mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 17 Oct 2023

253 papers

  1. Compositional preference models for aligning LMsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  2. Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter MergingLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  3. Group Preference Optimization: Few-Shot Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  4. GenEval: An Object-Focused Framework for Evaluating Text-to-Image AlignmentDiffusion models → Image generation, text-to-image and editing
  5. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionRetrieval-augmented generation → RAG robustness and adaptive retrieval
  6. Program Translation via Code DistillationMechanistic interpretability → Knowledge and representations inside LLMs
  7. Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4VMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  8. Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context LearningLLM safety and security → Membership inference attacks
  9. MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation CoefficientKnowledge distillation → Detection and dense prediction distillation
  10. Elucidating The Design Space of Classifier-Guided Diffusion GenerationDiffusion models → Diffusion foundations and sampling
  11. Watermarking LLMs with Weight QuantizationLLM safety and security → Watermarking generated content and models
  12. KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  13. Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-ExplanationsLLM reasoning → Reasoning benchmarks and evaluation
  14. On the Effectiveness of Creating Conversational Agent Personalities Through PromptingLLM agents and tool use → Social simulation and multi-agent debate
  15. BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian InferenceDiffusion models → Diffusion foundations and sampling
  16. Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  17. Accelerating Scalable Graph Neural Network Inference with Node-Adaptive PropagationEfficient LLM inference and serving → Early exit and edge inference
  18. ClarifyGPT: Empowering LLM-based Code Generation with Intention ClarificationWorld models → World models for language agents
  19. IoTGeM: Generalizable Models for Behaviour-Based IoT Attack Detection
  20. Neural Packing: from Visual Sensing to Reinforcement Learning
  21. Exploration of the Assessment for AVP Algorithm Training in Underground Parking Garages Simulation Scenario
  22. Algorithmic Robustness
  23. Data Drift Monitoring for Log Anomaly Detection Pipelines
  24. Audio-AdapterFusion: A Task-ID-free Approach for Efficient and Non-Destructive Multi-task Speech Recognition
  25. Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament
  26. Generative error correction for code-switching speech recognition using large language models
  27. H2O Open Ecosystem for State-of-the-art Large Language Models
  28. An Optimistic-Robust Approach for Dynamic Positioning of Omnichannel Inventories
  29. Holistic Parking Slot Detection with Polygon-Shaped Representations
  30. Learn Your Tokens: Word-Pooled Tokenization for Language Modeling
  31. High-Resolution Building and Road Detection from Sentinel-2
  32. Evidence of interrelated cognitive-like capabilities in large language models: Indications of artificial general intelligence or achievement?
  33. Learning a Hierarchical Planner from Humans in Multiple Generations
  34. Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks
  35. In defense of parameter sharing for model-compression
  36. Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance
  37. Classification of Safety Driver Attention During Autonomous Vehicle Operation
  38. TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification
  39. DIAR: Deep Image Alignment and Reconstruction using Swin Transformers
  40. Language Models as Zero-Shot Trajectory Generators
  41. Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors
  42. The Efficacy of Transformer-based Adversarial Attacks in Security Domains
  43. WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
  44. Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning
  45. Automated Evaluation of Personalized Text Generation using Large Language Models
  46. Predicting Human Perceptions of Robot Performance During Navigation Tasks
  47. Eliciting Human Preferences with Language Models
  48. BasahaCorpus: An Expanded Linguistic Resource for Readability Assessment in Central Philippine Languages
  49. Studying the Effects of Sex-related Differences on Brain Age Prediction using brain MR Imaging
  50. Alexpaca: Learning Factual Clarification Question Generation Without Examples
  51. When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting
  52. Partially Observable Stochastic Games with Neural Perception Mechanisms
  53. Online Algorithms with Uncertainty-Quantified Predictions
  54. Integrating 3D City Data through Knowledge Graphs
  55. Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
  56. Bias and Error Mitigation in Software-Generated Data: An Advanced Search and Optimization Framework Leveraging Generative Code Models
  57. MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning
  58. Learning Lens Blur Fields
  59. Multi-stage Large Language Model Correction for Speech Recognition
  60. Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach
  61. Thin and Deep Gaussian Processes
  62. Automatic News Summerization
  63. Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability
  64. Value-Biased Maximum Likelihood Estimation for Model-based Reinforcement Learning in Discounted Linear MDPs
  65. CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations
  66. End-to-End real time tracking of children's reading with pointer network
  67. Enhancing Plasticity for First Session Adaptation Continual Learning
  68. Contracting Tsetlin Machine with Absorbing Automata
  69. Whole-brain radiomics for clustered federated personalization in brain tumor segmentation
  70. On the Temperature of Bayesian Graph Neural Networks for Conformal Prediction
  71. ASP: Automatic Selection of Proxy dataset for efficient AutoML
  72. A Robust Deep Learning System for Motor Bearing Fault Detection: Leveraging Multiple Learning Strategies and a Novel Double Loss Function
  73. Tracking and Mapping in Medical Computer Vision: A Review
  74. VeRA: Vector-based Random Matrix Adaptation
  75. BitNet: Scaling 1-bit Transformers for Large Language Models
  76. Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective
  77. Explaining Deep Neural Networks for Bearing Fault Detection with Vibration Concepts
  78. DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis
  79. 4K4D: Real-Time 4D View Synthesis at 4K Resolution
  80. Functional Invariants to Watermark Large Transformers
  81. Stochastic Quantum Sampling for Non-Logconcave Distributions and Estimating Partition Functions
  82. EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
  83. From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
  84. Identifying Interpretable Visual Features in Artificial and Biological Neural Systems
  85. An Empirical Study of Translation Hypothesis Ensembling with Large Language Models
  86. Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
  87. Revisiting Map Relations for Unsupervised Non-Rigid Shape Matching
  88. VcT: Visual change Transformer for Remote Sensing Image Change Detection
  89. LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks
  90. Group-blind optimal transport to group parity and its constrained variants
  91. Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
  92. Neural Attention: Enhancing QKV Calculation in Self-Attention Mechanism with Neural Networks
  93. Towards Automatic Satellite Images Captions Generation Using Large Language Models
  94. Risk Estimation in a Markov Cost Process: Lower and Upper Bounds
  95. A voxel-level approach to brain age prediction: A method to assess regional brain aging
  96. Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles
  97. Faster Algorithms for Generalized Mean Densest Subgraph Problem
  98. DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversations
  99. VECHR: A Dataset for Explainable and Robust Classification of Vulnerability Type in the European Court of Human Rights
  100. Lie Group Decompositions for Equivariant Neural Networks
All 253
  1. Disentangling the Linguistic Competence of Privacy-Preserving BERT
  2. Enhancing Neural Machine Translation with Semantic Units
  3. Towards Generalizable Multi-Camera 3D Object Detection via Perspective Debiasing
  4. The effect of stemming and lemmatization on Portuguese fake news text classification
  5. Dual Cognitive Architecture: Incorporating Biases and Multi-Memory Systems for Lifelong Learning
  6. Contextualized Machine Learning
  7. Reinforcement learning with non-ergodic reward increments: robustness via ergodicity transformations
  8. Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
  9. Key Point-based Orientation Estimation of Strawberries for Robotic Fruit Picking
  10. Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
  11. Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation
  12. Utilising a Large Language Model to Annotate Subject Metadata: A Case Study in an Australian National Research Data Catalogue
  13. Multi Self-supervised Pre-fine-tuned Transformer Fusion for Better Intelligent Transportation Detection
  14. MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games
  15. QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering
  16. CorrTalk: Correlation Between Hierarchical Speech and Facial Activity Variances for 3D Animation
  17. An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent
  18. Assessing the Causal Impact of Humanitarian Aid on Food Security
  19. Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior
  20. ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation
  21. Self-supervision meets kernel graph neural models: From architecture to augmentations
  22. Video Super-Resolution Using a Grouped Residual in Residual Network
  23. xMEN: A Modular Toolkit for Cross-Lingual Medical Entity Normalization
  24. Emulating Human Cognitive Processes for Expert-Level Medical Question-Answering with Large Language Models
  25. Image Compression using only Attention based Neural Networks
  26. Utilizing Weak Supervision To Generate Indonesian Conservation Dataset
  27. An empirical study of automatic wildlife detection using drone thermal imaging and object detection
  28. Gromov-Wasserstein-like Distances in the Gaussian Mixture Models Space
  29. Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges
  30. Leveraging Large Language Model for Automatic Evolving of Industrial Data-Centric R&D Cycle
  31. CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
  32. Query2Triple: Unified Query Encoding for Answering Diverse Complex Queries over Knowledge Graphs
  33. Entity Matching using Large Language Models
  34. LiDAR-based 4D Occupancy Completion and Forecasting
  35. Learning to Sample Better
  36. Zipformer: A faster and better encoder for automatic speech recognition
  37. RealBehavior: A Framework for Faithfully Characterizing Foundation Models' Human-like Behavior Mechanisms
  38. Innovative Methods for Non-Destructive Inspection of Handwritten Documents
  39. Understanding Fairness Surrogate Functions in Algorithmic Fairness
  40. Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identification
  41. Improving Video Deepfake Detection: A DCT-Based Approach with Patch-Level Analysis
  42. Federated Learning with Nonvacuous Generalisation Bounds
  43. EEG motor imagery decoding: A framework for comparative analysis with channel attention mechanisms
  44. Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding
  45. Adversarial Bandits with Multi-User Delayed Feedback: Theory and Application
  46. Efficiently Visualizing Large Graphs
  47. Sparse Multi-Object Render-and-Compare
  48. FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stack
  49. Knowledge Extraction and Distillation from Large-Scale Image-Text Colonoscopy Records Leveraging Large Language and Vision Models
  50. MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection
  51. ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing
  52. Serenade: A Model for Human-in-the-loop Automatic Chord Estimation
  53. IMTLab: An Open-Source Platform for Building, Evaluating, and Diagnosing Interactive Machine Translation Systems
  54. Accurate prediction of international trade flows: Leveraging knowledge graphs and their embeddings
  55. Probing the Creativity of Large Language Models: Can models produce divergent semantic association?
  56. Causal discovery using dynamically requested knowledge
  57. Unsupervised Pre-Training Using Masked Autoencoders for ECG Analysis
  58. Uncovering wall-shear stress dynamics from neural-network enhanced fluid flow measurements
  59. The Quo Vadis of the Relationship between Language and Large Language Models
  60. Development of a high-resolution indoor radon map using a new machine learning-based probabilistic model and German radon survey data
  61. Long-form Simultaneous Speech Translation: Thesis Proposal
  62. Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control
  63. Non-parametric Conditional Independence Testing for Mixed Continuous-Categorical Variables: A Novel Method and Numerical Evaluation
  64. FROST: Towards Energy-efficient AI-on-5G Platforms -- A GPU Power Capping Evaluation
  65. Topological Expressivity of ReLU Neural Networks
  66. Sensitivity-Aware Amortized Bayesian Inference
  67. USDC: Unified Static and Dynamic Compression for Visual Transformer
  68. Super resolution of histopathological frozen sections via deep learning preserving tissue structure
  69. Minimally Informed Linear Discriminant Analysis: training an LDA model with unlabelled data
  70. 3D Structure-guided Network for Tooth Alignment in 2D Photograph
  71. Generalizability of CNN Architectures for Face Morph Presentation Attack
  72. Local Lipschitz Constant Computation of ReLU-FNNs: Upper Bound Computation with Exactness Verification
  73. Refining Latent Representations: A Generative SSL Approach for Heterogeneous Graph Learning
  74. Experimenting AI Technologies for Disinformation Combat: the IDMO Project
  75. Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads
  76. Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs
  77. SODA: Robust Training of Test-Time Data Adaptors
  78. DORec: Decomposed Object Reconstruction and Segmentation Utilizing 2D Self-Supervised Features
  79. MeKB-Rec: Personal Knowledge Graph Learning for Cross-Domain Recommendation
  80. Feature Pyramid biLSTM: Using Smartphone Sensors for Transportation Mode Detection
  81. Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models
  82. Enhancing Signed Graph Neural Networks through Curriculum-Based Training
  83. Multi-omics Sampling-based Graph Transformer for Synthetic Lethality Prediction
  84. Understanding writing style in social media with a supervised contrastively pre-trained transformer
  85. United We Stand: Using Epoch-wise Agreement of Ensembles to Combat Overfit
  86. Sim-to-Real Transfer of Adaptive Control Parameters for AUV Stabilization under Current Disturbance
  87. VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System
  88. Cheap Bootstrap for Fast Uncertainty Quantification of Stochastic Gradient Descent
  89. Privacy-Preserving Graph Embedding based on Local Differential Privacy
  90. Causal Feature Selection via Transfer Entropy
  91. Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
  92. k-t CLAIR: Self-Consistency Guided Multi-Prior Learning for Dynamic Parallel MR Image Reconstruction
  93. Nonet at SemEval-2023 Task 6: Methodologies for Legal Evaluation
  94. Understanding Contrastive Learning via Distributionally Robust Optimization
  95. Fast Graph Condensation with Structure-based Neural Tangent Kernel
  96. Spoofing Attack Detection in the Physical Layer with Robustness to User Movement
  97. Co-Learning Semantic-aware Unsupervised Segmentation for Pathological Image Registration
  98. Radio Map Estimation: Empirical Validation and Analysis
  99. Lyricist-Singer Entropy Affects Lyric-Lyricist Classification Performance
  100. Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters
  101. Core Building Blocks: Next Gen Geo Spatial GPT Application
  102. Matrix Compression via Randomized Low Rank and Low Precision Factorization
  103. Exploring Automatic Evaluation Methods based on a Decoder-based LLM for Text Generation
  104. SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning
  105. Compatible Transformer for Irregularly Sampled Multivariate Time Series
  106. Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
  107. Pure Exploration in Asynchronous Federated Bandits
  108. Hyperspectral In-Memory Computing with Optical Frequency Combs and Programmable Optical Memories
  109. From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling
  110. Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition
  111. LPFormer: An Adaptive Graph Transformer for Link Prediction
  112. Correction Focused Language Model Training for Speech Recognition
  113. Spatially-resolved hyperlocal weather prediction and anomaly detection using IoT sensor networks and machine learning techniques
  114. Mixed membership estimation for categorical data with weighted responses
  115. Why Do Students Drop Out? University Dropout Prediction and Associated Factor Analysis Using Machine Learning Techniques
  116. Latent class analysis with weighted responses
  117. Instructive Dialogue Summarization with Query Aggregations
  118. Exact nonlinear state estimation
  119. NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning
  120. Context-Aware Meta-Learning
  121. Deep Learning based Spatially Dependent Acoustical Properties Recovery
  122. EXMODD: An EXplanatory Multimodal Open-Domain Dialogue dataset
  123. The neural network models with delays for solving absolute value equations
  124. MRI brain tumor segmentation using informative feature vectors and kernel dictionary learning
  125. Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning
  126. Enhancing Deep Neural Network Training Efficiency and Performance through Linear Prediction
  127. Medical Image Segmentation via Sparse Coding Decoder
  128. Computing the optimal keyboard through a geometric analysis of the English language
  129. A State-Vector Framework for Dataset Effects
  130. A Local Graph Limits Perspective on Sampling-Based GNNs
  131. Restricted Tweedie Stochastic Block Models
  132. FusionU-Net: U-Net with Enhanced Skip Connection for Pathology Image Segmentation
  133. Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control
  134. Multi-point Feedback of Bandit Convex Optimization with Hard Constraints
  135. TEQ: Trainable Equivalent Transformation for Quantization of LLMs
  136. Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning
  137. UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models
  138. MASON-NLP at eRisk 2023: Deep Learning-Based Detection of Depression Symptoms from Social Media Texts
  139. Fast and Simple Spectral Clustering in Theory and Practice
  140. Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti
  141. Enhanced Transformer Architecture for Natural Language Processing
  142. Using Audio Data to Facilitate Depression Risk Assessment in Primary Health Care
  143. Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio
  144. Intelligent Software Tooling for Improving Software Development
  145. NuclearQA: A Human-Made Benchmark for Language Models for the Nuclear Domain
  146. Towards Training-free Open-world Segmentation via Image Prompt Foundation Models
  147. Machine Learning in the Quantum Age: Quantum vs. Classical Support Vector Machines
  148. Heterogenous Memory Augmented Neural Networks
  149. Unlocking Emergent Modularity in Large Language Models
  150. Surrogate Active Subspaces for Jump-Discontinuous Functions
  151. Emergent AI-Assisted Discourse: Case Study of a Second Language Writer Authoring with ChatGPT
  152. Instilling Inductive Biases with Subnetworks
  153. Analyzing Modularity Maximization in Approximation, Heuristic, and Graph Neural Network Algorithms for Community Detection