mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 31 Dec 2024

184 papers

  1. Goal Recognition using Actor-Critic OptimizationDeep reinforcement learning methods → Deep RL algorithms and representations
  2. Beyond Introspection: Reinforcing Thinking via Externalist Behavioral FeedbackLLM reasoning → Test-time compute and efficient thinking
  3. Titans: Learning to Memorize at Test TimeLLM reasoning → Test-time compute and efficient thinking
  4. Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  5. ICONS: Influence Consensus for Vision-Language Data SelectionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  6. Enabling New HDLs with AgentsLLM agents and tool use → Software engineering coding agents
  7. Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion SeparationDiffusion models → Inverse problems and image restoration
  8. DiC: Rethinking Conv3x3 Designs in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  9. DreamDrive: Generative 4D Scene Modeling from Street View ImagesWorld models → World models for autonomous driving
  10. Unbiased GNN Learning via Fairness-Aware Subgraph DiffusionDiffusion models → Flow matching, time series and science
  11. Online Video Understanding: OVBench and VideoChat-OnlineMultimodal LLMs / vision-language models → Video understanding with MLLMs
  12. Are the Values of LLMs Structurally Aligned with Humans? A Causal PerspectiveLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  13. VideoChat-Flash: Hierarchical Compression for Long-Context Video ModelingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  14. KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning AbilitiesLLM reasoning → Knowledge- and tool-augmented reasoning +1
  15. Probing Visual Language Priors in VLMsLLM reasoning → Multimodal reasoning +1
  16. Re-evaluating Automatic LLM System Ranking for Alignment with Human PreferenceLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  17. MCP-Solver: Integrating Language Models with Constraint Programming SystemsLLM agents and tool use → Tool learning and function calling
  18. Superposition in Transformers: A Novel Way of Building Mixture of ExpertsMixture-of-experts → MoE large language models
  19. A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and DefenseLLM safety and security → Safety alignment, refusal and guardrails
  20. Score-Based Metropolis-Hastings AlgorithmsDiffusion models → Diffusion foundations and sampling
  21. SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented TrainingDiffusion models → Robustness, privacy and adversarial aspects +1
  22. Differentiable Prompt Learning for Vision Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  23. Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image CaptioningDiffusion models → Image generation, text-to-image and editing
  24. Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agentsLLM reasoning → Reasoning for agents, planning and code +1
  25. S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral DomainDiffusion models → Diffusion recommenders
  26. Toward Information Theoretic Active Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
  27. Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for FreeDiffusion models → Diffusion foundations and sampling +1
  28. FORM: Learning Expressive and Transferable First-Order Logic Reward MachinesDeep reinforcement learning methods → Interpretable and logic-guided RL
  29. RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented InstructionsRetrieval-augmented generation → RAG pipeline design and evaluation
  30. MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  31. Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set ExpansionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  32. OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and ReasoningMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  33. MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation ModelsLLM reasoning → Spatial and embodied reasoning
  34. Retrieval-Augmented Generation with Graphs (GraphRAG)Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  35. From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language ModelsWorld models → Embodied and robot world models +1
  36. Dual Diffusion for Unified Image Generation and UnderstandingMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  37. EQUATOR: A Deterministic Framework for Evaluating LLM Reasoning with Open-Ended Questions. # v1.0.0-betaLLM reasoning → Reasoning benchmarks and evaluation
  38. Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and RethinkingLLM reasoning → Prompting and chain-of-thought reasoning
  39. Generative Emergent Communication: Large Language Model is a Collective World ModelWorld models → World models for language agents
  40. Towards Unraveling and Improving Generalization in World ModelsWorld models → Latent predictive world models +1
  41. Image Fusion for Cross-Domain Sequential Recommendation
  42. Green AI: Which Programming Language Consumes the Most?
  43. Hybrid Firefly-Genetic Algorithm for Single and Multi-dimensional 0-1 Knapsack Problems
  44. A Systematic Review of Machine Learning Methods for Multimodal EEG Data in Clinical Application
  45. LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models
  46. Proof Recommendation System for the HOL4 Theorem Prover
  47. Advanced Displacement Magnitude Prediction in Multi-Material Architected Lattice Structure Beams Using Physics Informed Neural Network Architecture
  48. Fuzzy Model Identification and Self Learning with Smooth Compositions
  49. A Novel Convolution and Attention Mechanism-based Model for 6D Object Pose Estimation
  50. Disagree and Commit: Degrees of Argumentation-based Agreements
  51. A Hybrid Deep Learning and Model-Checking Framework for Accurate Brain Tumor Detection and Validation
  52. Towards Sustainable Large Language Model Serving
  53. CRRG-CLIP: Automatic Generation of Chest Radiology Reports and Classification of Chest Radiographs
  54. Tech Report: Divide and Conquer 3D Real-Time Reconstruction for Improved IGS
  55. Estimation of 3T MR images from 1.5T images regularized with Physics based Constraint
  56. Pan-infection Foundation Framework Enables Multiple Pathogen Prediction
  57. GDSR: Global-Detail Integration through Dual-Branch Network with Wavelet Losses for Remote Sensing Image Super-Resolution
  58. GAN-TAT: A Novel Framework Using Protein Interaction Networks in Druggable Gene Identification
  59. SS-CTML: Self-Supervised Cross-Task Mutual Learning for CT Image Reconstruction
  60. A Fourfold Pathogen Reference Ontology Suite
  61. Geometry Matters: Benchmarking Scientific ML Approaches for Flow Prediction around Complex Geometries
  62. Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery
  63. Controlled Causal Hallucinations Can Estimate Phantom Nodes in Multiexpert Mixtures of Fuzzy Cognitive Maps
  64. Leaf diseases detection using deep learning methods
  65. Grade Inflation in Generative Models
  66. Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph
  67. 2 OLMo 2 Furious
  68. Finding Missed Code Size Optimizations in Compilers using LLMs
  69. Taming Feed-forward Reconstruction Models as Latent Encoders for 3D Generative Models
  70. Lightweight G-YOLOv11: Advancing Efficient Fracture Detection in Pediatric Wrist X-rays
  71. SoundBrush: Sound as a Brush for Visual Scene Editing
  72. Efficient Standardization of Clinical Notes using Large Language Models
  73. Applying Graph Explanation to Operator Fusion
  74. Different thresholding methods on Nearest Shrunken Centroid algorithm
  75. Matrix factorization and prediction for high dimensional co-occurrence count data via shared parameter alternating zero inflated Gamma model
  76. Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting
  77. Global dense vector representations for words or items using shared parameter alternating Tweedie model
  78. A Study on Context Length and Efficient Transformers for Biomedical Image Analysis
  79. Toward Corpus Size Requirements for Training and Evaluating Depression Risk Models Using Spoken Language
  80. Predicting Barge Presence and Quantity on Inland Waterways using Vessel Tracking Data: A Machine Learning Approach
  81. Optimizing Speech-Input Length for Speaker-Independent Depression Classification
  82. Time-Varying Graph Learning for Data with Heavy-Tailed Distribution
  83. STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
  84. VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
  85. "Dialogue" vs "Dialog" in NLP and AI research: Statistics from a Confused Discourse
  86. Gaze Prediction as a Function of Eye Movement Type and Individual Differences
  87. Setting Standards in Turkish NLP: TR-MMLU for Large Language Model Evaluation
  88. Advanced Lung Nodule Segmentation and Classification for Early Detection of Lung Cancer using SAM and Transfer Learning
  89. Sidewalk Hazard Detection Using Variational Autoencoder and One-Class SVM
  90. Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion
  91. An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems
  92. AraSTEM: A Native Arabic Multiple Choice Question Benchmark for Evaluating LLMs Knowledge In STEM Subjects
  93. Finding the Underlying Viscoelastic Constitutive Equation via Universal Differential Equations and Differentiable Physics
  94. Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction
  95. Adaptive Tabu Dropout for Regularization of Deep Neural Network
  96. Extending XReason: Formal Explanations for Adversarial Detection
  97. Rapid Learning in Constrained Minimax Games with Negative Momentum
  98. Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches
  99. PyMilo: A Python Library for ML I/O
  100. Exploiting Boundary Loss for the Hierarchical Panoptic Segmentation of Plants and Leaves
All 184
  1. Systematic Evaluation and Guidelines for Segment Anything Model in Surgical Video Analysis
  2. TinyHelen's First Curriculum: Training and Evaluating Tiny Language Models in a Simpler Language Environment
  3. Innovative Silicosis and Pneumonia Classification: Leveraging Graph Transformer Post-hoc Modeling and Ensemble Techniques
  4. H-Net: A Multitask Architecture for Simultaneous 3D Force Estimation and Stereo Semantic Segmentation in Intracardiac Catheters
  5. CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval
  6. Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements
  7. Fotheidil: an Automatic Transcription System for the Irish Language
  8. Active Learning of General Halfspaces: Label Queries vs Membership Queries
  9. Exploring Physics-Informed Neural Networks for Crop Yield Loss Forecasting
  10. Two Cases of Deduction with Non-referring Descriptions
  11. Alternating minimization for square root principal component pursuit
  12. Dementia Detection using Multi-modal Methods on Audio Data
  13. Addressing Challenges in Data Quality and Model Generalization for Malaria Detection
  14. Efficient support ticket resolution using Knowledge Graphs
  15. Unrolled Creative Adversarial Network For Generating Novel Musical Pieces
  16. Do Students with Different Personality Traits Demonstrate Different Physiological Signals in Video-based Learning?
  17. Knowledge-aware equation discovery with automated background knowledge extraction
  18. Intuitive Analysis of the Quantization-based Optimization: From Stochastic and Quantum Mechanical Perspective
  19. OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models
  20. B2Net: Camouflaged Object Detection via Boundary Aware and Boundary Fusion
  21. Whisper Turns Stronger: Augmenting Wav2Vec 2.0 for Superior ASR in Low-Resource Languages
  22. Outlier-Robust Linear System Identification Under Heavy-tailed Noise
  23. KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning
  24. Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
  25. TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification
  26. Efficient Relational Context Perception for Knowledge Graph Completion
  27. Trajectories of Change: Approaches for Tracking Knowledge Evolution
  28. Momentum-based minimization of the Ginzburg-Landau functional on Euclidean spaces and graphs
  29. Proactive Conversational Agents with Inner Thoughts
  30. Adventures in Demand Analysis Using AI
  31. Federated Dropout: Convergence Analysis and Resource Allocation
  32. STARFormer: A Novel Spatio-Temporal Aggregation Reorganization Transformer of FMRI for Brain Disorder Diagnosis
  33. Design Optimizer for Soft Growing Robot Manipulators in Three-Dimensional Environments
  34. Low-Rank Adaptation for Foundation Models: A Comprehensive Review
  35. SPDZCoder: Combining Expert Knowledge with LLMs for Generating Privacy-Computing Code
  36. A Novel Shape Guided Transformer Network for Instance Segmentation in Remote Sensing Images
  37. Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
  38. A New Dataset and Methodology for Malicious URL Classification
  39. PanoSLAM: Panoptic 3D Scene Reconstruction via Gaussian SLAM
  40. Temporal Information Reconstruction and Non-Aligned Residual in Spiking Neural Networks for Speech Classification
  41. CNC: Cross-modal Normality Constraint for Unsupervised Multi-class Anomaly Detection
  42. Chunk-Distilled Language Modeling
  43. SG-Splatting: Accelerating 3D Gaussian Splatting with Spherical Gaussians
  44. Dynamic Prompt Adjustment for Multi-Label Class-Incremental Learning
  45. GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression
  46. Loss-Aware Curriculum Learning for Chinese Grammatical Error Correction
  47. VoxVietnam: a Large-Scale Multi-Genre Dataset for Vietnamese Speaker Recognition
  48. OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies
  49. Autonomous Alignment with Human Value on Altruism through Considerate Self-imagination and Theory of Mind
  50. Improving Text-based Person Search via Part-level Cross-modal Correspondence
  51. Spatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction
  52. Temporal Dynamics Decoupling with Inverse Processing for Enhancing Human Motion Prediction
  53. M2I2: Learning Efficient Multi-Agent Communication via Masked State Modeling and Intention Inference
  54. Fast and Interpretable Mixed-Integer Linear Program Solving by Learning Model Reduction
  55. diffIRM: A Diffusion-Augmented Invariant Risk Minimization Framework for Spatiotemporal Prediction over Graphs
  56. SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation
  57. Research on vehicle detection based on improved YOLOv8 network
  58. Enhancing Deployment-Time Predictive Model Robustness for Code Analysis and Optimization
  59. Solving Partial Differential Equations with Random Feature Models
  60. ReFormer: Generating Radio Fakes for Data Augmentation
  61. Efficient Human-in-the-Loop Active Learning: A Novel Framework for Data Labeling in AI Systems
  62. LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts
  63. Echoes in AI: Quantifying lack of plot diversity in LLM outputs
  64. A review of faithfulness metrics for hallucination assessment in Large Language Models
  65. Outlier-Robust Training of Machine Learning Models
  66. Enhancing Wireless Sensor Network Security through Integration with the ServiceNow Cloud Platform
  67. Collaborative Approaches to Enhancing Smart Vehicle Cybersecurity by AI-Driven Threat Detection
  68. Automatically Planning Optimal Parallel Strategy for Large Language Models
  69. Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completion
  70. Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition
  71. Exploring Variability in Fine-Tuned Models for Text Classification with DistilBERT
  72. Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning
  73. Zero-Shot Strategies for Length-Controllable Summarization
  74. Federated Deep Subspace Clustering
  75. Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devices
  76. CancerKG.ORG A Web-scale, Interactive, Verifiable Knowledge Graph-LLM Hybrid for Assisting with Optimal Cancer Treatment and Care
  77. DecoratingFusion: A LiDAR-Camera Fusion Network with the Combination of Point-level and Feature-level Fusion
  78. The Potential of LLMs in Automating Software Testing: From Generation to Reporting
  79. Debunking the CUDA Myth Towards GPU-based AI Systems
  80. An Empirical Evaluation of Large Language Models on Consumer Health Questions
  81. Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
  82. GPT-4 on Clinic Depression Assessment: An LLM-Based Pilot Study
  83. MLLM-as-a-Judge for Image Safety without Human Labeling
  84. SepsisCalc: Integrating Clinical Calculators into Early Sepsis Prediction via Dynamic Temporal Graph Construction