Papers
Tue 28 Mar 2023
222 papers
- Training Language Models with Language Feedback at ScaleLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- Your Diffusion Model is Secretly a Zero-Shot ClassifierDiffusion models → Image generation, text-to-image and editing
- BC-IRL: Learning Generalizable Reward Functions from DemonstrationsOffline RL and imitation learning from data → Inverse reinforcement learning
- Visual Chain-of-Thought Diffusion ModelsLLM reasoning → Multimodal reasoning +1
- Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Cellular EXchange Imaging (CEXI): Evaluation of a diffusion model including water exchange in cells using numerical phantoms of permeable spheresDiffusion models → Medical imaging and segmentation
- Information-Theoretic GAN Compression with Variational Energy-based ModelKnowledge distillation → General knowledge distillation methods
- Offline RL with No OOD Actions: In-Sample Learning via Implicit Value RegularizationOffline RL and imitation learning from data → Offline RL algorithms
- HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
- DDMM-Synth: A Denoising Diffusion Model for Cross-modal Medical Image Synthesis with Sparse-view Measurement EmbeddingDiffusion models → Medical imaging and segmentation
- Explicit Planning Helps Language Models in Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- DisWOT: Student Architecture Search for Distillation WithOut TrainingKnowledge distillation → General knowledge distillation methods
- StyleDiffusion: Prompt-Embedding Inversion for Text-Based EditingDiffusion models → Image generation, text-to-image and editing
- Distributed Neural Representation for Reactive in situ Visualization
- Smart Home Environment Modelled with a Multi-Agent System
- Joint optimization of a β-VAE for ECG task-specific feature extraction
- Quantifying the Impact of Data Characteristics on the Transferability of Sleep Stage Scoring Models
- GeoTMI:Predicting quantum chemical property with easy-to-obtain geometry via positional denoising
- Sejarah dan Perkembangan Teknik Natural Language Processing (NLP) Bahasa Indonesia: Tinjauan tentang sejarah, perkembangan teknologi, dan aplikasi NLP dalam bahasa Indonesia
- Comparative Analysis of CHATGPT and the evolution of language models
- The challenge of redundancy on multi-agent value factorisation
- Robust and IP-Protecting Vertical Federated Learning against Unexpected Quitting of Parties
- Machine-learned Adversarial Attacks against Fault Prediction Systems in Smart Electrical Grids
- Cost Sensitive GNN-based Imbalanced Learning for Mobile Social Network Fraud Detection
- FeDiSa: A Semi-asynchronous Federated Learning Framework for Power System Fault and Cyberattack Discrimination
- Language Models Trained on Media Diets Can Predict Public Opinion
- Supervised Learning for Table Tennis Match Prediction
- How can Deep Learning Retrieve the Write-Missing Additional Diagnosis from Chinese Electronic Medical Record For DRG
- Improving Code Generation by Training with Natural Language Feedback
- A Hierarchical Game-Theoretic Decision-Making for Cooperative Multi-Agent Systems Under the Presence of Adversarial Agents
- Adaptive Scaffolding in Block-Based Programming via Synthesizing New Tasks as Pop Quizzes
- ChatGPT or academic scientist? Distinguishing authorship with over 99% accuracy using off-the-shelf machine learning tools
- Facial recognition technology and human raters can predict political orientation from images of expressionless faces even when controlling for demographics and self-presentation
- Language-Guided Audio-Visual Source Separation via Trimodal Consistency
- Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding
- On the Local Cache Update Rules in Streaming Federated Learning
- Flow supervision for Deformable NeRF
- FMAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation
- Worst-Case Control and Learning Using Partial Observations Over an Infinite Time-Horizon
- SynthRAD2023 Grand Challenge dataset: generating synthetic CT for radiotherapy
- Operator learning with PCA-Net: upper and lower complexity bounds
- Crime Prediction Using Machine Learning and Deep Learning: A Systematic Review and Future Directions
- Provable Robustness for Streaming Models with a Sliding Window
- A Machine Learning Outlook: Post-processing of Global Medium-range Forecasts
- Comparison of Methods that Combine Multiple Randomized Trials to Estimate Heterogeneous Treatment Effects
- Dice Semimetric Losses: Optimizing the Dice Score with Soft Labels
- SnakeVoxFormer: Transformer-based Single ImageVoxel Reconstruction with Run Length Encoding
- XAIR: A Framework of Explainable AI in Augmented Reality
- A "Perspectival" Mirror of the Elephant: Investigating Language Bias on Google, ChatGPT, YouTube, and Wikipedia
- UVCGAN v2: An Improved Cycle-Consistent GAN for Unpaired Image-to-Image Translation
- Accelerated Cyclic Coordinate Dual Averaging with Extrapolation for Composite Convex Optimization
- Writing Assistants Should Model Social Factors of Language
- Accelerated wind farm yaw and layout optimisation with multi-fidelity deep transfer learning wake models
- Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples
- TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
- On-line reinforcement learning for optimization of real-life energy trading strategy
- Optimisation via encodings: a renormalisation group perspective
- Scalable handwritten text recognition system for lexicographic sources of under-resourced languages and alphabets
- CryoFormer: Continuous Heterogeneous Cryo-EM Reconstruction using Transformer-based Neural Representations
- Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema
- Function Approximation with Randomly Initialized Neural Networks for Approximate Model Reference Adaptive Control
- Data Efficient Contrastive Learning in Histopathology using Active Sampling
- ytopt: Autotuning Scientific Applications for Energy Efficiency at Large Scales
- On Codex Prompt Engineering for OCL Generation: An Empirical Study
- CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution
- Convergence of the Stochastic Heavy Ball Method With Approximate Gradients and/or Block Updating
- Spatiotemporal Self-supervised Learning for Point Clouds in the Wild
- Tetra-AML: Automatic Machine Learning via Tensor Networks
- A Multi-objective Complex Network Pruning Framework Based on Divide-and-conquer and Global Performance Impairment Ranking
- Combinatorial Convolutional Neural Networks for Words
- Towards Reliable Uncertainty Quantification via Deep Ensembles in Multi-output Regression Task
- CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes
- ASIC: Aligning Sparse in-the-wild Image Collections
- Natural Selection Favors AIs over Humans
- LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
- Multi-modal learning for geospatial vegetation forecasting
- SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
- Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection
- Planning with Sequence Models through Iterative Energy Minimization
- Large-scale Training Data Search for Object Re-identification
- VMesh: Hybrid Volume-Mesh Representation for Efficient View Synthesis
- Learning Federated Visual Prompt in Null Space for MRI Reconstruction
- Towards Countering Essentialism through Social Bias Reasoning
- Diffusion Maps for Group-Invariant Manifolds
- When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP
- One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
- A Comparative Study of Federated Learning Models for COVID-19 Detection
- Transformer and Snowball Graph Convolution Learning for Brain functional network Classification
- Evaluating the Effectiveness of 2D and 3D Features for Predicting Tumor Response to Chemotherapy
- CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection
- Invariant preservation in machine learned PDE solvers via error correction
- Multimodal Manoeuvre and Trajectory Prediction for Automated Driving on Highways Using Transformer Networks
- Variational Distribution Learning for Unsupervised Text-to-Image Generation
- Hallucinations in Large Multilingual Translation Models
- KeyMatchNet: Zero-Shot Pose Estimation in 3D Point Clouds by Generalized Keypoint Matching
- Medical Image Analysis using Deep Relational Learning
- Carolina: a General Corpus of Contemporary Brazilian Portuguese with Provenance, Typology and Versioning Information
- Attention Boosted Autoencoder for Building Energy Anomaly Detection
- LinK: Linear Kernel for LiDAR-based 3D Perception
- Learnability, Sample Complexity, and Hypothesis Class Complexity for Regression Models
All 222
- Whole-body PET image denoising for reduced acquisition time
- Rethinking matching-based few-shot action recognition
- Practical solutions to the relative pose of three calibrated cameras
- Unmasked Teacher: Towards Training-Efficient Video Foundation Models
- Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video
- Exploring and Interacting with the Set of Good Sparse Generalized Additive Models
- An Optimal, Universal and Agnostic Decoding Method for Message Reconstruction, Bio and Technosignature Detection
- Synthetically generated text for supervised text analysis
- Egocentric Auditory Attention Localization in Conversations
- Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction
- A Survey on Malware Detection with Graph Representation Learning
- Adaptive Voronoi NeRFs
- Thread Counting in Plain Weave for Old Paintings Using Semi-Supervised Regression Deep Learning Models
- HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation
- SELF-VS: Self-supervised Encoding Learning For Video Summarization
- Sentiment Analysis Dataset in Moroccan Dialect: Bridging the Gap Between Arabic and Latin Scripted dialect
- Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
- Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modeling
- SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis
- Multimodal and multicontrast image fusion via deep generative models
- TraffNet: Learning Causality of Traffic Generation for What-if Prediction
- Randomly Initialized Subnetworks with Iterative Weight Recycling
- F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories
- A source separation approach to temporal graph modelling for computer networks
- Sparse Gaussian Processes with Spherical Harmonic Features Revisited
- Deep Selection: A Fully Supervised Camera Selection Network for Surgery Recordings
- Item Graph Convolution Collaborative Filtering for Inductive Recommendations
- Cluster-Guided Unsupervised Domain Adaptation for Deep Speaker Embedding
- Generating artificial digital image correlation data using physics-guided adversarial networks
- fRegGAN with K-space Loss Regularization for Medical Image Translation
- PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout
- Searching for long faint astronomical high energy transients: a data driven approach
- When Brain-inspired AI Meets AGI
- Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation
- Fully Hyperbolic Convolutional Neural Networks for Computer Vision
- From Private to Public: Benchmarking GANs in the Context of Private Time Series Classification
- Mask-Free Video Instance Segmentation
- Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm
- Efficient Quality Diversity Optimization of 3D Buildings through 2D Pre-optimization
- VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs
- Head3D: Complete 3D Head Generation via Tri-plane Feature Distillation
- Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition
- Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual Learning
- Novel View Synthesis of Humans using Differentiable Rendering
- STMixer: A One-Stage Sparse Action Detector
- A Multi-Granularity Matching Attention Network for Query Intent Classification in E-commerce Retrieval
- Efficient Alternating Minimization Solvers for Wyner Multi-View Unsupervised Learning
- The Wyner Variational Autoencoder for Unsupervised Multi-Layer Wireless Fingerprinting
- OpenInst: A Simple Query-Based Method for Open-World Instance Segmentation
- Exploring Deep Learning Methods for Classification of SAR Images: Towards NextGen Convolutions via Transformers
- That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentation
- GAS: A Gaussian Mixture Distribution-Based Adaptive Sampling Method for PINNs
- 4K-HAZE: A Dehazing Benchmark with 4K Resolution Hazy and Haze-Free Images
- Soft-prompt tuning to predict lung cancer using primary care free-text Dutch medical notes
- Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems
- CREATED: Generating Viable Counterfactual Sequences for Predictive Process Analytics
- Sparse Depth-Guided Attention for Accurate Depth Completion: A Stereo-Assisted Monitored Distillation Approach
- AutoKary2022: A Large-Scale Densely Annotated Dataset for Chromosome Instance Segmentation
- Enabling Inter-organizational Analytics in Business Networks Through Meta Machine Learning
- Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning
- The transformative potential of machine learning for experiments in fluid mechanics
- CONFIDE: Contextual Finite Differences Modelling of PDEs
- MS-MT: Multi-Scale Mean Teacher with Contrastive Unpaired Translation for Cross-Modality Vestibular Schwannoma and Cochlea Segmentation
- Pareto Optimization of a Laser Wakefield Accelerator
- Automated wildlife image classification: An active learning tool for ecological applications
- One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization
- Scaling Multi-Objective Security Games Provably via Space Discretization Based Evolutionary Search
- Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition
- Kernel interpolation generalizes poorly
- StarNet: Style-Aware 3D Point Cloud Generation
- FedAgg: Adaptive Federated Learning with Aggregated Gradients
- KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation
- SDAT: Sub-Dataset Alternation Training for Improved Image Demosaicing
- CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
- Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversion
- Ecosystem Graphs: The Social Footprint of Foundation Models
- RobustSwap: A Simple yet Robust Face Swapping Model against Attribute Leakage
- X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance
- Learning Second-Order Attentive Context for Efficient Correspondence Pruning
- Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization
- Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image Classification
- SVD-DIP: Overcoming the Overfitting Problem in DIP-based CT Reconstruction
- TabRet: Pre-training Transformer-based Tabular Models for Unseen Columns
- qEUBO: A Decision-Theoretic Acquisition Function for Preferential Bayesian Optimization
- On Feature Scaling of Recursive Feature Machines
- HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation
- System-status-aware Adaptive Network for Online Streaming Video Understanding
- Concentration of Contractive Stochastic Approximation: Additive and Multiplicative Noise
- Bayesian Free Energy of Deep ReLU Neural Network in Overparametrized Cases
- Deformable Kernel Expansion Model for Efficient Arbitrary-shaped Scene Text Detection
- Improving the Transferability of Adversarial Samples by Path-Augmented Method
- Adaptive Background Music for a Fighting Game: A Multi-Instrument Volume Modulation Approach
- Evaluation of ChatGPT for NLP-based Mental Health Applications
- Solving Regularized Exp, Cosh and Sinh Regression Problems
- Scalable, Detailed and Mask-Free Universal Photometric Stereo
- MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction
- Foundation Models and Fair Use
- Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks
- Bias or Diversity? Unraveling Fine-Grained Thematic Discrepancy in U.S. News Headlines
- Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyrics
- Distributed Graph Embedding with Information-Oriented Random Walks
- Enhancing Breast Cancer Risk Prediction by Incorporating Prior Images
- TFS-ViT: Token-Level Feature Stylization for Domain Generalization
- Model and Evaluation: Towards Fairness in Multilingual Text Classification
- Large-scale pretraining on pathological images for fine-tuning of small pathological benchmarks
- Deep Incomplete Multi-view Clustering with Cross-view Partial Sample and Prototype Alignment
- Efficient Deep Learning of Robust, Adaptive Policies using Tube MPC-Guided Data Augmentation
- Pre-training Transformers for Knowledge Graph Completion
- GNN-based physics solver for time-independent PDEs
- Cross-View Visual Geo-Localization for Outdoor Augmented Reality
- Numerical Methods for Convex Multistage Stochastic Optimization
- Colo-SCRL: Self-Supervised Contrastive Representation Learning for Colonoscopic Video Retrieval
- Unsupervised Pre-Training For Data-Efficient Text-to-Speech On Low Resource Languages
- Predicting Thermoelectric Power Factor of Bismuth Telluride During Laser Powder Bed Fusion Additive Manufacturing
- ChatGPT4PCG Competition: Character-like Level Generation for Science Birds
- Boundary-to-Solution Mapping for Groundwater Flows in a Toth Basin
- Predicting Adverse Neonatal Outcomes for Preterm Neonates with Multi-Task Learning
- Joint embedding in Hierarchical distance and semantic representation learning for link prediction
- Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network
- Structured Dynamic Pricing: Optimal Regret in a Global Shrinkage Model
- 4D Panoptic Segmentation as Invariant and Equivariant Field Prediction
- Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning