mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 4 Jun 2023

101 papers

  1. Systematic Visual Reasoning through Object-Centric Relational AbstractionLLM reasoning → Multimodal reasoning
  2. Data Quality in Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  3. Evaluating and Improving Tool-Augmented Computation-Intensive Math ReasoningLLM reasoning → Mathematical reasoning
  4. Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient InferenceKnowledge distillation → Knowledge distillation for LLMs
  5. Revisiting Data-Free Knowledge Distillation with Poisoned TeachersLLM safety and security → Machine unlearning +1
  6. Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D ScenesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  7. Temporal Dynamic Quantization for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  8. Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource SettingsEfficient LLM inference and serving → Early exit and edge inference
  9. Probing Physical Reasoning with Counter-Commonsense ContextLLM reasoning → Reasoning benchmarks and evaluation
  10. Detector Guidance for Multi-Object Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  11. Fine-Tuning Language Models with Advantage-Induced Policy AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  12. Point Cloud Video Anomaly Detection Based on Point Spatio-Temporal Auto-Encoder
  13. DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setup
  14. Provable convergence guarantees for black-box variational inference
  15. Deep learning powered real-time identification of insects using citizen science data
  16. Learning on Bandwidth Constrained Multi-Source Data with MIMO-inspired DPP MAP Inference
  17. RadLing: Towards Efficient Radiology Report Understanding
  18. Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacy
  19. Discussion Paper: The Threat of Real Time Deepfakes
  20. Contagion Effect Estimation Using Proximal Embeddings
  21. Modeling Cross-Cultural Pragmatic Inference with Codenames Duet
  22. Anomaly Detection Techniques in Smart Grid Systems: A Review
  23. Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search
  24. Adaptive and Personalized Exercise Generation for Online Language Learning
  25. For SALE: State-Action Representation Learning for Deep Reinforcement Learning
  26. The Power Of Simplicity: Why Simple Linear Models Outperform Complex Machine Learning Techniques -- Case Of Breast Cancer Diagnosis
  27. Active Inference-Based Optimization of Discriminative Neural Network Classifiers
  28. ESTISR: Adapting Efficient Scene Text Image Super-resolution for Real-Scenes
  29. Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation
  30. A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
  31. Taught by the Internet, Exploring Bias in OpenAIs GPT3
  32. Resilient Constrained Learning
  33. Sanity Checks for Saliency Methods Explaining Object Detectors
  34. A Generalized Alternating Method for Bilevel Learning under the Polyak-Lojasiewicz Condition
  35. Auto-Validate by-History: Auto-Program Data Quality Constraints to Validate Recurring Data Pipelines
  36. Complexity of Block Coordinate Descent with Proximal Regularization and Applications to Wasserstein CP-dictionary Learning
  37. Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL
  38. ContraBAR: Contrastive Bayes-Adaptive Deep RL
  39. Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation
  40. Biologically-Motivated Learning Model for Instructed Visual Processing
  41. Evaluating Continual Learning on a Home Robot
  42. Topological Quality of Subsets via Persistence Matching Diagrams
  43. Heteroskedastic Geospatial Tracking with Distributed Camera Networks
  44. An Information-Theoretic Analysis of Self-supervised Discrete Representations of Speech
  45. Perceptual Kalman Filters: Online State Estimation under a Perfect Perceptual-Quality Constraint
  46. Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures
  47. Scale Guided Hypernetwork for Blind Super-Resolution Image Quality Assessment
  48. NICE-SLAM with Adaptive Feature Grids
  49. EgoSpot:Egocentric Multimodal Control for Hands-Free Mobile Manipulation
  50. Fast Continual Multi-View Clustering with Incomplete Views
  51. Commonsense Knowledge Transfer for Pre-trained Language Models
  52. Evolution of Efficient Symbolic Communication Codes
  53. "Are you telling me to put glasses on the dog?'' Content-Grounded Annotation of Instruction Clarification Requests in the CoDraw Dataset
  54. Towards Deep Attention in Graph Neural Networks: Problems and Remedies
  55. GAN-based Deidentification of Drivers' Face Videos: An Assessment of Human Factors Implications in NDS Data
  56. Addressing Domain Shift via Knowledge Space Sharing for Generalized Zero-Shot Industrial Fault Diagnosis
  57. RSSOD-Bench: A large-scale benchmark dataset for Salient Object Detection in Optical Remote Sensing Imagery
  58. bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark
  59. Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations
  60. Concept Drift and Long-Tailed Distribution in Fine-Grained Visual Categorization: Benchmark and Method
  61. Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration
  62. Towards Robust Feature Learning with t-vFM Similarity for Continual Learning
  63. Long Text Generation Challenge
  64. Cross-LKTCN: Modern Convolution Utilizing Cross-Variable Dependency for Multivariate Time Series Forecasting Dependency for Multivariate Time Series Forecasting
  65. Random Feedback Alignment Algorithms to train Neural Networks: Why do they Align?
  66. Exploring the Impact of Model Scaling on Parameter-Efficient Tuning
  67. SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings
  68. Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation
  69. (Un)reasonable Allure of Ante-hoc Interpretability for High-stakes Domains: Transparency Is Necessary but Insufficient for Comprehensibility
  70. Cross-CBAM: A Lightweight network for Scene Segmentation
  71. Does Character-level Information Always Improve DRS-based Semantic Parsing?
  72. rPPG-MAE: Self-supervised Pre-training with Masked Autoencoders for Remote Physiological Measurement
  73. How neural networks learn to classify chaotic time series
  74. Onsite Job Scheduling by Adaptive Genetic Algorithm
  75. A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models
  76. Exposing Bias in Online Communities through Large-Scale Language Models
  77. 3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW
  78. Clarify Confused Nodes via Separated Learning
  79. Matrix Completion from General Deterministic Sampling Patterns
  80. Exploring and Verbalizing Academic Ideas by Concept Co-occurrence
  81. EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection
  82. USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Model
  83. End-to-End Joint Target and Non-Target Speakers ASR
  84. OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models
  85. SubspaceNet: Deep Learning-Aided Subspace Methods for DoA Estimation
  86. Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detection
  87. MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information
  88. Online estimation of the hand-eye transformation from surgical scenes
  89. Learning from AI: An Interactive Learning Method Using a DNN Model Incorporating Expert Knowledge as a Teacher
  90. A Technical Report for Polyglot-Ko: Open-Source Large-Scale Korean Language Models
  91. MoviePuzzle: Visual Narrative Reasoning through Multimodal Order Learning
  92. Large Language Model Augmented Narrative Driven Recommendations
  93. Sen2Pro: A Probabilistic Perspective to Sentence Embedding from Pre-trained Language Model
  94. SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model
  95. Retrieval-Enhanced Visual Prompt Learning for Few-shot Classification
  96. Extract and Attend: Improving Entity Translation in Neural Machine Translation
  97. ProTeCt: Prompt Tuning for Taxonomic Open Set Classification
  98. Learning Linear Causal Representations from Interventions under General Nonlinear Mixing
  99. Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions
  100. Prescriptive PCA: Dimensionality Reduction for Two-stage Stochastic Optimization
All 101
  1. ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives