mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 6 Oct 2023

198 papers

  1. Making Users Indistinguishable: Attribute-wise Unlearning in Recommender SystemsLLM safety and security → Membership inference attacks
  2. Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  3. DPM-TSE: A Diffusion Probabilistic Model for Target Sound ExtractionDiffusion models → Audio, speech and music
  4. DragD3D: Realistic Mesh Editing with Rigidity Control Driven by 2D Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  5. Generative Diffusion From An Action PrincipleDiffusion models → Diffusion foundations and sampling
  6. Ada-Instruct: Adapting Instruction Generators for Complex ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  7. Reverse Chain: A Generic-Rule for LLMs to Master Multi-API PlanningLLM agents and tool use → Tool learning and function calling
  8. Generalization Bound for Diffusion Models using Random FeaturesDiffusion models → Diffusion foundations and sampling
  9. Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced DatasetsOffline RL and imitation learning from data → Offline RL algorithms
  10. Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RLOffline RL and imitation learning from data → Offline RL algorithms
  11. RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective AugmentationRetrieval-augmented generation → Generation and context integration
  12. Language Agent Tree Search Unifies Reasoning Acting and Planning in Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  13. Leveraging Self-Consistency for Data-Efficient Amortized Bayesian InferenceLLM reasoning → Test-time compute and efficient thinking
  14. Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step InferenceDiffusion models → Diffusion foundations and sampling
  15. Confronting Reward Model Overoptimization with Constrained RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  16. Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts ConversionMixture-of-experts → MoE theory and gating functions
  17. An In-Context Learning Agent for Formal Theorem-ProvingLLM agents and tool use → Educational agents and math problem solving
  18. From task structures to world models: What do LLMs know?World models → World models for language agents
  19. Lending Interaction Wings to Recommender Systems with Conversational AgentsLLM agents and tool use → Agentic recommender systems
  20. VI-Diff: Unpaired Visible-Infrared Translation Diffusion Model for Single Modality Labeled Visible-Infrared Person Re-identificationDiffusion models → Image generation, text-to-image and editing
  21. Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof VerificationLLM safety and security → Federated unlearning and poisoning
  22. Observation-Guided Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
  23. Analysis of the Reasoning with Redundant Information Provided Ability of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  24. Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language ModelsRetrieval-augmented generation → Legal and financial RAG
  25. SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text GenerationLLM safety and security → Watermarking generated content and models
  26. Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  27. Understanding prompt engineering may not require rethinking generalizationLLM reasoning → Multimodal reasoning +1
  28. A Process for Topic Modelling Via Word Embeddings
  29. Multimodal Identification of Alzheimer's Disease: A Review
  30. Tool Wear Segmentation in Blanking Processes with Fully Convolutional Networks based Digital Image Processing
  31. Wafer Map Defect Patterns Semi-Supervised Classification Using Latent Vector Representation
  32. Should they? Mobile Biometrics and Technopolicy meet Queer Community Considerations
  33. In nomine patris... Elements for a semantics of medieval paternity
  34. Overview of AdaBoost : Reconciling its views to better understand its dynamics
  35. Conversational Factor Information Retrieval Model (ConFIRM)
  36. Document-Level Relation Extraction with Relation Correlation Enhancement
  37. ByteStack-ID: Integrated Stacked Model Leveraging Payload Byte Frequency for Grayscale Image-based Network Intrusion Detection
  38. The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric
  39. FMM-Head: Enhancing Autoencoder-based ECG anomaly detection with prior knowledge
  40. Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning
  41. Copy Suppression: Comprehensively Understanding an Attention Head
  42. Deconstructing Cooperation and Ostracism via Multi-Agent Reinforcement Learning
  43. FluxGAN: A Physics-Aware Generative Adversarial Network Model for Generating Microstructures That Maintain Target Heat Flux
  44. Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences
  45. SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics
  46. A Topological Perspective on Demystifying GNN-Based Link Prediction Performance
  47. DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
  48. A Comprehensive Performance Study of Large Language Models on Novel AI Accelerators
  49. Robust Transfer Learning with Unreliable Source Data
  50. Learning Optimal Power Flow Value Functions with Input-Convex Neural Networks
  51. PriViT: Vision Transformers for Fast Private Inference
  52. A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs
  53. Segmented Harmonic Loss: Handling Class-Imbalanced Multi-Label Clinical Data for Medical Coding with Large Language Models
  54. From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and Context
  55. Deep Model Predictive Optimization
  56. Interventions Against Machine-Assisted Statistical Discrimination
  57. An Algorithm to Train Unrestricted Sequential Discrete Morphological Neural Networks
  58. Universal Humanoid Motion Representations for Physics-Based Control
  59. A Double Machine Learning Approach for the Evaluation of COVID-19 Vaccine Effectiveness under the Test-Negative Design: Analysis of Qu'ebec Administrative Data
  60. Can pruning make Large Language Models more efficient?
  61. Transformer-Based Neural Surrogate for Link-Level Path Loss Prediction from Variable-Sized Maps
  62. Knolling Bot: Teaching Robots the Human Notion of Tidiness
  63. Binary Quantification and Dataset Shift: An Experimental Investigation
  64. ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
  65. Towards Foundation Models for Knowledge Graph Reasoning
  66. Talk like a Graph: Encoding Graphs for Large Language Models
  67. VTON-IT: Virtual Try-On using Image Translation
  68. Measuring Information in Text Explanations
  69. MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation
  70. Module-wise Adaptive Distillation for Multimodality Foundation Models
  71. Iris Liveness Detection Competition (LivDet-Iris) -- The 2023 Edition
  72. Multi-decadal Sea Level Prediction using Neural Networks and Spectral Clustering on Climate Model Large Ensembles and Satellite Altimeter Data
  73. Generating Less Certain Adversarial Examples Improves Robust Generalization
  74. LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation
  75. Envisioning Narrative Intelligence: A Creative Visual Storytelling Anthology
  76. DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversion
  77. Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
  78. SPADE: Sparsity-Guided Debugging for Deep Neural Networks
  79. Domain Randomization for Sim2real Transfer of Automatically Generated Grasping Datasets
  80. Utilizing Free Clients in Federated Learning for Focused Model Enhancement
  81. Risk factor aggregation and stress testing
  82. URLOST: Unsupervised Representation Learning without Stationarity or Topology
  83. T-Rep: Representation Learning for Time Series using Time-Embeddings
  84. Reward Dropout Improves Control: Bi-objective Perspective on Reinforced LM
  85. EMOFM: Ensemble MLP mOdel with Feature-based Mixers for Click-Through Rate Prediction
  86. Acoustic and linguistic representations for speech continuous emotion recognition in call center conversations
  87. Auto-survey Challenge
  88. Leveraging Data Geometry to Mitigate CSM in Steganalysis
  89. Higher-Order DeepTrails: Unified Approach to *Trails
  90. Demystifying Embedding Spaces using Large Language Models
  91. Effective Slogan Generation with Noise Perturbation
  92. Fast Neighborhood Search Heuristics for the Colored Bin Packing Problem
  93. Hierarchical Multi-Marginal Optimal Transport for Network Alignment
  94. BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity
  95. Functional Interpolation for Relative Positions Improves Long Context Transformers
  96. Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic
  97. Why Do We Need Weight Decay in Modern Deep Learning?
  98. CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis
  99. FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning
  100. Policy-Gradient Training of Language Models for Ranking
All 198
  1. On the Embedding Collapse when Scaling up Recommendation Models
  2. Improving Stability in Simultaneous Speech Translation: A Revision-Controllable Decoding Approach
  3. Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications
  4. MBTFNet: Multi-Band Temporal-Frequency Neural Network For Singing Voice Enhancement
  5. A Marketplace Price Anomaly Detection System at Scale
  6. Amortizing intractable inference in large language models
  7. SwimXYZ: A large-scale dataset of synthetic swimming motions and videos
  8. Transferring speech-generic and depression-specific knowledge for Alzheimer's disease detection
  9. Asymptotically free sketched ridge ensembles: Risks, cross-validation, and tuning
  10. Integrating Transformations in Probabilistic Circuits
  11. Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates
  12. Toward a Plug-and-Play Vision-Based Grasping Module for Robotics
  13. Deep Learning for Two-Stage Robust Integer Optimization
  14. Functional Geometry Guided Protein Sequence and Backbone Structure Co-Design
  15. Applying Reinforcement Learning to Option Pricing and Hedging
  16. Saliency-Guided Hidden Associative Replay for Continual Learning
  17. Robust Losses for Decision-Focused Learning
  18. Program Synthesis with Best-First Bottom-Up Search
  19. Adjustable Robust Reinforcement Learning for Online 3D Bin Packing
  20. Latent Graph Inference with Limited Supervision
  21. KoMultiText: Large-Scale Korean Text Dataset for Classifying Biased Speech in Real-World Online Services
  22. Distributed Deep Joint Source-Channel Coding with Decoder-Only Side Information
  23. Towards A Robust Group-level Emotion Recognition via Uncertainty-Aware Learning
  24. Coding by Design: GPT-4 empowers Agile Model Driven Development
  25. Convergent ADMM Plug and Play PET Image Reconstruction
  26. Identifying Representations for Intervention Extrapolation
  27. Graph learning in robotics: a survey
  28. Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
  29. Searching for Optimal Runtime Assurance via Reachability and Reinforcement Learning
  30. Assessing Robustness via Score-Based Adversarial Image Generation
  31. On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis
  32. Compositional Servoing by Recombining Demonstrations
  33. A Comprehensive Evaluation of Large Language Models on Benchmark Biomedical Text Processing Tasks
  34. DRIFT: Deep Reinforcement Learning for Intelligent Floating Platforms Trajectories
  35. Deep learning modelling of manufacturing and build variations on multi-stage axial compressors aerodynamics
  36. Collaborative Camouflaged Object Detection: A Large-Scale Dataset and Benchmark
  37. Semantic segmentation of longitudinal thermal images for identification of hot and cool spots in urban areas
  38. Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison
  39. Bringing Quantum Algorithms to Automated Machine Learning: A Systematic Review of AutoML Frameworks Regarding Extensibility for QML Algorithms
  40. Written and spoken corpus of real and fake social media postings about COVID-19
  41. The WayHome: Long-term Motion Prediction on Dynamically Scaled
  42. A Fixed-Parameter Tractable Algorithm for Counting Markov Equivalence Classes with the same Skeleton
  43. Cost-Effective Retraining of Machine Learning Models
  44. Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface
  45. mlirSynth: Automatic, Retargetable Program Raising in Multi-Level IR using Program Synthesis
  46. Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning
  47. On the Two Sides of Redundancy in Graph Neural Networks
  48. Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases
  49. Whole Slide Multiple Instance Learning for Predicting Axillary Lymph Node Metastasis
  50. DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions
  51. Degradation-Aware Self-Attention Based Transformer for Blind Image Super-Resolution
  52. Entropic Score metric: Decoupling Topology and Size in Training-free NAS
  53. Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions
  54. Dynamic Relation-Attentive Graph Neural Networks for Fraud Detection
  55. Amortized Network Intervention to Steer the Excitatory Point Processes
  56. Improving Neural Radiance Field using Near-Surface Sampling with Point Cloud Generation
  57. Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning
  58. From Zero to Hero: Detecting Leaked Data through Synthetic Data Injection and Model Querying
  59. Routing Arena: A Benchmark Suite for Neural Routing Solvers
  60. TiC: Exploring Vision Transformer in Convolution
  61. Reinforcement Learning with Fast and Forgetful Memory
  62. Aorta Segmentation from 3D CT in MICCAI SEG.A. 2023 Challenge
  63. Dense Random Texture Detection using Beta Distribution Statistics
  64. Automated 3D Segmentation of Kidneys and Tumors in MICCAI KiTS 2023 Challenge
  65. Nash Welfare and Facility Location
  66. ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer
  67. End-to-End Chess Recognition
  68. A Deeply Supervised Semantic Segmentation Method Based on GAN
  69. Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends
  70. Automatic Aspect Extraction from Scientific Texts
  71. AI Regulation in Europe: From the AI Act to Future Regulatory Challenges
  72. How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
  73. DEFT: A new distance-based feature set for keystroke dynamics
  74. AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs
  75. In the Blink of an Eye: Event-based Emotion Recognition
  76. Joint Projection Learning and Tensor Decomposition Based Incomplete Multi-view Clustering
  77. Genetic prediction of quantitative traits: a machine learner's guide focused on height
  78. PGraphDTA: Improving Drug Target Interaction Prediction using Protein Language Models and Contact Maps
  79. Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalization
  80. Excision And Recovery: Visual Defect Obfuscation Based Self-Supervised Anomaly Detection Strategy
  81. Accelerating optimization over the space of probability measures
  82. The Role of Federated Learning in a Wireless World with Foundation Models
  83. Runtime Monitoring DNN-Based Perception
  84. Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation
  85. Dementia Assessment Using Mandarin Speech with an Attention-based Speech Recognition Encoder
  86. AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems
  87. CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation
  88. Perfect Alignment May be Poisonous to Graph Contrastive Learning
  89. From Text to Self: Users' Perceptions of Potential of AI on Interpersonal Communication and Self
  90. HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model
  91. Quantized Transformer Language Model Implementations on Edge Devices
  92. Ultimate limit on learning non-Markovian behavior: Fisher information rate and excess information
  93. Sub-token ViT Embedding via Stochastic Resonance Transformers
  94. A Learnable Counter-condition Analysis Framework for Functional Connectivity-based Neurological Disorder Diagnosis
  95. Towards Increasing the Robustness of Predictive Steering-Control Autonomous Navigation Systems Against Dash Cam Image Angle Perturbations Due to Pothole Encounters
  96. Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction
  97. ILSH: The Imperial Light-Stage Head Dataset for Human Head View Synthesis
  98. Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations