Papers
Fri 16 Dec 2022
178 papers
- Point-E: A System for Generating 3D Point Clouds from Complex PromptsDiffusion models → 3D, point cloud and scene generation
- Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- Causal Temporal Reasoning for Markov Decision ProcessesLLM reasoning → Causal reasoning in LLMs
- JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- Uncovering the Disentanglement Capability in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Evaluating Step-by-Step Reasoning through Symbolic VerificationLLM reasoning → Reasoning benchmarks and evaluation
- MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text GenerationLLM reasoning → Reasoning benchmarks and evaluation
- Learning and Extrapolation of Robotic Skills using Task-Parameterized Equation Learner NetworksOffline RL and imitation learning from data → Robot manipulation imitation learning
- Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic ModelsDiffusion models → Video generation
- Fake it till you make it: Learning transferable representations from synthetic ImageNet clonesDiffusion models → Image generation, text-to-image and editing
- Teaching Small Language Models to ReasonLLM reasoning → Prompting and chain-of-thought reasoning
- Swing Distillation: A Privacy-Preserving Knowledge Distillation FrameworkKnowledge distillation → Federated, robust and private distillation
- Text-to-speech synthesis based on latent variable conversion using diffusion probabilistic model and variational autoencoderDiffusion models → Audio, speech and music
- Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Knowledge distillation → Detection and dense prediction distillation
- ALERT: Adapting Language Models to Reasoning TasksLLM reasoning → Reasoning benchmarks and evaluation
- Offline Reinforcement Learning for Visual NavigationOffline RL and imitation learning from data → Language-conditioned policies and VLAs
- Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert SamplingOffline RL and imitation learning from data → Offline RL algorithms
- SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image GenerationDiffusion models → Medical imaging and segmentation
- Scattering-induced entropy boost for highly-compressed optical sensing and encryption
- Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks
- Deep learning for bias-correcting CMIP6-class Earth system models
- One-shot skill assessment in high-stakes domains with limited data via meta learning
- Differentiating Student Feedbacks for Knowledge Tracing
- Machine Learning as an Accurate Predictor for Percolation Threshold of Diverse Networks
- Twitter's Agenda-Setting Role: A Study of Twitter Strategy for Political Diversion
- POIBERT: A Transformer-based Model for the Tour Recommendation Problem
- Dense Feature Memory Augmented Transformers for COVID-19 Vaccination Search Classification
- Using machine learning algorithms to determine the emotional disadaptation of a person by his rhythmogram
- Using machine learning algorithms to determine the post-COVID state of a person by his rhythmogram
- On Safe and Usable Chatbots for Promoting Voter Participation
- It is not "accuracy vs. explainability" -- we need both for trustworthy AI systems
- Machine Learning and Polymer Self-Consistent Field Theory in Two Spatial Dimensions
- Interpretable models for extrapolation in scientific machine learning
- Natural Language Processing in Customer Service: A Systematic Review
- CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
- Feature Disentanglement Learning with Switching and Aggregation for Video-based Person Re-Identification
- Machine Learning Systems are Bloated and Vulnerable
- Short-term Prediction of Household Electricity Consumption Using Customized LSTM and GRU Models
- Multi-Scales Data Augmentation Approach In Natural Language Inference For Artifacts Mitigation And Pre-Trained Model Optimization
- Analysis and application of multispectral data for water segmentation using machine learning
- Toward cross-subject and cross-session generalization in EEG-based emotion recognition: Systematic review, taxonomy, and methods
- Addressing Data Heterogeneity in Decentralized Learning via Topological Pre-processing
- Lateral Strain Imaging using Self-supervised and Physically Inspired Constraints in Unsupervised Regularized Elastography
- SkillFence: A Systems Approach to Practically Mitigating Voice-Based Confusion Attacks
- A Neural Network Warm-Start Approach for the Inverse Acoustic Obstacle Scattering Problem
- Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ
- Multi-person 3D pose estimation from unlabelled data
- DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation
- Neural Story Planning
- Speech Aware Dialog System Technology Challenge (DSTC11)
- Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition
- An Upper Bound for the Distribution Overlap Index and Its Applications
- Rarely a problem? Language models exhibit inverse scaling in their predictions following few-type quantifiers
- Multi-Task Learning for Sparsity Pattern Heterogeneity: Statistical and Computational Perspectives
- Quantum Kernel for Image Classification of Real World Manufacturing Defects
- TopoImb: Toward Topology-level Imbalance in Learning from Graphs
- Plansformer: Generating Symbolic Plans using Transformers
- An unfolding method based on conditional Invertible Neural Networks (cINN) using iterative training
- Hard Sample Aware Network for Contrastive Deep Graph Clustering
- EffMulti: Efficiently Modeling Complex Multimodal Interactions for Emotion Analysis
- Attentive Mask CLIP
- ColorSense: A Study on Color Vision in Machine Visual Recognition
- Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification
- Connecting Permutation Equivariant Neural Networks and Partition Diagrams
- Efficient Conditionally Invariant Representation Learning
- Estimating Higher-Order Mixed Memberships via the ℓ2,∞ Tensor Perturbation Bound
- GFPose: Learning 3D Human Pose Prior with Gradient Fields
- An annotated instance segmentation XXL-CT data-set from a historic airplane
- Self-Prompting Large Language Models for Zero-Shot Open-Domain QA
- Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation
- Brauer's Group Equivariant Neural Networks
- Hippocampus-Inspired Cognitive Architecture (HICA) for Operant Conditioning
- Development of A Real-time POCUS Image Quality Assessment and Acquisition Guidance System
- POTATO: The Portable Text Annotation Tool
- Planting and Mitigating Memorized Content in Predictive-Text Language Models
- Atrous Space Bender U-Net (ASBU-Net/LogiNet)
- Huruf: An Application for Arabic Handwritten Character Recognition Using Deep Learning
- Planning Visual-Tactile Precision Grasps via Complementary Use of Vision and Touch
- Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better
- De-risking Carbon Capture and Sequestration with Explainable CO2 Leakage Detection in Time-lapse Seismic Monitoring Images
- Rethinking Cooking State Recognition with Vision Transformers
- Semi-Siamese Network for Robust Change Detection Across Different Domains with Applications to 3D Printing
- Penalised regression with multiple sources of prior effects
- Nested Gradient Codes for Straggler Mitigation in Distributed Machine Learning
- Provable Fairness for Neural Network Models using Formal Verification
- Biomedical image analysis competitions: The state of current participation practice
- Simulating Road Spray Effects in Automotive Lidar Sensor Models
- An automated parameter domain decomposition approach for gravitational wave surrogates using hp-greedy refinement
- Fine-grained Czech News Article Dataset: An Interdisciplinary Approach to Trustworthiness Analysis
- Estimating truncation effects of quantum bosonic systems using sampling algorithms
- Context-aware Fine-tuning of Self-supervised Speech Models
- Learnable Commutative Monoids for Graph Neural Networks
- Predicting Autonomous Vehicle Collision Injury Severity Levels for Ethical Decision Making and Path Planning
- Detection-aware multi-object tracking evaluation
- Do Not Trust a Model Because It is Confident: Uncovering and Characterizing Unknown Unknowns to Student Success Predictors in Online-Based Learning
- Check-worthy Claim Detection across Topics for Automated Fact-checking
- Road Detection in Snowy Forest Environment using RGB Camera
- Robust Explanation Constraints for Neural Networks
- Weakly Supervised Video Anomaly Detection Based on Cross-Batch Clustering Guidance
- Federated Learning with Flexible Control
All 178
- LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images
- Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks
- Semantics-Empowered Communication: A Tutorial-cum-Survey
- BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric
- Implementation of general formal translators
- Neural Implicit k-Space for Binning-free Non-Cartesian Cardiac MR Imaging
- One-Stage Cascade Refinement Networks for Infrared Small Target Detection
- Free-form 3D Scene Inpainting with Dual-stream GAN
- Experiments on Generalizability of BERTopic on Multi-Domain Short Text
- Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing
- From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search
- Conditional Generative Adversarial Network for keystroke presentation attack
- Context Label Learning: Improving Background Class Representations in Semantic Segmentation
- Person Detection Using an Ultra Low-resolution Thermal Imager on a Low-cost MCU
- Deep Learning Methods for Calibrated Photometric Stereo and Beyond
- Decoder Tuning: Efficient Language Understanding as Decoding
- Utilizing distilBert transformer model for sentiment classification of COVID-19's Persian open-text responses
- LiFe-net: Data-driven Modelling of Time-dependent Temperatures and Charging Statistics Of Tesla's LiFePo4 EV Battery
- Assessing the Impact of Sequence Length Learning on Classification Tasks for Transformer Encoder Models
- Metaphorical Polysemy Detection: Conventional Metaphor meets Word Sense Disambiguation
- Lessons learned from the evaluation of Spanish Language Models
- Homonymy Information for English WordNet
- Traffic sign detection and recognition using event camera image reconstruction
- Fast-moving object counting with an event camera
- Instance-dependent Label Distribution Estimation for Learning with Label Noise
- GeneFormer: Learned Gene Compression using Transformer-based Context Modeling
- Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning
- PointAvatar: Deformable Point-based Head Avatars from Videos
- Shapley variable importance cloud for machine learning models
- Geometric Rectification of Creased Document Images based on Isometric Mapping
- Fast Learning of Dynamic Hand Gesture Recognition with Few-Shot Learning Models
- Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management
- Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation
- FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Tasks
- How to disagree well: Investigating the dispute tactics used on Wikipedia
- SplitGP: Achieving Both Generalization and Personalization in Federated Learning
- Adversarial Example Defense via Perturbation Grading Strategy
- Neural Enhanced Belief Propagation for Multiobject Tracking
- Generalization Bounds for Inductive Matrix Completion in Low-noise Settings
- Law to Binary Tree -- An Formal Interpretation of Legal Natural Language
- Lightweight integration of 3D features to improve 2D image segmentation
- Convolution-enhanced Evolving Attention Networks
- MEIL-NeRF: Memory-Efficient Incremental Learning of Neural Radiance Fields
- WavEnhancer: Unifying Wavelet and Transformer for Image Enhancement
- Mobile Augmented Reality with Federated Learning in the Metaverse
- An ensemble neural network approach to forecast Dengue outbreak based on climatic condition
- ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
- Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent language
- An Efficient Framework for Monitoring Subgroup Performance of Machine Learning Systems
- Can We Find Strong Lottery Tickets in Generative Models?
- Controllable Text Generation via Probability Density Estimation in the Latent Space
- Safe Evaluation For Offline Learning: Are We Ready To Deploy?
- Metaheuristic for Hub-Spoke Facility Location Problem: Application to Indian E-commerce Industry
- DQnet: Cross-Model Detail Querying for Camouflaged Object Detection
- Learning on Persistence Diagrams as Radon Measures
- Robust Learning Protocol for Federated Tumor Segmentation Challenge
- Rich Event Modeling for Script Event Prediction
- SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering
- HGAN: Hierarchical Graph Alignment Network for Image-Text Retrieval
- Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games
- Improving self-supervised representation learning via sequential adversarial masking
- Preventing RNN from Using Sequence Length as a Feature
- Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communication
- Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential Recommendation
- A Sieve Quasi-likelihood Ratio Test for Neural Networks with Applications to Genetic Association Studies
- RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
- Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
- A Simple Decentralized Cross-Entropy Method
- Geometry-aware Autoregressive Models for Calorimeter Shower Simulations
- An Energy-aware and Fault-tolerant Deep Reinforcement Learning based approach for Multi-agent Patrolling Problems
- Materials Discovery using Max K-Armed Bandit
- Toward Improved Generalization: Meta Transfer of Self-supervised Knowledge on Graphs
- Azimuth: Systematic Error Analysis for Text Classification
- Reinforcement Learning for Agile Active Target Sensing with a UAV
- Location-aware Adaptive Normalization: A Deep Learning Approach For Wildfire Danger Forecasting
- Meeting Summarization: A Survey of the State of the Art
- A unified information-theoretic model of EEG signatures of human language processing
- LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension