mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 30 Jan 2024

259 papers

  1. Rethinking Interpretability in the Era of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation +1
  2. PACE: A Pragmatic Agent for Enhancing Communication Efficiency Using Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless SystemsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. Security and Privacy Challenges of Large Language Models: A SurveyLLM safety and security → Prompt injection and agent security
  5. CaMU: Disentangling Causal Effects in Deep Model UnlearningLLM safety and security → Machine unlearning
  6. Efficient Tool Use with Chain-of-Abstraction ReasoningLLM reasoning → Reasoning benchmarks and evaluation +1
  7. Synthetic Dialogue Dataset Generation using LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. Robust Prompt Optimization for Defending Language Models Against Jailbreaking AttacksLLM safety and security → Jailbreaking
  9. You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale DistillationDiffusion models → Inverse problems and image restoration
  10. Weak-to-Strong Jailbreaking on Large Language ModelsLLM safety and security → Jailbreaking
  11. MouSi: Poly-Visual-Expert Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  12. GazeGPT: Augmenting Human Capabilities using Gaze-contingent Contextual AI for Smart EyewearMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  13. ContactGen: Contact-Guided Interactive 3D Human Generation for PartnersDiffusion models → Video generation
  14. Embracing Language Inclusivity and Diversity in CLIP through Continual Language LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  15. Transfer Learning for Text Diffusion ModelsDiffusion models → Discrete and text diffusion
  16. Zero-Shot Reinforcement Learning via Function EncodersDeep reinforcement learning methods → Deep RL algorithms and representations
  17. Conditional and Modal Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  18. Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo ChatLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. Explainable data-driven modeling via mixture of experts: towards effective blending of grey and black-box modelsMixture-of-experts → MoE theory and gating functions
  20. Online Robot Navigation and Manipulation with Distilled Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  21. Retrieval Augmented Deep Anomaly Detection for Tabular DataRetrieval-augmented generation → Privacy and security of RAG
  22. CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  23. M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  24. CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  25. Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion ControlDeep reinforcement learning methods → RL for robot locomotion and manipulation
  26. Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in ChessMixture-of-experts → MoE in reinforcement learning and robotics
  27. EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing DomainMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  28. Provably Robust Multi-bit Watermarking for AI-generated TextLLM safety and security → Watermarking generated content and models
  29. Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent DebateLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. Extrinsicaly Rewarded Soft Q Imitation Learning with DiscriminatorOffline RL and imitation learning from data → Imitation learning methods +1
  31. A Cross-Language Investigation into Jailbreak Attacks in Large Language ModelsLLM safety and security → Jailbreaking
  32. BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View DiffusionDiffusion models → 3D, point cloud and scene generation
  33. Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image PersonalizationDiffusion models → Image generation, text-to-image and editing
  34. Diffusion model for relational inferenceDiffusion models → Diffusion foundations and sampling
  35. Gradient-Based Language Model Red TeamingLLM safety and security → Prompt injection and agent security
  36. ILBiT: Imitation Learning for Robot Using Position and Torque Information based on Bilateral Control with TransformerOffline RL and imitation learning from data → Robot manipulation imitation learning
  37. Augmenting Replay in World Models for Continual Reinforcement LearningWorld models → Latent dynamics models and model-based RL +1
  38. Improving Reinforcement Learning from Human Feedback with Efficient Reward Model EnsembleLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  39. A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming
  40. STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models
  41. Neural Loss Function Evolution for Large-Scale Image Classifier Convolutional Neural Networks
  42. Realtime Facial Expression Recognition: Neuromorphic Hardware vs. Edge AI Accelerators
  43. Using Sequential Runtime Distributions for the Parallel Speedup Prediction of SAT Local Search
  44. Bridging Human Concepts and Computer Vision for Explainable Face Verification
  45. VerifIoU -- Robustness of Object Detection to Perturbations
  46. Multi-view Subspace Clustering via An Adaptive Consensus Graph Filter
  47. One-Spike SNN: Single-Spike Phase Coding with Base Manipulation for ANN-to-SNN Conversion Loss Minimization
  48. Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
  49. Human-Centric Goal Reasoning with Ripple-Down Rules
  50. Review of algorithms for predicting fatigue using EEG
  51. Progress in artificial intelligence applications based on the combination of self-driven sensors and deep learning
  52. QACP: An Annotated Question Answering Dataset for Assisting Chinese Python Programming Learners
  53. Spatial Computing: Concept, Applications, Challenges and Future Directions
  54. From Metrics to Meaning: Time to Rethink Evaluation in Human-AI Collaborative Design
  55. Exploring Prime Number Classification: Achieving High Recall Rate and Rapid Convergence with Sparse Encoding
  56. NanoNER: Named Entity Recognition for nanobiology using experts' knowledge and distant supervision
  57. When Large Language Models Meet Vector Databases: A Survey
  58. Commercial AI, Conflict, and Moral Responsibility: A theoretical analysis and practical approach to the moral responsibilities associated with dual-use AI technology
  59. Trust and ethical considerations in a multi-modal, explainable AI-driven chatbot tutoring system: The case of collaboratively solving Rubik's Cube
  60. Systematic Literature Review: Computational Approaches for Humour Style Classification
  61. Aalap: AI Assistant for Legal & Paralegal Functions in India
  62. SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis
  63. Identifying False Content and Hate Speech in Sinhala YouTube Videos by Analyzing the Audio
  64. Performance Assessment of ChatGPT vs Bard in Detecting Alzheimer's Dementia
  65. Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models
  66. Large Language Models in Cybersecurity: State-of-the-Art
  67. Unlocking the Power of Multi-institutional Data: Integrating and Harmonizing Genomic Data Across Institutions
  68. Exploitation Strategies in Conditional Markov Chain Search: A case study on the three-index assignment problem
  69. D-Nikud: Enhancing Hebrew Diacritization with LSTM and Pretrained Models
  70. Explainable AI for survival analysis: a median-SHAP approach
  71. Unraveling the Impact of Initial Choices and In-Loop Interventions on Learning Dynamics in Autonomous Scanning Probe Microscopy
  72. EvoMerge: Neuroevolution for Large Language Models
  73. Using the Abstract Computer Architecture Description Language to Model AI Hardware Accelerators
  74. Adapting Amidst Degradation: Cross Domain Li-ion Battery Health Estimation via Physics-Guided Test-Time Training
  75. Online speaker diarization of meetings guided by speech separation
  76. Anything in Any Scene: Photorealistic Video Object Insertion
  77. Arrows of Time for Large Language Models
  78. LeTO: Learning Constrained Visuomotor Policy with Differentiable Trajectory Optimization
  79. AdvGPS: Adversarial GPS for Multi-Agent Perception Attack
  80. Improving QA Model Performance with Cartographic Inoculation
  81. Towards Visual Syntactical Understanding
  82. Pixel to Elevation: Learning to Predict Elevation Maps at Long Range using Images for Autonomous Offroad Navigation
  83. Detecting mental disorder on social media: a ChatGPT-augmented explainable approach
  84. Rendering Wireless Environments Useful for Gradient Estimators: A Zero-Order Stochastic Federated Learning Method
  85. A Preliminary Study on Using Large Language Models in Software Pentesting
  86. Multiscale Parallel Tempering for Fast Sampling on Redistricting Plans
  87. Liquid Democracy for Low-Cost Ensemble Pruning
  88. Explaining Predictive Uncertainty by Exposing Second-Order Effects
  89. Difficulty Modelling in Mobile Puzzle Games: An Empirical Study on Different Methods to Combine Player Analytics and Simulated Data
  90. Can LLMs Replace Economic Choice Prediction Labs? The Case of Language-based Persuasion Games
  91. Integrating Generative AI in Hackathons: Opportunities, Challenges, and Educational Implications
  92. Superiority of Multi-Head Attention in In-Context Linear Regression
  93. Application of Neural Networks for the Reconstruction of Supernova Neutrino Energy Spectra Following Fast Neutrino Flavor Conversions
  94. Through-Wall Imaging based on WiFi Channel State Information
  95. Solving Boltzmann Optimization Problems with Deep Learning
  96. Step-size Optimization for Continual Learning
  97. Efficient Learning of Convolution Weights as Gaussian Mixture Model Posteriors
  98. Fine-tuning Transformer-based Encoder for Turkish Language Understanding Tasks
  99. Customizing Language Model Responses with Contrastive In-Context Learning
  100. Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens
All 259
  1. Arabic Tweet Act: A Weighted Ensemble Pre-Trained Transformer Model for Classifying Arabic Speech Acts on Twitter
  2. Time Series Supplier Allocation via Deep Black-Litterman Model
  3. Reproducibility, energy efficiency and performance of pseudorandom number generators in machine learning: a comparative study of python, numpy, tensorflow, and pytorch implementations
  4. YTCommentQA: Video Question Answerability in Instructional Videos
  5. A Latent Space Metric for Enhancing Prediction Confidence in Earth Observation Data
  6. A simple, strong baseline for building damage detection on the xBD dataset
  7. YOLO-World: Real-Time Open-Vocabulary Object Detection
  8. Effect of Weight Quantization on Learning Models by Typical Case Analysis
  9. Weaver: Foundation Models for Creative Writing
  10. ReacLLaMA: Merging chemical and textual information in chemical reactivity AI models
  11. Proactive Detection of Voice Cloning with Localized Watermarking
  12. SLIC: A Learned Image Codec Using Structure and Color
  13. LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation
  14. Achieving More Human Brain-Like Vision via Human EEG Representational Alignment
  15. ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
  16. Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning
  17. Self-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI
  18. Gazetteer-Enhanced Bangla Named Entity Recognition with BanglaBERT Semantic Embeddings K-Means-Infused CRF Model
  19. Adaptive Experiment Design with Synthetic Controls
  20. CPR++: Object Localization via Single Coarse Point Supervision
  21. NormEnsembleXAI: Unveiling the Strengths and Weaknesses of XAI Ensemble Techniques
  22. Single Word Change is All You Need: Using LLMs to Create Synthetic Training Examples for Text Classifiers
  23. Nested Construction of Polar Codes via Transformers
  24. Multi-Camera Asynchronous Ball Localization and Trajectory Prediction with Factor Graphs and Human Poses
  25. GraphViz2Vec: A Structure-aware Feature Generation Model to Improve Classification in GNNs
  26. Data-Driven Discovery of PDEs via the Adjoint Method
  27. A large dataset curation and benchmark for drug target interaction
  28. Learning Domain-Independent Green's Function For Elliptic Partial Differential Equations
  29. Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios
  30. Layered and Staged Monte Carlo Tree Search for SMT Strategy Synthesis
  31. An Open Software Suite for Event-Based Video
  32. Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models
  33. Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems
  34. SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Covers
  35. Personalized Differential Privacy for Ridge Regression
  36. Quantum time dynamics mediated by the Yang-Baxter equation and artificial neural networks
  37. Evaluation in Neural Style Transfer: A Review
  38. H-SynEx: Using synthetic images and ultra-high resolution ex vivo MRI for hypothalamus subregion segmentation
  39. MT-Ranker: Reference-free machine translation evaluation by inter-system ranking
  40. Deep Learning-Driven Approach for Handwritten Chinese Character Classification
  41. Traffic estimation in unobserved network locations using data-driven macroscopic models
  42. StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis
  43. NNOSE: Nearest Neighbor Occupational Skill Extraction
  44. Active Generation Network of Human Skeleton for Action Recognition
  45. Dynamical Survival Analysis with Controlled Latent States
  46. Non-central panorama indoor dataset
  47. SemScore: Automated Evaluation of Instruction-Tuned LLMs based on Semantic Textual Similarity
  48. Efficient Gesture Recognition on Spiking Convolutional Networks Through Sensor Fusion of Event-Based and Depth Data
  49. Outline of an Independent Systematic Blackbox Test for ML-based Systems
  50. OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision
  51. Atlanta Scaled layouts from non-central panoramas
  52. Floor extraction and door detection for visually impaired guidance
  53. BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation
  54. ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorization
  55. Explaining Explanations in Probabilistic Logic Programming
  56. Scalable Mechanism Design for Multi-Agent Path Finding
  57. Forecasting VIX using Bayesian Deep Learning
  58. Gower's similarity coefficients with automatic weight selection
  59. Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests
  60. Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR
  61. Enhancing Gaussian Process Surrogates for Optimization and Posterior Approximation via Random Exploration
  62. Data organization limits the predictability of binary classification
  63. Robust Kernel Sparse Subspace Clustering
  64. Multilayer Graph Approach to Deep Subspace Clustering
  65. LADDER: Revisiting the Cosmic Distance Ladder with Deep Learning Approaches and Exploring its Applications
  66. Heterogeneous treatment effect estimation with subpopulation identification for personalized medicine in opioid use disorder
  67. Static and Dynamic Synthesis of Bengali and Devanagari Signatures
  68. MF-MOS: A Motion-Focused Model for Moving Object Segmentation
  69. Evaluation of Out-of-Distribution Detection Performance on Autonomous Driving Datasets
  70. Finetuning Large Language Models for Vulnerability Detection
  71. Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels
  72. Causal Machine Learning for Cost-Effective Allocation of Development Aid
  73. Multiple Yield Curve Modeling and Forecasting using Deep Learning
  74. ActDroid: An active learning framework for Android malware detection
  75. Selection of gamma events from IACT images with deep learning methods
  76. Deep 3D World Models for Multi-Image Super-Resolution Beyond Optical Flow
  77. Distinguishing Fictional Voices: a Study of Authorship Verification Models for Quotation Attribution
  78. Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment
  79. Online Resource Allocation with Non-Stationary Customers
  80. Dynamical System Identification, Model Selection and Model Uncertainty Quantification by Bayesian Inference
  81. Segmentation and Characterization of Macerated Fibers and Vessels Using Deep Learning
  82. Multi-modal Representation Learning for Cross-modal Prediction of Continuous Weather Patterns from Discrete Low-Dimensional Data
  83. Dynamic MRI reconstruction using low-rank plus sparse decomposition with smoothness regularization
  84. Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation
  85. Sparse Portfolio Selection via Topological Data Analysis based Clustering
  86. Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials
  87. Cross-Lingual Transfer from Related Languages: Treating Low-Resource Maltese as Multilingual Code-Switching
  88. CAFCT-Net: A CNN-Transformer Hybrid Network with Contextual and Attentional Feature Fusion for Liver Tumor Segmentation
