mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 2 Jan 2025

222 papers

  1. Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offsLLM safety and security → Jailbreaking
  2. Many of Your DPOs are Secretly One: Attempting Unification Through Mutual InformationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  3. TreeLUT: An Efficient Alternative to Deep Neural Networks for Inference Acceleration Using Gradient Boosted Decision TreesEfficient LLM inference and serving → Early exit and edge inference
  4. Enhancing Reasoning through Process Supervision with Monte Carlo Tree SearchLLM reasoning → Reinforcement learning for reasoning
  5. GPT4Scene: Understand 3D Scenes from Videos with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  6. Unifying Specialized Visual Encoders for Video Language ModelsLLM reasoning → Multimodal reasoning
  7. Object-level Visual Prompts for Compositional Image GenerationDiffusion models → Image generation, text-to-image and editing
  8. Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  9. OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse ScenariosSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  10. Improving Medical Large Vision-Language Models with Abnormal-Aware FeedbackMultimodal LLMs / vision-language models → Medical vision-language models
  11. CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  12. Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of ExplainabilityMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  13. Aligning Large Language Models for Faithful Integrity Against Opposing ArgumentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  14. CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language ModelsLLM safety and security → Jailbreaking
  15. SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video RestorationDiffusion models → Inverse problems and image restoration
  16. Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow ThinkingLLM reasoning → Hallucination detection and mitigation
  17. CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 CountriesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  18. ProgCo: Program Helps Self-Correction of Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  19. Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive ImagingState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  20. CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo RatingsLLM reasoning → Reasoning for agents, planning and code
  21. Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base CompletionLLM reasoning → Knowledge- and tool-augmented reasoning
  22. Conditional Consistency Guided Image Translation and EnhancementDiffusion models → Image generation, text-to-image and editing
  23. Harnessing Multi-Agent LLMs for Complex Engineering Problem-Solving: A Framework for Senior Design ProjectsLLM agents and tool use → General LLM agent frameworks and benchmarks
  24. A Game Between the Defender and the Attacker for Trigger-based Black-box Model WatermarkingLLM safety and security → Watermarking generated content and models
  25. 3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint TransformerMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  26. A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural EvaluationLLM agents and tool use → GUI and mobile agents
  27. BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM InferenceEfficient LLM inference and serving → KV cache quantization
  28. Semantics-Guided Diffusion for Deep Joint Source-Channel Coding in Wireless Image TransmissionDiffusion models → Diffusion for compression and wireless
  29. Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal LearningRetrieval-augmented generation → Multimodal RAG
  30. EliGen: Entity-Level Controlled Image Generation with Regional AttentionDiffusion models → Image generation, text-to-image and editing
  31. Noise-Resilient Symbolic Regression with Dynamic Gating Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  32. Dynamic Scaling of Unit Tests for Code Reward ModelingLLM reasoning → Reasoning for agents, planning and code +1
  33. Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video ApproachMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  34. ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual LearningRetrieval-augmented generation → Generation and context integration
  35. KaLM-Embedding: Superior Training Data Brings A Stronger Embedding ModelRetrieval-augmented generation → Generation and context integration
  36. Deep Reinforcement Learning for Job Scheduling and Resource Management in Cloud Computing: An Algorithm-Level ReviewDeep reinforcement learning methods → RL for energy, networks and operations
  37. FlashInfer: Efficient and Customizable Attention Engine for LLM Inference ServingEfficient LLM inference and serving → KV cache optimization
  38. Bootstrapped Reward ShapingDeep reinforcement learning methods → Deep RL algorithms and representations
  39. Optimizing Noise Schedules of Generative Models in High DimensionssDiffusion models → Diffusion foundations and sampling
  40. Perspective Chapter: MOOCs in India: Evolution, Innovation, Impact, and Roadmap
  41. The Use of Generative Artificial Intelligence for Upper Secondary Mathematics Education Through the Lens of Technology Acceptance
  42. Operator Learning for Reconstructing Flow Fields from Sparse Measurements: an Energy Transformer Approach
  43. Multi-task Domain Adaptation for Computation Offloading in Edge-intelligence Networks
  44. A Shape-Based Functional Index for Objective Assessment of Pediatric Motor Function
  45. Calculating Customer Lifetime Value and Churn using Beta Geometric Negative Binomial and Gamma-Gamma Distribution in a NFT based setting
  46. Knowledge-Guided Biomarker Identification for Label-Free Single-Cell RNA-Seq Data: A Reinforcement Learning Perspective
  47. Toward Inclusive Educational AI: Auditing Frontier LLMs through a Multiplexity Lens
  48. FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles
  49. RealDiffFusionNet: Neural Controlled Differential Equation Informed Multi-Head Attention Fusion Networks for Disease Progression Modeling Using Real-World Data
  50. Model Checking in Medical Imaging for Tumor Detection and Segmentation
  51. Weakly Supervised Learning on Large Graphs
  52. Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection
  53. Benchmarking Constraint-Based Bayesian Structure Learning Algorithms: Role of Network Topology
  54. Rephotography in the Digital Era: Mass Rephotography and re.photos, the Web Portal for Rephotography
  55. ST-HCSS: Deep Spatio-Temporal Hypergraph Convolutional Neural Network for Soft Sensing
  56. KANS: Knowledge Discovery Graph Attention Network for Soft Sensing in Multivariate Industrial Processes
  57. Machine Learning-Based Differential Diagnosis of Parkinson's Disease Using Kinematic Feature Extraction and Selection
  58. Information Subtraction: Learning Representations for Conditional Entropy
  59. Explainable Neural Networks with Guarantees: A Sparse Estimation Approach
  60. Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts
  61. TART: Token-based Architecture Transformer for Neural Network Performance Prediction
  62. Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extraction
  63. General Information Metrics for Improving AI Model Training Efficiency
  64. Unsupervised learning for anticipating critical transitions
  65. Constructing and explaining machine learning models for chemistry: example of the exploration and design of boron-based Lewis acids
  66. Semialgebraic Neural Networks: From roots to representations
  67. Predicting the Performance of Black-box LLMs through Follow-up Queries
  68. Click-Calib: A Robust Extrinsic Calibration Method for Surround-View Systems
  69. Multi-view Bayesian optimisation in an input-output reduced space for engineering design
  70. Task-Driven Fixation Network: An Efficient Architecture with Fixation Selection
  71. BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery
  72. In Search of a Lost Metric: Human Empowerment as a Pillar of Socially Conscious Navigation
  73. A Metasemantic-Metapragmatic Framework for Taxonomizing Multimodal Communicative Alignment
  74. SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers
  75. Transfer Neyman-Pearson Algorithm for Outlier Detection
  76. Quantifying True Robustness: Synonymity-Weighted Similarity for Trustworthy XAI Evaluation
  77. DiagrammaticLearning: A Graphical Language for Compositional Training Regimes
  78. Explainable Brain Age Gap Prediction in Neurodegenerative Conditions using coVariance Neural Networks
  79. AI-Enabled Operations at Fermi Complex: Multivariate Time Series Prediction for Outage Prediction and Diagnosis
  80. Transfer Learning Analysis of Variational Quantum Circuits
  81. ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST
  82. Sequencing Silicates in the IRS Debris Disk Catalog I: Methodology for Unsupervised Clustering
  83. Embedding Similarity Guided License Plate Super Resolution
  84. An unsupervised method for MRI recovery: Deep image prior with structured sparsity
  85. Unleashing Correlation and Continuity for Hyperspectral Reconstruction from RGB Images
  86. CORAL: Concept Drift Representation Learning for Co-evolving Time-series
  87. A Survey of Deep Learning Methods in Protein Bioinformatics and its Impact on Protein Design
  88. VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control
  89. Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation
  90. Multi-Modal Video Feature Extraction for Popularity Prediction
  91. R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization
  92. A Multi-task Supervised Compression Model for Split Computing
  93. Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension
  94. Deep Discrete Encoders: Identifiable Deep Generative Models for Rich Data with Discrete Latent Layers
  95. JOG3R: Towards 3D-Consistent Video Generators
  96. Nested Attention: Semantic-aware Attention Values for Concept Personalization
  97. nnY-Net: Swin-NeXt with Cross-Attention for 3D Medical Images Segmentation
  98. Best Transition Matrix Esitimation or Best Label Noise Robustness Classifier? Two Possible Methods to Enhance the Performance of T-revision
  99. A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models
  100. Learning 3D Garment Animation from Trajectories of A Piece of Cloth
All 222
  1. ProjectedEx: Enhancing Generation in Explainable AI for Prostate Cancer
  2. Deep P-Spline: Theory, Fast Tuning, and Application
  3. Iris Recognition for Infants
  4. ScarNet: A Novel Foundation Model for Automated Myocardial Scar Quantification from LGE in Cardiac MRI
  5. Embedding-Based Approaches to Hyperpartisan News Detection
  6. Test-time Controllable Image Generation by Explicit Spatial Constraint Enforcement
  7. Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation
  8. ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding
  9. Rethinking Relation Extraction: Beyond Shortcuts to Generalization with a Debiased Benchmark
  10. AdaptVC: High Quality Voice Conversion with Adaptive Learning
  11. Machine Learning for Modeling Wireless Radio Metrics with Crowdsourced Data and Local Environment Features
  12. DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoring
  13. Simultaneous Latent State Estimation and Latent Linear Dynamics Discovery from Image Observations
  14. Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension
  15. The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation
  16. Domain-invariant feature learning in brain MR imaging for content-based image retrieval
  17. Fast data inversion for high-dimensional Ornstein-Uhlenbeck processes from noisy measurements
  18. Difficult Examples Hurt Unsupervised Contrastive Learning: A Theoretical Perspective
  19. Learning Spectral Methods by Transformers
  20. Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers
  21. Large Language Models for Mental Health Diagnostic Assessments: Exploring The Potential of Large Language Models for Assisting with Mental Health Diagnostic Assessments -- The Depression and Anxiety Case
  22. Citations and Trust in LLM Generated Responses
  23. LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networks
  24. Detection Augmented Bandit Procedures for Piecewise Stationary MABs: A Modular Approach
  25. ToolComp: A Multi-Tool Reasoning & Process Supervision Benchmark
  26. Optimized Relay Lens Design For High-Resolution Image Transmission In Military Target Detection Systems
  27. Tracing Partisan Bias to Its Emotional Fingerprints: A Computational Approach to Mitigation
  28. Marketing Mix Modeling in Lemonade
  29. HybridTrack: A Hybrid Approach for Robust Multi-Object Tracking
  30. Does a Large Language Model Really Speak in Human-Like Language?
  31. PIMAEX: Multi-Agent Exploration through Peer Incentivization
  32. Stealthy Backdoor Attack to Real-world Models in Android Apps
  33. Digital Guardians: Can GPT-4, Perspective API, and Moderation API reliably detect hate speech in reader comments of German online newspapers?
  34. Bayesian Active Learning By Distribution Disagreement
  35. SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization
  36. Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants
  37. An Efficient Attention Mechanism for Sequential Recommendation Tasks: HydraRec
  38. Asymmetric Reinforcing against Multi-modal Representation Bias
  39. High-Order Tensor Regression in Sparse Convolutional Neural Networks
  40. EHCTNet: Enhanced Hybrid of CNN and Transformer Network for Remote Sensing Image Change Detection
  41. Self-Refinement Strategies for LLM-based Product Attribute Value Extraction
  42. SVFR: A Unified Framework for Generalized Video Face Restoration
  43. Exploiting Latent Properties to Optimize Neural Codecs
  44. Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
  45. Comparative Analysis of Topic Modeling Techniques on ATSB Text Narratives Using Natural Language Processing
  46. Classification of Operational Records in Aviation Using Deep Learning Approaches
  47. TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer
  48. Towards Consumer-Grade Cybersickness Prediction: Multi-Model Alignment for Real-Time Vision-Only Inference
  49. A redescription mining framework for post-hoc explaining and relating deep learning models
  50. Empirical Analysis of Nature-Inspired Algorithms for Autism Spectrum Disorder Detection Using 3D Video Dataset
  51. LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge
  52. Sparis: Neural Implicit Surface Reconstruction of Indoor Scenes from Sparse Views
  53. Data Augmentation Techniques for Chinese Disease Name Normalization
  54. Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection
  55. Machine Learning-Based Prediction of ICU Readmissions in Intracerebral Hemorrhage Patients: Insights from the MIMIC Databases
  56. RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer
  57. L3D-Pose: Lifting Pose for 3D Avatars from a Single Camera in the Wild
  58. Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasets
  59. Deep Learning in Palmprint Recognition-A Comprehensive Survey
  60. Towards Interactive Deepfake Analysis
  61. Attending To Syntactic Information In Biomedical Event Extraction Via Graph Neural Networks
  62. Ultrasound Lung Aeration Map via Physics-Aware Neural Operators
  63. TexAVi: Generating Stereoscopic VR Video Clips from Text Descriptions
  64. Adaptive posterior distributions for uncertainty analysis of covariance matrices in Bayesian inversion problems for multioutput signals
  65. Adaptive Hardness-driven Augmentation and Alignment Strategies for Multi-Source Domain Adaptations
  66. Symmetries-enhanced Multi-Agent Reinforcement Learning
  67. Missing Data as Augmentation in the Earth Observation Domain: A Multi-View Learning Approach
  68. An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise
  69. InDeed: Interpretable image deep decomposition with guaranteed generalizability
  70. Source-free Semantic Regularization Learning for Semi-supervised Domain Adaptation
  71. DuMo: Dual Encoder Modulation Network for Precise Concept Erasure
  72. Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning
  73. TED: Turn Emphasis with Dialogue Feature Attention for Emotion Recognition in Conversation
  74. PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation
  75. Leverage Cross-Attention for End-to-End Open-Vocabulary Panoptic Reconstruction
  76. Pruning-based Data Selection and Network Fusion for Efficient Deep Learning
  77. Robust COVID-19 Detection from Cough Sounds using Deep Neural Decision Tree and Forest: A Comprehensive Cross-Datasets Evaluation
  78. HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment
  79. Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotion
  80. Regularized Proportional Fairness Mechanism for Resource Allocation Without Money
  81. MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classification
  82. BatStyler: Advancing Multi-category Style Generation for Source-free Domain Generalization
  83. MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization
  84. AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
  85. learning discriminative features from spectrograms using center loss for speech emotion recognition
  86. Disambiguation of Chinese Polyphones in an End-to-End Framework with Semantic Features Extracted by Pre-trained BERT
  87. Deformable Gaussian Splatting for Efficient and High-Fidelity Reconstruction of Surgical Scenes
  88. Long-range Brain Graph Transformer
  89. MMVA: Multimodal Matching Based on Valence and Arousal across Images, Music, and Musical Captions
  90. HoneypotNet: Backdoor Attacks Against Model Extraction
  91. Bridging Simplicity and Sophistication using GLinear: A Novel Architecture for Enhanced Time Series Prediction
  92. Graph Generative Pre-trained Transformer
  93. Evidential Calibrated Uncertainty-Guided Interactive Segmentation paradigm for Ultrasound Images
  94. BeliN: A Novel Corpus for Bengali Religious News Headline Generation using Contextual Feature Fusion
  95. Enhancing Precision of Automated Teller Machines Network Quality Assessment: Machine Learning and Multi Classifier Fusion Approaches
  96. An Efficient Outlier Detection Algorithm for Data Streaming
  97. Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
  98. HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach
  99. Risks of Cultural Erasure in Large Language Models
  100. TS-SatMVSNet: Slope Aware Height Estimation for Large-Scale Earth Terrain Multi-view Stereo
  101. SEDD: Scalable and Efficient Dataset Deduplication with GPUs
  102. ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
  103. Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras
  104. MSWA: Refining Local Attention with Multi-ScaleWindow Attention
  105. MSC-Bench: Benchmarking and Analyzing Multi-Sensor Corruption for Driving Perception
  106. Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models
  107. DynamicLip: Shape-Independent Continuous Authentication via Lip Articulator Dynamics
  108. Reasoning based on symbolic and parametric knowledge bases: a survey
  109. State-of-the-art AI-based Learning Approaches for Deepfake Generation and Detection, Analyzing Opportunities, Threading through Pros, Cons, and Future Prospects
  110. Towards Adversarially Robust Deep Metric Learning
  111. Hadamard Attention Recurrent Transformer: A Strong Baseline for Stereo Matching Transformer
  112. Efficient Connectivity-Preserving Instance Segmentation with Supervoxel-Based Loss Function
  113. Boosting Adversarial Transferability with Spatial Adversarial Alignment
  114. MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Model
  115. Prediction of Geoeffective CMEs Using SOHO Images and Deep Learning
  116. CryptoMamba: Leveraging State Space Models for Accurate Bitcoin Price Prediction
  117. EasySplat: View-Adaptive Learning makes 3D Gaussian Splatting Easy
  118. Multi-Objective Optimization-Based Anonymization of Structured Data for Machine Learning Application
  119. Physics-informed Gaussian Processes for Safe Envelope Expansion
  120. Exploring Information Processing in Large Language Models: Insights from Information Bottleneck Theory
  121. Is It Still Fair? Investigating Gender Fairness in Cross-Corpus Speech Emotion Recognition
  122. Are LLMs effective psychological assessors? Leveraging adaptive RAG for interpretable mental health screening through psychometric practice