mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 5 Oct 2024

161 papers

  1. Assessing the Performance of Human-Capable LLMs -- Are LLMs Coming for Your Job?LLM agents and tool use → General LLM agent frameworks and benchmarks
  2. Reward Learning From Preference With TiesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  3. From Incomplete Coarse-Grained to Complete Fine-Grained: A Two-Stage Framework for Spatiotemporal Data ReconstructionDiffusion models → Flow matching, time series and science
  4. Noise Crystallization and Liquid Noise: Zero-shot Video Generation using Image Diffusion ModelsDiffusion models → Video generation
  5. Improving LLM Reasoning through Scaling Inference Computation with Collaborative VerificationLLM reasoning → Test-time compute and efficient thinking
  6. Accelerating Diffusion Transformers with Token-wise Feature CachingDiffusion models → Diffusion foundations and sampling
  7. Fundamental Limitations on Subquadratic Alternatives to TransformersState-space sequence models (S4, Mamba) → Core SSM architectures for language
  8. DeFoG: Discrete Flow Matching for Graph GenerationDiffusion models → Flow matching, time series and science
  9. Compositional Diffusion Models for Powered Descent Trajectory Generation with Flexible ConstraintsDiffusion models → Diffusion and flow policies for robotics
  10. Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak AttacksLLM safety and security → Jailbreaking
  11. Metadata-based Data Exploration with Retrieval-Augmented Generation for Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  12. Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion DiscriminatorDiffusion models → Inverse problems and image restoration
  13. Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic PlanningMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  14. Improving Portfolio Optimization Results with Bandit NetworksDeep reinforcement learning methods → Adversarial robustness and RL in finance
  15. RainbowPO: A Unified Framework for Combining Improvements in Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  16. Accelerating Diffusion Models with One-to-Many Knowledge DistillationDiffusion models → Diffusion foundations and sampling +1
  17. Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language ModelsLLM safety and security → Jailbreaking
  18. DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed SpeechKnowledge distillation → Knowledge distillation for LLMs
  19. IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video SynthesisDiffusion models → Video generation
  20. Learning from negative feedback, or positive feedback or bothLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  21. Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion ModelDiffusion models → Inverse problems and image restoration
  22. ConDa: Fast Federated Unlearning with Contribution DampeningLLM safety and security → Federated unlearning and poisoning
  23. Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic TeacherKnowledge distillation → General knowledge distillation methods
  24. From Reading to Compressing: Exploring the Multi-document Reader for Prompt CompressionEfficient LLM inference and serving → Prompt and context compression
  25. Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference AlignmentLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  26. On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms +1
  27. TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable QuestionsLLM reasoning → Multimodal reasoning +1
  28. BloomWise: Enhancing Problem-Solving capabilities of Large Language Models using Bloom's-Taxonomy-Inspired PromptsLLM reasoning → Mathematical reasoning
  29. TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated StudentsLLM agents and tool use → Educational agents and math problem solving
  30. PAD: Personalized Alignment of LLMs at Decoding-TimeLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  31. Text2Chart31: Instruction Tuning for Chart Generation with Automatic FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  32. Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning TasksLLM reasoning → Multimodal reasoning +1
  33. TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated AnalysisLLM reasoning → Time series reasoning +1
  34. Gamified crowd-sourcing of high-quality data for visual fine-tuningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  35. ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMsLLM safety and security → Backdoor and data poisoning attacks
  36. Multiscale Latent Diffusion Model for Enhanced Feature Extraction from Medical ImagesDiffusion models → Medical imaging and segmentation
  37. YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  38. Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  39. Comparative Global AI Regulation: Policy Perspectives from the EU, China, and the US
  40. Code-Driven Law NO, Normware SI!
  41. A Unified Model for Compressed Sensing MRI Across Undersampling Patterns
  42. Solution for OOD-CV UNICORN Challenge 2024 Object Detection Assistance LLM Counting Ability Improvement
  43. Solution for Point Tracking Task of ECCV 2nd Perception Test Challenge 2024
  44. Understanding the Effect of Algorithm Transparency of Model Explanations in Text-to-SQL Semantic Parsing
  45. Transformers Utilization in Chart Understanding: A Review of Recent Advances & Future Trends
  46. Semantic Environment Atlas for Object-Goal Navigation
  47. Application of AI in Credit Risk Scoring for Small Business Loans: A case study on how AI-based random forest model improves a Delphi model outcome in the case of Azerbaijani SMEs
  48. El Nino Southern Oscillation and Atlantic Multidecadal Oscillation Impact on Hurricanes North Atlantic Basin
  49. Early-Cycle Internal Impedance Enables ML-Based Battery Cycle Life Predictions Across Manufacturers
  50. Comparative Analysis of Multi-Omics Integration Using Advanced Graph Neural Networks for Cancer Classification
  51. The OCON model: an old but gold solution for distributable supervised classification
  52. PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
  53. Comprehensive Monitoring of Air Pollution Hotspots Using Sparse Sensor Networks
  54. Dynamics-Encoded Deep Learning for Robust System Identification and Parameter Estimation
  55. Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis
  56. Bootstrap Sampling Rate Greater than 1.0 May Improve Random Forest Performance
  57. Spectral Densities, Structured Noise and Ensemble Averaging within Open Quantum Dynamics
  58. Efficiently Identifying Low-Quality Language Subsets in Multilingual Datasets: A Case Study on a Large-Scale Multilingual Audio Dataset
  59. Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods
  60. Enhancing Carbon Emission Reduction Strategies using OCO and ICOS data
  61. Unveiling the Impact of Local Homophily on GNN Fairness: In-Depth Analysis and New Benchmarks
  62. MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times
  63. Applying Hybrid Graph Neural Networks to Strengthen Credit Risk Analysis
  64. Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia
  65. Black Boxes and Looking Glasses: Multilevel Symmetries, Reflection Planes, and Convex Optimization in Deep Networks
  66. Mechanistic Behavior Editing of Language Models
  67. Language Model-Driven Data Pruning Enables Efficient Active Learning
  68. Evaluating Language Model Character Traits
  69. RoQLlama: A Lightweight Romanian Adapted Language Model
  70. Constructing Cloze Questions Generatively
  71. AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
  72. Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement
  73. Pareto Control Barrier Function for Inner Safe Set Maximization Under Input Constraints
  74. Is deeper always better? Replacing linear mappings with deep learning networks in the Discriminative Lexicon Model
  75. Implicit to Explicit Entropy Regularization: Benchmarking ViT Fine-tuning under Noisy Labels
  76. Entity Insertion in Multilingual Linked Corpora: The Case of Wikipedia
  77. Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills
  78. Enhancing Future Link Prediction in Quantum Computing Semantic Networks through LLM-Initiated Node Features
  79. Towards Propositional KLM-Style Defeasible Standpoint Logics
  80. Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations
  81. Persona Knowledge-Aligned Prompt Tuning Method for Online Debate
  82. Towards the Best Solution for Complex System Reliability: Can Statistics Outperform Machine Learning?
  83. Overview of Factify5WQA: Fact Verification through 5W Question-Answering
  84. Improving Distribution Alignment with Diversity-based Sampling
  85. SGD with memory: fundamental properties and stochastic acceleration
  86. AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results
  87. TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation
  88. Quantum Kolmogorov-Arnold networks by combining quantum signal processing circuits
  89. Equivariant Polynomial Functional Networks
  90. Correlation-Aware Select and Merge Attention for Efficient Fine-Tuning and Context Length Extension
  91. Equivariant Neural Functional Networks for Transformers
  92. Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
  93. Exploring Strengths and Weaknesses of Super-Resolution Attack in Deepfake Detection
  94. Deep Transfer Learning Based Peer Review Aggregation and Meta-review Generation for Scientific Articles
  95. IT3: Idempotent Test-Time Training
  96. LongGenBench: Long-context Generation Benchmark
  97. CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints
  98. Improving Generalization with Flat Hilbert Bayesian Inference
  99. Consistent Autoformalization for Constructing Mathematical Libraries
  100. Parametric Taylor series based latent dynamics identification neural networks
All 161
  1. Non-monotonic Extensions to Formal Concept Analysis via Object Preferences
  2. Unsupervised Assessment of Landscape Shifts Based on Persistent Entropy and Topological Preservation
  3. PortraVec: Image-Based Portrait Vectorization with Text-Guided Manipulation
  4. Fast Object Detection with a Machine Learning Edge Device
  5. DB-SAM: Delving into High Quality Universal Medical Image Segmentation
  6. Beyond Language: Applying MLX Transformers to Engineering Physics
  7. Towards Effective Counter-Responses: Aligning Human Preferences with Strategies to Combat Online Trolling
  8. Toxic Subword Pruning for Dialogue Response Generation on Large Language Models
  9. Applying Quantum Autoencoders for Time Series Anomaly Detection
  10. Neuro-Symbolic Entity Alignment via Variational Inference
  11. DAMMI:Daily Activities in a Psychologically Annotated Multi-Modal IoT dataset
  12. Reasoning with Natural Language Explanations
  13. Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?
  14. IceCloudNet: 3D reconstruction of cloud ice from Meteosat SEVIRI
  15. An Electrocardiogram Foundation Model Built on over 10 Million Recordings with External Evaluation across Multiple Domains
  16. Optimizing Medical Image Segmentation with Advanced Decoder Design
  17. WAVE-UNET: Wavelength based Image Reconstruction method using attention UNET for OCT images
  18. Rethinking Fair Representation Learning for Performance-Sensitive Tasks
  19. Riemann Sum Optimization for Accurate Integrated Gradients Computation
  20. Transport-Embedded Neural Architecture: Redefining the Landscape of physics aware neural models in fluid mechanics
  21. A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models
  22. The OCON model: an old but green solution for distributable supervised classification for acoustic monitoring in smart cities
  23. TV-based Deep 3D Self Super-Resolution for fMRI
  24. Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities
  25. Cross-Lingual Query-by-Example Spoken Term Detection: A Transformer-Based Approach
  26. High-Speed Stereo Visual SLAM for Low-Powered Computing Devices
  27. Designing Concise ConvNets with Columnar Stages
  28. Cross Resolution Encoding-Decoding For Detection Transformers
  29. GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization
  30. Taming the Tail: Leveraging Asymmetric Loss and Pade Approximation to Overcome Medical Image Long-Tailed Class Imbalance
  31. Epsilon-VAE: Denoising as Visual Decoding
  32. High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions
  33. PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation
  34. On Eliciting Syntax from Language Models via Hashing
  35. MROSS: Multi-Round Region-based Optimization for Scene Sketching
  36. ECon: On the Detection and Resolution of Evidence Conflicts
  37. Enhancing Graph Self-Supervised Learning with Graph Interplay
  38. LoRTA: Low Rank Tensor Adaptation of Large Language Models
  39. pFedGame -- Decentralized Federated Learning using Game Theory in Dynamic Topology
  40. RetCompletion:High-Speed Inference Image Completion with Retentive Network
  41. Large Language Models can Achieve Social Balance
  42. Beyond Imperfections: A Conditional Inpainting Approach for End-to-End Artifact Removal in VTON and Pose Transfer
  43. Lane Detection System for Driver Assistance in Vehicles
  44. Neuron-Level Sequential Editing for Large Language Models
  45. EndoPerfect: High-Accuracy Monocular Depth Estimation and 3D Reconstruction for Endoscopic Surgery via NeRF-Stereo Fusion
  46. BlockScan: Detecting Anomalies in Blockchain Transactions
  47. Is Score Matching Suitable for Estimating Point Processes?
  48. ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Training
  49. SyllableLM: Learning Coarse Semantic Units for Speech Language Models
  50. A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models
  51. IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
  52. Efficient Large-Scale Urban Parking Prediction: Graph Coarsening Based on Real-Time Parking Service Capability
  53. Improving Temporal Link Prediction via Temporal Walk Matrix Projection
  54. JAM: A Comprehensive Model for Age Estimation, Verification, and Comparability
  55. Hyperbolic Fine-Tuning for Large Language Models
  56. Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation
  57. FastLRNR and Sparse Physics Informed Backpropagation
  58. Impact of Regularization on Calibration and Robustness: from the Representation Space Perspective
  59. On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models
  60. Symmetry From Scratch: Group Equivariance as a Supervised Learning Task
  61. Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression