mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 21 May 2023

136 papers

  1. Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  2. Guided Motion Diffusion for Controllable Human Motion SynthesisDiffusion models → Video generation
  3. Understanding the Effect of Data Augmentation on Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  4. A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with TransformersLLM reasoning → Mathematical reasoning
  5. Watermarking Diffusion ModelDiffusion models → Robustness, privacy and adversarial aspects +1
  6. Augmenting Autotelic Agents with Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through PromptsLLM reasoning → Reasoning benchmarks and evaluation
  8. Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  9. DualVC: Dual-mode Voice Conversion using Intra-model Knowledge Distillation and Hybrid Predictive CodingKnowledge distillation → Speech and audio distillation
  10. DiffUCD:Unsupervised Hyperspectral Image Change Detection with Semantic Correlation Diffusion ModelDiffusion models → Inverse problems and image restoration
  11. Federated Offline Policy LearningOffline RL and imitation learning from data → Offline RL algorithms
  12. Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual ScenariosLLM reasoning → Audio-language model reasoning
  13. Generative Model Watermarking Suppressing High-Frequency ArtifactsLLM safety and security → Watermarking generated content and models
  14. From Patches to Objects: Exploiting Spatial Reasoning for Better Visual RepresentationsLLM reasoning → Spatial and embodied reasoning
  15. Learning Joint 2D & 3D Diffusion Models for Complete Molecule GenerationDiffusion models → Flow matching, time series and science
  16. Random Relabeling for Efficient Machine UnlearningLLM safety and security → Machine unlearning
  17. WiFi-TCN: Temporal Convolution for Human Interaction Recognition based on WiFi signal
  18. Exploring and Exploiting Data Heterogeneity in Recommendation
  19. Bounded Projection Matrix Approximation with Applications to Community Detection
  20. Predicting Stock Market Time-Series Data using CNN-LSTM Neural Network Model
  21. Unsupervised Discovery of Continuous Skills on a Sphere
  22. On the Limitations of Simulating Active Learning
  23. Discovering Causal Relations and Equations from Data
  24. Gene Set Summarization using Large Language Models
  25. Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages
  26. PRODIGY: Enabling In-context Learning Over Graphs
  27. iWarpGAN: Disentangling Identity and Style to Generate Synthetic Iris Images
  28. Modeling User Satisfaction Dynamics in Dialogue via Hawkes Process
  29. FAQ: Mitigating the Impact of Faults in the Weight Memory of DNN Accelerators through Fault-Aware Quantization
  30. Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies
  31. Equivariant geometric convolutions for emulation of dynamical systems
  32. Sparse Representer Theorems for Learning in Reproducing Kernel Banach Spaces
  33. Your smartphone could act as a pulse-oximeter and as a single-lead ECG
  34. A parametric distribution for exact post-selection inference with data carving
  35. A Framework for Bidirectional Decoding: Case Study in Morphological Inflection
  36. Hystoc: Obtaining word confidences for fusion of end-to-end ASR systems
  37. Self-Explainable Graph Neural Networks for Link Prediction
  38. Automated Few-shot Classification with Instruction-Finetuned Language Models
  39. Reproducibility Requires Consolidated Artifacts
  40. Generalizable synthetic MRI with physics-informed convolutional networks
  41. Conditional Generative Modeling for High-dimensional Marked Temporal Point Processes
  42. Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
  43. ChatGPT Is More Likely to Be Perceived as Male Than Female
  44. M2LADS: A System for Generating MultiModal Learning Analytics Dashboards in Open Education
  45. Confidence-aware Personalized Federated Learning via Variational Expectation Maximization
  46. CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion
  47. Markov α-Potential Games
  48. Wav2SQL: Direct Generalizable Speech-To-SQL Parsing
  49. Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models
  50. A Reinforcement Learning Approach for Robust Supervisory Control of UAVs Under Disturbances
  51. ToxBuster: In-game Chat Toxicity Buster with BERT
  52. On the Efficacy and Noise-Robustness of Jointly Learned Speech Emotion and Automatic Speech Recognition
  53. Explaining How Transformers Use Context to Build Predictions
  54. BertRLFuzzer: A BERT and Reinforcement Learning Based Fuzzer
  55. Multilingual Simplification of Medical Texts
  56. DreamWaltz: Make a Scene with Complex 3D Animatable Avatars
  57. TheoremQA: A Theorem-driven Question Answering dataset
  58. P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priors
  59. SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly
  60. DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection
  61. VAKTA-SETU: A Speech-to-Speech Machine Translation Service in Select Indic Languages
  62. Description-Based Text Similarity
  63. PCF-GAN: generating sequential data via the characteristic function of measures on the path space
  64. A Deeper (Autoregressive) Approach to Non-Convergent Discourse Parsing
  65. CNN-based Dendrite Core Detection from Microscopic Images of Directionally Solidified Ni-base Alloys
  66. Exploring How Generative Adversarial Networks Learn Phonological Representations
  67. Multi-Head State Space Model for Speech Recognition
  68. PanoContext-Former: Panoramic Total Scene Understanding with a Transformer
  69. Fair Without Leveling Down: A New Intersectional Fairness Definition
  70. Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network
  71. A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition
  72. Model Analysis & Evaluation for Ambiguous Question Answering
  73. Is Translation Helpful? An Empirical Analysis of Cross-Lingual Transfer in Low-Resource Dialog Generation
  74. Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
  75. Evaluating the Performance of Large Language Models on GAOKAO Benchmark
  76. Continually Improving Extractive QA via Human Feedback
  77. Quasi-Monte Carlo Graph Random Features
  78. Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks
  79. Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces
  80. Teaching the Pre-trained Model to Generate Simple Texts for Text Simplification
  81. Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model
  82. Unsupervised Multi-view Pedestrian Detection
  83. Non-flat ABA is an Instance of Bipolar Argumentation
  84. Advancing Referring Expression Segmentation Beyond Single Image
  85. Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter
  86. BreastSAM: A Study of Segment Anything Model for Breast Tumor Detection in Ultrasound Images
  87. A Pilot Study on Dialogue-Level Dependency Parsing for Chinese
  88. SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition
  89. BiasAsker: Measuring the Bias in Conversational AI System
  90. ParticleWNN: a Novel Neural Networks Framework for Solving Partial Differential Equations
  91. Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification
  92. VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations
  93. Mol-PECO: a deep learning model to predict human olfactory perception from molecular structures
  94. Evaluating Open-QA Evaluation
  95. CNN-based Methods for Object Recognition with High-Resolution Tactile Sensors
  96. Real-time Aerial Detection and Reasoning on Embedded-UAVs
  97. EM Pre-training for Multi-party Dialogue Response Generation
  98. Synthesizing Diverse Human Motions in 3D Indoor Scenes
  99. Deep Radar Inverse Sensor Models for Dynamic Occupancy Grid Maps
  100. Spatio-temporal Diffusion Point Processes
All 136
  1. Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits
  2. WOT-Class: Weakly Supervised Open-world Text Classification
  3. Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
  4. Joint Feature and Differentiable k -NN Graph Learning using Dirichlet Energy
  5. Pruning Pre-trained Language Models with Principled Importance and Self-regularization
  6. Layer Collaboration in the Forward-Forward Algorithm
  7. PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs
  8. SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extraction
  9. Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors
  10. Measuring Intersectional Biases in Historical Documents
  11. Machine Translation by Projecting Text into the Same Phonetic-Orthographic Space Using a Common Encoding
  12. HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer
  13. Towards Optimal Energy Management Strategy for Hybrid Electric Vehicle with Reinforcement Learning
  14. Machine Learning for Socially Responsible Portfolio Optimisation
  15. A Dual-level Detection Method for Video Copy Detection
  16. AutoPaint: A Self-Inpainting Method for Unsupervised Anomaly Detection
  17. Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models
  18. Bi-ViT: Pushing the Limit of Vision Transformer Quantization
  19. Data-driven Mixed Integer Optimization through Probabilistic Multi-variable Branching
  20. Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack
  21. PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation
  22. YOLOv3 with Spatial Pyramid Pooling for Object Detection with Unmanned Aerial Vehicles
  23. Temporal Fusion Transformers for Streamflow Prediction: Value of Combining Attention with Recurrence
  24. Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
  25. GRACE: Loss-Resilient Real-Time Video through Neural Codecs
  26. Task-agnostic Distillation of Encoder-Decoder Language Models
  27. Anomaly Detection Using One-Class SVM for Logs of Juniper Router Devices
  28. InstructVid2Vid: Controllable Video Editing with Natural Language Instructions
  29. Coronary Artery Semantic Labeling using Edge Attention Graph Matching Network
  30. Learning Large Graph Property Prediction via Graph Segment Training
  31. One-Shot Federated Learning for LEO Constellations that Reduces Convergence Time from Days to 90 Minutes
  32. When are ensembles really effective?
  33. i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data
  34. Alignment of Density Maps in Wasserstein Distance
  35. OntoType: Ontology-Guided and Pre-Trained Language Model Assisted Fine-Grained Entity Typing
  36. F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks