mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 1 Aug 2024

236 papers

  1. Abductive Reasoning in a Paraconsistent FrameworkLLM reasoning → Reasoning benchmarks and evaluation
  2. CIResDiff: A Clinically-Informed Residual Diffusion Model for Predicting Idiopathic Pulmonary Fibrosis ProgressionDiffusion models → Medical imaging and segmentation
  3. Towards Zero-Shot Annotation of the Built Environment with Vision-Language Models (Vision Paper)Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
  4. Enabling High Data Throughput Reinforcement Learning on GPUs: A Domain Agnostic Framework for Data-Driven Scientific ResearchDeep reinforcement learning methods → RL training of language and agent models
  5. Verification of Machine Unlearning is FragileLLM safety and security → Machine unlearning
  6. Towards Certified Unlearning for Deep Neural NetworksLLM safety and security → Machine unlearning
  7. Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable GenerationDiffusion models → Diffusion and flow policies for robotics
  8. MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated CapabilitiesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  9. AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task GenerationLLM reasoning → Reasoning for agents, planning and code +1
  10. Tamper-Resistant Safeguards for Open-Weight LLMsLLM safety and security → Jailbreaking
  11. Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of AttentionDiffusion models → Diffusion foundations and sampling
  12. Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language ModelLLM reasoning → Spatial and embodied reasoning +1
  13. A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate ConvergenceDeep reinforcement learning methods → RL for games and combinatorial optimization
  14. Collaborative Vision-Text Representation Optimizing for Open-Vocabulary SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  15. TurboEdit: Text-Based Image Editing Using Few-Step Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  16. Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up QuestionsRetrieval-augmented generation → Medical and biomedical RAG
  17. Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language ModelsLLM reasoning → Test-time compute and efficient thinking
  18. Pathway to Secure and Trustworthy ZSM for LLMs: Attacks, Defense, and OpportunitiesLLM safety and security → Membership inference attacks
  19. Reinforcement Learning applied to Insurance Portfolio PursuitDeep reinforcement learning methods → Adversarial robustness and RL in finance
  20. Disentangling Dense Embeddings with Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  21. Cross-Scan Mamba with Masked Training for Robust Spectral ImagingState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  22. Are Bigger Encoders Always Better in Vision Large Models?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  23. Alleviating Hallucination in Large Vision-Language Models with Active Retrieval AugmentationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  24. Mitigating Multilingual Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  25. Illustrating Classic Brazilian Books using a Text-To-Image Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  26. Intermittent Semi-Working Mask: A New Masking Paradigm for LLMsEfficient LLM inference and serving → KV cache optimization
  27. Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation ModelsLLM agents and tool use → Agent threats, guardrails and governance +1
  28. A new approach for encoding code and assisting code understandingLLM reasoning → Reasoning for agents, planning and code
  29. GalleryGPT: Analyzing Paintings with Large Multimodal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  30. MonoMM: A Multi-scale Mamba-Enhanced Network for Real-time Monocular 3D Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  31. Goal-Oriented Semantic Communication for Wireless Image Transmission via Stable DiffusionDiffusion models → Diffusion for compression and wireless
  32. DriveArena: A Closed-loop Generative Simulation Platform for Autonomous DrivingEnd-to-end autonomous driving → Generative simulation for driving
  33. On the Limitations and Prospects of Machine Unlearning for Generative AILLM safety and security → Machine unlearning
  34. Conformal Trajectory Prediction with Multi-View Data Integration in Cooperative DrivingEnd-to-end autonomous driving → Cooperative and V2X driving
  35. Few-shot Defect Image Generation based on Consistency ModelingDiffusion models → Flow matching, time series and science
  36. DiM-Gesture: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2 frameworkState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  37. Autonomous LLM-Enhanced Adversarial Attack for Text-to-MotionLLM safety and security → Jailbreaking
  38. A Simple Background Augmentation Method for Object Detection with Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  39. Advancing Medical Image Segmentation: Morphology-Driven Learning with Diffusion TransformerDiffusion models → Medical imaging and segmentation
  40. DistillGrasp: Integrating Features Correlation with Knowledge Distillation for Depth Completion of Transparent ObjectsKnowledge distillation → Detection and dense prediction distillation
  41. ADBM: Adversarial diffusion bridge model for reliable adversarial purificationDiffusion models → Robustness, privacy and adversarial aspects
  42. Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  43. ABC Align: Large Language Model Alignment for Safety & AccuracyLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  44. Towards Flexible Evaluation for Generative Visual Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  45. Diff3DETR:Agent-based Diffusion Model for Semi-supervised 3D Object DetectionDiffusion models → Image generation, text-to-image and editing
  46. RESC: A Reinforcement Learning Based Search-to-Control Framework for Quadrotor Local Planning in Dense EnvironmentsDeep reinforcement learning methods → RL for robot navigation and UAV control
  47. QUITO: Accelerating Long-Context Reasoning through Query-Guided Context CompressionLLM reasoning → Reasoning benchmarks and evaluation +1
  48. Clover-2: Accurate Inference for Regressive Lightweight Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  49. Enhanced Structured State Space Models via Grouped FIR Filtering and Attention Sink MechanismsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  50. Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  51. Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge DistillationKnowledge distillation → Speech and audio distillation
  52. OmniParser for Pure Vision Based GUI AgentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  53. Exploration of LLMs, EEG, and behavioral data to measure and support attention and sleep
  54. Queries With Exact Truth Values in Paraconsistent Description Logics
  55. Longitudinal Evaluation of Child Face Recognition and the Impact of Underlying Age
  56. Predictive maintenance solution for industrial systems -- an unsupervised approach based on log periodic power law
  57. Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey
  58. A self-adaptive system of systems architecture to enable its ad-hoc scalability: Unmanned Vehicle Fleet -- Mission Control Center Case study
  59. Artifical intelligence and inherent mathematical difficulty
  60. Open Set Recognition for Random Forest
  61. Improving Machine Learning Based Sepsis Diagnosis Using Heart Rate Variability
  62. Enhancing Online Road Network Perception and Reasoning with Standard Definition Maps
  63. Aggregation Models with Optimal Weights for Distributed Gaussian Processes
  64. PrivateGaze: Preserving User Privacy in Black-box Mobile Gaze Tracking Services
  65. Equivariant neural networks and piecewise linear representation theory
  66. Leveraging Large Language Models (LLMs) for Traffic Management at Urban Intersections: The Case of Mixed Traffic Scenarios
  67. Generalisation of Total Uncertainty in AI: A Theoretical Study
  68. Data-Driven Traffic Simulation for an Intersection in a Metropolis
  69. A dual-task mutual learning framework for predicting post-thrombectomy cerebral hemorrhage
  70. WHITE PAPER: A Brief Exploration of Data Exfiltration using GCG Suffixes
  71. Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization
  72. Automatic Pull Request Description Generation Using LLMs: A T5 Model Approach
  73. Granting GPT-4 License and Opportunity: Enhancing Accuracy and Confidence Estimation for Few-Shot Event Detection
  74. Distance-Preserving Representations for Genomic Spatial Reconstruction
  75. Early Stopping Based on Repeated Significance
  76. Parkinson's Disease Detection from Resting State EEG using Multi-Head Graph Structure Learning with Gradient Weighted Graph Attention Explanations
  77. Expressive MIDI-format Piano Performance Generation
  78. Discrete Randomized Smoothing Meets Quantum Computing
  79. Peptide Sequencing Via Protein Language Models
  80. Temporal Evolution of Knee Osteoarthritis: A Diffusion-based Morphing Model for X-ray Medical Image Synthesis
  81. Hybrid Querying Over Relational Databases and Large Language Models
  82. On the Relationship Between Monotone and Squared Probabilistic Circuits
  83. Medical SAM 2: Segment medical images as video via Segment Anything Model 2
  84. Online Detection of Anomalies in Temporal Knowledge Graphs with Interpretability
  85. UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation
  86. UlRe-NeRF: 3D Ultrasound Imaging through Neural Rendering with Ultrasound Reflection Direction Parameterization
  87. GLoCIM: Global-view Long Chain Interest Modeling for news recommendation
  88. Penalty Learning for Optimal Partitioning using Multilayer Perceptron
  89. A Novel Use of Pseudospectra in Mathematical Biology: Understanding HPA Axis Sensitivity
  90. Calibrating Bayesian Generative Machine Learning for Bayesiamplification
  91. Y Social: an LLM-powered Social Media Digital Twin
  92. Adaptive traffic signal safety and efficiency improvement by multi objective deep reinforcement learning approach
  93. UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model
  94. Text-Guided Video Masked Autoencoder
  95. Segment anything model 2: an application to 2D and 3D medical images
  96. A deep learning-enabled smart garment for accurate and versatile sleep conditions monitoring in daily life
  97. Leaf Angle Estimation using Mask R-CNN and LETR Vision Transformer
  98. DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency
  99. Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology
  100. CERT-ED: Certifiably Robust Text Classification for Edit Distance
All 236
  1. A Natural Language Processing Framework for Hotel Recommendation Based on Users' Text Reviews
  2. SAM 2: Segment Anything in Images and Videos
  3. MotionFix: Text-Driven 3D Human Motion Editing
  4. Investigating Brain Connectivity and Regional Statistics from EEG for early stage Parkinson's Classification
  5. Synthetic dual image generation for reduction of labeling efforts in semantic segmentation of micrographs with a customized metric function
  6. Point-supervised Brain Tumor Segmentation with Box-prompted MedSAM
  7. Future of Artificial Intelligence in Agile Software Development
  8. Joint Neural Networks for One-shot Object Recognition and Detection
  9. You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning
  10. Granular-Balls based Fuzzy Twin Support Vector Machine for Classification
  11. Accelerating Full Waveform Inversion By Transfer Learning
  12. Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning
  13. Can Developers Prompt? A Controlled Experiment for Code Documentation Generation
  14. Assessing the Variety of a Concept Space Using an Unbiased Estimate of Rao's Quadratic Index
  15. Learning in Multi-Objective Public Goods Games with Non-Linear Utilities
  16. Alpha-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification
  17. Scaling Backwards: Minimal Synthetic Pre-training?
  18. An effect analysis of the balancing techniques on the counterfactual explanations of student success prediction models
  19. Leveraging Entailment Judgements in Cross-Lingual Summarisation
  20. ChordSync: Conformer-Based Alignment of Chord Annotations to Music Audio
  21. Modeling stochastic eye tracking data: A comparison of quantum generative adversarial networks and Markov models
  22. ExpertAF: Expert Actionable Feedback from Video
  23. AutoM3L: An Automated Multimodal Machine Learning Framework with Large Language Models
  24. Aligning Multiple Knowledge Graphs in a Single Pass
  25. SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context
  26. SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
  27. Enhancing Multistep Prediction of Multivariate Market Indices Using Weighted Optical Reservoir Computing
  28. A Dirichlet stochastic block model for composition-weighted networks
  29. Towards End-to-End Explainable Facial Action Unit Recognition via Vision-Language Joint Learning
  30. Enhancing Ethereum Fraud Detection via Generative and Contrastive Self-supervision
  31. AMAES: Augmented Masked Autoencoder Pretraining on Public Brain MRI Data for 3D-Native Segmentation
  32. Privacy-preserving datasets by capturing feature distributions with Conditional VAEs
  33. Deep Learning in Medical Image Classification from MRI-based Brain Tumor Images
  34. DisTrack: a new Tool for Semi-automatic Misinformation Tracking in Online Social Networks
  35. SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data
  36. Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detection
  37. Unlocking Fair Use in the Generative AI Supply Chain: A Systematized Literature Review
  38. Downstream bias mitigation is all you need
  39. Using CSNNs to Perform Event-based Data Processing & Classification on ASL-DVS
  40. AutoPV: Automatically Design Your Photovoltaic Power Forecasting Model
  41. Learned Compression of Point Cloud Geometry and Attributes in a Single Model through Multimodal Rate-Control
  42. Regional quality estimation for echocardiography using deep learning
  43. Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses
  44. Convergence Analysis of Natural Gradient Descent for Over-parameterized Physics-Informed Neural Networks
  45. Analyzing the Effectiveness of Quantum Annealing with Meta-Learning
  46. MUFASA: Multi-View Fusion and Adaptation Network with Spatial Awareness for Radar Object Detection
  47. Learning to Embed Distributions via Maximum Kernel Entropy
  48. The Energy Cost of Artificial Intelligence Lifecycle in Communication Networks
  49. High-Quality, ROS Compatible Video Encoding and Decoding for High-Definition Datasets
  50. The Monetisation of Toxicity: Analysing YouTube Content Creators and Controversy-Driven Engagement
  51. ReSi: A Comprehensive Benchmark for Representational Similarity Measures
  52. Contrastive Learning with Adaptive Neighborhoods for Brain Age Prediction on 3D Stiffness Maps
  53. Hilbert curves for efficient exploratory landscape analysis neighbourhood sampling
  54. Identifying the Hierarchical Emotional Areas in the Human Brain Through Information Fusion
  55. Low-Power Vibration-Based Predictive Maintenance for Industry 4.0 using Neural Networks: A Survey
  56. VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection
  57. Block-Operations: Using Modular Routing to Improve Compositional Generalization
  58. How Effective are Self-Supervised Models for Contact Identification in Videos
  59. SegStitch: Multidimensional Transformer for Robust and Efficient Medical Imaging Segmentation
  60. Explainable Emotion Decoding for Human and Computer Vision
  61. Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendation
  62. Multi-label Sewer Pipe Defect Recognition with Mask Attention Feature Enhancement and Label Correlation Learning
  63. A Systematic Review on Long-Tailed Learning
  64. HBot: A Chatbot for Healthcare Applications in Traditional Chinese Medicine Based on Human Body 3D Visualization
  65. Towards Explainable and Interpretable Musical Difficulty Estimation: A Parameter-efficient Approach
  66. Image Super-Resolution with Taylor Expansion Approximation and Large Field Reception
  67. Infrequent Resolving Algorithm for Online Linear Programming
  68. Designing Efficient LLM Accelerators for Edge Devices
  69. Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
  70. DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration
  71. Ontological Relations from Word Embeddings
  72. Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval
  73. Rapid and Power-Aware Learned Optimization for Modular Receive Beamforming
  74. Efficient Patient Fine-Tuned Seizure Detection with a Tensor Kernel Machine
  75. A Qualitative Study on Using ChatGPT for Software Security: Perception vs. Practicality
  76. Augmenting Channel Simulator and Semi- Supervised Learning for Efficient Indoor Positioning
  77. CARMIL: Context-Aware Regularization on Multiple Instance Learning models for Whole Slide Images
  78. A Cross-Domain Benchmark for Active Learning
  79. Towards Evolutionary-based Automated Machine Learning for Small Molecule Pharmacokinetic Prediction
  80. MPT-PAR:Mix-Parameters Transformer for Panoramic Activity Recognition
  81. Towards Reliable Advertising Image Generation Using Human Feedback
  82. Unsupervised Pairwise Causal Discovery on Heterogeneous Data using Mutual Information Measures
  83. In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation
  84. Deepfake Media Forensics: State of the Art and Challenges Ahead
  85. What comes after transformers? -- A selective survey connecting ideas in deep learning
  86. EXAONEPath 1.0 Patch-level Foundation Model for Pathology
  87. Multimodal Fusion and Coherence Modeling for Video Topic Segmentation
  88. High-Precision Self-Supervised Monocular Depth Estimation with Rich-Resource Prior
  89. Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks
  90. DeliLaw: A Chinese Legal Counselling System Based on a Large Language Model
  91. DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training
  92. Hierarchically Structured Neural Bones for Reconstructing Animatable Objects from Casual Videos
  93. Securing the Diagnosis of Medical Imaging: An In-depth Analysis of AI-Resistant Attacks
  94. Neural Graph Matching for Video Retrieval in Large-Scale Video-driven E-commerce
  95. IN-Sight: Interactive Navigation through Sight
  96. MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench
  97. Vision-based Wearable Steering Assistance for People with Impaired Vision in Jogging
  98. DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation
  99. "Patriarchy Hurts Men Too." Does Your Model Agree? A Discussion on Fairness Assumptions
  100. OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack
  101. Exploiting Preferences in Loss Functions for Sequential Recommendation via Weak Transitivity
  102. Adversarial Text Rewriting for Text-aware Recommender Systems
  103. Translating Imaging to Genomics: Leveraging Transformers for Predictive Modeling
  104. Online Linear Programming with Batching
  105. Neural Octahedral Field: Octahedral prior for simultaneous smoothing and sharp edge regularization
  106. Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names
  107. EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head
  108. Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360deg
  109. Contrastive Graph Representation Learning with Adversarial Cross-view Reconstruction and Information Bottleneck
  110. RDP: Ranked Differential Privacy for Facial Feature Protection in Multiscale Sparsified Subspace
  111. Multi-Modal Parameter-Efficient Fine-tuning via Graph Neural Network
  112. Gradient Harmonization in Unsupervised Domain Adaptation
  113. Bailing-TTS: Chinese Dialectal Speech Synthesis Towards Human-like Spontaneous Representation
  114. Navigating Text-to-Image Generative Bias across Indic Languages
  115. Towards Scalable GPU-Accelerated SNN Training via Temporal Fusion
  116. MESA: Effective Matching Redundancy Reduction by Semantic Area Segmentation
  117. High Performance Im2win and Direct Convolutions using Three Tensor Layouts on SIMD Architectures
  118. UKAN-EP: Enhancing U-KAN with Efficient Attention and Pyramid Aggregation for 3D Multi-Modal MRI Brain Tumor Segmentation
  119. Improving Image De-raining Using Reference-Guided Transformers
  120. RoCo:Robust Collaborative Perception By Iterative Object Matching and Pose Adjustment
  121. Mobility-Aware Federated Self-supervised Learning in Vehicular Network
  122. Revocable Backdoor for Deep Model Trading
  123. LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting
  124. Discovering Car-following Dynamics from Trajectory Data through Deep Learning
  125. Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition
  126. Multiple Greedy Quasi-Newton Methods for Saddle Point Problems
  127. Empirical Bayes Linked Matrix Decomposition
  128. CDFGNN: a Systematic Design of Cache-based Distributed Full-Batch Graph Neural Network Training with Communication Reduction
  129. Invariant Discovery of Features Across Multiple Length Scales: Applications in Microscopy and Autonomous Materials Characterization
  130. multiGradICON: A Foundation Model for Multimodal Medical Image Registration
  131. Persistent de Rham-Hodge Laplacians in Eulerian representation for manifold topological learning
  132. Load Balancing in Federated Learning
  133. Penzai + Treescope: A Toolkit for Interpreting, Visualizing, and Editing Models As Data
  134. A Prior Embedding-Driven Architecture for Long Distance Blind Iris Recognition
  135. Prognosis of COVID-19 using Artificial Intelligence: A Systematic Review and Meta-analysis
  136. Gaussian Processes Sampling with Sparse Grids under Additive Schwarz Preconditioner