mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 28 Nov 2024

224 papers

  1. Supervised Learning-enhanced Multi-Group Actor Critic for Live Stream Allocation in FeedDeep reinforcement learning methods → RL training of language and agent models
  2. Challenges in Human-Agent CommunicationLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. MAG-V: A Multi-Agent Framework for Synthetic Data Generation and VerificationLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  4. MPQ-Diff: Mixed Precision Quantization for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  5. Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model FeaturesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  6. Streamlined Federated Unlearning: Unite as One to Be Highly EfficientLLM safety and security → Federated unlearning and poisoning
  7. Efficient Learning Content Retrieval with Knowledge InjectionRetrieval-augmented generation → Agentic RAG, agents and memory
  8. Bridging the Gap: Aligning Text-to-Image Diffusion Models with Specific FeedbackDiffusion models → Image generation, text-to-image and editing
  9. SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World EnvironmentsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  10. AMO Sampler: Enhancing Text Rendering with OvershootingDiffusion models → Image generation, text-to-image and editing
  11. On the Role of Discrete Representation in Sparse Mixture of ExpertsMixture-of-experts → Vision mixture-of-experts
  12. Global Tensor Motion PlanningOffline RL and imitation learning from data → Robot learning from demonstration
  13. DreamBlend: Advancing Personalized Fine-tuning of Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  14. Enhancing Sketch Animation: Text-to-Video Diffusion Models with Temporal Consistency and Rigidity ConstraintsDiffusion models → Image generation, text-to-image and editing
  15. Towards a Mechanistic Explanation of Diffusion Model GeneralizationDiffusion models → Diffusion foundations and sampling
  16. PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-TuningLLM safety and security → Federated unlearning and poisoning
  17. GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial TasksMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  18. Trajectory Attention for Fine-grained Video Motion ControlDiffusion models → Video generation
  19. GRAPE: Generalizing Robot Policy via Preference AlignmentVision-language-action models → Reinforcement learning and post-training +1
  20. Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition AttentionDiffusion models → Image generation, text-to-image and editing
  21. Quantum feedback control with a transformer neural network architectureDeep reinforcement learning methods → Quantum reinforcement learning
  22. Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting ScenesDiffusion models → 3D, point cloud and scene generation
  23. Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEGKnowledge distillation → Distillation for medical imaging
  24. On the Ethical Considerations of Generative AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  25. Track Anything Behind Everything: Zero-Shot Amodal Video Object SegmentationDiffusion models → Medical imaging and segmentation
  26. Convex Regularization and Convergence of Policy Gradient Flows under Safety ConstraintsDeep reinforcement learning methods → RL theory and sample complexity
  27. Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  28. Bayesian Deconvolution of Astronomical Images with Diffusion Models: Quantifying Prior-Driven Features in ReconstructionsDiffusion models → Inverse problems and image restoration
  29. TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  30. MSG Score: Automated Video Verification for Reliable Multi-Scene GenerationDiffusion models → Video generation
  31. Timestep Embedding Tells: It's Time to Cache for Video Diffusion ModelDiffusion models → Video generation
  32. VARCO-VISION: Expanding Frontiers in Korean Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  33. I Dream My Painting: Connecting MLLMs and Diffusion Models via Prompt Generation for Text-Guided Multi-Mask InpaintingDiffusion models → 3D, point cloud and scene generation
  34. Mars-PO: Multi-Agent Reasoning System Preference OptimizationLLM reasoning → Reasoning for agents, planning and code +2
  35. PCDreamer: Point Cloud Completion Through Multi-view Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  36. Synergizing Decision Making and Trajectory Planning Using Two-Stage Optimization for Autonomous VehiclesEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  37. Random Sampling for Diffusion-based Adversarial PurificationDiffusion models → Robustness, privacy and adversarial aspects
  38. RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation AnalysisRetrieval-augmented generation → Privacy and security of RAG
  39. Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar SubjectsDiffusion models → Image generation, text-to-image and editing
  40. ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming ChallengesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  41. VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational InferenceDiffusion models → 3D, point cloud and scene generation
  42. Data Augmentation with Diffusion Models for Colon Polyp Localization on the Low Data Regime: How much real data is enough?Diffusion models → Medical imaging and segmentation
  43. CoDiff-VC: A Codec-Assisted Diffusion Model for Zero-shot Voice ConversionDiffusion models → Audio, speech and music
  44. MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular ApplicationsLLM reasoning → Knowledge- and tool-augmented reasoning
  45. Evaluating Sparse Autoencoders on Targeted Concept Erasure TasksMechanistic interpretability → Sparse autoencoder training and evaluation
  46. A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical ChallengesDeep reinforcement learning methods → Deep RL algorithms and representations
  47. Adult learners recall and recognition performance and affective feedback when learning from an AI-generated synthetic video
  48. Integrating Functionalities To A System Via Autoencoder Hippocampus Network
  49. NERsocial: Efficient Named Entity Recognition Dataset Construction for Human-Robot Interaction Utilizing RapidNER
  50. Publication Trends in Artificial Intelligence Conferences: The Rise of Super Prolific Authors
  51. I See, Therefore I Do: Estimating Causal Effects for Image Treatments
  52. λ: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics
  53. Self-Supervised Learning for Graph-Structured Data in Healthcare Applications: A Comprehensive Review
  54. DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent
  55. CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for Predicting Disease Severity and Clinical Outcomes in COVID-19 Patients
  56. Using Images to Find Context-Independent Word Representations in Vector Space
  57. Applying IRT to Distinguish Between Human and Generative AI Responses to Multiple-Choice Assessments
  58. Towards Data-centric Machine Learning on Directed Graphs: a Survey
  59. Knowledge-Augmented Explainable and Interpretable Learning for Anomaly Detection and Diagnosis
  60. Semi-Supervised Neural Processes for Articulated Object Interactions
  61. Is Oracle Pruning the True Oracle?
  62. Differentiable Topology Estimating from Curvatures for 3D Shapes
  63. EFSA: Episodic Few-Shot Adaptation for Text-to-Image Retrieval
  64. Adversarial Exploitation of Data Diversity Improves Visual Localization
  65. FonTS: Text Rendering with Typography and Style Controls
  66. PP-SSL : Priority-Perception Self-Supervised Learning for Fine-Grained Recognition
  67. ETAP: Event-based Tracking of Any Point
  68. Road User Classification from High-Frequency GNSS Data Using Distributed Edge Intelligence
  69. Open-Sora Plan: Open-Source Large Video Generation Model
  70. Scaling Particle Collision Data Analysis
  71. Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
  72. Auto-Encoded Supervision for Perceptual Image Super-Resolution
  73. Electricity Price Prediction Using Multi-Kernel Gaussian Process Regression Combined with Kernel-Based Support Vector Regression
  74. Hybrid Discriminative Attribute-Object Embedding Network for Compositional Zero-Shot Learning
  75. Relation-Aware Meta-Learning for Zero-shot Sketch-Based Image Retrieval
  76. Training Multi-Layer Binary Neural Networks With Local Binary Error Signals
  77. Proceedings of the 2024 XCSP3 Competition
  78. OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
  79. Boundary-Decoder network for inverse prediction of capacitor electrostatic analysis
  80. BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis
  81. Video Set Distillation: Information Diversification and Temporal Densification
  82. Demographic Predictability in 3D CT Foundation Embeddings
  83. Deep Neural Network-Based Prediction of B-Cell Epitopes for SARS-CoV and SARS-CoV-2: Enhancing Vaccine Design through Machine Learning
  84. Act Now: A Novel Online Forecasting Framework for Large-Scale Streaming Data
  85. Virtual Sensing to Enable Real-Time Monitoring of Inaccessible Locations & Unmeasurable Parameters
  86. Any-Resolution AI-Generated Image Detection by Spectral Learning
  87. Concept-driven Off Policy Evaluation
  88. Scale-aware Message Passing For Graph Node Classification
  89. Zero-Forget Preservation of Semantic Communication Alignment in Distributed AI Networks
  90. Marconi: Prefix Caching for the Era of Hybrid LLMs
  91. Libra: Leveraging Temporal Images for Biomedical Radiology Analysis
  92. Parameter-Efficient Transfer Learning for Music Foundation Models
  93. Machine learning the Ising transition: A comparison between discriminative and generative approaches
  94. Conformal Calibration of Statistical Confidence Sets
  95. DENIAHL: In-Context Features Influence LLM Needle-In-A-Haystack Abilities
  96. Integrating Transit Signal Priority into Multi-Agent Reinforcement Learning based Traffic Signal Control
  97. Mapping Public Perception of Artificial Intelligence: Expectations, Risk-Benefit Tradeoffs, and Value As Determinants for Societal Acceptance
  98. OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendation
  99. CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections
  100. 3D Wasserstein generative adversarial network with dense U-Net based discriminator for preclinical fMRI denoising
All 224
  1. An Adversarial Learning Approach to Irregular Time-Series Forecasting
  2. Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation
  3. SAMa: Material-aware 3D Selection and Segmentation
  4. Generalized Gaussian Model for Learned Image Compression
  5. LD-EnSF: Synergizing Latent Dynamics with Ensemble Score Filters for Fast Data Assimilation with Sparse Observations
  6. Perspective of Software Engineering Researchers on Machine Learning Practices Regarding Research, Review, and Education
  7. Structured Object Language Modeling (SoLM): Native Structured Objects Generation Conforming to Complex Schemas with Self-Supervised Denoising
  8. Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptation
  9. Extracting Information in a Low-resource Setting: Case Study on Bioinformatics Workflows
  10. UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation
  11. TRASE: Tracking-free 4D Segmentation and Editing
  12. STAG-VIO: Stabilized Prompt-to-Geometry Interface for Robust Dynamic Visual--Inertial Odometry
  13. BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning
  14. The role of data-induced randomness in quantum machine learning classification tasks
  15. OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration
  16. Quantum Neural Networks in Practice: A Comparative Study with Classical Models from Standard Data Sets to Industrial Images
  17. On-chip Hyperspectral Image Segmentation with Fully Convolutional Networks for Scene Understanding in Autonomous Driving
  18. AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphones
  19. Skeleton Detection Using Dual Radars with Integration of Dual-View CNN Models and mmPose
  20. Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation
  21. Contrastive representations of high-dimensional, structured treatments
  22. Consolidating and Developing Benchmarking Datasets for the Nepali Natural Language Understanding Tasks
  23. Controlling Participation in Federated Learning with Feedback
  24. How far can bias go? Tracing bias from pretraining data to alignment
  25. InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception
  26. SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework
  27. Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution
  28. Habit Coach: Customising RAG-based chatbots to support behavior change
  29. Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstruction
  30. On the Unknowable Limits to Prediction
  31. Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection
  32. Cross-Spectral Attention for Unsupervised RGB-IR Face Verification and Person Re-identification
  33. ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities
  34. An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation
  35. Video Depth without Video Models
  36. SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation
  37. Large width penalization for neural network-based prediction interval estimation
  38. HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos
  39. Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs
  40. Neural Shadow Art
  41. LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair
  42. DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning
  43. Counting Stacked Objects
  44. Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
  45. Co-Learning: Towards Semi-Supervised Object Detection with Road-side Cameras
  46. On Moving Object Segmentation from Monocular Video with Transformers
  47. Examining Multimodal Gender and Content Bias in ChatGPT-4o
  48. Visual SLAMMOT Considering Multiple Motion Models
  49. Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures
  50. Advancing Generalization in PINNs through Latent-Space Representations
  51. Deep Learning for GWP Prediction: A Framework Using PCA, Quantile Transformation, and Ensemble Modeling
  52. Introducing Three New Benchmark Datasets for Hierarchical Text Classification
  53. Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models
  54. PREBA: A Hardware/Software Co-Design for Multi-Instance GPU based AI Inference Servers
  55. Integration of Contextual Descriptors in Ontology Alignment for Enrichment of Semantic Correspondence
  56. Detailed Object Description with Controllable Dimensions
  57. 360Recon: An Accurate Reconstruction Method Based on Depth Fusion from 360 Images
  58. Pralekha: Cross-Lingual Document Alignment for Indic Languages
  59. Beautimeter: Harnessing GPT for Assessing Architectural and Urban Beauty based on the 15 Properties of Living Structure
  60. Seeing SDG 6 from space: local-scale monitoring of piped water and sewage systems across Africa using satellite imagery and self-supervised learning
  61. Neural Window Decoder for SC-LDPC Codes
  62. ABROCA Distributions For Algorithmic Bias Assessment: Considerations Around Interpretation
  63. ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives
  64. Improving sub-seasonal wind-speed forecasts in Europe with a non-linear model
  65. LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm
  66. Dynamic Attention and Bi-directional Fusion for Safety Helmet Wearing Detection
  67. MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
  68. Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph
  69. Aggregating Data for Optimal and Private Learning
  70. Using a Feedback Loop for LLM-based Infrastructure as Code Generation
  71. TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
  72. DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs
  73. 3D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapes
  74. Enhancing Neural Network Robustness Against Fault Injection Through Non-linear Weight Transformations
  75. Pilot Contamination Aware Transformer for Downlink Power Control in Cell-Free Massive MIMO Networks
  76. A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages
  77. Talking to oneself in CMC: a study of self replies in Wikipedia talk pages
  78. Locally-Focused Face Representation for Sketch-to-Image Generation Using Noise-Induced Refinement
  79. An AI-Driven Multimodal Smart Home Platform for Continuous Monitoring and Assistance in Post-Stroke Motor Impairment
  80. GRU-PFG: Extract Inter-Stock Correlation from Stock Factors with Graph Neural Network
  81. MVFormer: Diversifying Feature Normalization and Token Mixing for Efficient Vision Transformers
  82. Harden Deep Neural Networks Against Fault Injections Through Weight Scaling
  83. USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task
  84. Intrinsic Gaussian Process Regression Modeling for Manifold-valued Response Variable
  85. SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing
  86. Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems
  87. Det-SAM2:Technical Report on the Self-Prompting Segmentation Framework Based on Segment Anything Model 2
  88. FAN-Unet: Enhancing Unet with vision Fourier Analysis Block for Biomedical Image Segmentation
  89. FiRe: Fixed-points of Restoration Priors for Solving Inverse Problems
  90. Perception of Visual Content: Differences Between Humans and Foundation Models
  91. Deep Plug-and-Play HIO Approach for Phase Retrieval
  92. SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
  93. Neural Operators for Predictor Feedback Control of Nonlinear Delay Systems
  94. ReMAP: Lossless Residual Neural Lifting for Scalable MAP Inference in Arbitrary-Order Markov Random Fields
  95. ICLERB: In-Context Learning Embedding and Reranker Benchmark
  96. Waterfall Transformer for Multi-person Pose Estimation
  97. Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
  98. Rephrasing Electronic Health Records for Pretraining Clinical Language Models
  99. Efficient Track Anything
  100. The Impact of Example Selection in Few-Shot Prompting on Automated Essay Scoring Using GPT Models
  101. EzSQL: An SQL intermediate representation for improving SQL-to-text Generation
  102. Devising a Set of Compact and Explainable Spoken Language Feature for Screening Alzheimer's Disease
  103. Federated Continual Graph Learning
  104. FedRGL: Robust Federated Graph Learning for Label Noise
  105. MSEMG: Surface Electromyography Denoising with a Mamba-based Efficient Network
  106. Textured As-Is BIM via GIS-informed Point Cloud Segmentation
  107. T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving
  108. CovHuSeg: An Enhanced Approach for Kidney Pathology Segmentation
  109. ArEEG_Words: Dataset for Envisioned Speech Recognition using EEG for Arabic Words
  110. Sneaking Syntax into Transformer Language Models with Tree Regularization
  111. ETSM: Automating Dissection Trajectory Suggestion and Confidence Map-Based Safety Margin Prediction for Robot-assisted Endoscopic Submucosal Dissection
  112. GTPC-SSCD: Gate-guided Two-level Perturbation Consistency-based Semi-Supervised Change Detection
  113. Swarm Intelligence-Driven Client Selection for Federated Learning in Cybersecurity applications
  114. Automating Energy-Efficient GPU Kernel Generation: A Fast Search-Based Compilation Approach
  115. A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problems
  116. Comprehensive Performance Evaluation of YOLOv11, YOLOv10, YOLOv9, YOLOv8 and YOLOv5 on Object Detection of Power Equipment
  117. RIGI: Rectifying Image-to-3D Generation Inconsistency via Uncertainty-aware Learning
  118. Redesigning the ensemble Kalman filter with a dedicated model of epistemic uncertainty
  119. Improving Batch Normalization with TTA for Robust Object Detection in Self-Driving
  120. COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection
  121. Improving Accuracy and Generalization for Efficient Visual Tracking
  122. CrossTracker: Robust Multi-modal 3D Multi-Object Tracking via Cross Correction
  123. An Integrated Artificial Intelligence Operating System for Advanced Low-Altitude Aviation Applications
  124. Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark