Papers
Fri 18 Nov 2022
149 papers
- Visual Programming: Compositional visual reasoning without trainingLLM reasoning → Multimodal reasoning
- Magic3D: High-Resolution Text-to-3D Content CreationDiffusion models → 3D, point cloud and scene generation
- A Structure-Guided Diffusion Model for Large-Hole Image CompletionDiffusion models → 3D, point cloud and scene generation
- PAL: Program-aided Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
- Patch-Based Denoising Diffusion Probabilistic Model for Sparse-View CT ReconstructionDiffusion models → Medical imaging and segmentation
- Task Residual for Tuning Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Rationale-aware Autonomous Driving Policy utilizing Safety Force Field implemented on CARLA SimulatorEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- Computational Short Cuts in Infinite Domain Constraint SatisfactionLLM safety and security → Backdoor and data poisoning attacks
- Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale ProductionMixture-of-experts → MoE large language models
- Dataset of Pathloss and ToA Radio Maps With Localization Application
- GPS++: An Optimised Hybrid MPNN/Transformer for Molecular Property Prediction
- Where did you tweet from? Inferring the origin locations of tweets based on contextual information
- Toward a Flexible Metadata Pipeline for Fish Specimen Images
- Explanation on Pretraining Bias of Finetuned Vision Transformer
- Masked Autoencoders for Egocentric Video Understanding @ Ego4D Challenge 2022
- EEG aided boosting of single-lead ECG based sleep staging with Deep Knowledge Distillation
- Step Counting with Attention-based LSTM
- Challenges in Gaussian Processes for Non Intrusive Load Monitoring
- A Network Classification Method based on Density Time Evolution Patterns Extracted from Network Automata
- Towards Automatic Prediction of Outcome in Treatment of Cerebral Aneurysms
- Dialogs Re-enacted Across Languages
- Recommending Related Products Using Graph Neural Networks in Directed Graphs
- Detect Only What You Specify : Object Detection with Linguistic Target
- 2CET-GAN: Pixel-Level GAN Model for Human Facial Expression Transfer
- IEEE Big Data Cup 2022: Privacy Preserving Matching of Encrypted Images with Deep Learning
- Adaptive Constraint Partition based Optimization Framework for Large-scale Integer Linear Programming(Student Abstract)
- SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness
- DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
- Semantic Encoder Guided Generative Adversarial Face Ultra-Resolution Network
- Provable Defense against Backdoor Policies in Reinforcement Learning
- Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization
- Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
- Differentiable Uncalibrated Imaging
- Social Diversity Reduces the Complexity and Cost of Fostering Fairness
- Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments
- Knowledge Graph Generation From Text
- Distributionally Robust Survival Analysis: A Novel Fairness Loss Without Demographics
- A Transformer Framework for Data Fusion and Multi-Task Learning in Smart Cities
- A Mathematical Programming Approach to Optimal Classification Forests
- A mixed-reality dataset for category-level 6D pose and size estimation of hand-occluded containers
- Hub-VAE: Unsupervised Hub-based Regularization of Variational Autoencoders
- Knowledge Graph Refinement based on Triplet BERT-Networks
- Discovering Locally Maximal Bipartite Subgraphs
- Building a Subspace of Policies for Scalable Continual Learning
- Neural Fields for Fast and Scalable Interpolation of Geophysical Ocean Variables
- Social media mining for toxicovigilance of prescription medications: End-to-end pipeline, challenges and future work
- Deep learning methods for drug response prediction in cancer: predominant and emerging trends
- BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
- Forecasting labels under distribution-shift for machine-guided sequence design
- CNeRV: Content-adaptive Neural Representation for Visual Data
- Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes
- CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval
- CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow
- Indexing AI Risks with Incidents, Issues, and Variants
- Informative Sample-Aware Proxy for Deep Metric Learning
- Environmental Sensor Placement with Convolutional Gaussian Neural Processes
- Comparing Explanation Methods for Traditional Machine Learning Models Part 2: Quantifying Model Explainability Faithfulness and Improvements with Dimensionality Reduction
- Invariant Learning via Diffusion Dreamed Distribution Shifts
- Always Valid Risk Monitoring for Online Matrix Completion
- Deep learning based landslide density estimation on SAR data for rapid response
- A Unified Approach to Differentially Private Bayes Point Estimation
- GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation
- Understanding the double descent curve in Machine Learning
- SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification
- Evaluating generative models in high energy physics
- Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks
- A Fair Loss Function for Network Pruning
- Estimating more camera poses for ego-centric videos is essential for VQ3D
- Exploring through Random Curiosity with General Value Functions
- TensAIR: Real-Time Training of Neural Networks from Data-streams
- Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction
- SolderNet: Towards Trustworthy Visual Inspection of Solder Joints in Electronics Manufacturing Using Explainable Artificial Intelligence
- A Copy Mechanism for Handling Knowledge Base Elements in SPARQL Neural Machine Translation
- Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probing
- Integrated Space Domain Awareness and Communication System
- Model-based Causal Bayesian Optimization
- Delving into Transformer for Incremental Semantic Segmentation
- HiveNAS: Neural Architecture Search using Artificial Bee Colony Optimization
- GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state
- Knowing What to Label for Few Shot Microscopy Image Cell Segmentation
- GNS: A generalizable Graph Neural Network-based simulator for particulate and fluid modeling
- Adversarial Detection by Approximation of Ensemble Boundary
- Leveraging Multi-stream Information Fusion for Trajectory Prediction in Low-illumination Scenarios: A Multi-channel Graph Convolutional Approach
- On the Alignment of Group Fairness with Attribute Privacy
- Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenes
- Layer-Stack Temperature Scaling
- LVOS: A Benchmark for Long-term Video Object Segmentation
- Improving Pixel-Level Contrastive Learning by Leveraging Exogenous Depth Information
- Deep Gaussian Processes for Air Quality Inference
- How Do Input Attributes Impact the Privacy Loss in Differential Privacy?
- Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action Corrections
- Overview of the HASOC Subtrack at FIRE 2022: Offensive Language Identification in Marathi
- Optimal service station design for traffic mitigation via genetic algorithm and neural network
- FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering
- Joint nnU-Net and Radiomics Approaches for Segmentation and Prognosis of Head and Neck Cancers with PET/CT images
- Rare Yet Popular: Evidence and Implications from Labeled Datasets for Network Anomaly Detection
- Spatio-Temporal Feedback Control of Small Target Motion Detection Visual System
- Global quantitative robustness of regression feed-forward neural networks
- Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance
All 149
- Scaling Native Language Identification with Transformer Adapters
- α DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling
- Stereo Image Rain Removal via Dual-View Mutual Attention
- Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text Images
- Credit-cognisant reinforcement learning for multi-agent cooperation
- UnconFuse: Avatar Reconstruction from Unconstrained Images
- Metadata Might Make Language Models Better
- Identifying Unique Spatial-Temporal Bayesian Network without Markov Equivalence
- Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projections
- How to train your draGAN: A task oriented solution to imbalanced classification
- Intrusion Detection in Internet of Things using Convolutional Neural Networks
- Data-Adaptive Discriminative Feature Localization with Statistically Guaranteed Interpretation
- Normal Reference Attention and Defective Feature Perception Network for Surface Defect Detection
- Overview of the WANLP 2022 Shared Task on Propaganda Detection in Arabic
- Contrastive Losses Are Natural Criteria for Unsupervised Video Summarization
- Decorr: Environment Partitioning for Invariant Learning and OOD Generalization
- Pedestrian Spatio-Temporal Information Fusion For Video Anomaly Detection
- Recent Advances in Algebraic Geometry and Bayesian Statistics
- Clustering based opcode graph generation for malware variant detection
- Vision Transformers in Medical Imaging: A Review
- Why the pseudo label based semi-supervised learning algorithm is effective?
- Adversarial Stimuli: Attacking Brain-Computer Interfaces via Perturbed Sensory Events
- Contrastive Knowledge Graph Error Detection
- DGD-cGAN: A Dual Generator for Image Dewatering and Restoration
- Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks
- LiSnowNet: Real-time Snow Removal for LiDAR Point Cloud
- A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach
- Asymptotics for The k-means
- Active Learning by Query by Committee with Robust Divergences
- A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning
- Structural Quality Metrics to Evaluate Knowledge Graphs
- Confounder Balancing for Instrumental Variable Regression with Latent Variable
- 3d human motion generation from the text via gesture action classification and the autoregressive model
- Influential Recommender System
- Protein language model rescue mutations highlight variant effects and structure in clinically relevant genes
- Look More but Care Less in Video Recognition
- Pandering in a Flexible Representative Democracy
- Multi-task Learning for Sparse Traffic Forecasting
- Weighted Ensemble Self-Supervised Learning
- Contrastive Positive Sample Propagation along the Audio-Visual Event Line
- Comparison between EM and FCM algorithms in skin tone extraction
- The Runner-up Solution for YouTube-VIS Long Video Challenge 2022
- Estimating defection in subscription-type markets: empirical analysis from the scholarly publishing industry
- AVATAR submission to the Ego4D AV Transcription Challenge
- Path Independent Equilibrium Models Can Better Exploit Test-Time Computation
- Ask4Help: Learning to Leverage an Expert for Embodied Tasks
- Potential Auto-driving Threat: Universal Rain-removal Attack
- A Persian ASR-based SER: Modification of Sharif Emotional Speech Database and Investigation of Persian Text Corpora
- Towards Explaining Subjective Ground of Individuals on Social Media