Papers
Sun 23 Oct 2022
139 papers
- Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and PlanningWorld models → Latent predictive world models
- Retrieval Augmentation for Commonsense Reasoning: A Unified ApproachLLM reasoning → Knowledge- and tool-augmented reasoning +1
- Deep Equilibrium Approaches to Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Respecting Transfer Gap in Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical MedicineRetrieval-augmented generation → Medical and biomedical RAG
- Learning General World Models in a Handful of Reward-Free DeploymentsWorld models → Latent dynamics models and model-based RL
- Climate Change Policy Exploration using Reinforcement Learning
- fMRI from EEG is only Deep Learning away: the use of interpretable DL to unravel EEG-fMRI relationships
- FingerFlex: Inferring Finger Trajectories from ECoG signals
- A BERT-based Deep Learning Approach for Reputation Analysis in Social Media
- Towards a Better Model with Dual Transformer for Drug Response Prediction
- TPU-MLIR: A Compiler For TPU Using MLIR
- The Art NFTs and Their Marketplaces
- Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharing
- Attention Based Relation Network for Facial Action Units Recognition
- Adversarial Pretraining of Self-Supervised Deep Networks: Past, Present and Future
- Artificial Intelligence-Based Methods for Fusion of Electronic Health Records and Imaging Data
- DALL-E 2 Fails to Reliably Capture Common Syntactic Processes
- A Greek Parliament Proceedings Dataset for Computational Linguistics and Political Analysis
- Stochastic Mirror Descent for Large-Scale Sparse Recovery
- IDD-3D: Indian Driving Dataset for 3D Unstructured Road Scenes
- Global Contrastive Batch Sampling via Optimization on Sample Permutations
- FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
- Socio-cognitive Optimization of Time-delay Control Problems using Evolutionary Metaheuristics
- Tighter Abstract Queries in Neural Network Verification
- Imbalanced Class Data Performance Evaluation and Improvement using Novel Generative Adversarial Network-based Approach: SSG and GBO
- Knowledge Transfer from Answer Ranking to Answer Generation
- K-SAM: Sharpness-Aware Minimization at the Speed of SGD
- Optimal Discriminant Analysis in High-Dimensional Latent Factor Models
- Tight relative estimation in the mean of Bernoulli random variables
- Explicit Second-Order Min-Max Optimization: Practical Algorithms and Complexity Analysis
- Kadabra: Adapting Kademlia for the Decentralized Web
- Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings
- Symmetry and Variance: Generative Parametric Modelling of Historical Brick Wall Patterns
- 1st Place Solution of The Robust Vision Challenge 2022 Semantic Segmentation Track
- Learning to Advise Humans in High-Stakes Settings
- EUREKA: EUphemism Recognition Enhanced through Knn-based methods and Augmentation
- Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification
- A Cooperative Reinforcement Learning Environment for Detecting and Penalizing Betrayal
- Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity
- Towards Pragmatic Production Strategies for Natural Language Generation Tasks
- Towards Real-Time Text2Video via CLIP-Guided, Pixel-Level Optimization
- An Interpretable Deep Semantic Segmentation Method for Earth Observation
- Pushing the Efficiency Limit Using Structured Sparse Convolutions
- Simple Alternating Minimization Provably Solves Complete Dictionary Learning
- RuCoLA: Russian Corpus of Linguistic Acceptability
- TAPE: Assessing Few-shot Russian Language Understanding
- Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence
- Code4Struct: Code Generation for Few-Shot Event Structure Prediction
- Data Augmentation for Automated Essay Scoring using Transformer Models
- Active Exploration for Robotic Manipulation
- LQGNet: Hybrid Model-Based and Data-Driven Linear Quadratic Stochastic Control
- Translation Word-Level Auto-Completion: What can we achieve out of the box?
- MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences
- Realistic Data Augmentation Framework for Enhancing Tabular Reasoning
- O-type Stars Stellar Parameter Estimation Using Recurrent Neural Networks
- Clustering-based Tile Embedding (CTE): A General Representation for Level Design with Skewed Tile Distributions
- When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarks
- An Improved RaftStereo Trained with A Mixed Dataset for the Robust Vision Challenge 2022
- Compressing Explicit Voxel Grid Representations: fast NeRFs become also small
- Local and Global Structure Preservation Based Spectral Clustering
- McQueen: a Benchmark for Multimodal Conversational Query Rewrite
- Manifold Alignment with Label Information
- Exploring the Value of Pre-trained Language Models for Clinical Named Entity Recognition
- Falsehoods that ML researchers believe about OOD detection
- Multi-Objective GFlowNets
- Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification
- On double-descent in uncertainty quantification in overparametrized models
- Beta R-CNN: Looking into Pedestrian Detection from Another Perspective
- VP-SLAM: A Monocular Real-time Visual SLAM with Points, Lines and Vanishing Points
- LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers
- UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection
- SC-wLS: Towards Interpretable Feed-forward Camera Re-localization
- Principal Component Classification
- Functional Indirection Neural Estimator for Better Out-of-distribution Generalization
- Self-supervised Amodal Video Object Segmentation
- Joint Rigid Motion Correction and Sparse-View CT via Self-Calibrating Neural Field
- Additive Interventions Yield Robust Multi-Domain Machine Translation Models
- A Faithful Deep Sensitivity Estimation for Accelerated Magnetic Resonance Imaging
- Span-based joint entity and relation extraction augmented with sequence tagging mechanism
- Generative Knowledge Graph Construction: A Review
- Accelerating the training of single-layer binary neural networks using the HHL quantum algorithm
- Few-Shot Meta Learning for Recognizing Facial Phenotypes of Genetic Disorders
- Batch Multi-Fidelity Active Learning with Budget Constraints
- On the Transformation of Latent Space in Fine-Tuned NLP Models
- Do Language Models Understand Measurements?
- Coupling User Preference with External Rewards to Enable Driver-centered and Resource-aware EV Charging Recommendation
- Focus Is What You Need For Chinese Grammatical Error Correction
- DyCSC: Modeling the Evolutionary Process of Dynamic Networks Based on Cluster Structure
- Face Emotion Recognization Using Dataset Augmentation Based on Neural Network
- How "Multi" is Multi-Document Summarization?
- BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets
- Holistic Interaction Transformer Network for Action Detection
- Less Emphasis on Difficult Layer Regions: Curriculum Learning for Singularly Perturbed Convection-Diffusion-Reaction Problems
- GAN-based Facial Attribute Manipulation
- Photo-realistic Neural Domain Randomization
- Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation
- ComFact: A Benchmark for Linking Contextual Commonsense Knowledge
- Towards Generalizable and Robust Text-to-SQL Parsing
- Lexical Generalization Improves with Larger Models and Longer Training
All 139
- Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks
- No-Regret Learning in Two-Echelon Supply Chain with Unknown Demand Distribution
- Improving Chinese Named Entity Recognition by Search Engine Augmentation
- Mapping Process for the Task: Wikidata Statements to Text as Wikipedia Sentences
- Extending Phrase Grounding with Pronouns in Visual Dialogues
- Cross-document Event Coreference Search: Task, Dataset and Modeling
- SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training
- Unsupervised Non-transferable Text Classification
- Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation
- Accelerated Linearized Laplace Approximation for Bayesian Deep Learning
- PoKE: Prior Knowledge Enhanced Emotional Support Conversation with Latent Variable
- Tucker-O-Minus Decomposition for Multi-view Tensor Subspace Clustering
- Neural Eigenfunctions Are Structured Representation Learners
- Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation
- RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data
- LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation
- Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions
- Fast Beam Alignment via Pure Exploration in Multi-armed Bandits
- Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach
- Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings
- Facial De-occlusion Network for Virtual Telepresence Systems
- Conformal Predictor for Improving Zero-shot Text Classification Efficiency
- Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval
- Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models
- Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games
- Transformers For Recognition In Overhead Imagery: A Reality Check
- GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injections
- DMODE: Differential Monocular Object Distance Estimation Module without Class Specific Information
- Online Probabilistic Model Identification using Adaptive Recursive MCMC
- Single Image Super-Resolution via a Dual Interactive Implicit Neural Network
- Meta-Reinforcement Learning for Building Energy Management System
- Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning
- MR-Based Electrical Property Reconstruction Using Physics-Informed Neural Networks
- Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control
- Language Model Pre-Training with Sparse Latent Typing
- Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization
- Feedback Assisted Adversarial Learning to Improve the Quality of Cone-beam CT Images
- Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling
- The Curious Case of Absolute Position Embeddings