Papers
Thu 27 Apr 2023
202 papers
- Generating images of rare concepts using pre-trained diffusion modelsDiffusion models → Image generation, text-to-image and editing
- Adversary Aware Continual LearningLLM safety and security → Backdoor and data poisoning attacks
- ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model TriggerLLM safety and security → Backdoor and data poisoning attacks
- Learning a Diffusion Prior for NeRFsDiffusion models → 3D, point cloud and scene generation
- Motion-Conditioned Diffusion Model for Controllable Video SynthesisDiffusion models → Video generation
- Analogy-Forming Transformers for Few-Shot 3D ParsingLLM reasoning → Spatial and embodied reasoning
- Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous DrivingWorld models → World models for autonomous driving
- CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual AssistantsLLM safety and security → Safety alignment, refusal and guardrails
- Self-discipline on multiple channelsKnowledge distillation → General knowledge distillation methods
- DataComp: In search of the next generation of multimodal datasetsDiffusion models → Image generation, text-to-image and editing
- Retrieval-based Knowledge Augmented Vision Language Pre-trainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Federated Prompting and Chain-of-Thought Reasoning for Improving LLMs AnsweringLLM reasoning → Test-time compute and efficient thinking
- Auto-Linear Phenomenon in Subsurface Imaging
- Molecule-Morphology Contrastive Pretraining for Transferable Molecular Representation
- Mean Estimation Under Heterogeneous Privacy: Some Privacy Can Be Free
- BactInt: A domain driven transfer learning approach and a corpus for extracting inter-bacterial interactions from biomedical text
- SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition
- Predicting the Price Movement of Cryptocurrencies Using Linear Law-based Transformation
- Understanding the Impact of Culture in Assessing Helpfulness of Online Reviews
- Modeling glycemia in humans by means of Grammatical Evolution
- Deep Ensembles to Improve Uncertainty Quantification of Statistical Downscaling Models under Climate Change Conditions
- On the use of Deep Generative Models for Perfect Prognosis Climate Downscaling
- BCQQ: Batch-Constraint Quantum Q-Learning with Cyclic Data Re-uploading
- Molecular Design Based on Integer Programming and Splitting Data Sets by Hyperplanes
- An Empirical Comparison of Optimizers for Quantum Machine Learning with SPSA-based Gradients
- The Rio Hortega University Hospital Glioblastoma dataset: a comprehensive collection of preoperative, early postoperative and recurrence MRI scans (RHUH-GBM)
- Uncertainty Aware Neural Network from Similarity and Sensitivity
- Visual Diagrammatic Queries in ViziQuer: Overview and Implementation
- Neural Implicit Dense Semantic SLAM
- Appropriateness is all you need!
- Augmented balancing weights as linear regression
- Discourse over Discourse: The Need for an Expanded Pragmatic Focus in Conversational AI
- Deep Spatiotemporal Clustering: A Temporal Clustering Approach for Multi-dimensional Climate Data
- Optimal partition of feature using Bayesian classifier
- Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization
- Adversarial Policy Optimization in Deep Reinforcement Learning
- High-dimensional Clustering onto Hamiltonian Cycle
- Multivariate Representation Learning for Information Retrieval
- Multimodal Dataset from Harsh Sub-Terranean Environment with Aerosol Particles for Frontier Exploration
- pyBibX -- A Python Library for Bibliometric and Scientometric Analysis Powered with Artificial Intelligence Tools
- Understanding Shared Speech-Text Representations
- Visual Referential Games Further the Emergence of Disentangled Representations
- OriCon3D: Effective 3D Object Detection using Orientation and Confidence
- A Chain Rule for the Expected Suprema of Bernoulli Processes
- Controllable One-Shot Face Video Synthesis With Semantic Aware Prior
- Nordic Vehicle Dataset (NVD): Performance of vehicle detectors using newly captured NVD from UAV in different snowy weather conditions
- Moccasin: Efficient Tensor Rematerialization for Neural Networks
- Robust and Fast Vehicle Detection using Augmented Confidence Map
- Gradient-based Maximally Interfered Retrieval for Domain Incremental 3D Object Detection
- Framing the News:From Human Perception to Large Language Model Inferences
- PMC-LLaMA: Towards Building Open-source Language Models for Medicine
- Machine Learning for Detection and Mitigation of Web Vulnerabilities and Web Attacks
- Analyzing Vietnamese Legal Questions Using Deep Neural Networks with Biaffine Classifiers
- HyperMODEST: Self-Supervised 3D Object Detection with Confidence Score Filtering
- Raspberry Pi Bee Health Monitoring Device
- Blind Signal Separation for Fast Ultrasound Computed Tomography
- Learning Environment for the Air Domain (LEAD)
- MINN: Learning the dynamics of differential-algebraic equations and application to battery modeling
- One-Step Distributional Reinforcement Learning
- Network Cascade Vulnerability using Constrained Bayesian Optimization
- Unsupervised Learning of Robust Spectral Shape Matching
- ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System
- Putting People in Their Place: Affordance-Aware Human Insertion into Scenes
- ViMQ: A Vietnamese Medical Question Dataset for Healthcare Dialogue System Development
- Make It So: Steering StyleGAN for Any Image Inversion and Editing
- LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions
- ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs
- IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers
- We're Afraid Language Models Aren't Modeling Ambiguity
- Maximizing Model Generalization for Machine Condition Monitoring with Self-Supervised Learning and Federated Learning
- Learning Articulated Shape with Keypoint Pseudo-labels from Web Images
- string2string: A Modern Python Library for String-to-String Algorithms
- Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
- Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
- Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplers
- Dynamic Pricing and Advertising with Demand Learning
- π-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
- Functional Diffusion Maps
- Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM
- Zero-shot Unsupervised Transfer Instance Segmentation
- Pseudo-Hamiltonian neural networks for learning partial differential equations
- Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics
- Structure Analysis of the FRP Rebar Using Computer Vision Techniques
- Industrial Engineering with Large Language Models: A case study of ChatGPT's performance on Oil & Gas problems
- LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Prediction
- SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection
- ZeroShotDataAug: Generating and Augmenting Training Data with ChatGPT
- Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space
- On the Generalization Error of Meta Learning for the Gibbs Algorithm
- Learning to Extrapolate: A Transductive Approach
- A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints
- Pushing the Boundaries of Tractable Multiperspective Reasoning: A Deduction Calculus for Standpoint EL+
- Person Re-ID through Unsupervised Hypergraph Rank Selection and Fusion
- q2d: Turning Questions into Dialogs to Teach Models How to Search
- ICE-Score: Instructing Large Language Models to Evaluate Code
- A Measurement of the Kuiper Belt's Mean Plane From Objects Classified By Machine Learning
- Incremental Generalized Category Discovery
- Double-Deck Multi-Agent Pickup and Delivery: Multi-Robot Rearrangement in Large-Scale Warehouses
- A Method for Classifying Snow Using Ski-Mounted Strain Sensors
- Combining HoloLens with Instant-NeRFs: Advanced Real-Time 3D Mobile Mapping
All 202
- Learning Absorption Rates in Glucose-Insulin Dynamics from Meal Covariates
- A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image
- Instance Segmentation in the Dark
- Controlled Text Generation with Natural Language Instructions
- EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation
- Semantic Frame Induction with Deep Metric Learning
- Distinguishing a planetary transit from false positives: a Transformer-based classification for planetary transit signals
- Adaptive manifold for imbalanced transductive few-shot learning
- FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations
- Variational Bayes Made Easy
- On Manifold Learning in Plato's Cave: Remarks on Manifold Learning and Physical Phenomena
- Standpoint Linear Temporal Logic
- Entity-Level Sentiment Analysis (ELSA): An exploratory task survey
- The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who
- Large Language Models are Strong Zero-Shot Retriever
- TorchBench: Benchmarking PyTorch with High API Surface Coverage
- A Modular Approach for Multilingual Timex Detection and Normalization using Deep Learning and Grammar-based methods
- Some of the variables, some of the parameters, some of the times, with some physics known: Identification with partial information
- LLT: An R package for Linear Law-based Feature Space Transformation
- A transparent approach to data representation
- Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games
- Quadric Representations for LiDAR Odometry, Mapping and Localization
- UIO at SemEval-2023 Task 12: Multilingual fine-tuning for sentiment classification in low-resource languages
- HPSCAN: Human Perception-Based Scattered Data Clustering
- NAP at SemEval-2023 Task 3: Is Less Really More? (Back-)Translation as Data Augmentation Strategies for Detecting Persuasion Techniques
- mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
- ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Task
- Exploring the flavor structure of quarks and leptons with reinforcement learning
- An Algorithm for Computing with Brauer's Group Equivariant Neural Network Layers
- Spiking Neural Network Decision Feedback Equalization for IM/DD Systems
- Categorification of Group Equivariant Neural Networks
- VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Bias
- Human Semantic Segmentation using Millimeter-Wave Radar Sparse Point Clouds
- TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regression
- Why not both? Complementing explanations with uncertainty, and the role of self-confidence in Human-AI collaboration
- Preference Inference from Demonstration in Multi-objective Multi-agent Decision Making
- Density Invariant Contrast Maximization for Neuromorphic Earth Observations
- Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation
- MCLFIQ: Mobile Contactless Fingerprint Image Quality
- Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification
- Learning Neural PDE Solvers with Parameter-Guided Channel Attention
- Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach
- Towards Precise Weakly Supervised Object Detection via Interactive Contrastive Learning of Context Information
- The Structurally Complex with Additive Parent Causality (SCARY) Dataset
- ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time
- Learning Human-Human Interactions in Images from Weak Textual Supervision
- SocNavGym: A Reinforcement Learning Gym for Social Navigation
- Categorical Foundations of Explainable AI: A Unifying Theory
- RegHEC: Hand-Eye Calibration via Simultaneous Multi-view Point Clouds Registration of Arbitrary Object
- JaxPruner: A concise library for sparsity research
- Cluster Flow: how a hierarchical clustering layer make allows deep-NNs more resilient to hacking, more human-like and easily implements relational reasoning
- ganX -- generate artificially new XRF a python library to generate MA-XRF raw data out of RGB images
- Origin Tracing and Detecting of LLMs
- Automatically Segment the Left Atrium and Scars from LGE-MRIs Using a Boundary-focused nnU-Net
- Compositional 3D Human-Object Neural Animation
- Interpretable Neural-Symbolic Concept Reasoning
- Lightweight, Pre-trained Transformers for Remote Sensing Timeseries
- A Parameterized Theory of PAC Learning
- Propagating Kernel Ambiguity Sets in Nonlinear Data-driven Dynamics Models
- Precise Few-shot Fat-free Thigh Muscle Segmentation in T1-weighted MRI
- Interweaved Graph and Attention Network for 3D Human Pose Estimation
- Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Records
- Spherical Inducing Features for Orthogonally-Decoupled Gaussian Processes
- COSST: Multi-organ Segmentation with Partially Labeled Datasets Using Comprehensive Supervisions and Self-training
- Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximization
- XAI-based Comparison of Input Representations for Audio Event Classification
- Edit Everything: A Text-Guided Generative System for Images Editing
- ContraNeRF: 3D-Aware Generative Model via Contrastive Learning with Unsupervised Implicit Pose Embedding
- Mimic-IV-ICD: A new benchmark for eXtreme MultiLabel Classification
- Rotation and Translation Invariant Representation Learning with Implicit Neural Representations
- SweCTRL-Mini: a data-transparent Transformer-based large language model for controllable text generation in Swedish
- Vision Conformer: Incorporating Convolutions into Vision Transformer Layers
- Cross-Domain Evaluation of POS Taggers: From Wall Street Journal to Fandom Wiki
- Contour Completion by Transformers and Its Application to Vector Font Data
- Optimization-Inspired Cross-Attention Transformer for Compressive Sensing
- A Review of Panoptic Segmentation for Mobile Mapping Point Clouds
- Adaptive-Mask Fusion Network for Segmentation of Drivable Road and Negative Obstacle With Untrustworthy Features
- Moderately Distributional Exploration for Domain Generalization
- SkinSAM: Empowering Skin Cancer Segmentation with Segment Anything Model
- Convergence of Adam Under Relaxed Assumptions
- Human-machine knowledge hybrid augmentation method for surface defect detection based few-data learning
- Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be
- Learning and Reasoning Multifaceted and Longitudinal Data for Poverty Estimates and Livelihood Capabilities of Lagged Regions in Rural India
- Automatic Localization and Detection Applicable to Robust Image Watermarking Resisting against Camera Shooting
- Fairness Uncertainty Quantification: How certain are you that the model is fair?
- UCF: Uncovering Common Features for Generalizable Deepfake Detection
- A Majorization-Minimization Gauss-Newton Method for 1-Bit Matrix Completion
- A Deep Registration Method for Accurate Quantification of Joint Space Narrowing Progression in Rheumatoid Arthritis
- Towards Explainable Collaborative Filtering with Taste Clusters Learning
- Oversampling Higher-Performing Minorities During Machine Learning Model Training Reduces Adverse Impact Slightly but Also Reduces Model Accuracy
- NIMS-OS: An automation software to implement a closed loop between artificial intelligence and robotic experiments in materials science
- Level Assembly as a Markov Decision Process
- Detection of Adversarial Physical Attacks in Time-Series Image Data
- Proportionally Representative Clustering
- MIPI 2023 Challenge on RGB+ToF Depth Completion: Methods and Results
- LSTM based IoT Device Identification
- Controllable Data Augmentation for Context-Dependent Text-to-SQL
- Rumor Detection with Hierarchical Representation on Bipartite Adhoc Event Trees
- CNN-based IoT Device Identification: A Comparative Study on Payload vs. Fingerprint
- Discovering Object-Centric Generalized Value Functions From Pixels
- Improving the Utility of Differentially Private Clustering through Dynamical Processing
- Neural Keyphrase Generation: Analysis and Evaluation