Papers
Mon 28 Nov 2022
236 papers
- Refining Generative Process with Discriminator Guidance in Score-based Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- SuS-X: Training-Free Name-Only Transfer of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image ClassificationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
- Post-training Quantization on Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Is Conditional Generative Modeling all you need for Decision-Making?Diffusion models → Diffusion and flow policies for robotics +1
- Learning from Good Trajectories in Offline Multi-Agent Reinforcement LearningOffline RL and imitation learning from data → Offline multi-agent RL
- Lightning Fast Video Anomaly Detection via Adversarial Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- GPT-Neo for commonsense reasoning -- a theoretical and practical lensLLM reasoning → Reasoning benchmarks and evaluation
- Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement LearningOffline RL and imitation learning from data → Robot learning from demonstration
- The Myth of Culturally Agnostic AI ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Offline Q-Learning on Diverse Multi-Task Data Both Scales And GeneralizesOffline RL and imitation learning from data → Offline RL algorithms
- Continuous diffusion for categorical dataDiffusion models → Discrete and text diffusion
- Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech RecognitionKnowledge distillation → Speech and audio distillation
- State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- DiffusionBERT: Improving Generative Masked Language Models with Diffusion ModelsDiffusion models → Discrete and text diffusion
- Fine-tuning language models to find agreement among humans with diverse preferencesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- Accelerating Antimicrobial Peptide Discovery with Latent Structure
- Is it Required? Ranking the Skills Required for a Job-Title
- The AI Definition and a Program Which Satisfies this Definition
- On the Effective Usage of Priors in RSS-based Localization
- Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces
- Semisoft Task Clustering for Multi-Task Learning
- Handling and extracting key entities from customer conversations using Speech recognition and Named Entity recognition
- PAC Verification of Statistical Algorithms
- Reinforced Genetic Algorithm for Structure-based Drug Design
- D'ecouvrir de nouvelles classes dans des donn'ees tabulaires
- SLAN: Self-Locator Aided Network for Cross-Modal Understanding
- In-Hand 3D Object Scanning from an RGB Sequence
- Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shape
- Physics Informed Neural Network for Dynamic Stress Prediction
- CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces
- Personalized Reward Learning with Interaction-Grounded Learning (IGL)
- COVID-19 Classification Using Deep Learning Two-Stage Approach
- On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation
- Using a Conditional Generative Adversarial Network to Control the Statistical Characteristics of Generated Images for IACT Data Analysis
- Provably Efficient Model-free RL in Leader-Follower MDP with Linear Function Approximation
- Handling Image and Label Resolution Mismatch in Remote Sensing
- A Visual Active Search Framework for Geospatial Exploration
- Mathematically Modeling the Lexicon Entropy of Emergent Language
- Towards Preserving Semantic Structure in Argumentative Multi-Agent via Abstract Interpretation
- Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature
- VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces
- Decentralized Learning with Multi-Headed Distillation
- Approximate Gibbs Sampler for Efficient Inference of Hierarchical Bayesian Models for Grouped Count Data
- Accelerated Nonnegative Tensor Completion via Integer Programming
- Superpoint Transformer for 3D Scene Instance Segmentation
- Understanding the Impact of Adversarial Robustness on Accuracy Disparity
- PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud
- Confidence-Aware Graph Neural Networks for Learning Reliability Assessment Commitments
- Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques
- Sketch-and-solve approaches to k-means clustering by semidefinite programming
- CWD: A Machine Learning based Approach to Detect Unknown Cloud Workloads
- Predicting Football Match Outcomes with eXplainable Machine Learning and the Kelly Index
- An Empirical Study of Library Usage and Dependency in Deep Learning Frameworks
- Controlled Language Generation for Language Learning Items
- Direct Heterogeneous Causal Learning for Resource Allocation Problems in Marketing
- Malign Overfitting: Interpolation Can Provably Preclude Invariance
- Predicting pathways for old and new metabolites through clustering
- Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models
- Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation
- H3WB: Human3.6M 3D WholeBody Dataset and Benchmark
- Neural networks: solving the chemistry of the interstellar medium
- PyTorch Adapt
- Deep Semi-supervised Learning with Double-Contrast of Features and Semantics
- Hand-Object Interaction Image Generation
- High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization
- What learning algorithm is in-context learning? Investigations with linear models
- SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding
- Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries
- SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation
- OpenScene: 3D Scene Understanding with Open Vocabularies
- Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources
- Beyond Invariance: Test-Time Label-Shift Adaptation for Distributions with "Spurious" Correlations
- Efficient Mirror Detection via Multi-level Heterogeneous Learning
- Benchmarking simulated and physical quantum processing units using quantum and hybrid algorithms
- Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data
- Frustratingly Easy Label Projection for Cross-lingual Transfer
- Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation
- Fast-SNARF: A Fast Deformer for Articulated Neural Fields
- A survey of deep learning optimizers -- first and second order methods
- FsaNet: Frequency Self-attention for Semantic Segmentation
- A Bayesian Approach for the Network Reconstruction of Interdependent Critical Infrastructure Systems from Cascading Failures
- Inapplicable Actions Learning for Knowledge Transfer in Reinforcement Learning
- On the Effectiveness of Parameter-Efficient Fine-Tuning
- Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality
- Exoplanet Detection by Machine Learning with Data Augmentation
- Automatically generating question-answer pairs for assessing basic reading comprehension in Swedish
- Neuro-Symbolic Spatio-Temporal Reasoning
- A Critical Analysis of Classifier Selection in Learned Bloom Filters
- Machine Learning for Health symposium 2022 -- Extended Abstract track
- Graph Neural Networks for Breast Cancer Data Integration
- Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies
- Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers
- AI Enabled Maneuver Identification via the Maneuver Identification Challenge
- Realtime Data-Efficient Portrait Stylization Based On Geometric Alignment
- Automatically Extracting Information in Medical Dialogue: Expert System And Attention for Labelling
- Graph Convolutional Network for Multi-Target Multi-Camera Vehicle Tracking
- Sentiment analysis and opinion mining on E-commerce site
- A Study of Representational Properties of Unsupervised Anomaly Detection in Brain MRI
- Differentiable Dictionary Search: Integrating Linear Mixing with Deep Non-Linear Modelling for Audio Source Separation
All 236
- Zero-Order Optimization for Gaussian Process-based Model Predictive Control
- G^3: Geolocation via Guidebook Grounding
- DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding
- Object Permanence in Object Detection Leveraging Temporal Priors at Inference Time
- Proactive Robot Assistance via Spatio-Temporal Object Modeling
- Physics-informed Neural Networks with Unknown Measurement Noise
- Discovering Dynamic Patterns from Spatiotemporal Data with Time-Varying Low-Rank Autoregression
- Meta-analysis of individualized treatment rules via sign-coherency
- Unsupervised Superpixel Generation using Edge-Sparse Embedding
- Learning to Learn: How to Continuously Teach Humans and Machines
- Considerations for meaningful sign language machine translation based on glosses
- Hypernetworks for Zero-shot Transfer in Reinforcement Learning
- Near-Field Channel Estimation for Extremely Large-Scale Array Communications: A model-based deep learning approach
- Probabilistic Modelling of Signal Mixtures with Differentiable Dictionaries
- Context-Adaptive Deep Neural Networks via Bridge-Mode Connectivity
- E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model
- Automated Detection of Dolphin Whistles with Convolutional Networks and Transfer Learning
- Perceive, Ground, Reason, and Act: A Benchmark for General-purpose Visual Representation
- On the Security Vulnerabilities of Text-to-SQL Models
- Exploring the Coordination of Frequency and Attention in Masked Image Modeling
- Causal Deep Reinforcement Learning Using Observational Data
- Shielding in Resource-Constrained Goal POMDPs
- You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets
- Beyond S-curves: Recurrent Neural Networks for Technology Forecasting
- A Survey on Conversational Search and Applications in Biomedicine
- Task-Aware Asynchronous Multi-Task Model with Class Incremental Contrastive Learning for Surgical Scene Understanding
- Low-resource Personal Attribute Prediction from Conversation
- Transductive Kernels for Gaussian Processes on Graphs
- RankDNN: Learning to Rank for Few-shot Learning
- MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer
- NeuralMPS: Non-Lambertian Multispectral Photometric Stereo via Spectral Reflectance Decomposition
- Stochastic Steffensen method
- Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors
- Conditional Progressive Generative Adversarial Network for satellite image generation
- Learning Coherent Clusters in Weakly-Connected Network Systems
- Flow: Per-Instance Personalized Federated Learning Through Dynamic Routing
- Establishment of Neural Networks Robust to Label Noise
- Topologically faithful image segmentation via induced matching of persistence barcodes
- Scientific and Creative Analogies in Pretrained Language Models
- Assessing Bias in Face Image Quality Assessment
- HERDPhobia: A Dataset for Hate Speech against Fulani in Nigeria
- A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
- Bayesian Network Models of Causal Interventions in Healthcare Decision Making: Literature Review and Software Evaluation
- ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awareness
- Lipschitz constant estimation for 1D convolutional neural networks
- DeepAngle: Fast calculation of contact angles in tomography images using deep learning
- Synthetic Principal Component Design: Fast Covariate Balancing with Synthetic Controls
- Reducing Domain Gap in Frequency and Spatial domain for Cross-modality Domain Adaptation on Medical Image Segmentation
- Shoupa: An AI System for Early Diagnosis of Parkinson's Disease
- Tackling Visual Control via Multi-View Exploration Maximization
- Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers
- RAMP: A Flat Nanosecond Optical Network and MPI Operations for Distributed Deep Learning Systems
- Meet-in-the-middle: Multi-scale upsampling and matching for cross-resolution face recognition
- Gamma-convergence of a nonlocal perimeter arising in adversarial machine learning
- Federated Learning for 5G Base Station Traffic Forecasting
- Application of the YOLOv5 Model for the Detection of Microobjects in the Marine Environment
- AquaFeL-PSO: A Monitoring System for Water Resources using Autonomous Surface Vehicles based on Multimodal PSO and Federated Learning
- Progressive Learning without Forgetting
- What's Behind the Mask: Estimating Uncertainty in Image-to-Image Problems
- CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control
- Revisiting Distance Metric Learning for Few-Shot Natural Language Classification
- Angular triangle distance for ordinal metric learning
- Large Pre-Trained Models with Extra-Large Vocabularies: A Contrastive Analysis of Hebrew BERT Models and a New One to Outperform Them All
- Metric Learning as a Service with Covariance Embedding
- Forged Image Detection using SOTA Image Classification Deep Learning Methods for Image Forensics with Error Level Analysis
- Distance Metric Learning Loss Functions in Few-Shot Scenarios of Supervised Language Models Fine-Tuning
- Deep Grading based on Collective Artificial Intelligence for AD Diagnosis and Prognosis
- Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs
- Continuous Episodic Control
- Easy Begun is Half Done: Spatial-Temporal Graph Modeling with ST-Curriculum Dropout
- MixFairFace: Towards Ultimate Fairness via MixFair Adapter in Face Recognition
- Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
- Toward Global Sensing Quality Maximization: A Configuration Optimization Scheme for Camera Networks
- Long-tail Cross Modal Hashing
- Heterogeneous Graph Learning for Multi-modal Medical Data Analysis
- GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Models
- Data-driven multinomial random forest: A new random forest variant with strong consistency
- Semi-supervised binary classification with latent distance learning
- Emerging trends in machine learning for computational fluid dynamics
- Explaining Deep Convolutional Neural Networks for Image Classification by Evolving Local Interpretable Model-agnostic Explanations
- Collective Intelligence for 2D Push Manipulations with Mobile Robots
- SI-GAT: A method based on improved Graph Attention Network for sonar image classification
- On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure
- Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings
- A Faster k-means++ Algorithm
- Generalized Category Discovery with Decoupled Prototypical Network
- LoNe Sampler: Graph node embeddings by coordinated local neighborhood sampling
- A Light Touch Approach to Teaching Transformers Multi-view Geometry
- PlasmoID: A dataset for Indonesian malaria parasite detection and segmentation in thin blood smear
- VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning
- MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection
- Discretized Linear Regression and Multiclass Support Vector Based Air Pollution Forecasting Technique
- Robot Kinematics: Motion, Kinematics and Dynamics
- Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting
- Class Adaptive Network Calibration
- DGI: Easy and Efficient Inference for GNNs
- Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation
- Lightweight and Flexible Deep Equilibrium Learning for CSI Feedback in FDD Massive MIMO
- Refined Semantic Enhancement towards Frequency Diffusion for Video Captioning
- FaiREE: Fair Classification with Finite-Sample and Distribution-Free Guarantee
- Pitfalls of Conditional Batch Normalization for Contextual Multi-Modal Learning
- Online Kernel CUSUM for Change-Point Detection
- FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network
- Learning to design without prior data: Discovering generalizable design strategies using deep learning and tree search
- Semi-Supervised Confidence-Level-based Contrastive Discrimination for Class-Imbalanced Semantic Segmentation
- High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors
- Interactive Visual Feature Search
- Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
- Mix and Localize: Localizing Sound Sources in Mixtures
- An adaptive shortest-solution guided decimation approach to sparse high-dimensional linear regression
- AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
- Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments
- Synthetic Low-Field MRI Super-Resolution Via Nested U-Net Architecture
- PCT-CycleGAN: Paired Complementary Temporal Cycle-Consistent Adversarial Networks for Radar-Based Precipitation Nowcasting
- CLIP2GAN: Towards Bridging Text with the Latent Space of GANs
- Machine Learning Accelerated PDE Backstepping Observers
- Renmin University of China at TRECVID 2022: Improving Video Search by Feature Fusion and Negation Understanding
- SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme Scheme
- Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability
- Imperceptible Adversarial Attack via Invertible Neural Networks
- Joint Multimodal Entity-Relation Extraction Based on Edge-enhanced Graph Alignment Network and Word-pair Relation Tagging
- AcceRL: Policy Acceleration Framework for Deep Reinforcement Learning
- Summer: WeChat Neural Machine Translation Systems for the WMT22 Biomedical Translation Task
- BJTU-WeChat's Systems for the WMT22 Chat Translation Task
- STAGE: Span Tagging and Greedy Inference Scheme for Aspect Sentiment Triplet Extraction
- A Model-data-driven Network Embedding Multidimensional Features for Tomographic SAR Imaging
- A Comprehensive Survey on Enterprise Financial Risk Analysis from Big Data and LLMs Perspective
- Arguments to Key Points Mapping with Prompt-based Learning
- Near-filed SAR Image Restoration with Deep Learning Inverse Technique: A Preliminary Study
- Solving 3D Radar Imaging Inverse Problems with a Multi-cognition Task-oriented Framework
- Dual Information Enhanced Multi-view Attributed Graph Clustering
- An Unpaired Cross-modality Segmentation Framework Using Data Augmentation and Hybrid Convolutional Networks for Segmenting Vestibular Schwannoma and Cochlea
- Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand
- Two Is Better Than One: Dual Embeddings for Complementary Product Recommendations
- Optimal Sparse Regression Trees
- QLAMMP: A Q-Learning Agent for Optimizing Fees on Automated Market Making Protocols