Papers
Thu 8 Dec 2022
176 papers
- Confidence-Conditioned Value Functions for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent ConnectionKnowledge distillation → General knowledge distillation methods
- Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation LearningKnowledge distillation → General knowledge distillation methods
- SINE: SINgle Image Editing with Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Multi-Concept Customization of Text-to-Image DiffusionDiffusion models → Image generation, text-to-image and editing
- Diffusion Guided Domain Adaptation of Image GeneratorsDiffusion models → Image generation, text-to-image and editing
- Task Bias in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Model-based trajectory stitching for improved behavioural cloning and its applicationsOffline RL and imitation learning from data → Imitation learning methods
- Vision and Structured-Language Pretraining for Cross-Modal Food RetrievalMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Learning Domain Invariant Prompt for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language ModelsLLM agents and tool use → Multimodal and embodied agents
- Executing your Commands via Motion Diffusion in Latent SpaceDiffusion models → Video generation
- Neural Structure Fields with Application to Crystal Structure Autoencoders
- ML-powered KQI estimation for XR services. A case study on 360-Video
- NP4G : Network Programming for Generalization
- Routine Outcome Monitoring in Psychotherapy Treatment using Sentiment-Topic Modelling Approach
- The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies
- Fairify: Fairness Verification of Neural Networks
- GenSyn: A Multi-stage Framework for Generating Synthetic Microdata using Macro Data Sources
- Nostradamus: Weathering Worth
- Automated Level Crossing System: A Computer Vision Based Approach with Raspberry Pi Microcontroller
- CausalEGM: a general causal inference framework by encoding generative modeling
- Structured Like a Language Model: Analysing AI as an Automated Subject
- Transformer-based normative modelling for anomaly detection of early schizophrenia
- EEG-NeXt: A Modernized ConvNet for The Classification of Cognitive Activity from EEG
- DDSupport: Language Learning Support System that Displays Differences and Distances from Model Speech
- P2T2: a Physically-primed deep-neural-network approach for robust T2 distribution estimation from quantitative T2-weighted MRI
- GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields
- PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data
- Pose Estimation for Human Wearing Loose-Fitting Clothes: Obtaining Ground Truth Posture Using HFR Camera and Blinking LEDs
- Phone2Proc: Bringing Robust Robots Into Our Chaotic World
- The R-algebra of Quasiknowledge and Convex Optimization
- Localized Contrastive Learning on Graphs
- System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games
- Explain to me like I am five -- Sentence Simplification Using Transformers
- Towards Understanding Fairness and its Composition in Ensemble Machine Learning
- Learning Options via Compression
- Optimizing Integrated Information with a Prior Guided Random Search Algorithm
- Towards Holistic Surgical Scene Understanding
- PALMER: Perception-Action Loop with Memory for Long-Horizon Planning
- Effective Dynamics of Generative Adversarial Networks
- 3D Inception-Based TransMorph: Pre- and Post-operative Multi-contrast MRI Registration in Brain Tumors
- Generalizing LTL Instructions via Future Dependent Options
- DDM-NET: End-to-end learning of keypoint feature Detection, Description and Matching for 3D localization
- Enhanced prediction accuracy with uncertainty quantification in monitoring CO2 sequestration using convolutional neural networks
- SpeechLMScore: Evaluating speech generation using speech language model
- STLGRU: Spatio-Temporal Lightweight Graph GRU for Traffic Flow Prediction
- A Dependable Hybrid Machine Learning Model for Network Intrusion Detection
- VASR: Visual Analogies of Situation Recognition
- Graph Learning Indexer: A Contributor-Friendly and Metadata-Rich Platform for Graph Learning Benchmarks
- Deep Architectures for Content Moderation and Movie Content Rating
- Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity
- ORCa: Glossy Objects as Radiance Field Cameras
- Towards Practical Application of Deep Learning in Diagnosis of Alzheimer's Disease
- Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement
- Compiler Optimization for Quantum Computing Using Reinforcement Learning
- Learning Video Representations from Large Language Models
- VideoDex: Learning Dexterity from Internet Videos
- UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation
- MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis
- SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation
- Few-View Object Reconstruction with Unknown Categories and Camera Poses
- A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
- Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflection
- A Survey of Graph Neural Networks for Social Recommender Systems
- Learning Quantum Processes and Hamiltonians via the Pauli Transfer Matrix
- Leveraging Unlabeled Data to Track Memorization
- General-Purpose In-Context Learning by Meta-Learning Transformers
- Spatio-Temporal Super-Resolution of Dynamical Systems using Physics-Informed Deep-Learning
- XRand: Differentially Private Defense against Explanation-Guided Attacks
- Objective Surgical Skills Assessment and Tool Localization: Results from the MICCAI 2021 SimSurgSkill Challenge
- A Distributed Block Chebyshev-Davidson Algorithm for Parallel Spectral Clustering
- The Differentiable Lens: Compound Lens Search over Glass Surfaces and Materials for Object Detection
- C-VTON: Context-Driven Image-Based Virtual Try-On Network
- Generating Holistic 3D Human Motion from Speech
- Mining Explainable Predictive Features for Water Quality Management
- OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
- DeeProb-kit: a Python Library for Deep Probabilistic Modelling
- A Rubric for Human-like Agents and NeuroAI
- Multi-View Mesh Reconstruction with Neural Deferred Shading
- BEVBert: Multimodal Map Pre-training for Language-guided Navigation
- Structure of Classifier Boundaries: Case Study for a Naive Bayes Classifier
- Models Developed for Spiking Neural Networks
- Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy
- Alleviating neighbor bias: augmenting graph self-supervise learning with structural equivalent positive samples
- CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution
- MIME: Human-Aware 3D Scene Generation
- HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration
- Implicit causality in GPT-2: a case study
- On the Robustness of Normalizing Flows for Inverse Problems in Imaging
- Power Consumption Modeling of 5G Multi-Carrier Base Stations: A Machine Learning Approach
- Bio-Inspired, Task-Free Continual Learning through Activity Regularization
- A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain Information
- Deep Variational Inverse Scattering
- Secure Over-the-Air Computation using Zero-Forced Artificial Noise
- On The Relevance Of The Differences Between HRTF Measurement Setups For Machine Learning
- Simulation of Attacker Defender Interaction in a Noisy Security Game
- Application of machine learning regression models to inverse eigenvalue problems
- Lie detection algorithms attract few users but vastly increase accusation rates
- Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection
All 176
- A Modality-level Explainable Framework for Misinformation Checking in Social Networks
- ChromaCorrect: Prescription Correction in Virtual Reality Headsets through Perceptual Guidance
- ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation
- Fast Parallel Bayesian Network Structure Learning
- Momentum Calibration for Text Generation
- Fruit Quality Assessment with Densely Connected Convolutional Neural Network
- Fast Parallel Exact Inference on Bayesian Networks: Poster
- A probabilistic autoencoder for causal discovery
- Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations
- Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation
- Towards Accurate Ground Plane Normal Estimation from Ego-Motion
- Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing
- An Empirical Study on Multi-Domain Robust Semantic Segmentation
- The Neural Correlates of Linguistic Structure Building: Comments on Kazanina & Tavano (2022)
- Differentially-Private Bayes Consistency
- Scientific Paper Extractive Summarization Enhanced by Citation Graphs
- Evaluating Zero-cost Active Learning for Object Detection
- DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding
- Beyond Discrete Genres: Mapping News Items onto a Multidimensional Framework of Genre Cues
- Customizing Number Representation and Precision
- Mind the Gap: Measuring Generalization Performance Across Multiple Objectives
- evosax: JAX-based Evolution Strategies
- GreenEyes: An Air Quality Evaluating Model based on WaveNet
- NRTR: Neuron Reconstruction with Transformer from 3D Optical Microscopy Images
- A Novel Hierarchical-Classification-Block Based Convolutional Neural Network for Source Camera Model Identification
- Latent Graph Representations for Critical View of Safety Assessment
- Relationship Quantification of Image Degradations
- Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation
- Targeted Adversarial Attacks against Neural Network Trajectory Predictors
- Design and Planning of Flexible Mobile Micro-Grids Using Deep Reinforcement Learning
- Combining Photogrammetric Computer Vision and Semantic Segmentation for Fine-grained Understanding of Coral Reef Growth under Climate Change
- The Ordered Matrix Dirichlet for State-Space Models
- Deep Incubation: Training Large Models by Divide-and-Conquering
- Progressive Multi-resolution Loss for Crowd Counting
- Complete Solution for Vehicle Re-ID in Surround-view Camera System
- Enhanced method for reinforcement learning based dynamic obstacle avoidance by assessment of collision risk
- DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset
- OCR-RTPS: An OCR-based real-time positioning system for the valet parking
- Group Generalized Mean Pooling for Vision Transformer
- Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Framework
- Shadow Removal by High-Quality Shadow Synthesis
- Re-purposing Perceptual Hashing based Client Side Scanning for Physical Surveillance
- All-to-key Attention for Arbitrary Style Transfer
- GTFLAT: Game Theory Based Add-On For Empowering Federated Learning Aggregation Techniques
- Physics-guided Data Augmentation for Learning the Solution Operator of Linear Differential Equations
- EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder
- Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning
- ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction
- Successive Prompting for Decomposing Complex Questions
- Strong identifiability and parameter learning in regression with heterogeneous response
- Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection
- Editing Models with Task Arithmetic
- Graph Matching with Bi-level Noisy Correspondence
- Federated Learning for Inference at Anytime and Anywhere
- Predicting dominant hand from spatiotemporal context varying physiological data
- Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence
- A Comprehensive Survey on Multi-hop Machine Reading Comprehension Approaches
- A Comprehensive Survey on Multi-hop Machine Reading Comprehension Datasets and Metrics
- Reinforcement Learning for Resilient Power Grids
- Investigating Glyph Phonetic Information for Chinese Spell Checking: What Works and What's Next
- Consistency-Aware Anchor Pyramid Network for Crowd Localization
- SpaceEditing: Integrating Human Knowledge into Deep Neural Networks via Interactive Latent Space Editing
- Elixir: A system to enhance data quality for multiple analytics on a video stream
- MixBoost: Improving the Robustness of Deep Neural Networks by Boosting Data Augmentation
- AutoPINN: When AutoML Meets Physics-Informed Neural Networks
- Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
- Learning to Dub Movies via Hierarchical Prosody Models
- Graph Neural Networks Meet Wireless Communications: Motivation, Applications, and Future Directions
- Demystifying Prompts in Language Models via Perplexity Estimation
- On Root Cause Localization and Anomaly Mitigation through Causal Inference
- Analysis of Deep Learning Architectures and Efficacy of Detecting Forest Fires
- Occlusion-Robust FAU Recognition by Mining Latent Space of Masked Autoencoders
- A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces
- RLSEP: Learning Label Ranks for Multi-label Classification
- Quantum-Inspired Approximations to Constraint Satisfaction Problems
- Statistical and Computational Guarantees for Influence Diagnostics