mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 16 Jan 2024

237 papers

  1. CNN-DRL with Shuffled Features in FinanceDeep reinforcement learning methods → Adversarial robustness and RL in finance
  2. LoMA: Lossless Compressed Memory AttentionEfficient LLM inference and serving → KV cache optimization
  3. MambaTab: A Plug-and-Play Model for Learning Tabular DataState-space sequence models (S4, Mamba) → Core SSM architectures for language
  4. REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
  5. Learning from Sparse Offline Datasets via Conservative Density EstimationOffline RL and imitation learning from data → Offline RL algorithms +1
  6. Adversarial Supervision Makes Layout-to-Image Diffusion Models ThriveDiffusion models → Image generation, text-to-image and editing
  7. Fixed Point Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  8. SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant TransformersDiffusion models → Diffusion foundations and sampling
  9. Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual InformationKnowledge distillation → General knowledge distillation methods
  10. Revealing Vulnerabilities in Stable Diffusion via Targeted AttacksDiffusion models → Robustness, privacy and adversarial aspects +1
  11. CodeComplex: Dataset for Worst-Case Time Complexity PredictionLLM reasoning → Reasoning for agents, planning and code
  12. DiConStruct: Causal Concept-based Explanations through Black-Box DistillationKnowledge distillation → General knowledge distillation methods
  13. Solving Continual Offline Reinforcement Learning with Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
  14. Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine TranslationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  15. RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on AgricultureRetrieval-augmented generation → Time series and agricultural RAG
  16. DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)LLM agents and tool use → Multimodal and embodied agents
  17. Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model InferenceMixture-of-experts → Efficient MoE training and inference systems
  18. Generative Denoise Distillation: Simple Stochastic Noises Induce Efficient Knowledge Transfer for Dense PredictionKnowledge distillation → Detection and dense prediction distillation
  19. RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool LearningLLM agents and tool use → Tool learning and function calling
  20. Application of LLM Agents in Recruitment: A Novel Framework for Resume ScreeningLLM agents and tool use → General LLM agent frameworks and benchmarks
  21. On Quantum Natural Policy GradientsDeep reinforcement learning methods → Quantum reinforcement learning
  22. Inferflow: an Efficient and Highly Configurable Inference Engine for Large Language ModelsEfficient LLM inference and serving → Serving systems and request scheduling
  23. AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics PerceptionMultimodal LLMs / vision-language models → Image editing and quality assessment
  24. Multi-scale 2D Temporal Map Diffusion Models for Natural Language Video LocalizationDiffusion models → Video generation
  25. Human vs. LMMs: Exploring the Discrepancy in Emoji Interpretation and Usage in Digital CommunicationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  26. MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible PipelineLLM reasoning → Mathematical reasoning
  27. PRewrite: Prompt Rewriting with Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  28. Key-point Guided Deformable Image Manipulation Using Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  29. ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech SynthesisDiffusion models → Audio, speech and music
  30. CycLight: learning traffic signal cooperation with a cycle-level strategyDeep reinforcement learning methods → RL for autonomous driving and traffic
  31. DIFFRENT: A Diffusion Model for Recording Environment Transfer of SpeechDiffusion models → Audio, speech and music
  32. EmoTalker: Emotionally Editable Talking Face Generation via Diffusion ModelDiffusion models → Audio, speech and music
  33. Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and OpportunitiesEnd-to-end autonomous driving → End-to-end system architecture
  34. Self-Imagine: Effective Unimodal Reasoning with Multimodal Models using Self-ImaginationLLM reasoning → Multimodal reasoning +1
  35. Water-Based Metaheuristics: How Water Dynamics Can Help Us to Solve NP-Hard Problems
  36. A Cost-Sensitive Transformer Model for Prognostics Under Highly Imbalanced Industrial Data
  37. Reinforcement-learning robotic sailboats: simulator and preliminary results
  38. Improved Performances and Motivation in Intelligent Tutoring Systems: Combining Machine Learning and Learner Choice
  39. Topic Modelling: Going Beyond Token Outputs
  40. Into the crossfire: evaluating the use of a language model to crowdsource gun violence reports
  41. Few-Shot Learning for Mental Disorder Detection: A Continuous Multi-Prompt Engineering Approach with Medical Knowledge Injection
  42. TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation
  43. Crowdsourced Adaptive Surveys
  44. Forecasting Cryptocurrency Staking Rewards
  45. Semidefinite programming relaxations and debiasing for MAXCUT-based clustering
  46. Open-Source Fermionic Neural Networks with Ionic Charge Initialization
  47. Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task
  48. Importance-Aware Image Segmentation-based Semantic Communication for Autonomous Driving
  49. Uncertainty-Aware Calibration of a Hot-Wire Anemometer With Gaussian Process Regression
  50. Memory, Space, and Planning: Multiscale Predictive Representations
  51. PUPAE: Intuitive and Actionable Explanations for Time Series Anomalies
  52. NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription
  53. RiemannONets: Interpretable Neural Operators for Riemann Problems
  54. Contribution Functions for Quantitative Bipolar Argumentation Graphs: A Principle-based Analysis
  55. Evaluating the Utility of Conformal Prediction Sets for AI-Advised Image Labeling
  56. DCRMTA: Deep Causal Representation Learning for Multi-Touch Attribution
  57. B-Cos Aligned Transformers Learn Human-Interpretable Features
  58. The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images
  59. Binaural Angular Separation Network
  60. Robust Localization of Key Fob Using Channel Impulse Response of Ultra Wide Band Sensors for Keyless Entry Systems
  61. Generative AI for O-RAN Slicing: A Semi-Supervised Approach with VAE and Contrastive Learning
  62. Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization
  63. Shabari: Delayed Decision-Making for Faster and Efficient Serverless Functions
  64. Using i-vectors for subject-independent cross-session EEG transfer learning
  65. RIDGE: Reproducibility, Integrity, Dependability, Generalizability, and Efficiency Assessment of Medical Image Segmentation Models
  66. Efficient Neural Representation of Volumetric Data using Coordinate-Based Networks
  67. Image Fusion in Remote Sensing: An Overview and Meta Analysis
  68. Improving ASR Contextual Biasing with Guided Attention
  69. Revisiting Self-supervised Learning of Speech Representation from a Mutual Information Perspective
  70. Stochastic Subnetwork Annealing: A Regularization Technique for Fine Tuning Pruned Subnetworks
  71. AiGen-FoodReview: A Multimodal Dataset of Machine-Generated Restaurant Reviews and Images on Social Media
  72. Surface-Enhanced Raman Spectroscopy and Transfer Learning Toward Accurate Reconstruction of the Surgical Zone
  73. Link Me Baby One More Time: Social Music Discovery on Spotify
  74. Learning Implicit Representation for Reconstructing Articulated Objects
  75. lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning
  76. The Impact of Differential Feature Under-reporting on Algorithmic Fairness
  77. Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model's Generalizability in Permafrost Mapping
  78. Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
  79. HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
  80. The weird and the wonderful in our Solar System: Searching for serendipity in the Legacy Survey of Space and Time
  81. MMToM-QA: Multimodal Theory of Mind Question Answering
  82. Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video
  83. EgoGen: An Egocentric Synthetic Data Generator
  84. Machine Learning-Based Analysis of Ebola Virus' Impact on Gene Expression in Nonhuman Primates
  85. A Framework for Scalable Ambient Air Pollution Concentration Estimation
  86. Bag of Tricks to Boost Adversarial Transferability
  87. AgentMixer: Multi-Agent Correlated Policy Factorization
  88. MA2GCN: Multi Adjacency relationship Attention Graph Convolutional Networks for Traffic Prediction using Trajectory data
  89. HierSFL: Local Differential Privacy-aided Split Federated Learning in Mobile Edge Computing
  90. A Telerehabilitation System for the Selection, Evaluation and Remote Management of Therapies
  91. Unsupervised Pre-Training for 3D Leaf Instance Segmentation
  92. Investigating Fouling Efficiency in Football Using Expected Booking (xB) Model
  93. Selecting Subsets of Source Data for Transfer Learning with Applications in Metal Additive Manufacturing
  94. MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World
  95. Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
  96. WAVES: Benchmarking the Robustness of Image Watermarks
  97. RoHM: Robust Human Motion Reconstruction via Diffusion
  98. Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
  99. Tuning Language Models by Proxy
  100. ADVENT: Attack/Anomaly Detection in VANETs
All 237
  1. Registration of algebraic varieties using Riemannian optimization
  2. Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation
  3. Explaining Time Series via Contrastive and Locally Sparse Perturbations
  4. N-Adaptive Ritz Method: A Neural Network Enriched Partition of Unity for Boundary Value Problems
  5. Scalable Pre-training of Large Autoregressive Image Models
  6. Spatial Entity Resolution between Restaurant Locations and Transportation Destinations in Southeast Asia
  7. MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment
  8. GATS: Gather-Attend-Scatter
  9. Video Quality Assessment Based on Swin TransformerV2 and Coarse to Fine Strategy
  10. From Graphs to Hypergraphs: Hypergraph Projection and its Remediation
  11. PPSURF: Combining Patches and Point Convolutions for Detailed Surface Reconstruction
  12. Supporting Student Decisions on Learning Recommendations: An LLM-Based Chatbot with Knowledge Graph Contextualization for Conversational Explainability and Mentoring
  13. Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
  14. X Hacking: The Threat of Misguided AutoML
  15. The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing
  16. EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis
  17. Harnessing Orthogonality to Train Low-Rank Neural Networks
  18. Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
  19. ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
  20. Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering
  21. Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans
  22. Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models
  23. A Novel Approach in Solving Stochastic Generalized Linear Regression via Nonconvex Programming
  24. TUMTraf Event: Calibration and Fusion Resulting in a Dataset for Roadside Event-Based and RGB Cameras
  25. Instilling Multi-round Thinking to Text-guided Image Generation
  26. Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training
  27. Nonparametric Evaluation of Noisy ICA Solutions
  28. Enhancing Evolving Domain Generalization through Dynamic Latent Representations
  29. Statistical inference for pairwise comparison models
  30. Emergent Communication in Continuous Worlds: Self-Organisation of Conceptually Grounded Vocabularies at Scale
  31. Reinforcement Learning for Conversational Question Answering over Knowledge Graph
  32. Security and Privacy Issues and Solutions in Federated Learning for Digital Healthcare
  33. Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directions
  34. GD doesn't make the cut: Three ways that non-differentiability affects neural network training
  35. U-DIADS-Bib: a full and few-shot pixel-precise dataset for document layout analysis of ancient manuscripts
  36. Improving Limited Supervised Foot Ulcer Segmentation Using Cross-Domain Augmentation
  37. Ask the experts: sourcing high-quality datasets for nutritional counselling through Human-AI collaboration
  38. From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers
  39. Enhancing Dynamical System Modeling through Interpretable Machine Learning Augmentations: A Case Study in Cathodic Electrophoretic Deposition
  40. Faster ISNet for Background Bias Mitigation on Deep Neural Networks
  41. Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining
  42. Interrogating AI: Characterizing Emergent Playful Interactions with ChatGPT
  43. Training and Comparison of nnU-Net and DeepMedic Methods for Autosegmentation of Pediatric Brain Tumors
  44. TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding
  45. High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Rendering
  46. A Micro Architectural Events Aware Real-Time Embedded System Fault Injector
  47. Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine
  48. Deep Learning-based Group Causal Inference in Multivariate Time-series
  49. Robotic Imitation of Human Actions
  50. KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation
  51. Sparse PCA with False Discovery Rate Controlled Variable Selection
  52. Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translation
  53. Morphology and Syntax of the Tamil Language
  54. Weighted Spectral Filters for Kernel Interpolation on Spheres: Estimates of Prediction Accuracy for Noisy Data
  55. Hallucination Detection and Hallucination Mitigation: An Investigation
  56. SAMF: Small-Area-Aware Multi-focus Image Fusion for Object Detection
  57. Personalized Federated Learning of Probabilistic Models: A PAC-Bayesian Approach
  58. Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models
  59. Estimating Model Performance Under Covariate Shift Without Labels
  60. Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-M2DF)
  61. Boosting Gradient Ascent for Continuous DR-submodular Maximization
  62. Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
  63. Learn What You Need in Personalized Federated Learning
  64. OpenDPD: An Open-Source End-to-End Learning & Benchmarking Framework for Wideband Power Amplifier Modeling and Digital Pre-Distortion
  65. Anchor function: a type of benchmark functions for studying language models
  66. QoS Improvement in Multi User Cellular-Symbiotic Radio Network Assisted by Active-STAR-RIS
  67. SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models
  68. Causal Machine Learning for Moderation Effects
  69. The Faiss library
  70. Modeling Spoof Noise by De-spoofing Diffusion and its Application in Face Anti-spoofing
  71. Large Language Models are Null-Shot Learners
  72. Siamese Content-based Search Engine for a More Transparent Skin and Breast Cancer Diagnosis through Histological Imaging
  73. An Explainable Proxy Model for Multiabel Audio Segmentation
  74. Multi-Technique Sequential Information Consistency For Dynamic Visual Place Recognition In Changing Environments
  75. Probabilistically Robust Watermarking of Neural Networks
  76. Fast Kernel Summation in High Dimensions via Slicing and Fourier Transforms
  77. Multitask Learning in Minimally Invasive Surgical Vision: A Review
  78. A Generative Adversarial Attack for Multilingual Text Classifiers
  79. Optimizing k in kNN Graphs with Graph Learning Perspective
  80. Enhancing Wind Speed and Wind Power Forecasting Using Shape-Wise Feature Engineering: A Novel Approach for Improved Accuracy and Robustness
  81. Efficient and Mathematically Robust Operations for Certified Neural Networks Inference
  82. Privacy Preserving Adaptive Experiment Design
  83. Towards Causal Relationship in Indefinite Data: Baseline Model and New Datasets
  84. Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning
  85. ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classification
  86. Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
  87. Generative Multi-Modal Knowledge Retrieval with Large Language Models
  88. Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms
  89. End-to-End Optimized Image Compression with the Frequency-Oriented Transform
  90. DPAFNet:Dual Path Attention Fusion Network for Single Image Deraining
  91. OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box Prompts
  92. Deep Linear Array Pushbroom Image Restoration: A Degradation Pipeline and Jitter-Aware Restoration Network
  93. Statistical Test for Attention Map in Vision Transformer
  94. Fundamental limits of community detection from multi-view data: multi-layer, dynamic and partially labeled block models
  95. TLIC: Learned Image Compression with ROI-Weighted Distortion and Bit Allocation
  96. Differentially Private Sliced Inverse Regression: Minimax Optimality and Algorithm
  97. Machine Learning on Dynamic Graphs: A Survey on Applications
  98. ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field
  99. Transferring Core Knowledge via Learngenes
  100. LLMs for Test Input Generation for Semantic Caches
  101. Machine Learning-Based Malicious Vehicle Detection for Security Threats and Attacks in Vehicle Ad-hoc Network (VANET) Communications
  102. The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation
  103. SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecasting
  104. E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning
  105. No-Clean-Reference Image Super-Resolution: Application to Electron Microscopy
  106. Mobile Contactless Palmprint Recognition: Use of Multiscale, Multimodel Embeddings
  107. Deep Shape-Texture Statistics for Completely Blind Image Quality Evaluation
  108. Hardware Acceleration for Real-Time Wildfire Detection Onboard Drone Networks
  109. Resolving Ethics Trade-offs in Implementing Responsible AI
  110. KTVIC: A Vietnamese Image Captioning Dataset on the Life Domain
  111. Inpainting Normal Maps for Lightstage data
  112. Fairness Concerns in App Reviews: A Study on AI-based Mobile Apps
  113. DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignment
  114. A Survey of Resource-efficient LLM and Multimodal Foundation Models
  115. A Study on Training and Developing Large Language Models for Behavior Tree Generation
  116. Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions
  117. Spatial-Semantic Collaborative Cropping for User Generated Content
  118. UV-SAM: Adapting Segment Anything Model for Urban Village Identification
  119. Predicting Next Useful Location With Context-Awareness: The State-Of-The-Art
  120. Adversarial Masking Contrastive Learning for vein recognition
  121. Transformer-based approach for Ethereum Price Prediction Using Crosscurrency correlation and Sentiment Analysis
  122. Representation Learning on Event Stream via an Elastic Net-incorporated Tensor Network
  123. Achieve Fairness without Demographics for Dermatological Disease Diagnosis
  124. Augmenting Ground-Level PM2.5 Prediction via Kriging-Based Pseudo-Label Generation
  125. Toward Clinically Trustworthy Deep Learning: Applying Conformal Prediction to Intracranial Hemorrhage Detection
  126. Robust Tiny Object Detection in Aerial Images amidst Label Noise
  127. SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation
  128. Incremental Extractive Opinion Summarization Using Cover Trees
  129. Enhancing Robustness of LLM-Synthetic Text Detectors for Academic Writing: A Comprehensive Analysis
  130. Cross-Modal Semi-Dense 6-DoF Tracking of an Event Camera in Challenging Conditions
  131. Calpric: Inclusive and Fine-grain Labeling of Privacy Policies with Crowdsourcing and Active Learning
  132. 3D Lane Detection from Front or Surround-View using Joint-Modeling & Matching
  133. BanglaNet: Bangla Handwritten Character Recognition using Ensembling of Convolutional Neural Network
  134. Structure-based out-of-distribution (OOD) materials property prediction: a benchmark study
  135. JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims
  136. Spatial Channel State Information Prediction with Generative AI: Towards Holographic Communication and Digital Radio Twin
  137. Small Object Detection by DETR via Information Augmentation and Adaptive Feature Fusion