mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 5 Oct 2023

249 papers

  1. Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor AttacksLLM safety and security → Backdoor and data poisoning attacks
  2. Diffusing on Two Levels and Optimizing for Multiple Properties: A Novel Approach to Generating Molecules with Desirable PropertiesDiffusion models → Flow matching, time series and science
  3. Diffusion Models as Masked Audio-Video LearnersDiffusion models → Audio, speech and music
  4. LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  5. Chameleon: Increasing Label-Only Membership Leakage with Adaptive PoisoningLLM safety and security → Membership inference attacks
  6. Improved Baselines with Visual Instruction TuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  7. Aligning Text-to-Image Diffusion Models with Reward BackpropagationDiffusion models → Diffusion and flow policies for robotics
  8. MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical ReasoningLLM reasoning → Mathematical reasoning
  9. A Long Way to Go: Investigating Length Correlations in RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  10. DSPy: Compiling Declarative Language Model Calls into Self-Improving PipelinesSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  11. Agent Instructs Large Language Models to be General Zero-Shot ReasonersLLM reasoning → Reasoning benchmarks and evaluation +1
  12. Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  13. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  14. SmoothLLM: Defending Large Language Models Against Jailbreaking AttacksLLM safety and security → Jailbreaking
  15. LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit CalibrationKnowledge distillation → General knowledge distillation methods
  16. Certification of Deep Learning Models for Medical Image SegmentationDiffusion models → Medical imaging and segmentation
  17. Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent ArchitecturesLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent DiffusionDiffusion models → Image generation, text-to-image and editing
  19. Deep Generative Models of Music ExpectationDiffusion models → Audio, speech and music
  20. FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth EstimatorsDiffusion models → 3D, point cloud and scene generation
  21. ACT-Net: Anchor-context Action Detection in Surgery VideosDiffusion models → Medical imaging and segmentation
  22. Realistic Speech-to-Face Generation with Speech-Conditioned Latent Diffusion Model with Face PriorDiffusion models → Audio, speech and music
  23. Denoising Diffusion Step-aware ModelsDiffusion models → Diffusion foundations and sampling
  24. Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual PlanningLLM reasoning → Multimodal reasoning
  25. Concise and Organized Perception Facilitates Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  26. Learning Personalized Alignment for Evaluating Open-ended Text GenerationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  27. A Two-stage Based Social Preference Recognition in Multi-Agent Autonomous Driving SystemEnd-to-end autonomous driving → Cooperative and V2X driving
  28. MLAgentBench: Evaluating Language Agents on Machine Learning ExperimentationLLM agents and tool use → Web, search, and research agents
  29. A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's IntentionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. Expedited Training of Visual Conditioned Language Generation via Redundancy ReductionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  31. EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  32. Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal ReasoningLLM reasoning → Spatial and embodied reasoning
  33. A Review of Deep Reinforcement Learning in Serverless Computing: Function Scheduling and Resource Auto-Scaling
  34. A Kernel Perspective on Behavioural Metrics for Markov Decision Processes
  35. Adaptive Dynamic Programming for Energy-Efficient Base Station Cell Switching
  36. Parking Spot Classification based on surround view camera system
  37. Zero-shot Learning of Drug Response Prediction for Preclinical Drug Screening
  38. Domain Generalization for Medical Image Analysis: A Review
  39. Observatory: Characterizing Embeddings of Relational Tables
  40. Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms
  41. Taming Binarized Neural Networks and Mixed-Integer Programs
  42. Validating transformers for redaction of text from electronic health records in real-world healthcare
  43. Design Principles for Lifelong Learning AI Accelerators
  44. HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation
  45. How toxic is antisemitism? Potentials and limitations of automated toxicity scoring for antisemitic online content
  46. AI-based automated active learning for discovery of hidden dynamic processes: A use case in light microscopy
  47. Tuning In to Neural Encoding: Linking Human Brain and Artificial Supervised Representations of Language
  48. Simultaneous Dimensionality Reduction: A Data Efficient Approach for Multimodal Representations Learning
  49. Improved prediction of ligand-protein binding affinities by meta-modeling
  50. On Wasserstein distances for affine transformations of random vectors
  51. LaTeX: Language Pattern-aware Triggering Event Detection for Adverse Experience during Pandemics
  52. Beyond Random Augmentations: Pretraining with Hard Views
  53. Exploring the evolution of research topics during the COVID-19 pandemic
  54. Improving classifier decision boundaries using nearest neighbors
  55. Multitask Learning for Time Series Data with 2D Convolution
  56. Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
  57. An Efficient Content-based Time Series Retrieval System
  58. Toward a Foundation Model for Time Series Data
  59. Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control
  60. RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels
  61. Coloring Deep CNN Layers with Activation Hue Loss
  62. PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability
  63. Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond
  64. CrysFormer: Protein Structure Prediction via 3d Patterson Maps and Partial Structure Attention
  65. Class-Incremental Learning Using Generative Experience Replay Based on Time-aware Regularization
  66. TWICE Dataset: Digital Twin of Test Scenarios in a Controlled Environment
  67. Characterizing the Features of Mitotic Figures Using a Conditional Diffusion Probabilistic Model
  68. Accelerated Neural Network Training with Rooted Logistic Objectives
  69. Trustworthy Formal Natural Language Specifications
  70. Information Geometry for the Working Information Theorist
  71. Small batch deep reinforcement learning
  72. Non Commutative Convolutional Signal Models in Neural Networks: Stability to Small Deformations
  73. Automatic and Human-AI Interactive Text Generation
  74. Benchmarking a foundation LLM on its ability to re-label structure names in accordance with the AAPM TG-263 report
  75. FNOSeg3D: Resolution-Robust 3D Image Segmentation with Fourier Neural Operator
  76. Consistency Regularization Improves Placenta Segmentation in Fetal EPI MRI Time Series
  77. Model Complexity of Program Phases
  78. Variational Barycentric Coordinates
  79. MultiHU-TD: Multifeature Hyperspectral Unmixing Based on Tensor Decomposition
  80. OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning
  81. Euclid: Identification of asteroid streaks in simulated images using deep learning
  82. From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learning
  83. Contextualized Structural Self-supervised Learning for Ontology Matching
  84. Learning A Disentangling Representation For PU Learning
  85. Integrating Audio-Visual Features for Multimodal Deepfake Detection
  86. ECAvg: An Edge-Cloud Collaborative Learning Approach using Averaged Weights
  87. WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
  88. Logical Languages Accepted by Transformer Encoders with Hard Attention
  89. Cold-start Bundle Recommendation via Popularity-based Coalescence and Curriculum Heating
  90. Fishnets: Information-Optimal, Scalable Aggregation for Sets and Graphs
  91. Grokking as a First Order Phase Transition in Two Layer Networks
  92. Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation
  93. HandMeThat: Human-Robot Communication in Physical and Social Environments
  94. Lightweight Boosting Models for User Response Prediction Using Adversarial Validation
  95. PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction
  96. Functional data learning using convolutional neural networks
  97. Investigating Alternative Feature Extraction Pipelines For Clinical Note Phenotyping
  98. The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
  99. ContactGen: Generative Contact Modeling for Grasp Generation
  100. Robust Novelty Detection through Style-Conscious Feature Ranking
All 249
  1. Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
  2. Stochastic interpolants with data-dependent couplings
  3. Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer
  4. Anytime-valid t-tests and confidence sequences for Gaussian means with unknown variance
  5. SteP: Stacked LLM Policies for Web Actions
  6. Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
  7. Artificial Intelligence Index Report 2023
  8. OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks
  9. Pose-Free Generalizable Rendering Transformer
  10. Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities
  11. Multimarginal generative modeling with stochastic interpolants
  12. Probabilistic Generative Modeling for Procedural Roundabout Generation for Developing Countries
  13. DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
  14. Hadamard Domain Training with Integers for Class Incremental Quantized Learning
  15. GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
  16. MapperGPT: Large Language Models for Linking and Mapping Entities
  17. Robustness-Guided Image Synthesis for Data-Free Quantization
  18. Visual inspection for illicit items in X-ray images using Deep Learning
  19. Strategic Evaluation: Subjects, Evaluators, and Society
  20. Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics
  21. Rethinking Algorithmic Fairness for Human-AI Collaboration
  22. TRAM: Bridging Trust Regions and Sharpness Aware Minimization
  23. Distributional PAC-Learning from Nisan's Natural Proofs
  24. Evaluating Self-Supervised Speech Representations for Indigenous American Languages
  25. CLEVRER-Humans: Describing Physical and Causal Events the Human Way
  26. Wasserstein Distortion: Unifying Fidelity and Realism
  27. High-Degrees-of-Freedom Dynamic Neural Fields for Robot Self-Modeling and Motion Planning
  28. PeaTMOSS: Mining Pre-Trained Models in Open-Source Software
  29. CLASSify: A Web-Based Tool for Machine Learning
  30. Animatable Virtual Humans: Learning pose-dependent human representations in UV space for interactive performance synthesis
  31. Adversarial Machine Learning for Social Good: Reframing the Adversary as an Ally
  32. Solving a Class of Non-Convex Minimax Optimization in Federated Learning
  33. GENER: A Parallel Layer Deep Learning Network To Detect Gene-Gene Interactions From Gene Expression Data
  34. How Good Are Synthetic Medical Images? An Empirical Study with Lung Ultrasound
  35. Comparing Time-Series Analysis Approaches Utilized in Research Papers to Forecast COVID-19 Cases in Africa: A Literature Review
  36. FASER: Binary Code Similarity Search through the use of Intermediate Representations
  37. Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints
  38. Sampling via Gradient Flows in the Space of Probability Measures
  39. TimeGPT-1
  40. Smoothing Methods for Automatic Differentiation Across Conditional Branches
  41. Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End
  42. Causal Inference in Gene Regulatory Networks with GFlowNet: Towards Scalability in Large Systems
  43. Targeted Adversarial Attacks on Generalizable Neural Radiance Fields
  44. Analysis of learning a flow-based generative model from limited sample complexity
  45. Residual Multi-Fidelity Neural Network Computing
  46. BID-NeRF: RGB-D image pose estimation with inverted Neural Radiance Fields
  47. Redefining Digital Health Interfaces with Large Language Models
  48. MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images
  49. Stable Training of Probabilistic Models Using the Leave-One-Out Maximum Log-Likelihood Objective
  50. Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
  51. Distribution-free risk assessment of regression-based machine learning algorithms
  52. Towards Unified Deep Image Deraining: A Survey and A New Benchmark
  53. 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation
  54. Joint Group Invariant Functions on Data-Parameter Domain Induce Universal Neural Networks
  55. Deep Ridgelet Transform: Voice with Koopman Operator Proves Universality of Formal Deep Networks
  56. Vehicle-to-Everything Cooperative Perception for Autonomous Driving
  57. Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations
  58. PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification
  59. High-dimensional Bayesian Optimization with Group Testing
  60. Exploring DINO: Emergent Properties and Limitations for Synthetic Aperture Radar Imagery
  61. Otago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine Learning Models
  62. RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing
  63. IceCloudNet: Cirrus and mixed-phase cloud prediction from SEVIRI input learned from sparse supervision
  64. How the level sampling process impacts zero-shot generalisation in deep reinforcement learning
  65. TPDR: A Novel Two-Step Transformer-based Product and Class Description Match and Retrieval Method
  66. BTDNet: a Multi-Modal Approach for Brain Tumor Radiogenomic Classification
  67. The Geometric Structure of Fully-Connected ReLU Layers
  68. The ICASSP SP Cadenza Challenge: Music Demixing/Remixing for Hearing Aids
  69. Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation
  70. Controllable Multi-document Summarization: Coverage & Coherence Intuitive Policy with Large Language Model Based Rewards
  71. Ammonia-Net: A Multi-task Joint Learning Model for Multi-class Segmentation and Classification in Tooth-marked Tongue Diagnosis
  72. The Blame Problem in Evaluating Local Explanations, and How to Tackle it
  73. Towards Understanding Generalization and Stability Gaps between Centralized and Decentralized Federated Learning
  74. A Quantitatively Interpretable Model for Alzheimer's Disease Prediction Using Deep Counterfactuals
  75. Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization
  76. FLAIM: AIM-based Synthetic Data Generation in the Federated Setting
  77. The North System for Formosa Speech Recognition Challenge 2023
  78. Variational Inference for GARCH-family Models
  79. Mitigating the Influence of Domain Shift in Skin Lesion Classification: A Benchmark Study of Unsupervised Domain Adaptation Methods on Dermoscopic Images
  80. Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Covering
  81. Neural Language Model Pruning for Automatic Speech Recognition
  82. Pre-Training and Fine-Tuning Generative Flow Networks
  83. LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction
  84. Over-the-Air Federated Learning with Compressed Sensing: Is Sparsification Necessary?
  85. RUSOpt: Robotic UltraSound Probe Normalization with Bayesian Optimization for In-plane and Out-plane Scanning
  86. EAG-RS: A Novel Explainability-guided ROI-Selection Framework for ASD Diagnosis via Inter-regional Relation Learning
  87. A Complementary Global and Local Knowledge Network for Ultrasound denoising with Fine-grained Refinement
  88. Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
  89. GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks
  90. Interpolating between Clustering and Dimensionality Reduction with Gromov-Wasserstein
  91. Learning to Simplify Spatial-Temporal Graphs in Gait Analysis
  92. Uncertainty quantification for deep learning-based schemes for solving high-dimensional backward stochastic differential equations
  93. Unpacking Human-AI Interaction in Safety-Critical Industries: A Systematic Literature Review
  94. OpenPatch: a 3D patchwork for Out-Of-Distribution detection
  95. Machine learning the interaction network in coupled dynamical systems
  96. Procedural Text Mining with Large Language Models
  97. Point-Based Radiance Fields for Controllable Human Motion Synthesis
  98. Design Optimizer for Planar Soft-Growing Robot Manipulators
  99. Evaluating Hallucinations in Chinese Large Language Models
  100. Swin-Tempo: Temporal-Aware Lung Nodule Detection in CT Scans as Video Sequences Using Swin Transformer-Enhanced UNet
  101. CSI: Enhancing the Robustness of 3D Point Cloud Recognition against Corruption
  102. Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria
  103. Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Games
  104. Deep Geometric Learning with Monotonicity Constraints for Alzheimer's Disease Progression
  105. Tractable Bounding of Counterfactual Queries by Knowledge Compilation
  106. An Integrated Algorithm for Robust and Imperceptible Audio Adversarial Examples
  107. Combining Datasets with Different Label Sets for Improved Nucleus Segmentation and Classification
  108. LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework
  109. Probabilistic Forecasting of Day-Ahead Electricity Prices and their Volatility with LSTMs
  110. Continual Test-time Domain Adaptation via Dynamic Sample Selection
  111. Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System
  112. Real-time Multi-modal Object Detection and Tracking on Edge for Regulatory Compliance Monitoring
  113. Fine-tune Language Models to Approximate Unbiased In-context Learning
  114. Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain
  115. Investigating the Limitation of CLIP Models: The Worst-Performing Categories
  116. BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs
  117. Enhanced Human-Robot Collaboration using Constrained Probabilistic Human-Motion Prediction
  118. Certifiably Robust Graph Contrastive Learning
  119. Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses
  120. Learning Energy Decompositions for Partial Inference of GFlowNets
  121. A Latent Variable Approach for Non-Hierarchical Multi-Fidelity Adaptive Sampling
  122. Can pre-trained models assist in dataset distillation?
  123. DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training
  124. SoK: Access Control Policy Generation from High-level Natural Language Requirements
  125. PoseAction: Action Recognition for Patients in the Ward using Deep Learning Approaches
  126. Burning the Adversarial Bridges: Robust Windows Malware Detection Against Binary-level Mutations
  127. A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores
  128. A 5' UTR Language Model for Decoding Untranslated Regions of mRNA and Function Predictions
  129. Classifying Whole Slide Images: What Matters?
  130. Mitigating Pilot Contamination and Enabling IoT Scalability in Massive MIMO Systems
  131. Fragment-based Pretraining and Finetuning on Molecular Graphs
  132. Ablation Study to Clarify the Mechanism of Object Segmentation in Multi-Object Representation Learning
  133. T-GAE: Transferable Graph Autoencoder for Network Alignment
  134. InstructProtein: Aligning Human and Protein Language via Knowledge Instruction
  135. UniPredict: Large Language Models are Universal Tabular Classifiers
  136. Predicting Emergent Abilities with Infinite Resolution Evaluation
  137. Assessing Electricity Service Unfairness with Transfer Counterfactual Learning
  138. Molecule Design by Latent Prompt Transformer
  139. Sparse Deep Learning for Time Series Data: Theory and Applications
  140. Learning Hierarchical Relational Representations through Relational Convolutions
  141. Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization
  142. Deep Representations of First-person Pronouns for Prediction of Depression Symptom Severity
  143. History Matching for Geological Carbon Storage using Data-Space Inversion with Spatio-Temporal Data Parameterization
  144. Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms
  145. TacoGFN: Target-conditioned GFlowNet for Structure-based Drug Design
  146. Know2BIO: A Comprehensive Dual-View Benchmark for Evolving Biomedical Knowledge Graphs
  147. Learning Energy-Based Prior Model with Diffusion-Amortized MCMC
  148. Formal and Practical Elements for the Certification of Machine Learning Systems
  149. FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation