mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 31 Oct 2023

261 papers

  1. Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving +1
  2. Robust Safety Classifier for Large Language Models: Adversarial Prompt ShieldLLM safety and security → Safety alignment, refusal and guardrails
  3. The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  4. Towards A Natural Language Interface for Flexible Multi-Agent Task AssignmentLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. A Tractable Inference Perspective of Offline RLOffline RL and imitation learning from data → Offline RL algorithms
  6. Diversity and Diffusion: Observations on Synthetic Image Distributions with Stable DiffusionDiffusion models → Image generation, text-to-image and editing
  7. Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  8. SEINE: Short-to-Long Video Diffusion Model for Generative Transition and PredictionDiffusion models → Video generation
  9. Learning From Mistakes Makes LLM Better ReasonerLLM reasoning → Mathematical reasoning
  10. Offline RL with Observation Histories: Analyzing and Improving Sample ComplexityOffline RL and imitation learning from data → Offline RL algorithms
  11. Addressing Limitations of State-Aware Imitation Learning for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  12. LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70BLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  13. Diffusion Reconstruction of Ultrasound Images with Informative UncertaintyDiffusion models → Medical imaging and segmentation
  14. Learning Lyapunov-Stable Polynomial Dynamical Systems through ImitationOffline RL and imitation learning from data → Imitation learning methods
  15. Unleashing the Power of Pre-trained Language Models for Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  16. Predictive Control for Autonomous Driving with Uncertain, Multi-modal PredictionsEnd-to-end autonomous driving → Reinforcement learning for driving
  17. CapsFusion: Rethinking Image-Text Data at ScaleLLM reasoning → Multimodal reasoning +1
  18. Leveraging Word Guessing Games to Assess the Intelligence of Large Language ModelsLLM agents and tool use → Reinforcement learning for LLM agents
  19. A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in ConversationsKnowledge distillation → Multimodal distillation
  20. Generate What You Prefer: Reshaping Sequential Recommendation via Guided DiffusionDiffusion models → Diffusion recommenders
  21. A Survey on Federated Unlearning: Challenges, Methods, and Future DirectionsLLM safety and security → Federated unlearning and poisoning
  22. Enhancing the Spatial Awareness Capability of Multi-Modal Large Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  23. AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent InteractionLLM agents and tool use → Social simulation and multi-agent debate
  24. Class Incremental Learning with Pre-trained Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  25. PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality DetectionLLM reasoning → Reasoning benchmarks and evaluation
  26. Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and ObservationsLLM reasoning → Mathematical reasoning
  27. A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental InteractionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  28. DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and TextLLM reasoning → Knowledge- and tool-augmented reasoning
  29. Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched PromptsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  30. Multi-Agent Consensus Seeking via Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  31. Unlearn What You Want to Forget: Efficient Unlearning for LLMsLLM safety and security → Machine unlearning
  32. Synthesizing Diabetic Foot Ulcer Images with Diffusion ModelDiffusion models → Medical imaging and segmentation
  33. The Missing U for Efficient Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  34. A Synthetic Modal Generation of Additive Manufacturing Roughness Surfaces from Images
  35. Filter bubbles and affective polarization in user-personalized large language model outputs
  36. EIT: Earnest Insight Toolkit for Evaluating Students' Earnestness in Interactive Lecture Participation Exercises
  37. Automated Parliaments: A Solution to Decision Uncertainty and Misalignment in Language Models
  38. Investigating AI's Challenges in Reasoning and Explanation from a Historical Perspective
  39. Towards Instance-Optimality in Online PAC Reinforcement Learning
  40. Fast, accurate, and interpretable decoding of electrocorticographic signals using dynamic mode decomposition
  41. Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints
  42. A Comprehensive Study on Model Initialization Techniques Ensuring Efficient Federated Learning
  43. Relation Extraction from News Articles (RENA): A Tool for Epidemic Surveillance
  44. Investigating Relative Performance of Transfer and Meta Learning
  45. Fraud Analytics Using Machine-learning & Engineering on Big Data (FAME) for Telecom
  46. Large-Scale Multi-Robot Assembly Planning for Autonomous Manufacturing
  47. XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision
  48. Decodable and Sample Invariant Continuous Object Encoder
  49. Image Restoration with Point Spread Function Regularization and Active Learning
  50. Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization
  51. Object-centric Video Representation for Long-term Action Anticipation
  52. ChipNeMo: Domain-Adapted LLMs for Chip Design
  53. Hierarchical Information-sharing Convolutional Neural Network for the Prediction of Arctic Sea Ice Concentration and Velocity
  54. Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
  55. Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Language
  56. Longer Fixations, More Computation: Gaze-Guided Recurrent Neural Networks
  57. Score Normalization for a Faster Diffusion Exponential Integrator Sampler
  58. Medi-CAT: Contrastive Adversarial Training for Medical Image Classification
  59. RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios
  60. Two-Stage Classifier for Campaign Negativity Detection using Axis Embeddings: A Case Study on Tweets of Political Users during 2021 Presidential Election in Iran
  61. Adaptive and non-adaptive minimax rates for weighted Laplacian-eigenmap based nonparametric regression
  62. Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data
  63. Joint Depth Prediction and Semantic Segmentation with Multi-View SAM
  64. On the effect of curriculum learning with developmental data for grammar acquisition
  65. Q-Learning for Stochastic Control under General Information Structures and Non-Markovian Environments
  66. Extracting the Multiscale Causal Backbone of Brain Dynamics
  67. BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B
  68. BERTwich: Extending BERT's Capabilities to Model Dialectal and Noisy Text
  69. EXTRACT: Explainable Transparent Control of Bias in Embeddings
  70. FairWASP: Fast and Optimal Fair Wasserstein Pre-processing
  71. Deep Compressed Learning for 3D Seismic Inversion
  72. Bandit-Driven Batch Selection for Robust Learning under Label Noise
  73. Seeking Truth and Beauty in Flavor Physics with Machine Learning
  74. NoMoPy: Noise Modeling in Python
  75. Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection
  76. YOLOv8-Based Visual Detection of Road Hazards: Potholes, Sewer Covers, and Manholes
  77. View Classification and Object Detection in Cardiac Ultrasound to Localize Valves via Deep Learning
  78. Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning
  79. Ensemble models outperform single model uncertainties and predictions for operator-learning of hypersonic flows
  80. The Generative AI Paradox: "What It Can Create, It May Not Understand"
  81. Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective
  82. On the Kolmogorov neural networks
  83. SC-MIL: Sparsely Coded Multiple Instance Learning for Whole Slide Image Classification
  84. FPO++: Efficient Encoding and Rendering of Dynamic Neural Radiance Fields by Analyzing and Enhancing Fourier PlenOctrees
  85. Unexpected Improvements to Expected Improvement for Bayesian Optimization
  86. What's In My Big Data?
  87. DDAM-PS: Diligent Domain Adaptive Mixer for Person Search
  88. Farthest Greedy Path Sampling for Two-shot Recommender Search
  89. Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders
  90. Vanishing Gradients in Reinforcement Finetuning of Language Models
  91. Bayesian Multistate Bennett Acceptance Ratio Methods
  92. Text-Transport: Toward Learning Causal Effects of Natural Language
  93. HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
  94. NeRF Revisited: Fixing Quadrature Instability in Volume Rendering
  95. Compression with Exact Error Distribution for Federated Learning
  96. Latent Field Discovery In Interacting Dynamical Systems With Neural Fields
  97. Balancing Act: Constraining Disparate Impact in Sparse Models
  98. Density Matrix Emulation of Quantum Recurrent Neural Networks for Multivariate Time Series Prediction
  99. StairNet: Visual Recognition of Stairs for Human-Robot Locomotion
  100. Non-Compositionality in Sentiment: New Data and Analyses
All 261
  1. Closed Drafting as a Case Study for First-Principle Interpretability, Memory, and Generalizability in Deep Reinforcement Learning
  2. Dynamic Batch Norm Statistics Update for Natural Robustness
  3. Performance Improvement in Multi-class Classification via Automated Hierarchy Generation and Exploitation through Extended LCPN Schemes
  4. Histopathological Image Analysis with Style-Augmented Feature Domain Mixing for Improved Generalization
  5. Using Skew to Assess the Quality of GAN-generated Image Features
  6. Defining a New NLP Playground
  7. Projecting basis functions with tensor networks for Gaussian process regression
  8. Deepfake detection by exploiting surface anomalies: the SurFake approach
  9. The Unreasonable Effectiveness of Random Target Embeddings for Continuous-Output Neural Machine Translation
  10. Graph Matching via convex relaxation to the simplex
  11. Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback
  12. What a Whole Slide Image Can Tell? Subtype-guided Masked Transformer for Pathological Image Captioning
  13. Enhanced Synthetic MRI Generation from CT Scans Using CycleGAN with Feature Extraction
  14. Modular Boundaries in Recurrent Neural Networks
  15. Brain-like Flexible Visual Inference by Harnessing Feedback-Feedforward Alignment
  16. Online Conversion with Switching Costs: Robust and Learning-Augmented Algorithms
  17. FLODCAST: Flow and Depth Forecasting via Multimodal Recurrent Architectures
  18. Increasing The Performance of Cognitively Inspired Data-Efficient Language Models via Implicit Structure Building
  19. Zero-Shot Medical Information Retrieval via Knowledge Graph Embedding
  20. Stochastic Gradient Descent for Gaussian Processes Done Right
  21. Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
  22. Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization
  23. One-shot backpropagation for multi-step prediction in physics-based system identification -- EXTENDED VERSION
  24. Taking control: Policies to address extinction risks from advanced AI
  25. Breaking the Token Barrier: Chunking and Convolution for Efficient Long Text Classification with BERT
  26. Privacy-preserving design of graph neural networks with applications to vertical federated learning
  27. Optimizing accuracy and diversity: a multi-task approach to forecast combinations
  28. Directed Cyclic Graph for Causal Discovery from Multivariate Functional Data
  29. Group-Feature (Sensor) Selection With Controlled Redundancy Using Neural Networks
  30. Parametric Fairness with Statistical Guarantees
  31. Neural Retrievers are Biased Towards LLM-Generated Content
  32. Generative Learning of Continuous Data by Tensor Networks
  33. BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis
  34. Requirement falsification for cyber-physical systems using generative models
  35. Log-based Anomaly Detection of Enterprise Software: An Empirical Study
  36. Long-Tailed Learning as Multi-Objective Optimization
  37. Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users
  38. Unveiling Black-boxes: Explainable Deep Learning Models for Patent Classification
  39. Exploring Practitioner Perspectives On Training Data Attribution Explanations
  40. Global Transformer Architecture for Indoor Room Temperature Forecasting
  41. Linked Papers With Code: The Latest in Machine Learning as an RDF Knowledge Graph
  42. Critical Role of Artificially Intelligent Conversational Chatbot
  43. Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation
  44. Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning
  45. ACL Anthology Helper: A Tool to Retrieve and Manage Literature from ACL Anthology
  46. Interpretable Neural PDE Solvers using Symbolic Frameworks
  47. Machine learning detects terminal singularities
  48. FlexTrain: A Dynamic Training Framework for Heterogeneous Devices Environments
  49. Towards a Deep Understanding of Multilingual End-to-End Speech Translation
  50. AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms
  51. Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks
  52. LAVSS: Location-Guided Audio-Visual Spatial Audio Separation
  53. Analyzing the Impact of Companies on AI Research Based on Publications
  54. Ontologies for Models and Algorithms in Applied Mathematics and Related Disciplines
  55. Integrating curation into scientific publishing to train AI models
  56. The Phase Transition Phenomenon of Shuffled Regression
  57. SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark
  58. Raising the ClaSS of Streaming Time Series Segmentation
  59. Assessing and Enhancing Robustness of Deep Learning Models with Corruption Emulation in Digital Pathology
  60. Discussing the Spectrum of Physics-Enhanced Machine Learning; a Survey on Structural Mechanics Applications
  61. DDC-PIM: Efficient Algorithm/Architecture Co-design for Doubling Data Capacity of SRAM-based Processing-In-Memory
  62. Coalitional Manipulations and Immunity of the Shapley Value
  63. Meta Learning for Multi-View Visuomotor Systems
  64. Thermal-Infrared Remote Target Detection System for Maritime Rescue based on Data Augmentation with 3D Synthetic Data
  65. FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
  66. Multi-Base Station Cooperative Sensing with AI-Aided Tracking
  67. Utilitarian Algorithm Configuration
  68. A hybrid approach for solving the gravitational N-body problem with Artificial Neural Networks
  69. High-Resolution Reference Image Assisted Volumetric Super-Resolution of Cardiac Diffusion Weighted Imaging
  70. Do large language models solve verbal analogies like children do?
  71. A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis
  72. Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods
  73. Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm
  74. A Machine Learning-Based Framework for Clustering Residential Electricity Load Profiles to Enhance Demand Response Programs
  75. Distil the informative essence of loop detector data set: Is network-level traffic forecasting hungry for more data?
  76. Hidden Conflicts in Neural Networks and Their Implications for Explainability
  77. Mathematical Introduction to Deep Learning: Methods, Implementations, and Theory
  78. Muscle volume quantification: guiding transformers with anatomical priors
  79. Combining Shape Completion and Grasp Prediction for Fast and Versatile Grasping with a Multi-Fingered Hand
  80. A Low-cost Strategic Monitoring Approach for Scalable and Interpretable Error Detection in Deep Neural Networks
  81. Automatic Generators for a Family of Matrix Multiplication Routines with Apache TVM
  82. Recaptured Raw Screen Image and Video Demoir'eing via Channel and Spatial Modulations
  83. InstructCoder: Instruction Tuning Large Language Models for Code Editing
  84. ChiSCor: A Corpus of Freely Told Fantasy Stories by Dutch Children for Computational Linguistics and Cognitive Science
  85. Improving Entropy-Based Test-Time Adaptation from a Clustering View
  86. Erato: Automatizing Poetry Evaluation
  87. SemanticBoost: Elevating Motion Generation with Augmented Textual Cues
  88. FA Team at the NTCIR-17 UFO Task
  89. Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests
  90. GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data
  91. HWD: A Novel Evaluation Score for Styled Handwritten Text Generation
  92. Causal Interpretation of Self-Attention in Pre-Trained Transformers
  93. Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation
  94. Revolutionizing Global Food Security: Empowering Resilience through Integrated AI Foundation Models and Data-Driven Solutions
  95. Verification of Neural Networks Local Differential Classification Privacy
  96. Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation
  97. IARS SegNet: Interpretable Attention Residual Skip connection SegNet for melanoma segmentation
  98. Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents
  99. Accelerating Non-Conjugate Gaussian Processes By Trading Off Computation For Uncertainty
  100. AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Data
  101. Machine learning refinement of in situ images acquired by low electron dose LC-TEM
  102. Extracting Entities of Interest from Comparative Product Reviews
  103. From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation
  104. Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning
  105. Beyond Average Return in Markov Decision Processes
  106. Low-Dose CT Image Enhancement Using Deep Learning
  107. Learning to Play Chess from Textbooks (LEAP): a Corpus for Evaluating Chess Moves based on Sentiment Analysis
  108. Advancing Bayesian Optimization via Learning Correlated Latent Space
  109. Artificial Intelligence for reverse engineering: application to detergents using Raman spectroscopy
  110. Diversified Node Sampling based Hierarchical Transformer Pooling for Graph Representation Learning
  111. Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior
  112. Contrast-agent-induced deterministic component of CT-density in the abdominal aorta during routine angiography: proof of concept study
  113. Breathing Life into Faces: Speech-driven 3D Facial Animation with Natural Head Pose and Detailed Shape
  114. Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning
  115. HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds
  116. Choose A Table: Tensor Dirichlet Process Multinomial Mixture Model with Graphs for Passenger Trajectory Clustering
  117. STDA-Meta: A Meta-Learning Framework for Few-Shot Traffic Prediction
  118. A Systematic Review for Transformer-based Long-term Series Forecasting
  119. Does GPT-4 pass the Turing test?
  120. Handover Protocol Learning for LEO Satellite Networks: Access Delay and Collision Minimization
  121. Calibration by Distribution Matching: Trainable Kernel Calibration Metrics
  122. UWFormer: Underwater Image Enhancement via a Semi-Supervised Multi-Scale Transformer
  123. Network Contention-Aware Cluster Scheduling with Reinforcement Learning
  124. ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
  125. General-Purpose Retrieval-Enhanced Medical Prediction Model Using Near-Infinite History
  126. Importance Estimation with Random Gradient for Neural Network Pruning
  127. Video-Helpful Multimodal Machine Translation
  128. In Search of Lost Online Test-time Adaptation: A Survey
  129. Generating Continuations in Multilingual Idiomatic Contexts
  130. FedRec+: Enhancing Privacy and Addressing Heterogeneity in Federated Recommendation Systems
  131. Visible to Thermal image Translation for improving visual task in low light conditions
  132. Self-Supervised Pre-Training for Precipitation Post-Processor
  133. Learning to Discover Skills through Guidance
  134. LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations
  135. GraphTransformers for Geospatial Forecasting of Hurricane Trajectories
  136. Compact Binary Systems Waveform Generation with Generative Pre-trained Transformer
  137. Understanding and Visualizing Droplet Distributions in Simulations of Shallow Clouds
  138. Is Robustness Transferable across Languages in Multilingual Neural Machine Translation?
  139. GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval
  140. MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
  141. Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision
  142. Decision-Making for Autonomous Vehicles with Interaction-Aware Behavioral Prediction and Social-Attention Neural Network
  143. Efficient Robust Bayesian Optimization for Arbitrary Uncertain Inputs
  144. EELBERT: Tiny Models through Dynamic Embeddings
  145. Contrastive Difference Predictive Coding
  146. DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
  147. Improving Prompt Tuning with Learned Prompting Layers
  148. Ling-CL: Understanding NLP Models through Linguistic Curricula
  149. Team I2R-VI-FF Technical Report on EPIC-KITCHENS VISOR Hand Object Segmentation Challenge 2023
  150. Refined Equivalent Pinhole Model for Large-scale 3D Reconstruction from Spaceborne CCD Imagery
  151. Making Large Language Models Better Data Creators
  152. Efficient Classification of Student Help Requests in Programming Courses Using Large Language Models
  153. Plagiarism and AI Assistance Misuse in Web Programming: Unfair Benefits and Characteristics
  154. Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds
  155. Medical Image Denosing via Explainable AI Feature Preserving Loss
  156. Robust Learning for Smoothed Online Convex Optimization with Feedback Delay
  157. Data Market Design through Deep Learning
  158. p-Poisson surface reconstruction in curl-free flow from point clouds
  159. Evaluating Neural Language Models as Cognitive Models of Language Acquisition
  160. Bridging the Gap Between Variational Inference and Wasserstein Gradient Flows
  161. Keyword-optimized Template Insertion for Clinical Information Extraction via Prompt-based Learning