  89. Zero-shot Classification using Hyperdimensional Computing
  90. A Tournament of Transformation Models: B-Spline-based vs. Mesh-based Multi-Objective Deformable Image Registration
  91. State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Tracking
  92. Repositioning the Subject within Image
  93. Evaluating ML-Based Anomaly Detection Across Datasets of Varied Integrity: A Case Study
  94. Coseparable Nonnegative Tensor Factorization With T-CUR Decomposition
  95. Analysis of Knowledge Tracing performance on synthesised student data
  96. H2O-Danube-1.8B Technical Report
  97. Reviving Undersampling for Long-Tailed Learning
  98. An Embeddable Implicit IUVD Representation for Part-based 3D Human Surface Reconstruction
  99. Encoding Temporal Statistical-space Priors via Augmented Representation
  100. Detecting LLM-assisted writing in scientific communication: Are we there yet?
  101. PBSCR: The Piano Bootleg Score Composer Recognition Dataset
  102. Online Algorithm for Node Feature Forecasting in Temporal Graphs
  103. Learnable Prompt as Pseudo-Imputation: Rethinking the Necessity of Traditional EHR Data Imputation in Downstream Clinical Prediction
  104. Performance Insights-based AI-driven Football Transfer Fee Prediction
  105. Accelerated Cloud for Artificial Intelligence (ACAI)
  106. HawkEye: Advancing Robust Regression with Bounded, Smooth, and Insensitive Loss Function
  107. Graph Fairness Learning under Distribution Shifts
  108. A Literature Review on Fetus Brain Motion Correction in MRI
  109. All-optical complex field imaging using diffractive processors
  110. IN-Flow: Instance Normalization Flow for Non-stationary Time Series Forecasting
  111. Leveraging Nested MLMC for Sequential Neural Posterior Estimation with Intractable Likelihoods
  112. Activity Detection for Massive Connectivity in Cell-free Networks with Unknown Large-scale Fading, Channel Statistics, Noise Variance, and Activity Probability: A Bayesian Approach
  113. MolPLA: A Molecular Pretraining Framework for Learning Cores, R-Groups and their Linker Joints
  114. Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning
  115. One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training
  116. SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget
  117. AI Oversight and Human Mistakes: Evidence from Centre Court
  118. MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images
  119. Detecting Racist Text in Bengali: An Ensemble Deep Learning Framework
  120. MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
  121. ShaRP: Explaining Rankings and Preferences with Shapley Values
  122. Generative AI-based closed-loop fMRI system
  123. MESA: Matching Everything by Segmenting Anything
  124. Engineering A Large Language Model From Scratch
  125. Towards Generating Informative Textual Description for Neurons in Language Models
  126. Widely Linear Matched Filter: A Lynchpin towards the Interpretability of Complex-valued CNNs
  127. Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models
  128. Optimal-Landmark-Guided Image Blending for Face Morphing Attacks
  129. SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing
  130. OptiState: State Estimation of Legged Robots using Gated Networks with Transformer-based Vision and Kalman Filtering
  131. Prospects for inconsistency detection using large language models and sheaves
  132. LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field Cameras
  133. Multivariate Beta Mixture Model: Probabilistic Clustering With Flexible Cluster Shapes
  134. Multi-granularity Correspondence Learning from Long-term Noisy Videos
  135. Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers
  136. EdgeOL: Efficient in-situ Online Learning on Edge Devices
  137. Calibration-then-Calculation: A Variance Reduced Metric Framework in Deep Click-Through Rate Prediction Models
  138. Characterization of Magnetic Labyrinthine Structures Through Junctions and Terminals Detection Using Template Matching and CNN
  139. Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
  140. Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selection
  141. Polynomial Chaos Expansions on Principal Geodesic Grassmannian Submanifolds for Surrogate Modeling and Uncertainty Quantification
  142. The Detection and Understanding of Fictional Discourse
  143. T3: Transparent Tracking & Triggering for Fine-grained Overlap of Compute & Collectives
  144. AutoIE: An Automated Framework for Information Extraction from Scientific Literature
  145. Improving Global Weather and Ocean Wave Forecast with Large Artificial Intelligence Models
  146. Fast Dual-Regularized Autoencoder for Sparse Biological Data
  147. VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality
  148. Generalization of LiNGAM that allows confounding
  149. History-Aware Conversational Dense Retrieval
  150. OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
  151. Recovering Mental Representations from Large Language Models with Markov Chain Monte Carlo
  152. Rademacher Complexity of Neural ODEs via Chen-Fliess Series
  153. Using Motion Forecasting for Behavior-Based Virtual Reality (VR) Authentication
  154. Incoherent Probability Judgments in Large Language Models
  155. Speeding up and reducing memory usage for scientific machine learning via mixed precision
  156. TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese
  157. Breaking Free Transformer Models: Task-specific Context Attribution Promises Improved Generalizability Without Fine-tuning Pre-trained LLMs
  158. The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Exploration
  159. I came, I saw, I certified: some perspectives on the safety assurance of cyber-physical systems