  82. Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks
  83. Nonlinear Sheaf Diffusion in Graph Neural Networks
  84. Never-Ending Behavior-Cloning Agent for Robotic Manipulation
  85. Learning with Logical Constraints but without Shortcut Satisfaction
  86. Task Indicating Transformer for Task-conditional Dense Predictions
  87. DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion
  88. Small, Versatile and Mighty: A Range-View Perception Framework
  89. Softened Symbol Grounding for Neuro-symbolic Systems
  90. DEEP-IoT: Downlink-Enhanced Efficient-Power Internet of Things
  91. Axe the X in XAI: A Plea for Understandable AI
  92. Embedded Multi-label Feature Selection via Orthogonal Regression
  93. ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting
  94. Universal Auto-encoder Framework for MIMO CSI Feedback
  95. Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification
  96. Semantic Text Transmission via Prediction with Small Language Models: Cost-Similarity Trade-off
  97. Optimization of array encoding for ultrasound imaging
  98. A Survey of Route Recommendations: Methods, Applications, and Opportunities
  99. Shifted Interpolation for Differential Privacy
  100. Gender Bias in Large Language Models across Multiple Languages
  101. Graph Construction with Flexible Nodes for Traffic Demand Prediction
  102. CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation
  103. ARED: Argentina Real Estate Dataset
  104. Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval
  105. Event-Driven Learning for Spiking Neural Networks
  106. Large Convolutional Model Tuning via Filter Subspace
  107. Improving Acne Image Grading with Label Distribution Smoothing
  108. Spatial Cascaded Clustering and Weighted Memory for Unsupervised Person Re-identification
  109. Extracting Polymer Nanocomposite Samples from Full-Length Documents
  110. Deciphering diffuse scattering with machine learning and the equivariant foundation model: The case of molten FeO
  111. "Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach
  112. Robust deep labeling of radiological emphysema subtypes using squeeze and excitation convolutional neural networks: The MESA Lung and SPIROMICS Studies
  113. Cloud-based Federated Learning Framework for MRI Segmentation
  114. EUROPA: A Legal Multilingual Keyphrase Generation Dataset
  115. Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach
  116. YOLO-MED : Multi-Task Interaction Network for Biomedical Images
  117. CASIMIR: A Corpus of Scientific Articles enhanced with Multiple Author-Integrated Revisions
  118. Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance
  119. Causal Bandits with General Causal Models and Interventions
  120. On Cyclical MCMC Sampling
  121. Diffraction and Scattering Aware Radio Map and Environment Reconstruction using Geometry Model-Assisted Deep Learning
  122. DISORF: A Distributed Online 3D Reconstruction Framework for Mobile Robots
  123. A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection
  124. Transcription and translation of videos using fine-tuned XLSR Wav2Vec2 on custom dataset and mBART
  125. Trustworthy Self-Attention: Enabling the Network to Focus Only on the Most Relevant References
  126. ChartReformer: Natural Language-Driven Chart Image Editing
  127. MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysis
  128. Substitute adjustment via recovery of latent variables
  129. AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs