mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 20 Oct 2023

257 papers

  1. Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt EditingLLM reasoning → Prompting and chain-of-thought reasoning
  2. FABULA: Intelligence Report Generation Using Retrieval-Augmented Narrative ConstructionRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  3. GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?Diffusion models → Flow matching, time series and science
  4. Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative ModelsLLM safety and security → Backdoor and data poisoning attacks
  5. Specific versus General Principles for Constitutional AILLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  6. Fundamental Limits of Membership Inference Attacks on Machine Learning ModelsLLM safety and security → Membership inference attacks
  7. Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader ImagesKnowledge distillation → General knowledge distillation methods
  8. TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  9. Enhancing Abstractiveness of Summarization Models through Calibrated DistillationKnowledge distillation → Knowledge distillation for LLMs
  10. Localizing and Editing Knowledge in Text-to-Image Generative ModelsDiffusion models → Image generation, text-to-image and editing
  11. Optimizing Retrieval-augmented Reader Models via Token EliminationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  12. Contrastive Preference Learning: Learning from Human Feedback without RLLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  13. MarineGPT: Unlocking Secrets of Ocean to the PublicMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  14. The History and Risks of Reinforcement Learning and Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  15. Why Can Large Language Models Generate Correct Chain-of-Thoughts?LLM reasoning → Prompting and chain-of-thought reasoning
  16. Retrieval-Augmented Neural Response Generation Using Logical Reasoning and Relevance ScoringLLM reasoning → Knowledge- and tool-augmented reasoning +1
  17. Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  18. ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip ConnectionDiffusion models → Diffusion foundations and sampling
  19. Teaching Language Models to Self-Improve through Interactive DemonstrationsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  20. Improving Question Generation with Multi-level Content PlanningLLM reasoning → Knowledge- and tool-augmented reasoning
  21. DistillCSE: Distilled Contrastive Learning for Sentence EmbeddingsKnowledge distillation → Knowledge distillation for LLMs
  22. Benchmarking Sequential Visual Input Reasoning and Prediction in Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  23. Self-Consistency of Large Language Models under AmbiguityLLM reasoning → Test-time compute and efficient thinking
  24. GenDistiller: Distilling Pre-trained Language Models based on Generative ModelsKnowledge distillation → Knowledge distillation for LLMs
  25. Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language ModelsKnowledge distillation → Knowledge distillation for LLMs
  26. POSQA: Probe the World Models of LLMs with Size ComparisonsWorld models → World models for language agents
  27. Tuna: Instruction Tuning using Feedback from Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  28. SILC: Improving Vision Language Pretraining with Self-DistillationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  29. Democratizing Reasoning Ability: Tailored Learning from Large Language ModelLLM reasoning → Prompting and chain-of-thought reasoning
  30. Combining Policy Gradient and Safety-Based Control for Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
  31. CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-trainingMultimodal LLMs / vision-language models → Medical vision-language models
  32. DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model StatisticsDiffusion models → Diffusion foundations and sampling
  33. Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open WorldsLLM agents and tool use → Multimodal and embodied agents
  34. Single-pixel 3D imaging based on fusion temporal data of single photon detector and millimeter-wave radar
  35. Enhancing the machine vision performance with multi-spectral light sources
  36. The Impact of Performance Expectancy, Workload, Risk, and Satisfaction on Trust in ChatGPT: Cross-sectional Survey Analysis
  37. Can We Trust the Similarity Measurement in Federated Learning?
  38. Semantic Modelling of Organizational Knowledge as a Basis for Enterprise Data Governance 4.0 -- Application to a Unified Clinical Data Model
  39. She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models
  40. WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models
  41. AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models
  42. Towards Detecting Contextual Real-Time Toxicity for In-Game Chat
  43. A Sparse Bayesian Learning for Diagnosis of Nonstationary and Spatially Correlated Faults with Application to Multistation Assembly Systems
  44. Towards Subject Agnostic Affective Emotion Recognition
  45. Deep Learning Approaches for Dynamic Mechanical Analysis of Viscoelastic Fiber Composites
  46. Physics-Informed Graph Convolutional Networks: Towards a generalized framework for complex geometries
  47. An Event based Prediction Suffix Tree
  48. Reference-based Restoration of Digitized Analog Videotapes
  49. ARNIQA: Learning Distortion Manifold for Image Quality Assessment
  50. DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset
  51. Bounding the Worst-class Error: A Boosting Approach
  52. A Novel Transfer Learning Method Utilizing Acoustic and Vibration Signals for Rotating Machinery Fault Diagnosis
  53. Weighted Joint Maximum Mean Discrepancy Enabled Multi-Source-Multi-Target Unsupervised Domain Adaptation Fault Diagnosis
  54. Interpretable Deep Reinforcement Learning for Optimizing Heterogeneous Energy Storage Systems
  55. Towards equilibrium molecular conformation generation with GFlowNets
  56. Dance Your Latents: Consistent Dance Generation through Spatial-temporal Subspace Attention Guided by Motion Flow
  57. Competitive Advantage Attacks to Decentralized Federated Learning
  58. Not all Fake News is Written: A Dataset and Analysis of Misleading Video Headlines
  59. Implications of Annotation Artifacts in Edge Probing Test Datasets
  60. Exponential weight averaging as damped harmonic motion
  61. Gradual Domain Adaptation: Theory and Algorithms
  62. Ecologically Valid Explanations for Label Variation in NLI
  63. A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brains
  64. Spectral-Aware Augmentation for Enhanced Graph Representation Learning
  65. Fast hyperboloid decision tree algorithms
  66. CNN-based Prediction of Partition Path for VVC Fast Inter Partitioning Using Motion Fields
  67. Foundation Model's Embedded Representations May Detect Distribution Shift
  68. Universal Representation of Permutation-Invariant Functions on Vectors and Tensors
  69. Plausibility Processing in Transformer Language Models: Focusing on the Role of Attention Heads in GPT
  70. Adversarial Attacks on Fairness of Graph Neural Networks
  71. Geometric Learning with Positively Decomposable Kernels
  72. FERI: A Multitask-based Fairness Achieving Algorithm with Applications to Fair Organ Transplantation
  73. FATA-Trans: Field And Time-Aware Transformer for Sequential Tabular Data
  74. Yet Another Model for Arabic Dialect Identification
  75. A Better Match for Drivers and Riders: Reinforcement Learning at Lyft
  76. Enhanced Low-Dimensional Sensing Mapless Navigation of Terrestrial Mobile Robots Using Double Deep Reinforcement Learning Techniques
  77. Learning to (Learn at Test Time)
  78. RoseNet: Predicting Energy Metrics of Double InDel Mutants Using Deep Learning
  79. Normalizing flow-based deep variational Bayesian network for seismic multi-hazards and impacts estimation from InSAR imagery
  80. Improving Molecular Properties Prediction Through Latent Space Fusion
  81. Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks
  82. A Unified View of Evaluation Metrics for Structured Prediction
  83. Comparative Analysis of Machine Learning Algorithms for Solar Irradiance Forecasting in Smart Grids
  84. Enhancing Illicit Activity Detection using XAI: A Multimodal Graph-LLM Framework
  85. How Much Consistency Is Your Accuracy Worth?
  86. Seq2seq is All You Need for Coreference Resolution
  87. Copyright Violations and Large Language Models
  88. Compositional Deep Probabilistic Models of DNA Encoded Libraries
  89. PACE: Human and Camera Motion Estimation from in-the-wild Videos
  90. Graph AI in Medicine
  91. U-BEV: Height-aware Bird's-Eye-View Segmentation and Neural Map-based Relocalization
  92. Learning Interatomic Potentials at Multiple Scales
  93. Evaluating sleep-stage classification: how age and early-late sleep affects classification performance
  94. ALDi: Quantifying the Arabic Level of Dialectness of Text
  95. FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning
  96. Inter-Scale Dependency Modeling for Skin Lesion Segmentation with Transformer-based Networks
  97. Enhancing drug and cell line representations via contrastive learning for improved anti-cancer drug prioritization
  98. Neural-Base Music Generation for Intelligence Duplication
  99. Exploring Linguistic Probes for Morphological Generalization
  100. CAPIVARA: Cost-Efficient Approach for Improving Multilingual CLIP Performance on Low-Resource Languages
All 257
  1. Towards Realistic Mechanisms That Incentivize Federated Participation and Contribution
  2. Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models
  3. Information Value: Measuring Utterance Predictability as Distance from Plausible Alternatives
  4. On Synthetic Data for Back Translation
  5. Using Human-like Mechanism to Weaken Effect of Pre-training Weight Bias in Face-Recognition Convolutional Neural Network
  6. StereoMap: Quantifying the Awareness of Human-like Stereotypes in Large Language Models
  7. Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models
  8. ManifoldNeRF: View-dependent Image Feature Supervision for Few-shot Neural Radiance Fields
  9. Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis
  10. Explainable Depression Symptom Detection in Social Media
  11. Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification
  12. Benchmarking and Improving Text-to-SQL Generation under Ambiguity
  13. An experimental study for early diagnosing Parkinson's disease using machine learning
  14. Optimal Transport for Measures with Noisy Tree Metric
  15. BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues
  16. Deep-Learning-based Change Detection with Spaceborne Hyperspectral PRISMA data
  17. What you see is what you get: Experience ranking with deep neural dataset-to-dataset similarity for topological localisation
  18. Bridging Information-Theoretic and Geometric Compression in Language Models
  19. Semi-supervised multimodal coreference resolution in image narrations
  20. Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning
  21. Hunayn: Elevating Translation Beyond the Literal
  22. Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making
  23. Analyzing the contribution of different passively collected data to predict Stress and Depression
  24. MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark
  25. FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer
  26. Skin Lesion Segmentation Improved by Transformer-based Networks with Inter-scale Dependency Modeling
  27. Learning with Unmasked Tokens Drives Stronger Vision Learners
  28. ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction
  29. Simultaneous Machine Translation with Tailored Reference
  30. POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization
  31. Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering
  32. SPARE: A Single-Pass Neural Model for Relational Databases
  33. Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery
  34. Semantic Decomposition of Question and SQL for Text-to-SQL Parsing
  35. Progressive Dual Priori Network for Generalized Breast Tumor Segmentation
  36. Boosting Generalization with Adaptive Style Techniques for Fingerprint Liveness Detection
  37. Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
  38. A Simple Baseline for Knowledge-Based Visual Question Answering
  39. Reward Shaping for Happier Autonomous Cyber Security Agents
  40. Cache & Distil: Optimising API Calls to Large Language Models
  41. On sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery
  42. ROSS: Radar Off-road Semantic Segmentation
  43. Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
  44. The Perils & Promises of Fact-checking with Large Language Models
  45. Towards Understanding Sycophancy in Language Models
  46. A Diachronic Perspective on User Trust in AI under Uncertainty
  47. Positive-Unlabeled Node Classification with Structure-aware Graph Learning
  48. Technical Report for ICCV 2023 Visual Continual Learning Challenge: Continuous Test-time Adaptation for Semantic Segmentation
  49. Controlled Randomness Improves the Performance of Transformer Models
  50. Variational measurement-based quantum computation for generative modeling
  51. RaceLens: A Machine Intelligence-Based Application for Racing Photo Analysis
  52. Explaining Interactions Between Text Spans
  53. Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation
  54. Analogical Proportions and Creativity: A Preliminary Study
  55. Feature Selection and Hyperparameter Fine-tuning in Artificial Neural Networks for Wood Quality Classification
  56. Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning
  57. Application of deep learning for livestock behaviour recognition: A systematic literature review
  58. A review of individual tree crown detection and delineation from optical remote sensing images
  59. Personalized identification, prediction, and stimulation of neural oscillations via data-driven models of epileptic network dynamics
  60. Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
  61. An Analysis of Dα seeding for k-means
  62. Ask Language Model to Clean Your Noisy Translation Data
  63. Stable Nonconvex-Nonconcave Training via Linear Interpolation
  64. Correspondence learning between morphologically different robots via task demonstrations
  65. Two-Stage Triplet Loss Training with Curriculum Augmentation for Audio-Visual Retrieval
  66. Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning
  67. Superpixel Semantics Representation and Pre-training for Vision-Language Task
  68. The Past, Present, and Future of Typological Databases in NLP
  69. Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption
  70. Y-Diagonal Couplings: Approximating Posteriors with Conditional Wasserstein Distances
  71. HRTF Interpolation using a Spherical Neural Process Meta-Learner
  72. FLTracer: Accurate Poisoning Attack Provenance in Federated Learning
  73. Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations
  74. Towards Enhancing Relational Rules for Knowledge Graph Link Prediction
  75. Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading
  76. Definition-independent Formalization of Soundscapes: Towards a Formal Methodology
  77. BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model
  78. Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability
  79. OpenAnnotate3D: Open-Vocabulary Auto-Labeling System for Multi-modal 3D Data
  80. Equivariant Deep Weight Space Alignment
  81. RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup
  82. Optimal Best Arm Identification with Fixed Confidence in Restless Bandits
  83. Learning Successor Features with Distributed Hebbian Temporal Memory
  84. Music Augmentation and Denoising For Peak-Based Audio Fingerprinting
  85. Assumption violations in causal discovery and the robustness of score matching
  86. Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing
  87. Accelerated sparse Kernel Spectral Clustering for large scale data clustering problems
  88. APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
  89. ScalableMap: Scalable Map Learning for Online Long-Range Vectorized HD Map Construction
  90. A Human-Robot Mutual Learning System with Affect-Grounded Language Acquisition and Differential Outcomes Training
  91. Single-view 3D reconstruction via inverse procedural modeling
  92. SigFormer: Signature Transformers for Deep Hedging
  93. EASTER: Embedding Aggregation-based Heterogeneous Models Training in Vertical Federated Learning
  94. PSGText: Stroke-Guided Scene Text Editing with PSP Module
  95. Dissecting Causal Biases
  96. Towards General Error Diagnosis via Behavioral Testing in Machine Translation
  97. Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation
  98. Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos
  99. EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View
  100. DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data
  101. Analyzing Cognitive Plausibility of Subword Tokenization
  102. NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding
  103. DeepFracture: A Generative Approach for Predicting Brittle Fractures with Neural Discrete Representation Learning
  104. Challenges and Contributing Factors in the Utilization of Large Language Models (LLMs)
  105. Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets
  106. FLAIR: a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery
  107. Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting
  108. CylinderTag: An Accurate and Flexible Marker for Cylinder-Shape Objects Pose Estimation Based on Projective Invariants
  109. Coarse-to-Fine Dual Encoders are Better Frame Identification Learners
  110. Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models
  111. Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models
  112. Non-Negative Spherical Relaxations for Universe-Free Multi-Matching and Clustering
  113. Test-Time Self-Adaptive Small Language Models for Question Answering
  114. Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting
  115. PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning
  116. Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks
  117. Interpreting Indirect Answers to Yes-No Questions in Multiple Languages
  118. SALMONN: Towards Generic Hearing Abilities for Large Language Models
  119. Unified Pretraining for Recommendation via Task Hypergraphs
  120. Learning Recurrent Models with Temporally Local Rules
  121. pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning
  122. Pathologist-Like Explanations Unveiled: an Explainable Deep Learning System for White Blood Cell Classification
  123. InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution
  124. Meta-learning of Physics-informed Neural Networks for Efficiently Solving Newly Given PDEs
  125. An Exploratory Study on Simulated Annealing for Feature Selection in Learning-to-Rank
  126. On the Language Encoder of Contrastive Cross-modal Models
  127. MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model
  128. UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene
  129. A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation
  130. DIG-MILP: a Deep Instance Generator for Mixed-Integer Linear Programming with Feasibility Guarantee
  131. Domain-specific optimization and diverse evaluation of self-supervised models for histopathology
  132. ManiCast: Collaborative Manipulation with Cost-Aware Human Forecasting
  133. Visual Grounding Helps Learn Word Meanings in Low-Data Regimes
  134. Knowledge Graph Context-Enhanced Diversified Recommendation
  135. Diagnosis-oriented Medical Image Compression with Efficient Transfer Learning
  136. TempGNN: Temporal Graph Neural Networks for Dynamic Session-Based Recommendations
  137. FLEE-GNN: A Federated Learning System for Edge-Enhanced Graph Neural Network in Analyzing Geospatial Resilience of Multicommodity Food Flows
  138. Anomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Approaches
  139. Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking
  140. Transparency challenges in policy evaluation with causal machine learning -- improving usability and accountability
  141. An Efficient Federated Learning Framework for Training Semantic Communication System
  142. Auxiliary Features-Guided Super Resolution for Monte Carlo Rendering
  143. Interaction Screening and Pseudolikelihood Approaches for Tensor Learning in Ising Models
  144. Multi-level Contrastive Learning for Script-based Character Understanding
  145. Absolute Policy Optimization
  146. The Less the Merrier? Investigating Language Representation in Multilingual Models
  147. ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
  148. Enhancing Zero-Shot Crypto Sentiment with Fine-tuned Language Model and Prompt Engineering
  149. Scalable Neural Network Kernels
  150. Equivariant Transformer is all you need
  151. Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
  152. HierCas: Hierarchical Temporal Graph Attention Networks for Popularity Prediction in Information Cascades
  153. PTSR: Patch Translator for Image Super-Resolution
  154. Zone Evaluation: Revealing Spatial Bias in Object Detection
  155. MultiCoNER v2: a Large Multilingual dataset for Fine-grained and Noisy Named Entity Recognition
  156. Primacy Effect of ChatGPT
  157. Identification of Abnormality in Maize Plants From UAV Images Using Deep Learning Approaches