mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 1 Nov 2023

253 papers

  1. RoboVQA: Multimodal Long-Horizon Reasoning for RoboticsLLM reasoning → Spatial and embodied reasoning
  2. VQA-GEN: A Visual Question Answering Benchmark for Domain GeneralizationLLM reasoning → Multimodal reasoning
  3. On Manipulating Scene Text in the Wild with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  4. ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action DetectionMultimodal LLMs / vision-language models → Video understanding with MLLMs
  5. De-Diffusion Makes Text a Strong Cross-Modal InterfaceDiffusion models → Image generation, text-to-image and editing
  6. Controllable Music Production with Diffusion Models and Guidance GradientsDiffusion models → Audio, speech and music
  7. Crosslingual Retrieval Augmented In-context Learning for BanglaRetrieval-augmented generation → Generation and context integration
  8. Efficient LLM Inference on CPUsEfficient LLM inference and serving → Serving systems and request scheduling
  9. Intriguing Properties of Data Attribution on Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  10. Generating HSR Bogie Vibration Signals via Pulse Voltage-Guided Conditional Diffusion ModelDiffusion models → Flow matching, time series and science
  11. Comparing Optimization Targets for Contrast-Consistent SearchMechanistic interpretability → Probing deception, bias and beliefs
  12. Group Distributionally Robust Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  13. Diffusion models for probabilistic programmingDiffusion models → Discrete and text diffusion
  14. Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound VideosDiffusion models → Medical imaging and segmentation
  15. A Systematic Comparison of Syllogistic Reasoning in Humans and Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  16. Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo LabellingKnowledge distillation → Speech and audio distillation
  17. NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural NetworksKnowledge distillation → Federated, robust and private distillation
  18. Towards Omni-supervised Referring Expression SegmentationKnowledge distillation → Detection and dense prediction distillation
  19. LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video TranslationDiffusion models → Video generation
  20. Space Narrative: Generating Images and 3D Scenes of Chinese Garden from Text using Deep LearningDiffusion models → Image generation, text-to-image and editing
  21. JADE: A Linguistics-based Safety Evaluation Platform for Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  22. Mixture-of-Experts for Open Set Domain Adaptation: A Dual-Space Detection ApproachMixture-of-experts → Vision mixture-of-experts
  23. SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy ConversationsLLM reasoning → Clinical and biomedical applications
  24. Rethinking Decision Transformer via Hierarchical Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  25. Adaptive Latent Diffusion Model for 3D Medical Image to Image Translation: Multi-modal Magnetic Resonance Imaging StudyDiffusion models → Medical imaging and segmentation
  26. Plug-and-Play Policy Planner for Large Language Model Powered Dialogue AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  27. Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral AnalysisLLM reasoning → Prompting and chain-of-thought reasoning
  28. ChatGPT-Powered Hierarchical Comparisons for Image ClassificationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  29. MTAC: Hierarchical Reinforcement Learning-based Multi-gait Terrain-adaptive Quadruped Controller
  30. Walnut Detection Through Deep Learning Enhanced by Multispectral Synthetic Images
  31. Delta Score: Improving the Binding Assessment of Structure-Based Drug Design Methods
  32. An Innovative Tool for Uploading/Scraping Large Image Datasets on Social Networks
  33. Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio
  34. An Improved Transformer-based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach
  35. From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems
  36. Ontology-Driven Processing of Transdisciplinary Domain Knowledge
  37. Assessing Upper Limb Motor Function in the Immediate Post-Stroke Perioud Using Accelerometry
  38. Transferability and explainability of deep learning emulators for regional climate model projections: Perspectives for future applications
  39. Relax: Composable Abstractions for End-to-End Dynamic Machine Learning
  40. Notion of Explainable Artificial Intelligence -- An Empirical Investigation from A Users Perspective
  41. Solving MaxSAT with Matrix Multiplication
  42. Applications of the Theory of Aggregated Markov Processes in Stochastic Learning Theory
  43. Patch-Based Deep Unsupervised Image Segmentation using Graph Cuts
  44. Adversarial Examples in the Physical World: A Survey
  45. Data-Driven Model Selections of Second-Order Particle Dynamics via Integrating Gaussian Processes with Low-Dimensional Interacting Structures
  46. On The Open Prompt Challenge In Conditional Audio Generation
  47. In-Context Prompt Editing For Conditional Audio Generation
  48. SALLM: Security Assessment of Generated Code
  49. COSTAR: Improved Temporal Counterfactual Estimation with Self-Supervised Learning
  50. SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimization
  51. Learning Collective Behaviors from Observation
  52. Low-latency Real-time Voice Conversion on CPU
  53. Pretraining Data Mixtures Enable Narrow Model Selection Capabilities in Transformer Models
  54. Automatic Disfluency Detection from Untranscribed Speech
  55. Generalizing Nonlinear ICA Beyond Structural Sparsity
  56. Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning
  57. Training Dynamics of Contextual N-Grams in Language Models
  58. Zero Coordinate Shift: Whetted Automatic Differentiation for Physics-informed Operator Learning
  59. Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems
  60. SmoothHess: ReLU Network Feature Interactions via Stein's Lemma
  61. A Multi-Agent Reinforcement Learning Framework for Public Health Decision Analysis
  62. Electronic excited states from physically-constrained machine learning
  63. healthAIChain: Improving security and safety using Blockchain Technology applications in AI-based healthcare systems
  64. Sharp Noisy Binary Search with Monotonic Probabilities
  65. Constant-time Motion Planning with Anytime Refinement for Manipulation
  66. Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity Typing
  67. A quantum-classical performance separation in nonconvex optimization
  68. A Call to Arms: AI Should be Critical for Social Media Analysis of Conflict Zones
  69. Mahalanobis-Aware Training for Out-of-Distribution Detection
  70. Neural Field Dynamics Model for Granular Object Piles Manipulation
  71. GIST: Generated Inputs Sets Transferability in Deep Learning
  72. Beyond still images: Temporal features and input variance resilience
  73. Tipping Points of Evolving Epidemiological Networks: Machine Learning-Assisted, Data-Driven Effective Modeling
  74. Automatic counting of planting microsites via local visual detection and global count estimation
  75. Construction Artifacts in Metaphor Identification Datasets
  76. Accelerating Electronic Stopping Power Predictions by 10 Million Times with a Combination of Time-Dependent Density Functional Theory and Machine Learning
  77. Harnessing machine learning for accurate treatment of overlapping opacity species in general circulation models
  78. Conformalized Deep Splines for Optimal and Efficient Prediction Sets
  79. SAGE: Smart home Agent with Grounded Execution
  80. Language Model Training Paradigms for Clinical Feature Embeddings
  81. Hand Gesture Classification on Praxis Dataset: Trading Accuracy for Expense
  82. Challenges for Linguistically-Driven Computer-Based Sign Recognition from Continuous Signing for American Sign Language
  83. Learning to Design and Use Tools for Robotic Manipulation
  84. Are These the Same Apple? Comparing Images Based on Object Intrinsics
  85. Sorting with Predictions
  86. Can Large Language Models Design Accurate Label Functions?
  87. Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?
  88. Real-Time Magnetic Tracking and Diagnosis of COVID-19 via Machine Learning
  89. PET Tracer Conversion among Brain PET via Variable Augmented Invertible Network
  90. tmn at #SMM4H 2023: Comparing Text Preprocessing Techniques for Detecting Tweets Self-reporting a COVID-19 Diagnosis
  91. Enhancing Clustering Representations with Positive Proximity and Cluster Dispersion Learning
  92. End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
  93. Decision Support Framework for Home Health Caregiver Allocation Using Optimally Tuned Spectral Clustering and Genetic Algorithm
  94. Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving
  95. On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval
  96. Software Repositories and Machine Learning Research in Cyber Security
  97. What User Behaviors Make the Differences During the Process of Visual Analytics?
  98. Collaboration in Immersive Environments: Challenges and Solutions
  99. Improving Interpersonal Communication by Simulating Audiences with Language Models
  100. Little Giants: Exploring the Potential of Small LLMs as Evaluation Metrics in Summarization in the Eval4NLP 2023 Shared Task
All 253
  1. Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation
  2. Deep Learning-Based Classification of Gamma Photon Interactions in Room-Temperature Semiconductor Radiation Detectors
  3. Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs
  4. Complexity of Single Loop Algorithms for Nonlinear Programming with Stochastic Objective and Constraints
  5. Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
  6. Recovering Linear Causal Models with Latent Variables via Cholesky Factorization of Covariance Matrix
  7. Emotion Detection for Misinformation: A Review
  8. ProcSim: Proxy-based Confidence for Robust Similarity Learning
  9. Latent Space Translation via Semantic Alignment
  10. Variational Gaussian Processes For Linear Inverse Problems
  11. TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in Rain
  12. Explicit Morphological Knowledge Improves Pre-training of Language Models for Hebrew
  13. Adaptive Spatio-temporal Estimation on the Graph Edges via Line Graph Transformation
  14. Emergence of Collective Open-Ended Exploration from Decentralized Meta-Reinforcement Learning
  15. FAIRLABEL: Correcting Bias in Labels
  16. Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
  17. A Bi-level Framework for Traffic Accident Duration Prediction: Leveraging Weather and Road Condition Data within a Practical Optimum Pipeline
  18. Formal Translation from Reversing Petri Nets to Coloured Petri Nets
  19. Noise Correction on Subjective Datasets
  20. A Collaborative Filtering-Based Two Stage Model with Item Dependency for Course Recommendation
  21. Occluded Person Re-Identification with Deep Learning: A Survey and Perspectives
  22. Structure Learning with Adaptive Random Neighborhood Informed MCMC
  23. Rethinking Variational Inference for Probabilistic Programs with Stochastic Support
  24. Coop: Memory is not a Commodity
  25. Boosting Summarization with Normalizing Flows and Aggressive Training
  26. PAUMER: Patch Pausing Transformer for Semantic Segmentation
  27. Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value
  28. Flexible Tails for Normalising Flows, with Application to the Modelling of Financial Return Data
  29. Revealing CNN Architectures via Side-Channel Analysis in Dataflow-based Inference Accelerators
  30. Transfer learning for improved generalizability in causal physics-informed neural networks for beam simulations
  31. Personalized Assignment to One of Many Treatment Arms via Regularized and Clustered Joint Assignment Forests
  32. LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing
  33. Scalable kernel balancing weights in a nationwide observational study of hospital profit status and heart attack outcomes
  34. A Robust Deep Learning Method with Uncertainty Estimation for the Pathological Classification of Renal Cell Carcinoma based on CT Images
  35. CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders
  36. Detecting Visual Cues in the Intensive Care Unit and Association with Patient Clinical Status
  37. Online Student-t Processes with an Overall-local Scale Structure for Modelling Non-stationary Data
  38. MNN: Mixed Nearest-Neighbors for Self-Supervised Learning
  39. Learning to optimize by multi-gradient for multi-objective optimization
  40. ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
  41. Polynomial Chaos Surrogate Construction for Random Fields with Parametric Uncertainty
  42. Continual atlas-based segmentation of prostate MRI
  43. Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle
  44. An Embedded Diachronic Sense Change Model with a Case Study from Ancient Greek
  45. Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial
  46. Active Noise Control Portable Device Design
  47. Advances in Embodied Navigation Using Large Language Models: A Survey
  48. Learning impartial policies for sequential counterfactual explanations using Deep Reinforcement Learning
  49. Text Rendering Strategies for Pixel Language Models
  50. REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning
  51. Improving Cardiovascular Disease Prediction Through Comparative Analysis of Machine Learning Models: A Case Study on Myocardial Infarction
  52. Rule-Based Error Classification for Analyzing Differences in Frequent Errors
  53. Robustness Tests for Automatic Machine Translation Metrics with Adversarial Attacks
  54. Bayes-enhanced Multi-view Attention Networks for Robust POI Recommendation
  55. Deep Neural Networks for Automatic Speaker Recognition Do Not Learn Supra-Segmental Temporal Features
  56. DEFN: Dual-Encoder Fourier Group Harmonics Network for Three-Dimensional Indistinct-Boundary Object Segmentation
  57. Fixed-Budget Best-Arm Identification in Sparse Linear Bandits
  58. Style Locality for Controllable Generation with kNN Language Models
  59. Asynchronous SGD on Graphs: a Unified Framework for Asynchronous Decentralized and Federated Optimization
  60. Robust and Conjugate Gaussian Process Regression
  61. Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design
  62. Optimal Budgeted Rejection Sampling for Generative Models
  63. Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture
  64. Progressive Recurrent Network for Shadow Removal
  65. CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
  66. Hessian Eigenvectors and Principal Component Analysis of Neural Network Weight Matrices
  67. Discourse Relations Classification and Cross-Framework Discourse Relation Classification Through the Lens of Cognitive Dimensions: An Empirical Investigation
  68. On the Opportunities of Green Computing: A Survey
  69. Form follows Function: Text-to-Text Conditional Graph Generation based on Functional Requirements
  70. Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation
  71. Enhancing Traffic Object Detection in Variable Illumination with RGB-Event Fusion
  72. Event-based Background-Oriented Schlieren
  73. Crop Disease Classification using Support Vector Machines with Green Chromatic Coordinate (GCC) and Attention based feature extraction for IoT based Smart Agricultural Applications
  74. Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards
  75. Neural Implicit Field Editing Considering Object-environment Interaction
  76. Efficient Human-AI Coordination via Preparatory Language-based Convention
  77. Feature-oriented Deep Learning Framework for Pulmonary Cone-beam CT (CBCT) Enhancement with Multi-task Customized Perceptual Loss
  78. AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification
  79. Couples can be tractable: New algorithms and hardness results for the Hospitals / Residents problem with Couples
  80. A Spatial-Temporal Transformer based Framework For Human Pose Assessment And Correction in Education Scenarios
  81. Open-Set Face Recognition with Maximal Entropy and Objectosphere Loss
  82. Enhanced Knowledge Injection for Radiology Report Generation
  83. Augmenting deep neural networks with symbolic knowledge: Towards trustworthy and interpretable AI for education
  84. Fixation-based Self-calibration for Eye Tracking in VR Headsets
  85. NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function
  86. Will Code Remain a Relevant User Interface for End-User Programming with Generative AI Models?
  87. Uncertainty quantification and out-of-distribution detection using surjective normalizing flows
  88. Architecture of Data Anomaly Detection-Enhanced Decentralized Expert System for Early-Stage Alzheimer's Disease Prediction
  89. Learning Cooperative Trajectory Representations for Motion Forecasting
  90. Performance Optimization of Deep Learning Sparse Matrix Kernels on Intel Max Series GPU
  91. Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition
  92. Rethinking Samples Selection for Contrastive Learning: Mining of Potential Samples
  93. QFree: A Universal Value Function Factorization for Multi-Agent Reinforcement Learning
  94. Adversarially Robust Distributed Count Tracking via Partial Differential Privacy
  95. A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
  96. Body and Head Orientation Estimation from Low-Resolution Point Clouds in Surveillance Settings
  97. fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding
  98. The Open DAC 2023 Dataset and Challenges for Sorbent Discovery in Direct Air Capture
  99. MetisFL: An Embarrassingly Parallelized Controller for Scalable & Efficient Federated Learning Workflows
  100. SDF4CHD: Generative Modeling of Cardiac Anatomies with Congenital Heart Defects
  101. Latent Space Inference For Spatial Transcriptomics
  102. Multi-task Representation Learning for Pure Exploration in Bilinear Bandits
  103. Robust Graph Clustering via Meta Weighting for Noisy Graphs
  104. HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning
  105. Semantic Hearing: Programming Acoustic Scenes with Binaural Hearables
  106. Flooding Regularization for Stable Training of Generative Adversarial Networks
  107. Data Augmentation for Code Translation with Comparable Corpora and Multiple References
  108. Federated Topic Model and Model Pruning Based on Variational Autoencoder
  109. Unsupervised Lexical Simplification with Context Augmentation
  110. From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities
  111. Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation
  112. Stacking an autoencoder for feature selection of zero-day threats
  113. Detecting Syllable-Level Pronunciation Stress with A Self-Attention Model
  114. Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusion
  115. An Empirical Study of Frame Selection for Text-to-Video Retrieval
  116. Semantic Representation Learning of Scientific Literature based on Adaptive Feature and Graph Neural Network
  117. IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models
  118. Graph Representation Learning for Infrared and Visible Image Fusion
  119. Inference of CO2 flow patterns -- a feasibility study
  120. Precise Error Rates for Computationally Efficient Testing
  121. Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks
  122. Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models
  123. Model-driven Engineering for Machine Learning Components: A Systematic Literature Review
  124. TLMCM Network for Medical Image Hierarchical Multi-Label Classification
  125. Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection
  126. OpenForest: A data catalogue for machine learning in forest monitoring
  127. Generalization Bounds for Label Noise Stochastic Gradient Descent
  128. ChatCoder: Chat-based Refine Requirement Improves LLMs' Code Generation
  129. Syntactic Inductive Bias in Transformer Language Models: Especially Helpful for Low-Resource Languages?
  130. Incentivized Collaboration in Active Learning
  131. Solutions to Elliptic and Parabolic Problems via Finite Difference Based Unsupervised Small Linear Convolutional Neural Networks
  132. Active Neural Topological Mapping for Multi-Agent Exploration
  133. RAUNE-Net: A Residual and Attention-Driven Underwater Image Enhancement Method
  134. 1DFormer: a Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Tracking
  135. The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis
  136. Implicit biases in multitask and continual learning from a backward error analysis perspective
  137. Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
  138. DistDNAS: Search Efficient Feature Interactions within 2 Hours
  139. DINO-Mix: Enhancing Visual Place Recognition with Foundational Vision Model and Feature Mixing
  140. StableFDG: Style and Attention Based Learning for Federated Domain Generalization
  141. Transformers are Provably Optimal In-context Estimators for Wireless Communications
  142. Domain decomposition-based coupling of physics-informed neural networks via the Schwarz alternating method
  143. Is GPT Powerful Enough to Analyze the Emotions of Memes?
  144. Can Large Language Models Capture Public Opinion about Global Warming? An Empirical Assessment of Algorithmic Fidelity and Bias
  145. WinNet: Make Only One Convolutional Layer Effective for Time Series Forecasting
  146. Consistent Video-to-Video Transfer Using Synthetic Dataset
  147. A Unified Framework to Enforce, Discover, and Promote Symmetry in Machine Learning
  148. What Formal Languages Can Transformers Express? A Survey
  149. Magmaw: Modality-Agnostic Adversarial Attacks on Machine Learning-Based Wireless Communication Systems
  150. Continuous Training and Fine-tuning for Domain-Specific Language Models in Medical Question Answering
  151. Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities
  152. Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
  153. Machine learning for accuracy in density functional approximations