mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 20 Sep 2023

230 papers

  1. SCREWS: A Modular Framework for Reasoning with RevisionsLLM reasoning → Test-time compute and efficient thinking
  2. "It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational AgentsLLM agents and tool use → Agent threats, guardrails and governance
  3. Cloud-Based Hierarchical Imitation Learning for Scalable Transfer of Construction Skills from Human Workers to Assisting RobotsOffline RL and imitation learning from data → Robot manipulation imitation learning
  4. Latent Diffusion Models for Structural Component DesignDiffusion models → 3D, point cloud and scene generation
  5. Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler ChallengeLLM safety and security → Vision-language and text-to-image safety
  6. Light Field Diffusion for Single-View Novel View SynthesisDiffusion models → 3D, point cloud and scene generation
  7. DreamLLM: Synergistic Multimodal Comprehension and CreationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  8. FreeU: Free Lunch in Diffusion U-NetDiffusion models → Diffusion foundations and sampling
  9. Text2Reward: Reward Shaping with Language Models for Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  10. Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial IntelligenceLLM agents and tool use → Social simulation and multi-agent debate
  11. Weight Averaging Improves Knowledge Distillation under Domain ShiftKnowledge distillation → General knowledge distillation methods
  12. You Only Look at Screens: Multimodal Chain-of-Action AgentsLLM agents and tool use → GUI and mobile agents
  13. Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical ModelsDiffusion models → Diffusion foundations and sampling
  14. EDMP: Ensemble-of-costs-guided Diffusion for Motion PlanningDiffusion models → Diffusion and flow policies for robotics
  15. Discuss Before Moving: Visual Language Navigation via Multi-expert DiscussionsWorld models → World models for navigation
  16. Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  17. Face Aging via Diffusion-based EditingDiffusion models → Image generation, text-to-image and editing
  18. Speak While You Think: Streaming Speech Synthesis During Text GenerationLLM reasoning → Audio-language model reasoning
  19. Are Large Language Models Really Robust to Word-Level Perturbations?LLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  20. CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  21. Investigating Personalization Methods in Text to Music GenerationDiffusion models → Audio, speech and music
  22. Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image GenerationKnowledge distillation → Knowledge distillation for LLMs
  23. PSDiff: Diffusion Model for Person Search with Iterative and Collaborative RefinementDiffusion models → Image generation, text-to-image and editing
  24. Design of Chain-of-Thought in Math Problem SolvingLLM reasoning → Prompting and chain-of-thought reasoning
  25. Score Mismatching for Generative ModelingDiffusion models → Diffusion foundations and sampling
  26. Combining low-dose CT-based radiomics and metabolomics for early lung cancer screening support
  27. AI (r)evolution -- where are we heading? Thoughts about the future of music and sound technologies in the era of deep learning
  28. GPT-MolBERTa: GPT Molecular Features Language Model for molecular property prediction
  29. Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization
  30. Fairness Hub Technical Briefs: AUC Gap
  31. SR-PredictAO: Session-based Recommendation with High-Capability Predictor Add-On
  32. Semi-supervised News Discourse Profiling with Contrastive Learning
  33. RAI4IoE: Responsible AI for Enabling the Internet of Energy
  34. LLM Guided Inductive Inference for Solving Compositional Problems
  35. Large-scale Pretraining Improves Sample Efficiency of Active Learning based Molecule Virtual Screening
  36. Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Framework
  37. Federated Learning with Neural Graphical Models
  38. A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
  39. Generative AI in Mafia-like Game Simulation
  40. Popularity Degradation Bias in Local Music Recommendation
  41. Construction of Paired Knowledge Graph-Text Datasets Informed by Cyclic Evaluation
  42. Towards Effective Disambiguation for Machine Translation with Large Language Models
  43. Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation
  44. Neural Image Compression Using Masked Sparse Visual Representation
  45. Distribution-Independent Regression for Generalized Linear Models with Oblivious Corruptions
  46. Drift Control of High-Dimensional RBM: A Computational Method Based on Neural Networks
  47. Orbital AI-based Autonomous Refuelling Solution
  48. Potential and limitations of random Fourier features for dequantizing quantum machine learning
  49. An Evaluation of Machine Learning Approaches for Early Diagnosis of Autism Spectrum Disorder
  50. Attentive VQ-VAE
  51. A survey on the semantics of sequential patterns with negation
  52. GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Multi-Human View Synthesis
  53. Leveraging Negative Signals with Self-Attention for Sequential Music Recommendation
  54. Statistical Complexity of Quantum Learning
  55. Hate speech detection in algerian dialect using deep learning
  56. Hand Gesture Recognition with Two Stage Approach Using Transfer Learning and Deep Ensemble Learning
  57. Dataset Factory: A Toolchain For Generative Computer Vision Datasets
  58. Sentence Attention Blocks for Answer Grounding
  59. Continuous Levels of Detail for Light Field Networks
  60. CATS: Conditional Adversarial Trajectory Synthesis for Privacy-Preserving Trajectory Data Publication Using Deep Learning Approaches
  61. SpeechAlign: a Framework for Speech Translation Alignment Evaluation
  62. Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalization
  63. Examining the Limitations of Computational Rumor Detection Models Trained on Static Datasets
  64. Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding
  65. BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model
  66. SignBank+: Preparing a Multilingual Sign Language Dataset for Machine Translation Using Large Language Models
  67. Hierarchical reinforcement learning with natural language subgoals
  68. Limitations in odour recognition and generalisation in a neuromorphic olfactory circuit
  69. EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization
  70. Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
  71. TrueLearn: A Python Library for Personalised Informational Recommendations with (Implicit) Feedback
  72. Likelihood-based Sensor Calibration using Affine Transformation
  73. RMT: Retentive Networks Meet Vision Transformers
  74. Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning
  75. Chain-of-Verification Reduces Hallucination in Large Language Models
  76. Flow Annealed Kalman Inversion for Gradient-Free Inference in Bayesian Inverse Problems
  77. Fictional Worlds, Real Connections: Developing Community Storytelling Social Chatbots through LLMs
  78. Creating walls to avoid unwanted points in root finding and optimization
  79. Multi-view Fuzzy Representation Learning with Rules based Model
  80. Model-free tracking control of complex dynamical trajectories with machine learning
  81. Multi-Label Takagi-Sugeno-Kang Fuzzy System
  82. Budget-Aware Pruning: Handling Multiple Domains with Less Parameters
  83. AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition
  84. Digital twins of nonlinear dynamical systems: A perspective
  85. Multi-Step Model Predictive Safety Filters: Reducing Chattering by Increasing the Prediction Horizon
  86. Using deep learning to construct stochastic local search SAT solvers with performance bounds
  87. Distribution and volume based scoring for Isolation Forests
  88. SkeleTR: Towrads Skeleton-based Action Recognition in the Wild
  89. Signature Activation: A Sparse Signal View for Holistic Saliency
  90. Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction
  91. A Systematic Review of Few-Shot Learning in Medical Imaging
  92. Generative Pre-Training of Time-Series Data for Unsupervised Fault Detection in Semiconductor Manufacturing
  93. CalibFPA: A Focal Plane Array Imaging System based on Online Deep-Learning Calibration
  94. KOSMOS-2.5: A Multimodal Literate Model
  95. CNNs for JPEGs: A Study in Computational Cost
  96. Enhancing motion trajectory segmentation of rigid bodies using a novel screw-based trajectory-shape representation
  97. Transformers versus LSTMs for electronic trading
  98. Safurai 001: New Qualitative Approach for Code LLM Evaluation
  99. Long-Form End-to-End Speech Translation via Latent Alignment Segmentation
  100. Studying Lobby Influence in the European Parliament
All 230
  1. Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff
  2. Preconditioned Federated Learning
  3. Learning and DiSentangling Patient Static Information from Time-series Electronic HEalth Record (STEER)
  4. Dynamic Hand Gesture-Featured Human Motor Adaptation in Tool Delivery using Voice Recognition
  5. Knowledge Graph Question Answering for Materials Science (KGQA4MAT): Developing Natural Language Interface for Metal-Organic Frameworks Knowledge Graph (MOF-KG) Using LLM
  6. 3D Face Reconstruction: the Road to Forensics
  7. A Comprehensive Survey on Rare Event Prediction
  8. Self-supervised learning unveils change in urban housing from street-level images
  9. C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters
  10. GECTurk: Grammatical Error Correction and Detection Dataset for Turkish
  11. Using Property Elicitation to Understand the Impacts of Fairness Regularizers
  12. Article Classification with Graph Neural Networks and Multigraphs
  13. TRAVID: An End-to-End Video Translation Framework
  14. You can have your ensemble and run it too -- Deep Ensembles Spread Over Time
  15. Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism
  16. Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition
  17. How to turn your camera into a perfect pinhole model
  18. DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services
  19. WFTNet: Exploiting Global and Local Periodicity in Long-term Time Series Forecasting
  20. Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric Chest X-ray images
  21. Dynamic Pricing of Applications in Cloud Marketplaces using Game Theory
  22. A Competition-based Pricing Strategy in Cloud Markets using Regret Minimization Techniques
  23. Rating Prediction in Conversational Task Assistants with Behavioral and Conversational-Flow Features
  24. FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion
  25. Create and Find Flatness: Building Flat Training Spaces in Advance for Continual Learning
  26. Generalizing Across Domains in Diabetic Retinopathy via Variational Autoencoders
  27. A Cost-Aware Mechanism for Optimized Resource Provisioning in Cloud Computing
  28. CPLLM: Clinical Prediction with Large Language Models
  29. Beyond Accuracy: Measuring Representation Capacity of Embeddings to Preserve Structural and Contextual Information
  30. Overview of AuTexTification at IberLEF 2023: Detection and Attribution of Machine-Generated Text in Multiple Domains
  31. Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting
  32. The Wizard of Curiosities: Enriching Dialogues with Fun Facts
  33. Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates
  34. Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Information
  35. Open-endedness induced through a predator-prey scenario using modular robots
  36. Machine Learning Data Suitability and Performance Testing Using Fault Injection Testing Framework
  37. Grounded Complex Task Segmentation for Conversational Assistants
  38. StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding
  39. From Classification to Segmentation with Explainable AI: A Study on Crack Detection and Growth Monitoring
  40. Sequence-to-Sequence Spanish Pre-trained Language Models
  41. TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models
  42. The Scenario Refiner: Grounding subjects in images at the morphological level
  43. Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text
  44. Hierarchical Multi-Agent Reinforcement Learning for Air Combat Maneuvering
  45. Grassroots Operator Search for Model Edge Adaptation
  46. Colour Passing Revisited: Lifted Model Construction with Commutative Factors
  47. OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
  48. ChatGPT-4 as a Tool for Reviewing Academic Books in Spanish
  49. Towards Robust Few-shot Point Cloud Semantic Segmentation
  50. Towards a Prediction of Machine Learning Training Time to Support Continuous Learning Systems Development
  51. Leveraging Diversity in Online Interactions
  52. Generalized Few-Shot Point Cloud Segmentation Via Geometric Words
  53. Automatic Bat Call Classification using Transformer Networks
  54. Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering
  55. A Model-Based Machine Learning Approach for Assessing the Performance of Blockchain Applications
  56. Using Artificial Intelligence for the Automation of Knitting Patterns
  57. The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute
  58. When to Trust AI: Advances and Challenges for Certification of Neural Networks
  59. RHALE: Robust and Heterogeneity-aware Accumulated Local Effects
  60. Long-tail Augmented Graph Contrastive Learning for Recommendation
  61. Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentation
  62. AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration
  63. Assessment of Pre-Trained Models Across Languages and Grammars
  64. Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation
  65. Learning Deformable 3D Graph Similarity to Track Plant Cells in Unregistered Time Lapse Images
  66. CNN-based local features for navigation near an asteroid
  67. ProtoExplorer: Interpretable Forensic Analysis of Deepfake Videos using Prototype Exploration and Refinement
  68. Online Calibration of a Single-Track Ground Vehicle Dynamics Model by Tight Fusion with Visual-Inertial Odometry
  69. Optimize-via-Predict: Realizing out-of-sample optimality in data-driven optimization
  70. GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation
  71. GL-Fusion: Global-Local Fusion Network for Multi-view Echocardiogram Video Segmentation
  72. Prototype of a robotic system to assist the learning process of English language with text-generation through DNN
  73. More complex encoder is not all you need
  74. Shape Anchor Guided Holistic Indoor Scene Understanding
  75. Contrastive Pseudo Learning for Open-World DeepFake Attribution
  76. Locate and Verify: A Two-Stream Network for Improved Deepfake Detection
  77. Hyperspectral Benchmark: Bridging the Gap between HSI Applications through Comprehensive Dataset and Pretraining
  78. Ano-SuPs: Multi-size anomaly detection for manufactured products by identifying suspected patches
  79. BroadBEV: Collaborative LiDAR-camera Fusion for Broad-sighted Bird's Eye View Map Construction
  80. PRAT: PRofiling Adversarial aTtacks
  81. Self-supervised Domain-agnostic Domain Adaptation for Satellite Images
  82. AttentionMix: Data augmentation method that relies on BERT attention mechanism
  83. Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration
  84. A New Interpretable Neural Network-Based Rule Model for Healthcare Decision Making
  85. Delays in Reinforcement Learning
  86. K-pop Lyric Translation: Dataset, Analysis, and Neural-Modelling
  87. Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer
  88. Learning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval
  89. Practical Probabilistic Model-based Deep Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling
  90. Embed-Search-Align: DNA Sequence Alignment using Transformer Models
  91. Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning
  92. Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation
  93. Visual Question Answering in the Medical Domain
  94. Weak Supervision for Label Efficient Visual Bug Detection
  95. Symbolic Regression on Sparse and Noisy Data with Gaussian Processes
  96. InkStream: Real-time GNN Inference on Streaming Graphs via Incremental Update
  97. Dynamic Tiling: A Model-Agnostic, Adaptive, Scalable, and Inference-Data-Centric Approach for Efficient and Accurate Small Object Detection
  98. Extreme Scenario Selection in Day-Ahead Power Grid Operational Planning
  99. UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt
  100. Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concreteness
  101. XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates
  102. fakenewsbr: A Fake News Detection Platform for Brazilian Portuguese
  103. Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables
  104. Containing Analog Data Deluge at Edge through Frequency-Domain Compression in Collaborative Compute-in-Memory Networks
  105. Heterogeneous Entity Matching with Complex Attribute Associations using BERT and Neural Networks
  106. Clustered FedStack: Intermediate Global Models with Bayesian Information Criterion
  107. Making Small Language Models Better Multi-task Learners with Mixture-of-Task-Adapters
  108. Federated Learning in Intelligent Transportation Systems: Recent Applications and Open Problems
  109. CaveSeg: Deep Semantic Segmentation and Scene Parsing for Autonomous Underwater Cave Exploration
  110. Scalable Acceleration for Classification-Based Derivative-Free Optimization
  111. The Topology and Geometry of Neural Representations
  112. Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach
  113. Information Leakage from Data Updates in Machine Learning Models
  114. Conformalized Multimodal Uncertainty Regression and Reasoning
  115. 3D-U-SAM Network For Few-shot Tooth Segmentation in CBCT Images
  116. ModelGiF: Gradient Fields for Model Functional Distance
  117. Controllable Dynamic Appearance for Neural 3D Portraits
  118. STARNet: Sensor Trustworthiness and Anomaly Recognition via Approximated Likelihood Regret for Robust Edge Autonomy
  119. It's Simplex! Disaggregating Measures to Improve Certified Robustness
  120. PPD: A New Valet Parking Pedestrian Fisheye Dataset for Autonomous Driving
  121. Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model
  122. COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification
  123. SpikingNeRF: Making Bio-inspired Neural Networks See through the Real World
  124. Is GPT4 a Good Trader?
  125. Adaptive Multi-Agent Deep Reinforcement Learning for Timely Healthcare Interventions
  126. Towards Data-centric Graph Machine Learning: Review and Outlook
  127. PAGER: A Framework for Failure Analysis of Deep Regression Models
  128. Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
  129. SPFQ: A Stochastic Algorithm and Its Error Analysis for Neural Network Quantization
  130. SEMPART: Self-supervised Multi-resolution Partitioning of Image Semantics