mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 16 Jan 2025

216 papers

  1. A Dynamic and High-Precision Method for Scenario-Based HRA Synthetic Data Collection in Multi-Agent Collaborative Environments Driven by LLMsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  2. Geometry-Preserving Encoder/Decoder in Latent Generative ModelsDiffusion models → Diffusion foundations and sampling
  3. From Explainability to Interpretability: Interpretable Policies in Reinforcement Learning Via Model ExplanationDeep reinforcement learning methods → Interpretable and logic-guided RL
  4. PIXELS: Progressive Image Xemplar-based Editing with Latent SurgeryDiffusion models → Image generation, text-to-image and editing
  5. Lossy Compression with Pretrained Diffusion ModelsDiffusion models → Diffusion for compression and wireless
  6. Enhancing Generalization in Chain of Thought Reasoning for Smaller ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  7. Conversational Text Extraction with Large Language Models Using Retrieval-Augmented SystemsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  8. Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning InterfaceLLM safety and security → Jailbreaking
  9. GeoManip: Geometric Constraints as General Interfaces for Robot ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  10. Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are WrongLLM reasoning → Reasoning benchmarks and evaluation
  11. Distilling Multi-modal Large Language Models for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  12. SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic FacesDiffusion models → 3D, point cloud and scene generation
  13. OmniThink: Expanding Knowledge Boundaries in Machine Writing through ThinkingLLM reasoning → Knowledge- and tool-augmented reasoning +1
  14. FAST: Efficient Action Tokenization for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  15. Inference-Time Scaling for Diffusion Models beyond Scaling Denoising StepsLLM reasoning → Diffusion reasoning and test-time scaling +1
  16. A Simple Aerial Detection Baseline of Multimodal Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  17. Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the KeyMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  18. Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language ModelsWorld models → World models for language agents +1
  19. Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and ReviewDiffusion models → Diffusion foundations and sampling
  20. CHIRP: A Fine-Grained Benchmark for Open-Ended Response Evaluation in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  21. LLM-Based Routing in Mixture of Experts: A Novel Framework for TradingMixture-of-experts → MoE for time series and graphs
  22. Beyond Reward Hacking: Causal Rewards for Large Language Model AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  23. WMamba: Wavelet-based Mamba for Face Forgery DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  24. EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  25. Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding LearningKnowledge distillation → Speech and audio distillation
  26. AdaFV: Rethinking of Visual-Language alignment for VLM accelerationLLM reasoning → Multimodal reasoning
  27. Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge DistillationKnowledge distillation → Distillation for continual learning
  28. RE-POSE: Synergizing Reinforcement Learning-Based Partitioning and Offloading for Edge Object DetectionDeep reinforcement learning methods → RL training of language and agent models
  29. Pruning for Sparse Diffusion Models based on Gradient FlowDiffusion models → Diffusion foundations and sampling
  30. Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model RobustnessMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  31. A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation StrategyLLM safety and security → Safety alignment, refusal and guardrails
  32. AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological CounselingLLM agents and tool use → Medical and scientific domain agents
  33. Vision-Language Models Do Not Understand NegationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  34. MoE2: Optimizing Collaborative Inference for Edge Large Language ModelsMixture-of-experts → Efficient MoE training and inference systems
  35. PICE: A Semantic-Driven Progressive Inference System for LLM Serving in Cloud-Edge NetworksEfficient LLM inference and serving → Early exit and edge inference
  36. YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality TasksLLM agents and tool use → Multimodal and embodied agents
  37. Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction AttacksLLM safety and security → Watermarking generated content and models
  38. Soft Knowledge Distillation with Multi-Dimensional Cross-Net Attention for Image Restoration Models CompressionKnowledge distillation → General knowledge distillation methods
  39. SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPsLLM agents and tool use → General LLM agent frameworks and benchmarks
  40. RoboReflect: A Robotic Reflective Reasoning Framework for Grasping Ambiguous-Condition ObjectsLLM reasoning → Spatial and embodied reasoning
  41. Domain-conditioned and Temporal-guided Diffusion Modeling for Accelerated Dynamic MRI ReconstructionDiffusion models → Medical imaging and segmentation
  42. Finding the Trigger: Causal Abductive Reasoning on Video EventsLLM reasoning → Multimodal reasoning
  43. To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  44. Knowledge Distillation for Image Restoration : Simultaneous Learning from Degraded and Clean ImagesKnowledge distillation → General knowledge distillation methods
  45. Clone-Robust AI AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  46. FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time TrainingLLM reasoning → Clinical and biomedical applications
  47. Democratizing AI Governance: Balancing Expertise and Public Participation
  48. Optimization Strategies for Enhancing Resource Efficiency in Transformers & Large Language Models
  49. PixelBrax: Learning Continuous Control from Pixels End-to-End on the GPU
  50. The Streaming Batch Model for Efficient and Fault-Tolerant Heterogeneous Execution
  51. Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search
  52. Revisiting Rogers' Paradox in the Context of Human-AI Interaction
  53. Poxel: Voxel Reconstruction for 3D Printing
  54. VillageNet: Graph-based, Easily-interpretable, Unsupervised Clustering for Broad Biomedical Applications
  55. Semi-Supervised Image-Based Narrative Extraction: A Case Study with Historical Photographic Records
  56. ASTRA: A Scene-aware TRAnsformer-based model for trajectory prediction
  57. CLAP-S: Support Set Based Adaptation for Downstream Fiber-optic Acoustic Recognition
  58. An LLM-Guided Tutoring System for Social Skills Training
  59. Detection of Vascular Leukoencephalopathy in CT Images
  60. Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
  61. Coded Deep Learning: Framework and Algorithm
  62. CrossModalityDiffusion: Multi-Modal Novel View Synthesis with Unified Intermediate Representation
  63. Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts
  64. Bridging Language Barriers in Healthcare: A Study on Arabic LLMs
  65. pFedWN: A Personalized Federated Learning Framework for D2D Wireless Networks with Heterogeneous Data
  66. BN-Pool: Bayesian Nonparametric Pooling for Graphs
  67. Generalized Single-Image-Based Morphing Attack Detection Using Deep Representations from Vision Transformer
  68. Qwen it detect machine-generated text?
  69. Graph Neural Networks for Travel Distance Estimation and Route Recommendation Under Probabilistic Hazards
  70. SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation
  71. VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
  72. Sentiment Analysis in Twitter Social Network Centered on Cryptocurrencies Using Machine Learning
  73. Multi-Head Self-Attending Neural Tucker Factorization
  74. Learnings from Scaling Visual Tokenizers for Reconstruction and Generation
  75. Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues
  76. SRE-Conv: Symmetric Rotation Equivariant Convolution for Biomedical Image Classification
  77. Enhancing Lexicon-Based Text Embeddings with Large Language Models
  78. Suggesting Code Edits in Interactive Machine Learning Notebooks Using Large Language Models
  79. KU AIGEN ICL EDI@BC8 Track 3: Advancing Phenotype Named Entity Recognition and Normalization for Dysmorphology Physical Examination Reports
  80. Random Subspace Cubic-Regularization Methods, with Applications to Low-Rank Functions
  81. ComplexVAD: Detecting Interaction Anomalies in Video
  82. Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI
  83. Generating particle physics Lagrangians with transformers
  84. Parallel multi-objective metaheuristics for smart communications in vehicular networks
  85. Attention based Bidirectional GRU hybrid model for inappropriate content detection in Urdu language
  86. Comparative Insights from 12 Machine Learning Models in Extracting Economic Ideology from Political Text
  87. FLOL: Fast Baselines for Real-World Low-Light Enhancement
  88. CyberMentor: AI Powered Learning Tool Platform to Address Diverse Student Needs in Cybersecurity Education
  89. The Goofus & Gallant Story Corpus for Practical Value Alignment
  90. Domain Adaptation of Foundation LLMs for e-Commerce
  91. Practical Continual Forgetting for Pre-trained Vision Models
  92. Cueless EEG imagined speech for subject identification: dataset and benchmarks
  93. A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
  94. Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation
  95. U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection
  96. Rough kernel hedging
  97. Incorporating Quantum Advantage in Quantum Circuit Generation through Genetic Programming
  98. Authenticated Delegation and Authorized AI Agents
  99. Fokker-Planck to Callan-Symanzik: evolution of weight matrices under training
  100. A Survey of Research in Large Language Models for Electronic Design Automation
All 216
  1. The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models
  2. Monte Carlo Tree Search with Velocity Obstacles for safe and efficient motion planning in dynamic environments
  3. NS-Gym: Open-Source Simulation Environments and Benchmarks for Non-Stationary Markov Decision Processes
  4. CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding
  5. Electronic Health Records: Towards Digital Twins in Healthcare
  6. Unified Face Matching and Physical-Digital Spoofing Attack Detection
  7. Platform-Aware Mission Planning
  8. Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework
  9. Artificial Intelligence-Driven Clinical Decision Support Systems
  10. Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML
  11. ARMAX identification of low rank graphical models
  12. Adversarial-Ensemble Kolmogorov Arnold Networks for Enhancing Indoor Wi-Fi Positioning: A Defensive Approach Against Spoofing and Signal Manipulation Attacks
  13. Managed-Retention Memory: A New Class of Memory for the AI Era
  14. From Scarcity to Capability: Empowering Fake News Detection in Low-Resource Languages with LLMs
  15. Mesh2SLAM in VR: A Fast Geometry-Based SLAM Framework for Rapid Prototyping in Virtual Reality Applications
  16. Reducing the Sensitivity of Neural Physics Simulators to Mesh Topology via Pretraining
  17. IFRA: a machine learning-based Instrumented Fall Risk Assessment Scale derived from Instrumented Timed Up and Go test in stroke patients
  18. Metrics for Inter-Dataset Similarity with Example Applications in Synthetic Data and Feature Selection Evaluation -- Extended Version
  19. Atleus: Accelerating Transformers on the Edge Enabled by 3D Heterogeneous Manycore Architectures
  20. Sequential PatchCore: Anomaly Detection for Surface Inspection using Synthetic Impurities
  21. Towards Spectral Convergence of Locally Linear Embedding on Manifolds with Boundary
  22. MatrixNet: Learning over symmetry groups using learned group representations
  23. A New Teacher-Reviewer-Student Framework for Semi-supervised 2D Human Pose Estimation
  24. Stylomech: Unveiling Authorship via Computational Stylometry in English and Romanized Sinhala
  25. Overshoot: Taking advantage of future gradients in momentum-based stochastic optimization
  26. Text-driven Adaptation of Foundation Models for Few-shot Surgical Workflow Analysis
  27. Exploring AI-based System Design for Pixel-level Protected Health Information Detection in Medical Images
  28. Intra-day Solar and Power Forecast for Optimization of Intraday Market Participation
  29. Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matrices
  30. AI in Support of Diversity and Inclusion
  31. MOGNET: A Mux-residual quantized Network leveraging Online-Generated weights
  32. Confidence Estimation for Error Detection in Text-to-SQL Systems
  33. Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
  34. Augmenting a Large Language Model with a Combination of Text and Visual Data for Conversational Visualization of Global Geospatial Data
  35. Multi-task deep-learning for sleep event detection and stage classification
  36. PIER: A Novel Metric for Evaluating What Matters in Code-Switching
  37. Multimodal Marvels of Deep Learning in Medical Diagnosis: A Comprehensive Review of COVID-19 Detection
  38. HydraMix: Multi-Image Feature Mixing for Small Data Image Classification
  39. AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation
  40. Omni-Emotion: Extending Video MLLM with Detailed Face and Audio Modeling for Multimodal Emotion Analysis
  41. VanGogh: A Unified Multimodal Diffusion-based Framework for Video Colorization
  42. Comparison of Various SLAM Systems for Mobile Robot in an Indoor Environment
  43. The Devil is in the Details: Simple Remedies for Image-to-LiDAR Representation Learning
  44. Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators
  45. MonoSOWA: Scalable monocular 3D Object detector Without human Annotations
  46. Utilizing AI Language Models to Identify Prognostic Factors for Coronary Artery Disease: A Study in Mashhad Residents
  47. Predicting Air Temperature from Volumetric Urban Morphology with Machine Learning
  48. DEFOM-Stereo: Depth Foundation Model Based Stereo Matching
  49. Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes
  50. Teaching Wav2Vec2 the Language of the Brain
  51. On the Relation between Optical Aperture and Automotive Object Detection
  52. Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement
  53. Solving the Unsolvable: Translating Case Law in Hong Kong
  54. Scaling up self-supervised learning for improved surgical foundation models
  55. CaPa: Carve-n-Paint Synthesis for Efficient 4K Textured Mesh Generation
  56. ADAGE: A generic two-layer framework for adaptive agent based modelling
  57. AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring
  58. Dynamic Neural Style Transfer for Artistic Image Generation using VGG19
  59. FASP: Fast and Accurate Structured Pruning of Large Language Models
  60. Towards Robust and Realistic Human Pose Estimation via WiFi Signals
  61. Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTE
  62. PISCO: Self-Supervised k-Space Regularization for Improved Neural Implicit k-Space Representations of Dynamic MRI
  63. Fast Searching of Extreme Operating Conditions for Relay Protection Setting Calculation Based on Graph Neural Network and Reinforcement Learning
  64. Joint Transmission and Deblurring: A Semantic Communication Approach Using Events
  65. ELM-DeepONets: Backpropagation-Free Training of Deep Operator Networks via Extreme Learning Machines
  66. Quantum-Enhanced Transformers for Robust Acoustic Scene Classification in IoT Environments
  67. SVIA: A Street View Image Anonymization Framework for Self-Driving Applications
  68. Evaluating LLM Abilities to Understand Tabular Electronic Health Records: A Comprehensive Study of Patient Data Extraction and Retrieval
  69. Image Segmentation with transformers: An Overview, Challenges and Future
  70. Aligning Instruction Tuning with Pre-training
  71. Identification of Traditional Medicinal Plant Leaves Using an effective Deep Learning model and Self-Curated Dataset
  72. Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning
  73. Style4Rec: Enhancing Transformer-based E-commerce Recommendation Systems with Style and Shopping Cart Information
  74. PAL: Prompting Analytic Learning with Missing Modality for Multi-Modal Class-Incremental Learning
  75. Making Your Dreams A Reality: Decoding the Dreams into a Coherent Video Story from fMRI Signals
  76. ChartInsighter: An Approach for Mitigating Hallucination in Time-series Chart Summary Generation with A Benchmark Dataset
  77. UVRM: A Scalable 3D Reconstruction Model from Unposed Videos
  78. Rational Tuning of LLM Cascades via Probabilistic Modeling
  79. SE-BSFV: Online Subspace Learning based Shadow Enhancement and Background Suppression for ViSAR under Complex Background
  80. Estimating shared subspace with AJIVE: the power and limitation of multiple data matrices
  81. Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
  82. Identifying Information from Observations with Uncertainty and Novelty
  83. On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
  84. Algorithm for Semantic Network Generation from Texts of Low Resource Languages Such as Kiswahili
  85. Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning
  86. Shape-Based Single Object Classification Using Ensemble Method Classifiers
  87. Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errors
  88. Understanding Mental Health Content on Social Media and Its Effect Towards Suicidal Ideation
  89. Creating Virtual Environments with 3D Gaussian Splatting: A Comparative Study
  90. Physics-informed deep learning for infectious disease forecasting
  91. Efficient Few-Shot Medical Image Analysis via Hierarchical Contrastive Vision-Language Learning
  92. LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport
  93. SEAL: Entangled White-box Watermarks on Low-Rank Adaptation
  94. Free-Knots Kolmogorov-Arnold Network: On the Analysis of Spline Knots and Advancing Stability
  95. SoccerSynth-Detection: A Synthetic Dataset for Soccer Player Detection
  96. Text Semantics to Flexible Design: A Residential Layout Generation Method Based on Stable Diffusion Model
  97. Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
  98. Bias for Action: Video Implicit Neural Representations with Bias Modulation
  99. Large Language Model is Secretly a Protein Sequence Optimizer
  100. Are Open-Vocabulary Models Ready for Detection of MEP Elements on Construction Sites
  101. Perspective Transition of Large Language Models for Solving Subjective Tasks
  102. On the convergence rate of noisy Bayesian Optimization with Expected Improvement
  103. OpticFusion: Multi-Modal Neural Implicit 3D Reconstruction of Microstructures by Fusing White Light Interferometry and Optical Microscopy
  104. Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition
  105. Task Vectors in In-Context Learning: Emergence, Formation, and Benefit
  106. AI-based Identity Fraud Detection: A Systematic Review
  107. Mono-Forward: Revisiting Forward-Forward through Objective-Locality Decomposition
  108. Tessellated Linear Model for Age Prediction from Voice
  109. Estimating Task-based Performance Bounds for Accelerated MRI Image Reconstruction Methods by Use of Learned-Ideal Observers
  110. Foundations of Large Language Models
  111. ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers
  112. A Simple Graph Contrastive Learning Framework for Short Text Classification
  113. Interpretable Droplet Digital PCR Assay for Trustworthy Molecular Diagnostics
  114. Adaptive Law-Based Transformation (ALT): A Lightweight Feature Representation for Time Series Classification
  115. Boosting Short Text Classification with Multi-Source Information Exploration and Dual-Level Contrastive Learning
  116. Surgical Visual Understanding (SurgVU) Dataset