mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 25 May 2024

182 papers

  1. Agile Robotics: Optimal Control, Reinforcement Learning, and Differentiable SimulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  2. InstructPatentGPT: Training patent language models to follow instructions with human feedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  3. Towards Unlocking Insights from Logbooks Using AIRetrieval-augmented generation → RAG pipeline design and evaluation
  4. Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State TrackingRetrieval-augmented generation → RAG for recommendation
  5. Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image CharacterLLM safety and security → Vision-language and text-to-image safety
  6. Towards Black-Box Membership Inference Attack for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  7. UU-Mamba: Uncertainty-aware U-Mamba for Cardiac Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  8. Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie GroupsDiffusion models → Flow matching, time series and science
  9. Dynamic Inhomogeneous Quantum Resource Scheduling with Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
  10. STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-MakingLLM reasoning → Reasoning for agents, planning and code +1
  11. R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion ModelDiffusion models → Robustness, privacy and adversarial aspects
  12. Learning to Reason via Program Generation, Emulation, and SearchLLM reasoning → Reasoning for agents, planning and code
  13. Devil's Advocate: Anticipatory Reflection for LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. Deep Reinforcement Learning with Enhanced PPO for Safe Mobile Robot NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
  15. MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference TimeLLM reasoning → Mathematical reasoning
  16. Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based DiscriminationDiffusion models → Diffusion foundations and sampling
  17. AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. Vision Language Models for Spreadsheet Understanding: Challenges and OpportunitiesMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  19. No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning AttacksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  20. Underwater Image Enhancement by Diffusion Model with Customized CLIP-ClassifierDiffusion models → Inverse problems and image restoration
  21. GeneAgent: Self-verification Language Agent for Gene Set Knowledge Discovery using Domain DatabasesLLM agents and tool use → Medical and scientific domain agents
  22. Adaptive Q-Network: On-the-fly Target Selection for Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  23. Diffusion-Reward Adversarial Imitation LearningDiffusion models → Diffusion and flow policies for robotics +1
  24. Safe Deep Model-Based Reinforcement Learning with Lyapunov FunctionsDeep reinforcement learning methods → Safe and constrained RL
  25. Accelerating Inference of Retrieval-Augmented Generation via Sparse Context SelectionRetrieval-augmented generation → Generation and context integration
  26. Diffusion-based Reinforcement Learning via Q-weighted Variational Policy OptimizationDiffusion models → Diffusion and flow policies for robotics +1
  27. Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous controlDeep reinforcement learning methods → Deep RL algorithms and representations
  28. Accelerating Transformers with Spectrum-Preserving Token MergingEfficient LLM inference and serving → Token pruning and merging for ViTs
  29. AIGB: Generative Auto-bidding via Conditional Diffusion ModelingDiffusion models → Diffusion and flow policies for robotics
  30. Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz EstimatesDiffusion models → Diffusion foundations and sampling
  31. Diverse Teacher-Students for Deep Safe Semi-Supervised Learning under Class MismatchKnowledge distillation → General knowledge distillation methods
  32. Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit ScoreMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  33. Theoretical Study of Conflict-Avoidant Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  34. Keypoint-based Progressive Chain-of-Thought Distillation for LLMsLLM reasoning → Prompting and chain-of-thought reasoning
  35. Pausing Policy Learning in Non-stationary Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  36. MoEUT: Mixture-of-Experts Universal TransformersMixture-of-experts → Expert routing strategies
  37. Constrained Ensemble Exploration for Unsupervised Skill DiscoveryDeep reinforcement learning methods → Deep RL algorithms and representations
  38. PTQ4DiT: Post-training Quantization for Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  39. Verified Safe Reinforcement Learning for Neural Network Dynamic ModelsDeep reinforcement learning methods → Safe and constrained RL
  40. Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Models
  41. An Empirical Study of Excitation and Aggregation Design Adaptions in CLIP4Clip for Video-Text Retrieval
  42. Paths of A Million People: Extracting Life Trajectories from Wikipedia
  43. Expanded Gating Ranges Improve Activation Functions
  44. Secure Hierarchical Federated Learning in Vehicular Networks Using Dynamic Client Selection and Anomaly Detection
  45. Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey
  46. Transitional Uncertainty with Layered Intermediate Predictions
  47. Overcoming Negative Transfer by Online Selection: Distant Domain Adaptation for Fault Diagnosis
  48. StatWhy: Formal Verification Tool for Statistical Hypothesis Testing Programs
  49. Revisit, Extend, and Enhance Hessian-Free Influence Functions
  50. On the Inflation of KNN-Shapley Value
  51. Video Prediction Models as General Visual Encoders
  52. Qsco: A Quantum Scoring Module for Open-set Supervised Anomaly Detection
  53. LLMs for User Interest Exploration in Large-scale Recommendation Systems
  54. LDPKiT: Superimposing Remote Queries for Privacy-Preserving Distillation
  55. Navigating AI Fallibility: Examining People's Reactions and Perceptions of AI after Encountering Personality Misrepresentations
  56. A Differential Equation Approach for Wasserstein GANs and Beyond
  57. A Second-Order Perspective on Model Compositionality and Incremental Learning
  58. Learning Point Spread Function Invertibility Assessment for Image Deconvolution
  59. BOLD: Boolean Logic Deep Learning
  60. RoboArm-NMP: a Learning Environment for Neural Motion Planning
  61. LEAST: "Local" text-conditioned image style transfer
  62. A Classifier-Free Incremental Learning Framework for Scalable Medical Image Segmentation
  63. SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
  64. Time-SSM: Simplifying and Unifying State Space Models for Time Series Forecasting
  65. An Empirical Exploration of Trust Dynamics in LLM Supply Chains
  66. Efficiently Parameterized Neural Metriplectic Systems
  67. Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients
  68. Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples
  69. LUCIE: A Lightweight Uncoupled ClImate Emulator with long-term stability and physical consistency for O(1000)-member ensembles
  70. Neural Network-Based Tracking and 3D Reconstruction of Baseball Pitch Trajectories from Single-View 2D Video
  71. Comparative Analysis of Open-Source Language Models in Summarizing Medical Text Data
  72. Generating configurations of increasing lattice size with machine learning and the inverse renormalization group
  73. LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters
  74. Generation of synthetic data using breast cancer dataset and classification with resnet18
  75. ModelLock: Locking Your Model With a Spell
  76. Generating clickbait spoilers with an ensemble of large language models
  77. Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
  78. ConStat: Performance-Based Contamination Detection in Large Language Models
  79. AI-Assisted Detector Design for the EIC (AID(2)E)
  80. Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge
  81. M3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
  82. A GPU-Accelerated Bi-linear ADMM Algorithm for Distributed Sparse Machine Learning
  83. Assessing Image Inpainting via Re-Inpainting Self-Consistency Evaluation
  84. Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
  85. Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks
  86. Deep Multi-Manifold Transformation Based Multivariate Time Series Fault Detection
  87. HETHUB: A Distributed Training System with Heterogeneous Cluster for Large-Scale Models
  88. GeoAdaLer: Geometric Insights into Adaptive Stochastic Gradient Descent Algorithms
  89. Combining Radiomics and Machine Learning Approaches for Objective ASD Diagnosis: Verifying White Matter Associations with ASD
  90. Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation
  91. FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference
  92. AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models
  93. N-BVH: Neural ray queries with bounding volume hierarchies
  94. A transfer learning framework for weak-to-strong generalization
  95. A better approach to diagnose retinal diseases: Combining our Segmentation-based Vascular Enhancement with deep learning features
  96. Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing
  97. Detecting Adversarial Data using Perturbation Forgery
  98. Local Causal Structure Learning in the Presence of Latent Variables
  99. Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning
  100. DAFFNet: A Dual Attention Feature Fusion Network for Classification of White Blood Cells
All 182
  1. Structural Disentanglement of Causal and Correlated Concepts
  2. Learning Visual-Semantic Subspace Representations
  3. GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning
  4. VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence
  5. Evolutionary Large Language Model for Automated Feature Transformation
  6. FlightPatchNet: Multi-Scale Patch Network with Differential Coding for Flight Trajectory Prediction
  7. A 7K Parameter Model for Underwater Image Enhancement based on Transmission Map Prior
  8. Maintaining and Managing Road Quality:Using MLP and DNN
  9. Rocket Landing Control with Grid Fins and Path-following using MPC
  10. Differentiable Cluster Graph Neural Network
  11. Graph Neural PDE Solvers with Conservation and Similarity-Equivariance
  12. Boosting Adversarial Transferability with Low-Cost Optimization via Maximin Expected Flatness
  13. Bi-reachability in Petri nets with data
  14. Multi-Player Approaches for Dueling Bandits
  15. Acquiring Better Load Estimates by Combining Anomaly and Change Point Detection in Power Grid Time-series Measurements
  16. A Declarative Query Language for Scientific Machine Learning
  17. Mixture of In-Context Prompters for Tabular PFNs
  18. Improving Multi-lingual Alignment Through Soft Contrastive Learning
  19. DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries
  20. SuDA: Support-based Domain Adaptation for Sim2Real Motion Capture with Flexible Sensors
  21. 5W1H Extraction With Large Language Models
  22. Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection
  23. GreenCOD: A Green Camouflaged Object Detection Method
  24. C3LLM: Conditional Multimodal Content Generation Using Large Language Models
  25. Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
  26. Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting
  27. Automating the Selection of Proxy Variables of Unmeasured Confounders
  28. iREL at SemEval-2024 Task 9: Improving Conventional Prompting Methods for Brain Teasers
  29. How Well Do Deep Learning Models Capture Human Concepts? The Case of the Typicality Effect
  30. Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity
  31. Unsupervised Meta-Learning via In-Context Learning
  32. Gradient Propagation in Retrosynthetic Space: An Efficient Framework for Synthesis Plan Generation
  33. Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
  34. Method and Software Tool for Generating Artificial Databases of Biomedical Images Based on Deep Neural Networks
  35. Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
  36. REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation
  37. SNOBERT: A Benchmark for clinical notes entity linking in the SNOMED CT clinical terminology
  38. Multi-scale Quaternion CNN and BiGRU with Cross Self-attention Feature Fusion for Fault Diagnosis of Bearing
  39. Enabling On-Device Learning via Experience Replay with Efficient Dataset Condensation
  40. Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
  41. OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All
  42. MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space
  43. Reliable Source Approximation: Source-Free Unsupervised Domain Adaptation for Vestibular Schwannoma MRI Segmentation
  44. Improving 3D Occupancy Prediction through Class-balancing Loss and Multi-scale Representation
  45. Lateralization MLP: A Simple Brain-inspired Architecture for Diffusion
  46. MINet: Multi-scale Interactive Network for Real-time Salient Object Detection of Strip Steel Surface Defects
  47. PLUG: Revisiting Amodal Segmentation with Foundation Model and Hierarchical Focus
  48. Towards Completeness-Oriented Tool Retrieval for Large Language Models
  49. Estimating the normal-inverse-Wishart distribution
  50. Deep-PE: A Learning-Based Pose Evaluator for Point Cloud Registration
  51. From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals
  52. Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets
  53. Continuous Temporal Domain Generalization
  54. SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generation
  55. DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution
  56. IncomeSCM: From tabular data set to time-series simulator and causal estimation benchmark
  57. SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
  58. FedSheafHN: Personalized Federated Learning on Graph-structured Data
  59. Federated Learning for Non-factorizable Models using Deep Generative Prior Approximations
  60. A Bi-Objective Approach to Last-Mile Delivery Routing Considering Driver Preferences
  61. Theoretical Analysis of Weak-to-Strong Generalization
  62. Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention
  63. Explainable Molecular Property Prediction: Aligning Chemical Concepts with Predictions via Language Models
  64. Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection
  65. Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness
  66. DiffuBox: Refining 3D Object Detection with Point Diffusion
  67. Online Resource Allocation for Edge Intelligence with Colocated Model Retraining and Inference
  68. Feature Protection For Out-of-distribution Generalization
  69. ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces
  70. Convergence Behavior of an Adversarial Weak Supervision Method
  71. Pessimistic Backward Policy for GFlowNets
  72. Streaming Long Video Understanding with Large Language Models
  73. Intensity and Texture Correction of Omnidirectional Image Using Camera Images for Indirect Augmented Reality
  74. Disentangling Heterogeneous Knowledge Concept Embedding for Cognitive Diagnosis on Untested Knowledge
  75. Does SGD really happen in tiny subspaces?
  76. Carnatic Raga Identification System using Rigorous Time-Delay Neural Network
  77. Selfie Taking with Facial Expression Recognition Using Omni-directional Camera
  78. Efficient Temporal Action Segmentation via Boundary-aware Query Voting
  79. Data Complexity Estimates for Operator Learning
  80. R'enyi Neural Processes
  81. TreeFormers -- An Exploration of Vision Transformers for Deforestation Driver Classification
  82. Transductive Confidence Machine and its application to Medical Data Sets