Papers
Fri 9 Jun 2023
247 papers
- Large Language Models Are Semi-Parametric Reinforcement Learning AgentsLLM agents and tool use → Agent memory systems
- Value function estimation using conditional diffusion models for controlDiffusion models → Diffusion and flow policies for robotics
- DocumentCLIP: Linking Figures and Main Body Text in Reflowed DocumentsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Explaining SAT Solving Using Causal ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Boosting GUI Prototyping with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Mind2Web: Towards a Generalist Agent for the WebLLM agents and tool use → Web, search, and research agents
- How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- S3: Increasing GPU Utilization during Generative Inference for Higher ThroughputEfficient LLM inference and serving → KV cache optimization
- Iteratively Refined Behavior Regularization for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Beyond Surface Statistics: Scene Representations in a Latent Diffusion ModelDiffusion models → 3D, point cloud and scene generation
- Boosting Fast and High-Quality Speech Synthesis with Linear DiffusionDiffusion models → Audio, speech and music
- One-Shot Machine Unlearning with Mnemonic CodeLLM safety and security → Machine unlearning
- RePaint-NeRF: NeRF Editting via Semantic Masks and Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Quantifying the Knowledge in GNNs for Reliable Distillation into MLPsKnowledge distillation → Graph neural network distillation
- Simplicial Message Passing for Chemical Property Prediction
- CrysMMNet: Multimodal Representation for Crystal Property Prediction
- Leveraging text data for causal inference using electronic health records
- KAPLA: Pragmatic Representation and Fast Solving of Scalable NN Accelerator Dataflow
- Molecule Design by Latent Space Energy-Based Modeling and Gradual Distribution Shifting
- Best Practices for Machine Learning Systems: An Industrial Framework for Analysis and Optimization
- Interpretation of immunofluorescence slides by deep learning techniques: anti-nuclear antibodies case study
- The Age of Synthetic Realities: Challenges and Opportunities
- A Survey on Cross-Architectural IoT Malware Threat Hunting
- Improving Frame-level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition
- GPT-Calls: Enhancing Call Segmentation and Tagging by Generating Synthetic Conversations via Large Language Models
- Understanding Telecom Language Through Large Language Models
- A Theory of Unsupervised Speech Recognition
- Implementing BERT and fine-tuned RobertA to detect AI generated news by ChatGPT
- SARN: Structurally-Aware Recurrent Network for Spatio-Temporal Disaggregation
- Knowledge Enhanced Multi-Domain Recommendations in an AI Assistant Application
- NERFBK: A High-Quality Benchmark for NERF-Based 3D Reconstruction
- Protect Your Prompts: Protocols for IP Protection in LLM Applications
- Response Time Improves Choice Prediction and Function Estimation for Gaussian Process Models of Perception and Preferences
- PLPCA: Persistent Laplacian Enhanced-PCA for Microarray Data Analysis
- Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity
- SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers
- SAGE-NDVI: A Stereotype-Breaking Evaluation Metric for Remote Sensing Image Dehazing Using Satellite-to-Ground NDVI Knowledge
- Everybody Compose: Deep Beats To Music
- 14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
- Energy-Dissipative Evolutionary Deep Operator Neural Networks
- Contrastive Learning for Predicting Cancer Prognosis Using Gene Expression Values
- Using Auxiliary Data to Boost Precision in the Analysis of A/B Tests on an Online Educational Platform: New Data and New Results
- A Domain-Independent Agent Architecture for Adaptive Operation in Evolving Open Worlds
- DeepLCZChange: A Remote Sensing Deep Learning Model Architecture for Urban Climate Resilience
- Attention-stacked Generative Adversarial Network (AS-GAN)-empowered Sensor Data Augmentation for Online Monitoring of Manufacturing System
- Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints
- Measuring and Modifying Factual Knowledge in Large Language Models
- Spectral gap-based deterministic tensor completion
- Vector Summaries of Persistence Diagrams for Permutation-based Hypothesis Testing
- Understanding the Benefits of Image Augmentations
- Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models
- Feature Programming for Multivariate Time Series Prediction
- Design Principles for Model Generalization and Scalable AI Integration in Radio Access Networks
- Strategic Apple Tasting
- Online Learning with Set-Valued Feedback
- Record Deduplication for Entity Distribution Modeling in ASR Transcripts
- Understanding the Effect of the Long Tail on Neural Network Compression
- iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning
- Using Foundation Models to Detect Policy Violations with Minimal Supervision
- Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration
- AVScan2Vec: Feature Learning on Antivirus Scan Data for Production-Scale Malware Corpora
- Conformalizing Machine Translation Evaluation
- BioGAN: An unpaired GAN-based image to image translation model for microbiological images
- A Robust Twin Parametric Margin Support Vector Machine for Multiclass Classification
- Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptions
- Morphosyntactic probing of multilingual BERT models
- FLSL: Feature-level Self-supervised Learning
- NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics
- Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording
- ElectroCardioGuard: Preventing Patient Misidentification in Electrocardiogram Databases through Neural Networks
- Share, Collaborate, Benchmark: Advancing Travel Demand Research through rigorous open-source collaboration
- Consistent Explanations in the Face of Model Indeterminacy via Ensembling
- Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation
- Open Data on GitHub: Unlocking the Potential of AI
- FastDoc: Domain-Specific Fast Continual Pre-training Technique using Document-Level Metadata and Taxonomy
- FasterViT: Fast Vision Transformers with Hierarchical Attention
- A Unified Model and Dimension for Interactive Estimation
- Hidden symmetries of ReLU networks
- Active-Learning-Driven Surrogate Modeling for Efficient Simulation of Parametric Nonlinear Systems
- PoET: A generative model of protein families as sequences-of-sequences
- Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks
- HypLL: The Hyperbolic Learning Library
- EfficientBioAI: Making Bioimaging AI Models Efficient in Energy, Latency and Representation
- Read, look and detect: Bounding box annotation from image-caption pairs
- Artificial intelligence and radiation protection. A game changer or an update?
- SentiGOLD: A Large Bangla Gold Standard Multi-Domain Sentiment Analysis Dataset and its Evaluation
- Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers
- LDMRes-Net: Enabling Efficient Medical Image Segmentation on IoT and Edge Platforms
- Bayesian Calibration of MEMS Accelerometers
- Forecasting Electric Vehicle Charging Station Occupancy: Smarter Mobility Data Challenge
- Zero-Shot Dialogue Relation Extraction by Relating Explainable Triggers and Relation Names
- Null/No Information Rate (NIR): a statistical test to assess if a classification accuracy is significant for a given problem
- WePaMaDM-Outlier Detection: Weighted Outlier Detection using Pattern Approaches for Mass Data Mining
- Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents
- Safety and Fairness for Content Moderation in Generative Models
- Prodigy: An Expeditiously Adaptive Parameter-Free Learner
- NuCLR: Nuclear Co-Learned Representations
- Error Feedback Can Accurately Compress Preconditioners
- Leveraging Large Language Models for Scalable Vector Graphics-Driven Image Understanding
All 247
- HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork
- Realistic Saliency Guided Image Enhancement
- Computational Flash Photography through Intrinsics
- SENS: Part-Aware Sketch-based Implicit Neural Shape Modeling
- Learning Not to Spoof
- Developing Speech Processing Pipelines for Police Accountability
- Trapping LLM Hallucinations Using Tagged Context Prompts
- Combining a Meta-Policy and Monte-Carlo Planning for Scalable Type-Based Reasoning in Partially Observable Environments
- Virtual Node Tuning for Few-shot Node Classification
- Assisting Language Learners: Automated Trans-Lingual Definition Generation via Contrastive Prompt Learning
- Higher Chest X-ray Resolution Improves Classification Performance
- GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields
- A Graph Dynamics Prior for Relational Inference
- Reconstructing Human Expressiveness in Piano Performances with a Transformer Network
- WindowNet: Learnable Windows for Chest X-ray Classification
- SNeL: A Structured Neuro-Symbolic Language for Entity-Based Multimodal Scene Understanding
- RANS-PINN based Simulation Surrogates for Predicting Turbulent Flows
- FinGPT: Open-Source Financial Large Language Models
- HiTZ@Antidote: Argumentation-driven Explainable Artificial Intelligence for Digital Medicine
- Self-Interpretable Time Series Prediction with Counterfactual Explanations
- DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds
- Dynamic Partial Computation Offloading for the Metaverse in In-Network Computing
- A Large-Scale Analysis on Self-Supervised Video Representation Learning
- Causal Effect Estimation from Observational and Interventional Data Through Matrix Weighted Linear Estimators
- Distributed Consensus Algorithm for Decision-Making in Multi-agent Multi-armed Bandit
- Automated Labeling of German Chest X-Ray Radiology Reports using Deep Learning
- Approximate information state based convergence analysis of recurrent Q-learning
- QBSD: Quartile-Based Seasonality Decomposition for Cost-Effective RAN KPI Forecasting
- Liquidity takers behavior representation through a contrastive learning approach
- Beyond Detection: Visual Realism Assessment of Deepfakes
- Federated Learning for Medical Image Analysis: A Survey
- 3D objects and scenes classification, recognition, segmentation, and reconstruction using 3D point cloud data: A review
- Query Rewriting with Disjunctive Existential Rules and Mappings
- Language Models Can Learn Exceptions to Syntactic Rules
- Automating Model Comparison in Factor Graphs
- Adaptive Contextual Perception: How to Generalize to New Backgrounds and Ambiguous Objects
- DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles
- Path Neural Networks: Expressive and Accurate Graph Neural Networks
- Overcoming Adversarial Attacks for Human-in-the-Loop Applications
- Prediction of Transportation Index for Urban Patterns in Small and Medium-sized Indian Cities using Hybrid RidgeGAN Model
- Evaluating the Social Impact of Generative AI Systems in Systems and Society
- Improving Estimation of the Koopman Operator with Kolmogorov-Smirnov Indicator Functions
- Robust Data-driven Prescriptiveness Optimization
- Speaker Embeddings as Individuality Proxy for Voice Stress Detection
- Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions
- Sketch2Stress: Sketching with Structural Stress Awareness
- 2DeteCT -- A large 2D expandable, trainable, experimental Computed Tomography dataset for machine learning
- TreeDQN: Sample-Efficient Off-Policy Reinforcement Learning for Combinatorial Optimization
- One-step corrected projected stochastic gradient descent for statistical estimation
- C(NN)FD -- a deep learning framework for turbomachinery CFD analysis
- TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses
- An Efficient Speech Separation Network Based on Recurrent Fusion Dilated Convolution and Channel Attention
- Good, but not always Fair: An Evaluation of Gender Bias for three commercial Machine Translation Systems
- Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations
- FedWon: Triumphing Multi-domain Federated Learning Without Normalization
- Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions
- Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction
- Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?
- Leaving the Lines Behind: Vision-Based Crop Row Exit for Agricultural Robot Navigation
- Faster Discrete Convex Function Minimization with Predictions: The M-Convex Case
- Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!
- Efficient Encoder-Decoder and Dual-Path Conformer for Comprehensive Feature Learning in Speech Enhancement
- Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
- How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
- Deterministic equivalent of the Conjugate Kernel matrix associated to Artificial Neural Networks
- Motion-DVAE: Unsupervised learning for fast human motion denoising
- How Object Information Improves Skeleton-based Human Action Recognition in Assembly Tasks
- Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach
- Expectation-Complete Graph Representations with Homomorphisms
- Can Large Language Models Infer Causation from Correlation?
- Sketch Beautification: Learning Part Beautification and Structure Refinement for Sketches of Man-made Objects
- Towards the Exploitation of LLM-based Chatbot for Providing Legal Support to Palestinian Cooperatives
- How Can Recommender Systems Benefit from Large Language Models: A Survey
- Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms
- Incorporating Prior Knowledge in Deep Learning Models via Pathway Activity Autoencoders
- HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection
- Explaining Reinforcement Learning with Shapley Values
- Interactive Explanation with Varying Level of Details in an Explainable Scientific Literature Recommender System
- RankFormer: Listwise Learning-to-Rank Using Listwide Labels
- A Gated Attention Transformer for Multi-Person Pose Tracking
- DynaBench: A benchmark dataset for learning dynamical systems from low-resolution data
- Causality between Sentiment and Cryptocurrency Prices
- Strategies to exploit XAI to improve classification systems
- Two-level histograms for dealing with outliers and heavy tail distributions
- End-to-End Neural Network Compression via fracℓ1ℓ2 Regularized Latency Surrogates
- Quantitative Ink Analysis: Estimating the Number of Inks in Documents through Hyperspectral Imaging
- Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
- Adaptivity Complexity for Causal Graph Discovery
- Transformer-based Time-to-Event Prediction for Chronic Kidney Disease Deterioration
- Weight Re-Mapping for Variational Quantum Algorithms
- Weight Freezing: A Regularization Approach for Fully Connected Layers with an Application in EEG Classification
- A Boosted Model Ensembling Approach to Ball Action Spotting in Videos: The Runner-Up Solution to CVPR'23 SoccerNet Challenge
- Self-Paced Absolute Learning Progress as a Regularized Approach to Curriculum Learning
- Fair yet Asymptotically Equal Collaborative Learning
- Efficient GNN Explanation via Learning Removal-based Attribution
- From psychological traits to safety warnings: three studies on recommendations in a smart home environment
- Advancing Counterfactual Inference through Nonlinear Quantile Regression
- DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures
- An End-to-End Reinforcement Learning Approach for Job-Shop Scheduling Problems Based on Constraint Programming
- Two Independent Teachers are Better Role Model
- Challenges and Opportunities for the Design of Smart Speakers
- Leaping through tree space: continuous phylogenetic inference for rooted and unrooted trees
- DP-HyPO: An Adaptive Private Hyperparameter Optimization Framework
- Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions
- The Role of Diverse Replay for Generalisation in Reinforcement Learning
- Explaining Predictive Uncertainty with Information Theoretic Shapley Values
- Ridge Estimation with Nonlinear Transformations
- Learning Domain-Aware Detection Head with Prompt Tuning
- Transferring Foundation Models for Generalizable Robotic Manipulation
- Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests
- Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech
- Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization
- On the Challenges and Perspectives of Foundation Models for Medical Image Analysis
- Exploring Effective Mask Sampling Modeling for Neural Image Compression
- Finite-Time Analysis of Minimax Q-Learning for Two-Player Zero-Sum Markov Games: Switching System Approach
- JABBERWOCK: A Tool for WebAssembly Dataset Generation and Its Application to Malicious Website Detection
- Group Equivariant Fourier Neural Operators for Partial Differential Equations
- Explainable Representation Learning of Small Quantum States
- DIFT: Dynamic Iterative Field Transforms for Memory Efficient Optical Flow
- Single-Stage Visual Relationship Learning using Conditional Queries
- ModeT: Learning Deformable Image Registration via Motion Decomposition Transformer
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- Lightweight Monocular Depth Estimation via Token-Sharing Transformer
- Emotion Detection from EEG using Transfer Learning
- Bayes optimal learning in high-dimensional linear regression with network side information
- Illumination Controllable Dehazing Network based on Unsupervised Retinex Embedding
- Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks
- I run as fast as a rabbit, can you? A Multilingual Simile Dialogue Dataset
- Topology-Aware Uncertainty for Image Segmentation
- QuestEnvSim: Environment-Aware Simulated Motion Tracking from Sparse Sensors
- Improving LiDAR 3D Object Detection via Range-based Point Cloud Density Optimization
- COVER: A Heuristic Greedy Adversarial Attack on Prompt-based Learning in Language Models
- GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment
- Communication-Efficient Zeroth-Order Distributed Online Optimization: Algorithm, Theory, and Applications
- Privacy Aware Question-Answering System for Online Mental Health Risk Assessment
- Differentially Private Sharpness-Aware Training
- Specifying and Solving Robust Empirical Risk Minimization Problems Using CVXPY
- WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction
- Customizing General-Purpose Foundation Models for Medical Report Generation
- Toward Data Efficient Model Merging between Different Datasets without Performance Degradation
- On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning
- Reconstructing the somatotopic organization of the corticospinal tract remains a challenge for modern tractography methods
- Improving Quantum Circuit Synthesis with Machine Learning
- Low-rank Adaptation Method for Wav2vec2-based Fake Audio Detection
- Spatial Re-parameterization for N:M Sparsity
- Word sense extension
- A Unified Generative Approach to Product Attribute-Value Identification