mlsanityData to 7 Oct 2026

Papers

New on arXiv

Wed 13 Nov 2024

241 papers

  1. CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI FeedbackLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  2. ClevrSkills: Compositional Language and Visual Reasoning in RoboticsLLM reasoning → Spatial and embodied reasoning
  3. DART-LLM: Dependency-Aware Multi-Robot Task Decomposition and Execution using Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  4. Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted CaptionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  5. Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert SelectionMixture-of-experts → Efficient MoE training and inference systems
  6. Sparse Upcycling: Inference Inefficient FinetuningMixture-of-experts → MoE large language models
  7. Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better SamplesDiffusion models → Diffusion foundations and sampling
  8. The Limited Impact of Medical Adaptation of Large Language and Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  9. LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMsLLM safety and security → Jailbreaking
  10. Multimodal Instruction Tuning with Hybrid State Space ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  11. Offline Adaptation of Quadruped Locomotion using Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  12. LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are NeededWorld models → World models for language agents
  13. Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in TransformersLLM reasoning → Reasoning benchmarks and evaluation
  14. Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  15. Retrieval Augmented Recipe GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  16. Analogical Reasoning Within a Conceptual HyperspaceLLM reasoning → Reasoning benchmarks and evaluation
  17. Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering ModelsDiffusion models → Image generation, text-to-image and editing
  18. Robot See, Robot Do: Imitation Reward for Noisy Financial EnvironmentsOffline RL and imitation learning from data → Inverse reinforcement learning
  19. LG-Gaze: Learning Geometry-aware Continuous Prompts for Language-Guided Gaze EstimationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  20. Neural Corrective Machine UnrankingLLM safety and security → Machine unlearning
  21. Building Trustworthy AI: Transparent AI Systems via Large Language Models, Ontologies, and Logical Reasoning (TranspNet)LLM reasoning → Reasoning for agents, planning and code
  22. Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  23. LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive HashingMixture-of-experts → Efficient MoE training and inference systems
  24. Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRALLM safety and security → Machine unlearning
  25. Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic DataRetrieval-augmented generation → RAG pipeline design and evaluation
  26. One STEP at a time: Language Agents are Stepwise PlannersLLM agents and tool use → General LLM agent frameworks and benchmarks
  27. Enhanced Classroom Dialogue Sequences Analysis with a Hybrid AI Agent: Merging Expert Rule-Base with Large Language ModelsLLM agents and tool use → Educational agents and math problem solving
  28. The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and DefenseLLM safety and security → Jailbreaking
  29. V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object DetectionDiffusion models → 3D, point cloud and scene generation
  30. MambaXCTrack: Mamba-based Tracker with SSM Cross-correlation and Motion Prompt for Ultrasound Needle TrackingState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  31. Physics Informed Distillation for Diffusion ModelsDiffusion models → Flow matching, time series and science
  32. Modeling Stochastic Conditional Dynamics from Sparse Observations via Kernel-Stabilized Flow MatchingDiffusion models → Flow matching, time series and science
  33. RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward RedistributionLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  34. Collaborative Participatory Research with LLM Agents in South Asia: An Empirically-Grounded Methodological Initiative and Agenda from Field Evidence in Sri LankaLLM agents and tool use → Social simulation and multi-agent debate
  35. Open-World Task and Motion Planning via Vision-Language Model Generated ConstraintsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  36. InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders
  37. The Femininomenon of Inequality: A Data-Driven Analysis and Cluster Profiling in Indonesia
  38. The use of knowledge in open-ended systems
  39. Quantity versus Diversity: Influence of Data on Detecting EEG Pathology with Advanced ML Models
  40. Towards Efficient Neurally-Guided Program Induction for ARC-AGI
  41. A Composite Fault Diagnosis Model for NPPs Based on Bayesian-EfficientNet Module
  42. Direct Speech-to-Speech Neural Machine Translation: A Survey
  43. SAM-I2I: Unleash the Power of Segment Anything Model for Medical Image Translation
  44. Physics-Informed Neural Networks for Electrical Circuit Analysis: Applications in Dielectric Material Modeling
  45. Boolean-aware Boolean Circuit Classification: A Comprehensive Study on Graph Neural Network
  46. Hateful Meme Detection through Context-Sensitive Prompting and Fine-Grained Labeling
  47. Challenges in the Differential Classification of Individual Diagnoses from Co-Occurring Autism and ADHD Using Survey Data
  48. Machine learning approaches to explore important features behind bird flight modes
  49. ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening
  50. Set-Based Retrograde Analysis: Precomputing the Solution to 24-card Bridge Double Dummy Deals
  51. Drone Detection using Deep Neural Networks Trained on Pure Synthetic Data
  52. Continuous GNN-based Anomaly Detection on Edge using Efficient Adaptive Knowledge Graph Learning
  53. Liner Shipping Network Design with Reinforcement Learning
  54. A multidimensional measurement of photorealistic avatar quality of experience
  55. Language-Model Prior Overcomes Cold-Start Items
  56. Minimax Optimal Two-Sample Testing under Local Differential Privacy
  57. Multimodal Object Detection using Depth and Image Data for Manufacturing Parts
  58. Optimisation Strategies for Ensuring Fairness in Machine Learning: With and Without Demographics
  59. SAFELOC: Overcoming Data Poisoning Attacks in Heterogeneous Federated Machine Learning for Indoor Localization
  60. The Systems Engineering Approach in Times of Large Language Models
  61. Anomaly Detection in Large-Scale Cloud Systems: An Industry Case and Dataset
  62. Pay Attention to the Keys: Visual Piano Transcription Using Transformers
  63. Transformer-based Time-Series Biomarker Discovery for COPD Diagnosis
  64. CoMiX: Cross-Modal Fusion with Deformable Convolutions for HSI-X Semantic Segmentation
  65. Cut Your Losses in Large-Vocabulary Language Models
  66. Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment
  67. Refusal in LLMs is an Affine Function
  68. Microfoundation Inference for Strategic Prediction
  69. Computed tomography using meta-optics
  70. Parameter Inference via Differentiable Diffusion Bridge Importance Sampling
  71. IDCIA: Immunocytochemistry Dataset for Cellular Image Analysis
  72. Non-Euclidean High-Order Smooth Convex Optimization
  73. Reliability, Resilience and Human Factors Engineering for Trustworthy AI Systems
  74. CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt
  75. Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness
  76. Fluoroformer: Scaling multiple instance learning to multiplexed images via attention-based channel fusion
  77. Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head
  78. Clustered Patch Embeddings for Permutation-Invariant Classification of Whole Slide Images
  79. Classification of Keratitis from Eye Corneal Photographs using Deep Learning
  80. Predicting household socioeconomic position in Mozambique using satellite and household imagery
  81. Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
  82. PyGen: A Collaborative Human-AI Approach to Python Package Creation
  83. 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization
  84. A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos
  85. Causal Explanations for Image Classifiers
  86. CamemBERT 2.0: A Smarter French Language Model Aged to Perfection
  87. Unsupervised Parameter-free Outlier Detection using HDBSCAN* Outlier Profiles
  88. Interaction Testing in Variation Analysis
  89. Oblique Bayesian additive regression trees
  90. Data-driven Surface Solar Irradiance Estimation using Neural Operators at Global Scale
  91. AstroM3: A self-supervised multimodal model for astronomy
  92. Conditional Local Importance by Quantile Expectations
  93. Process-aware Human Activity Recognition
  94. Rethinking CyberSecEval: An LLM-Aided Approach to Evaluation Critique
  95. FinRobot: AI Agent for Equity Research and Valuation with Large Language Models
  96. Deep Learning Accelerated Quantum Transport Simulations in Nanoelectronics: From Break Junctions to Field-Effect Transistors
  97. Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence
  98. Locally Private Sampling with Public Data
  99. Can sparse autoencoders be used to decompose and interpret steering vectors?
  100. Zero-shot Cross-lingual Transfer Learning with Multiple Source and Target Languages for Information Extraction: Language Selection and Adversarial Training
All 241
  1. LUDO: Low-Latency Understanding of Deformable Objects using Point Cloud Occupancy Functions
  2. Optimal Oblivious Subspace Embeddings with Near-optimal Sparsity
  3. Sharingan: Extract User Action Sequence from Desktop Recordings
  4. SANDWICH: Towards an Offline, Differentiable, Fully-Trainable Wireless Neural Ray-Tracing Surrogate
  5. Mapping Methane -- The Impact of Dairy Farm Practices on Emissions Through Satellite Data and Machine Learning
  6. Flow reconstruction in time-varying geometries using graph neural networks
  7. Energy Dissipation Preserving Physics Informed Neural Network for Allen-Cahn Equations
  8. ScaleNet: Scale Invariance Learning in Directed Graphs
  9. Masked Image Modeling Boosting Semi-Supervised Semantic Segmentation
  10. Weakly-Supervised Anomaly Detection in Surveillance Videos Based on Two-Stream I3D Convolution Network
  11. Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos
  12. Multi-Perspective Stance Detection
  13. Optimal Transport-Based Displacement Interpolation with Data Augmentation for Reduced Order Modeling of Nonlinear Dynamical Systems
  14. A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models
  15. Bayesian Comparisons Between Representations
  16. Recommender systems and reinforcement learning for human-building interaction and context-aware support: A text mining-driven review of scientific literature
  17. Polymetis:Large Language Modeling for Multiple Material Domains
  18. Analyst Reports and Stock Performance: Evidence from the Chinese Market
  19. High-resolution optical and acoustic remote sensing datasets of the Puck Lagoon, Southern Baltic
  20. Are Triggers Needed for Document-Level Event Extraction?
  21. Searching Latent Program Spaces
  22. MVKTrans: Multi-View Knowledge Transfer for Robust Multiomics Classification
  23. TRACE: Transformer-based Risk Assessment for Clinical Evaluation
  24. Rethinking negative sampling in content-based news recommendation
  25. FedSub: Introducing Class-aware Subnetworks Fusion to Enhance Personalized Federated Learning
  26. Scholarly Wikidata: Population and Exploration of Conference Data in Wikidata using LLMs
  27. A Likelihood Approach for Inference of Population Heterogeneity in Particle Ensembles with Second-Order Langevin Dynamics
  28. Diagnosing Neural Convergence with Topological Alignment Spectra
  29. Theoretical Analysis of Byte-Pair Encoding
  30. A Machine Learning Algorithm for Finite-Horizon Stochastic Control Problems in Economics
  31. A Survey on Vision Autoregressive Model
  32. OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Fused Geometric and Semantic Guidance
  33. UniMat: Unifying Materials Embeddings through Multi-modal Learning
  34. Toward Human Understanding with Controllable Synthesis
  35. MikuDance: Animating Character Art with Mixed Motion Dynamics
  36. Accelerating Quasi-Static Time Series Simulations with Foundation Models
  37. Estimating unknown parameters in differential equations with a reinforcement learning based PSO method
  38. A System Level Performance Evaluation for Superconducting Digital Systems
  39. DipMe: Haptic Recognition of Granular Media for Tangible Interactive Applications
  40. Towards Secure Intelligent O-RAN Architecture: Vulnerabilities, Threats and Promising Technical Solutions using LLMs
  41. Graph Neural Network Generalization with Gaussian Mixture Model Based Augmentation
  42. Deep Generative Demand Learning for Newsvendor and Pricing
  43. Zero-shot capability of SAM-family models for bone segmentation in CT scans
  44. Precision-Focused Reinforcement Learning Model for Robotic Object Pushing
  45. Dynamic Subset Tuning: Expanding the Operational Range of Parameter-Efficient Training for Large Language Models
  46. Lo-MARVE: A Low Cost Autonomous Underwater Vehicle for Marine Exploration
  47. Generalized Pose Space Embeddings for Training In-the-Wild using Anaylis-by-Synthesis
  48. A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL
  49. Slender Object Scene Segmentation in Remote Sensing Image Based on Learnable Morphological Skeleton with Segment Anything Model
  50. Hopfield-Fenchel-Young Networks: A Unified Framework for Associative Memory Retrieval
  51. DeepUQ: Assessing the Aleatoric Uncertainties from two Deep Learning Methods
  52. Optimizing Automatic Summarization of Long Clinical Records Using Dynamic Context Extension:Testing and Evaluation of the NBCE Method
  53. An Empirical Examination of the Evaluative AI Framework
  54. Intelligent Algorithms For Signature Diagnostics Of Three-Phase Motors
  55. NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation
  56. UIFormer: A Unified Transformer-based Framework for Incremental Few-Shot Object Detection and Instance Segmentation
  57. Saliency Map-based Image Retrieval using Invariant Krawtchouk Moments
  58. Grammarization-Based Grasping with Deep Multi-Autoencoder Latent Space Exploration by Reinforcement Learning Agent
  59. Leveraging LLMs for Predictive Insights in Food Policy and Behavioral Interventions
  60. LogLLM: Log-based Anomaly Detection Using Large Language Models
  61. Learning Locally Adaptive Metrics that Enhance Structural Representation with textttLAMINAR
  62. CorrSynth -- A Correlated Sampling Method for Diverse Dataset Generation from LLMs
  63. Leveraging Pre-Trained Neural Networks to Enhance Machine Learning with Variational Quantum Circuits
  64. Graph Neural Networks in Supply Chain Analytics and Optimization: Concepts, Perspectives, Dataset and Benchmarks
  65. APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments
  66. Deeper Insights into Learning Performance of Stochastic Configuration Networks
  67. MLV2-Net: Rater-Based Majority-Label Voting for Consistent Meningeal Lymphatic Vessel Segmentation
  68. Neural Topic Modeling with Large Language Models in the Loop
  69. ACROSS: A Deformation-Based Cross-Modal Representation for Robotic Tactile Perception
  70. Classification and Morphological Analysis of DLBCL Subtypes in H&E-Stained Slides
  71. Efficient Whole Slide Image Classification through Fisher Vector Representation
  72. Gendered Words and Grant Rates: A Textual Analysis of Disparate Outcomes in the Patent System
  73. A spatiotemporal fused network considering electrode spatial topology and time-window transition for MDD detection
  74. Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding
  75. Explainers' Mental Representations of Explainees' Needs in Everyday Explanations
  76. BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis
  77. Towards Operationalizing Right to Data Protection
  78. Towards Objective and Unbiased Decision Assessments with LLM-Enhanced Hierarchical Attention Networks
  79. Impact of Iris Pigmentation on Performance Bias in Visible Iris Verification Systems: A Comparative Study
  80. UNSCT-HRNet: Modeling Anatomical Uncertainty for Landmark Detection in Total Hip Arthroplasty
  81. Methodology for an Analysis of Influencing Factors on 3D Object Detection Performance
  82. Learning Model Agnostic Explanations via Constraint Programming
  83. A survey on Graph Deep Representation Learning for Facial Expression Recognition
  84. HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere
  85. ℓ0 factor analysis
  86. A Generation Framework with Strict Constraints for Crystal Materials Design
  87. Symbolic-AI-Fusion Deep Learning (SAIF-DL): Encoding Knowledge into Training with Answer Set Programming Loss Penalties by a Novel Loss Function Approach
  88. Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
  89. Biomass phenotyping of oilseed rape through UAV multi-view oblique imaging with 3DGS and SAM model
  90. AD-DINO: Attention-Dynamic DINO for Distance-Aware Embodied Reference Understanding
  91. Towards Evaluating Large Language Models for Graph Query Generation
  92. Learning Dynamic Cognitive Map with Autonomous Navigation
  93. 3D Multi-Object Tracking with Semi-Supervised GRU-Kalman Filter
  94. Properties of fairness measures in the context of varying class imbalance and protected group ratios
  95. A Heterogeneous Graph Neural Network Fusing Functional and Structural Connectivity for MCI Diagnosis
  96. Material Property Prediction with Element Attribute Knowledge Graphs and Multimodal Representation Learning
  97. DiVR: incorporating context from diverse VR scenes for human trajectory prediction
  98. Quantifying Qualitative Insights: Leveraging LLMs to Market Predict
  99. BAMAX: Backtrack Assisted Multi-Agent Exploration using Reinforcement Learning
  100. CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision
  101. RLInspect: An Interactive Visual Approach to Assess Reinforcement Learning Algorithm
  102. Expected information gain estimation via density approximations: Sample allocation and dimension reduction
  103. Interpretable Syntactic Representations Enable Hierarchical Word Vectors
  104. EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation
  105. Developing an Effective Training Dataset to Enhance the Performance of AI-based Speaker Separation Systems
  106. Federated Graph Learning with Graphless Clients
  107. Multiscale Graph Construction Using Non-local Cluster Features
  108. A Fuzzy Reinforcement LSTM-based Long-term Prediction Model for Fault Conditions in Nuclear Power Plants
  109. Surprisingly Popular Voting for Concentric Rank-Order Models
  110. Coverage Analysis for Digital Cousin Selection -- Improving Multi-Environment Q-Learning
  111. Optimal Decentralized Smoothed Online Convex Optimization
  112. Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach
  113. A Chinese Multi-label Affective Computing Dataset Based on Social Media Network Users
  114. Bangla Grammatical Error Detection Leveraging Transformer-based Token Classification
  115. Generative AI for Data Augmentation in Wireless Networks: Analysis, Applications, and Case Study
  116. DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning
  117. DEEGITS: Deep Learning based Framework for Measuring Heterogenous Traffic State in Challenging Traffic Scenarios
  118. MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval
  119. SASE: A Searching Architecture for Squeeze and Excitation Operations
  120. Learning-Augmented Algorithms for Online Concave Packing and Convex Covering Problems
  121. Motion Control for Enhanced Complex Action Video Generation
  122. Neural Conjugate Flows: Physics-informed architectures with flow structure
  123. Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
  124. Responsible AI in Construction Safety: Systematic Evaluation of Large Language Models and Prompt Engineering
  125. PerceiverS: A Multi-Scale Perceiver with Effective Segmentation for Long-Term Expressive Symbolic Music Generation
  126. Evaluating Molecule Synthesizability via Retrosynthetic Planning and Reaction Prediction
  127. Robust Divergence Learning for Missing-Modality Segmentation
  128. DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach
  129. TowerDebias: A Novel Unfairness Removal Method Based on the Tower Property
  130. Choix d'un espace de repr'esentation image adapt'e `a la d'etection de r'eseaux routiers
  131. Noisy image decomposition: a new structure, texture and noise model based on local adaptivity
  132. Restoration algorithms and system performance evaluation for active imagers
  133. RESOLVE: Relational Reasoning with Symbolic and Object-Level Features Using Vector Symbolic Processing
  134. Hashing for Protein Structure Similarity Search
  135. MBA-SLAM: Motion Blur Aware Gaussian Splatting SLAM
  136. Knowledge Bases in Support of Large Language Models for Processing Web News
  137. A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look
  138. LBONet: Supervised Spectral Descriptors for Shape Analysis
  139. Least Squares Training of Quadratic Convolutional Neural Networks with Applications to System Theory
  140. GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees
  141. Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropy