mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 20 Dec 2022

271 papers

  1. LAMBADA: Backward Chaining for Automated Reasoning in Natural LanguageLLM reasoning → Reasoning benchmarks and evaluation
  2. Parsel: Algorithmic Reasoning with Language Models by Composing DecompositionsLLM reasoning → Reasoning benchmarks and evaluation
  3. Self-Instruct: Aligning Language Models with Self-Generated InstructionsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  4. Cross-modal Attention Congruence Regularization for Vision-Language Relation AlignmentMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  5. DimonGen: Diversified Generative Commonsense Reasoning for Explaining Concept RelationshipsLLM reasoning → Reasoning benchmarks and evaluation
  6. A Survey of Deep Learning for Mathematical ReasoningLLM reasoning → Mathematical reasoning
  7. When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric MemoriesRetrieval-augmented generation → Generation and context integration
  8. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step QuestionsLLM reasoning → Knowledge- and tool-augmented reasoning
  9. DePlot: One-shot visual language reasoning by plot-to-table translationLLM reasoning → Multimodal reasoning
  10. Generic Temporal Reasoning with Differential Analysis and ExplanationLLM reasoning → Knowledge- and tool-augmented reasoning
  11. Perplexed by Quality: A Perplexity-based Method for Adult and Harmful Content Detection in Multilingual Heterogeneous Web DataLLM safety and security → Safety alignment, refusal and guardrails
  12. Fine-Grained Distillation for Long Document RetrievalKnowledge distillation → Knowledge distillation for LLMs
  13. Towards Reasoning in Large Language Models: A SurveyLLM reasoning → Reasoning benchmarks and evaluation
  14. SeqDiffuSeq: Text Diffusion with Encoder-Decoder TransformersDiffusion models → Discrete and text diffusion
  15. Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?LLM reasoning → Multimodal reasoning
  16. Adam: Dense Retrieval Distillation with Adaptive Dark ExamplesKnowledge distillation → General knowledge distillation methods
  17. True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4LLM reasoning → Reasoning benchmarks and evaluation
  18. VSVC: Backdoor attack against Keyword Spotting based on Voiceprint Selection and Voice ConversionLLM safety and security → Audio jailbreaks and speech backdoors
  19. Large Language Models Are Reasoning TeachersLLM reasoning → Prompting and chain-of-thought reasoning
  20. Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What MattersLLM reasoning → Prompting and chain-of-thought reasoning
  21. On Improving Summarization Factual Consistency from Natural Language FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  22. A Survey on Human Action Recognition
  23. Unsupervised Question Duplicate and Related Questions Detection in e-learning platforms
  24. Toward an AI-enabled Connected Industry: AGV Communication and Sensor Measurement Datasets
  25. Combined mechanistic and machine learning method for construction of oil reservoir permeability map consistent with well test measurements
  26. Uncertainty in Real-Time Semantic Segmentation on Embedded Systems
  27. Common Practices and Taxonomy in Deep Multi-view Fusion for Remote Sensing Applications
  28. Pain level and pain-related behaviour classification using GRU-based sparsely-connected RNNs
  29. FunkNN: Neural Interpolation for Functional Generation
  30. Likelihood-based generalization of Markov parameter estimation and multiple shooting objectives in system identification
  31. Multi-Metric AutoRec for High Dimensional and Sparse User Behavior Data Prediction
  32. A portable widefield fundus camera with high dynamic range imaging capability
  33. Scene-aware Egocentric 3D Human Pose Estimation
  34. Variational Quantum Soft Actor-Critic for Robotic Arm Control
  35. Smooth Sailing: Improving Active Learning for Pre-trained Language Models with Representation Smoothness Analysis
  36. Trustworthy Social Bias Measurement
  37. Evaluation for Change
  38. A survey on text generation using generative adversarial networks
  39. Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks
  40. Adapting the Exploration Rate for Value-of-Information-Based Reinforcement Learning
  41. C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation
  42. Task Ambiguity in Humans and Language Models
  43. Generation-Augmented Query Expansion For Code Retrieval
  44. METEOR Guided Divergence for Video Captioning
  45. Local Differential Privacy Image Generation Using Flow-based Deep Generative Models
  46. Privacy-Protecting Behaviours of Risk Detection in People with Dementia using Videos
  47. A Physics-Informed Neural Network to Model Port Channels
  48. Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias
  49. There's Plenty of Room Right Here: Biological Systems as Evolved, Overloaded, Multi-scale Machines
  50. evoML Yellow Paper: Evolutionary AI and Optimisation Studio
  51. In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models
  52. KronA: Parameter Efficient Tuning with Kronecker Adapter
  53. Inversion of Bayesian Networks
  54. High-Throughput, High-Performance Deep Learning-Driven Light Guide Plate Surface Visual Quality Inspection Tailored for Real-World Manufacturing Environments
  55. mFACE: Multilingual Summarization with Factual Consistency Evaluation
  56. Full-Body Articulated Human-Object Interaction
  57. Ontologically Faithful Generation of Non-Player Character Dialogues
  58. MolCPT: Molecule Continuous Prompt Tuning to Generalize Molecular Representation Learning
  59. Temporal Output Discrepancy for Loss Estimation-based Active Learning
  60. Open-Vocabulary Temporal Action Detection with Off-the-Shelf Image-Text Features
  61. Resonant Anomaly Detection with Multiple Reference Datasets
  62. Video Segmentation Learning Using Cascade Residual Convolutional Neural Network
  63. Re-evaluating the Need for Multimodal Signals in Unsupervised Grammar Induction
  64. BLIND: Bias Removal With No Demographics
  65. Character-Aware Models Improve Visual Text Rendering
  66. Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers
  67. On-the-fly Denoising for Data Augmentation in Natural Language Understanding
  68. DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines
  69. Unleashing the Power of Visual Prompting At the Pixel Level
  70. PairReranker: Pairwise Reranking for Natural Language Generation
  71. A Length-Extrapolatable Transformer
  72. RangeAugment: Efficient Online Augmentation with Range Learning
  73. Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation
  74. InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds
  75. T-Projection: High Quality Annotation Projection for Sequence Labeling Tasks
  76. Semantically-informed Hierarchical Event Modeling
  77. Pretraining Without Attention
  78. Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts
  79. UNO-QA: An Unsupervised Anomaly-Aware Framework with Test-Time Clustering for OCTA Image Quality Assessment
  80. Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?
  81. HyperBO+: Pre-training a universal prior for Bayesian optimization with hierarchical Gaussian processes
  82. Does CLIP Bind Concepts? Probing Compositionality in Large Image Models
  83. Measure More, Question More: Experimental Studies on Transformer-based Language Models and Complement Coercion
  84. DISCO: Distilling Counterfactuals with Large Language Models
  85. Evaluating Psychological Safety of Large Language Models
  86. HYRR: Hybrid Infused Reranking for Passage Retrieval
  87. Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval
  88. SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks
  89. Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End
  90. Privacy-Preserving Domain Adaptation of Semantic Parsers
  91. CausalDialogue: Modeling Utterance-level Causality in Conversations
  92. Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?
  93. Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training
  94. A Measure-Theoretic Characterization of Tight Language Models
  95. SimpleStyle: An Adaptable Style Transfer Approach
  96. Precise Zero-Shot Dense Retrieval without Relevance Labels
  97. Execution-Based Evaluation for Open-Domain Code Generation
  98. Generalized Simultaneous Perturbation-based Gradient Search with Reduced Estimator Bias
  99. ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models
  100. Little Red Riding Hood Goes Around the Globe:Crosslingual Story Planning and Generation with Large Language Models
All 271
  1. BMX: Boosting Natural Language Generation Metrics with Explainability
  2. Controllable Text Generation with Language Constraints
  3. SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization
  4. Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models
  5. MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue
  6. Towards Sequence Utility Maximization under Utility Occupancy Measure
  7. Is GPT-3 a Good Data Annotator?
  8. Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization
  9. Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters
  10. Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization
  11. Policy Gradient in Robust MDPs with Global Convergence Guarantee
  12. Is Semantic Communications Secure? A Tale of Multi-Domain Adversarial Attacks
  13. Scheduling with Predictions
  14. QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity
  15. Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics
  16. HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios
  17. Deep Riemannian Networks for End-to-End EEG Decoding
  18. Localising In-Domain Adaptation of Transformer-Based Biomedical Language Models
  19. Settling the Reward Hypothesis
  20. Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
  21. DDIPNet and DDIPNet+: Discriminant Deep Image Prior Networks for Remote Sensing Image Classification
  22. ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations
  23. Geographic and Geopolitical Biases of Language Models
  24. AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection
  25. Contrastive Learning Reduces Hallucination in Conversations
  26. A deep learning Attention model to solve the Vehicle Routing Problem and the Pick-up and Delivery Problem with Time Windows
  27. Needle in a Haystack: An Analysis of High-Agreement Workers on MTurk for Summarization
  28. Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learning
  29. Empowering Sentence Encoders with Prompting and Label Retrieval for Zero-shot Text Classification
  30. UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation Pipeline
  31. To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering
  32. What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary
  33. Data Curation Alone Can Stabilize In-context Learning
  34. The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Results
  35. Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering
  36. Masked Event Modeling: Self-Supervised Pretraining for Event Cameras
  37. Modeling Human Eye Movements with Neural Networks in a Maze-Solving Task
  38. Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis
  39. Optimizing Serially Concatenated Neural Codes with Classical Decoders
  40. Does It Affect You? Social and Learning Implications of Using Cognitive-Affective State Recognition for Proactive Human-Robot Tutoring
  41. Berlin V2X: A Machine Learning Dataset from Multiple Vehicles and Radio Access Technologies
  42. CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning
  43. Weakly supervised training of universal visual concepts for multi-domain semantic segmentation
  44. Construction of extra-large scale screening tools for risks of severe mental illnesses using real world healthcare data
  45. Image quality prediction using synthetic and natural codebooks: comparative results
  46. Learned-Database Systems Security
  47. HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation
  48. Beyond Triplet: Leveraging the Most Data for Multimodal Machine Translation
  49. Efficient and Sound Differentiable Programming in a Functional Array-Processing Language
  50. Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecasting
  51. Which Pixel to Annotate: a Label-Efficient Nuclei Segmentation Framework
  52. Probabilistic Quantile Factor Analysis
  53. Cell-Free Data Power Control Via Scalable Multi-Objective Bayesian Optimisation
  54. Extrinsic Evaluation of Machine Translation Metrics
  55. Quantifying and Visualizing Vascular Branching Geometry with Micro-CT: Normalization of Intra- and Inter-Specimen Variations
  56. Strong uniform convergence of Laplacians of random geometric and directed kNN graphs on compact manifolds
  57. Identifying and Manipulating the Personality Traits of Language Models
  58. High-resolution canopy height map in the Landes forest (France) based on GEDI, Sentinel-1, and Sentinel-2 data with a deep learning approach
  59. ReCode: Robustness Evaluation of Code Generation Models
  60. Eff-3DPSeg: 3D organ-level plant shoot segmentation using annotation-efficient point clouds
  61. Nonparametric plug-in classifier for multiclass classification of S.D.E. paths
  62. In and Out-of-Domain Text Adversarial Robustness via Label Smoothing
  63. Original or Translated? On the Use of Parallel Data for Translation Quality Estimation
  64. MDL-based Compressing Sequential Rules
  65. Learning efficient backprojections across cortical hierarchies in real time
  66. Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning
  67. Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagery
  68. Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study
  69. A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks
  70. StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation
  71. CSMPQ:Class Separability Based Mixed-Precision Quantization
  72. GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator
  73. Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches
  74. ParallelNet: Multi-mode Trajectory Prediction by Multi-mode Trajectory Fusion
  75. Redistribution of Weights and Activations for AdderNet Quantization
  76. EIT: Enhanced Interactive Transformer
  77. Emotion Selectable End-to-End Text-based Speech Editing
  78. Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite
  79. Do I have the Knowledge to Answer? Investigating Answerability of Knowledge Base Questions
  80. IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages
  81. Toward Human-Like Evaluation for Natural Language Generation with Error Analysis
  82. CGCV:Context Guided Correlation Volume for Optical Flow Neural Networks
  83. On the Role of Parallel Data in Cross-lingual Transfer Learning
  84. Document-level Relation Extraction with Relation Correlations
  85. Hoyer regularizer is all you need for ultra low-latency spiking neural networks
  86. Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages
  87. Seafloor-Invariant Caustics Removal from Underwater Imagery
  88. Planning-oriented Autonomous Driving
  89. Human-Guided Fair Classification for Natural Language Processing
  90. Quirk or Palmer: A Comparative Study of Modal Verb Frameworks with Annotated Datasets
  91. Tracking by Associating Clips
  92. Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection
  93. Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation
  94. A Comparison Between Tsetlin Machines and Deep Neural Networks in the Context of Recommendation Systems
  95. Content Adaptive Latents and Decoder for Neural Image Compression
  96. Image Segmentation-based Unsupervised Multiple Objects Discovery
  97. Efficient aggregation of face embeddings for decentralized face recognition deployments (extended version)
  98. On the Applicability of Synthetic Data for Re-Identification
  99. Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework
  100. Visual Transformers for Primates Classification and Covid Detection
  101. Computer Vision Methods for Automating Turbot Fish Cutting
  102. Hybrid Rule-Neural Coreference Resolution System based on Actor-Critic Learning
  103. End to End Generative Meta Curriculum Learning For Medical Data Augmentation
  104. An Information-Theoretic Approach to Transferability in Task Transfer Learning
  105. Galaxy Image Classification using Hierarchical Data Learning with Weighted Sampling and Label Smoothing
  106. Rumour detection using graph neural network and oversampling in benchmark Twitter dataset
  107. A Survey on Pretrained Language Models for Neural Code Intelligence
  108. Constructing Organism Networks from Collaborative Self-Replicators
  109. DOC: Improving Long Story Coherence With Detailed Outline Control
  110. Out-of-sample scoring and automatic selection of causal estimators
  111. RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction
  112. AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning
  113. I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons
  114. WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning
  115. VoronoiPatches: Evaluating A New Data Augmentation Method
  116. A Framework of Customer Review Analysis Using the Aspect-Based Opinion Mining Approach
  117. OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection
  118. Asynchronous Distributed Bilevel Optimization
  119. An Augmentation Strategy for Visually Rich Documents
  120. A Twitter BERT Approach for Offensive Language Detection in Marathi
  121. Real-time Health Monitoring of Heat Exchangers using Hypernetworks and PINNs
  122. InterMulti:Multi-view Multimodal Interactions with Text-dominated Hierarchical High-order Fusion for Emotion Analysis
  123. Do language models have coherent mental models of everyday things?
  124. When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods
  125. On the Blind Spots of Model-Based Evaluation Metrics for Text Generation
  126. When Do Decompositions Help for Machine Reading?
  127. DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization
  128. Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities
  129. Benchmarking Spatial Relationships in Text-to-Image Generation
  130. DocAsRef: An Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely
  131. Language Modeling with Latent Situations
  132. PLUE: Language Understanding Evaluation Benchmark for Privacy Policies in English
  133. Identifying latent distances with Finslerian geometry
  134. Enhancing Task Bot Engagement with Synthesized Open-Domain Dialog
  135. CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context
  136. Multi-head Uncertainty Inference for Adversarial Attack Detection
  137. Calibrating Deep Neural Networks using Explicit Regularisation and Dynamic Data Pruning
  138. (QA)2: Question Answering with Questionable Assumptions
  139. Defending Against Disinformation Attacks in Open-Domain Question Answering
  140. Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation
  141. Are Deep Neural Networks SMARTer than Second Graders?
  142. Dynamic Molecular Graph-based Implementation for Biophysical Properties Prediction
  143. Multi-Reference Image Super-Resolution: A Posterior Fusion Approach
  144. Using Machine Learning to Determine Morphologies of z<1 AGN Host Galaxies in the Hyper Suprime-Cam Wide Survey
  145. Texture Representation via Analysis and Synthesis with Generative Adversarial Networks
  146. Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
  147. Benchmarking person re-identification datasets and approaches for practical real-world implementations
  148. Continual Mean Estimation Under User-Level Privacy
  149. Flareon: Stealthy any2any Backdoor Injection via Poisoned Augmentation
  150. Unified Framework for Histopathology Image Augmentation and Classification via Generative Models
  151. Sophisticated deep learning with on-chip optical diffractive tensor processing
  152. Insights into undergraduate pathways using course load analytics
  153. Data Augmentation on Graphs: A Technical Survey
  154. Learning Subgrid-scale Models with Neural Ordinary Differential Equations
  155. Distributional Robustness Bounds Generalization Errors
  156. Uncertainty Quantification of MLE for Entity Ranking with Covariates
  157. Beyond Surrogate Modeling: Learning the Local Volatility Via Shape Constraints
  158. BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics
  159. Domain Generalization with Correlated Style Uncertainty
  160. MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency
  161. Future Sight: Dynamic Story Generation with Large Pretrained Language Models
  162. Dialog2API: Task-Oriented Dialogue with API Description and Example Programs
  163. Robust and Resource-efficient Machine Learning Aided Viewport Prediction in Virtual Reality
  164. AnyTOD: A Programmable Task-Oriented Dialog System
  165. AI applications in forest monitoring need remote sensing benchmark datasets
  166. A Generalized Variable Importance Metric and Estimator for Black Box Machine Learning Models
  167. Improving the Robustness of Summarization Models by Detecting and Removing Input Noise
  168. Bandit approach to conflict-free multi-agent Q-learning in view of photonic implementation
  169. Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC
  170. Input Normalized Stochastic Gradient Descent Training of Deep Neural Networks
  171. Variational Factorization Machines for Preference Elicitation in Large-Scale Recommender Systems