Papers
Tue 24 May 2022
254 papers
- Reward Uncertainty for Exploration in Preference-based Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Sparse Mixers: Combining MoE and Mixing to build a more efficient BERTMixture-of-experts → MoE large language models
- TALM: Tool Augmented Language ModelsLLM agents and tool use → Tool learning and function calling
- Learning to Drive Using Sparse Imitation Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving
- HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Large Language Models are Zero-Shot ReasonersLLM reasoning → Prompting and chain-of-thought reasoning
- Real-Time Trajectory Planning for Autonomous Driving with Gaussian Process and Incremental RefinementEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature SharingKnowledge distillation → General knowledge distillation methods
- Maieutic Prompting: Logically Consistent Reasoning with Recursive ExplanationsLLM reasoning → Prompting and chain-of-thought reasoning
- WeDef: Weakly Supervised Backdoor Defense for Text ClassificationLLM safety and security → Backdoor and data poisoning attacks
- Hierarchical Planning Through Goal-Conditioned Offline Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
- Fine-grained Poisoning Attack to Local Differential Privacy Protocols for Mean and Variance EstimationLLM safety and security → Membership inference attacks
- Compressing Deep Graph Neural Networks via Adversarial Knowledge DistillationKnowledge distillation → Graph neural network distillation
- Auxiliary Task Guided Interactive Attention Model for Question Difficulty Prediction
- FabKG: A Knowledge graph of Manufacturing Science domain utilizing structured and unconventional unstructured knowledge source
- Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Control
- Graph Neural Networks Intersect Probabilistic Graphical Models: A Survey
- The risk ethics of autonomous vehicles: a continuous trolley problem in regular road traffic
- Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning
- Justifying Social-Choice Mechanism Outcome for Improving Participant Satisfaction
- Associative Learning Mechanism for Drug-Target Interaction Prediction
- Symbol Emergence as Inter-personal Categorization with Head-to-head Latent Word
- RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation
- Boosting Tail Neural Network for Realtime Custom Keyword Spotting
- SALAD: Source-free Active Label-Agnostic Domain Adaptation for Classification, Segmentation and Detection
- A Paradigm Change for Formal Syntax: Computational Algorithms in the Grammar of English
- Mathematical Models of Human Drivers Using Artificial Risk Fields
- DPSNN: A Differentially Private Spiking Neural Network with Temporal Enhanced Pooling
- Differentially Private AUC Computation in Vertical Federated Learning
- Linear Connectivity Reveals Generalization Strategies
- AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
- Convolutional Neural Processes for Inpainting Satellite Images
- Multi-Head Online Learning for Delayed Feedback Modeling
- FLUTE: Figurative Language Understanding through Textual Explanations
- Jointly Optimizing Color Rendition and In-Camera Backgrounds in an RGB Virtual Production Stage
- Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks
- MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification
- Fine-tuned Language Models are Continual Learners
- Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models
- Toward Understanding Bias Correlations for Mitigation in NLP
- Toxicity Detection with Generative Prompt-based Inference
- PLAtE: A Large-scale Dataset for List Page Web Extraction
- Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Media
- First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization
- Gaussian Pre-Activations in Neural Networks: Myth or Reality?
- Hardness of Maximum Likelihood Learning of DPPs
- Learning to Model Editing Processes
- TorchNTK: A Library for Calculation of Neural Tangent Kernels of PyTorch Models
- Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint
- Low-rank Optimal Transport: Approximation, Statistics and Debiasing
- A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection
- Face2Text revisited: Improved data set and baseline results
- K-12BERT: BERT for K-12 education
- Certified Robustness Against Natural Language Attacks by Causal Intervention
- Multilevel sentiment analysis in arabic
- Beyond Impossibility: Balancing Sufficiency, Separation and Accuracy
- Scoring Coreference Chains with Split-Antecedent Anaphors
- ColdGuess: A General and Effective Relational Graph Convolutional Network to Tackle Cold Start Cases
- Fast & Furious: Modelling Malware Detection as Evolving Data Streams
- Structured Prompt Tuning
- Adaptive multilingual speech recognition with pretrained models
- Garden-Path Traversal in GPT-2
- FreDo: Frequency Domain-based Long-Term Time Series Forecasting
- lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents
- Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video
- Wavelet Feature Maps Compression for Image-to-Image CNNs
- Policy Compliance Detection via Expression Tree Inference
- History Compression via Language Models in Reinforcement Learning
- OnePose: One-Shot Object Pose Estimation without CAD Models
- Differentiable Dynamics for Articulated 3d Human Motion Reconstruction
- Interpretation Quality Score for Measuring the Quality of interpretability methods
- Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing
- Efficient anti-symmetrization of a neural network layer by taming the sign problem
- RevUp: Revise and Update Information Bottleneck for Event Representation
- GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models
- Asynchronous Neural Networks for Learning in Graphs
- Unsupervised Learning of Hierarchical Conversation Structure
- EBM Life Cycle: MCMC Strategies for Synthesis, Defense, and Density Modeling
- VIRATrustData: A Trust-Annotated Corpus of Human-Chatbot Conversations About COVID-19 Vaccines
- Gacs-Korner Common Information Variational Autoencoder
- ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutions
- Chunk-based Nearest Neighbor Machine Translation
- When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems
- Psychotic Relapse Prediction in Schizophrenia Patients using A Mobile Sensing-based Supervised Deep Learning Model
- GLObal Building heights for Urban Studies (UT-GLOBUS) for city- and street- scale urban simulations: Development and first applications
- ClaimDiff: Comparing and Contrasting Claims on Contentious Issues
- Aerial Vision-and-Dialog Navigation
- T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation
- DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages
- Principled Paraphrase Generation with Parallel Corpora
- EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start
- PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation
- Forecasting Multilinear Data via Transform-Based Tensor Autoregression
- Absolute Triangulation Algorithms for Space Exploration
- Merkel Podcast Corpus: A Multimodal Dataset Compiled from 16 Years of Angela Merkel's Weekly Video Podcasts
- Reassessing Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization
- Continual Learning with Global Alignment
- Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning
- StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning
- Partial-input baselines show that NLI models can ignore context, but they don't
All 254
- Evidential Temporal-aware Graph-based Social Event Detection via Dempster-Shafer Theory
- A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation -- through the Lens of Semantic Similarity Rating
- Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums
- Do it Like the Doctor: How We Can Design a Model That Uses Domain Knowledge to Diagnose Pneumothorax
- D2UF: Deep Coded Aperture Design and Unrolling Algorithm for Compressive Spectral Image Fusion
- Not too little, not too much: a theoretical analysis of graph (over)smoothing
- Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer
- Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis
- One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks
- Improving the Latent Space of Image Style Transfer
- Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks
- Detecting Deforestation from Sentinel-1 Data in the Absence of Reliable Reference Data
- Full-Reference Calibration-Free Image Quality Assessment
- Inference of a Rumor's Source in the Independent Cascade Model
- Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for Imbalanced Data Classification
- The Curious Case of Control
- Stereographic Markov Chain Monte Carlo
- Federated singular value decomposition for high dimensional data
- Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width
- DNNAbacus: Toward Accurate Computational Cost Prediction for Deep Neural Networks
- Bias Discovery in Machine Learning Models for Mental Health
- Sim-To-Real Transfer of Visual Grounding for Human-Aided Ambiguity Resolution
- Information-Directed Selection for Top-Two Algorithms
- GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation
- Ensemble Multi-Relational Graph Neural Networks
- Classification of Phonological Parameters in Sign Languages
- Deep Reinforcement Learning for Multi-class Imbalanced Training
- Context Attention Network for Skeleton Extraction
- On statistic alignment for domain adaptation in structural health monitoring
- HCFRec: Hash Collaborative Filtering via Normalized Flow with Structural Consensus for Efficient Recommendation
- Privacy-Preserving Image Classification Using Vision Transformer
- FedEntropy: Efficient Device Grouping for Federated Learning Using Maximum Entropy Judgment
- RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder
- Defending a Music Recommender Against Hubness-Based Adversarial Attacks
- Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections
- VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification
- Effect of Gender, Pose and Camera Distance on Human Body Dimensions Estimation
- Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance
- PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
- Concurrent Credit Assignment for Data-efficient Reinforcement Learning
- Naive Few-Shot Learning: Uncovering the fluid intelligence of machines
- Analysing the Greek Parliament Records with Emotion Classification
- SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
- Graph Convolutional Reinforcement Learning for Collaborative Queuing Agents
- mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
- Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition
- Highly Accurate FMRI ADHD Classification using time distributed multi modal 3D CNNs
- Learning Stabilizing Policies in Stochastic Control Systems
- Realization Theory Of Recurrent Neural ODEs Using Polynomial System Embeddings
- Word-order typology in Multilingual BERT: A case study in subordinate-clause detection
- OPOM: Customized Invisible Cloak towards Face Privacy Protection
- Universal Dependency Treebank for Odia Language
- Exploiting Dynamic and Fine-grained Semantic Scope for Extreme Multi-label Text Classification
- Weak Convergence of Approximate reflection coupling and its Application to Non-convex Optimization
- Generative Models for Reproducible Coronary Calcium Scoring
- Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy
- The Data-Production Dispositif
- A Wireless-Vision Dataset for Privacy Preserving Human Activity Recognition
- ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts
- Bandwidth Selection for Gaussian Kernel Ridge Regression via Jacobian Control
- 3D helical CT Reconstruction with a Memory Efficient Learned Primal-Dual Architecture
- Diffuse Map Guiding Unsupervised Generative Adversarial Network for SVBRDF Estimation
- SHARP: Shape-Aware Reconstruction of People in Loose Clothing
- Causal Influences Decouple From Their Underlying Network Structure In Echo State Networks
- GraSens: A Gabor Residual Anti-aliasing Sensing Framework for Action Recognition using WiFi
- Assessing the Quality of Computational Notebooks for a Frictionless Transition from Exploration to Production
- Pynblint: a Static Analyzer for Python Jupyter Notebooks
- The Authenticity Gap in Human Evaluation
- Image Trinarization Using a Partial Differential Equations: A Novel Approach to Automatic Sperm Image Analysis
- Robust 3D Object Detection in Cold Weather Conditions
- Compression-aware Training of Neural Networks using Frank-Wolfe
- Community Question Answering Entity Linking via Leveraging Auxiliary Data
- Building an Effective Automated Assessment System for C/C++ Introductory Programming Courses in ODL Environment
- An Adaptive Contrastive Learning Model for Spike Sorting
- Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges and Vision
- Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditions
- An interpretation of the final fully connected layer
- Automatic Verification of Sound Abstractions for Generalized Planning
- Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs
- A Quadrature Rule combining Control Variates and Adaptive Importance Sampling
- Mind The Gap: Alleviating Local Imbalance for Unsupervised Cross-Modality Medical Image Segmentation
- Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)
- Hierarchical Vectorization for Portrait Images
- Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration
- Building a Dialogue Corpus Annotated with Expressed and Experienced Emotions
- Overview of STEM Science as Process, Method, Material, and Data Named Entities
- Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning
- Faithful Explanations for Deep Graph Models
- Collaborative 3D Object Detection for Automatic Vehicle Systems via Learnable Communications
- Lutma: a Frame-Making Tool for Collaborative FrameNet Development
- Charon: a FrameNet Annotation Tool for Multimodal Corpora
- Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model
- TraCon: A novel dataset for real-time traffic cones detection using deep learning
- Unsupervised Difference Learning for Noisy Rigid Image Alignment
- Advanced Manufacturing Configuration by Sample-efficient Batch Bayesian Optimization
- Lack of Fluency is Hurting Your Translation Model
- Thunder: Thumbnail based Fast Lightweight Image Denoising Network
- Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free
- Penalized Proximal Policy Optimization for Safe Reinforcement Learning
- Learning to Assemble Geometric Shapes
- NFL: Robust Learned Index via Distribution Transformation
- Hybrid Manufacturing Process Planning for Arbitrary Part and Tool Shapes
- Package Theft Detection from Smart Home Security Cameras
- SepIt: Approaching a Single Channel Speech Separation Bound
- Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition
- Symbolic Expression Transformer: A Computer Vision Approach for Symbolic Regression
- G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection
- Accelerating Frank-Wolfe via Averaging Step Directions
- Meta Policy Learning for Cold-Start Conversational Recommendation
- Quadratic models for understanding catapult dynamics of neural networks
- Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture
- AFNet-M: Adaptive Fusion Network with Masks for 2D+3D Facial Expression Recognition
- Attributing AUC-ROC to Analyze Binary Classifier Performance
- Wireless Ad Hoc Federated Learning: A Fully Distributed Cooperative Machine Learning
- Constrained Monotonic Neural Networks
- Multi-Augmentation for Efficient Visual Representation Learning for Self-supervised Pre-training
- Learning Context-Aware Service Representation for Service Recommendation in Workflow Composition
- Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees
- D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat
- Ranking-Based Siamese Visual Tracking
- UNet#: A UNet-like Redesigning Skip Connections for Medical Image Segmentation
- Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models
- UMSNet: An Universal Multi-sensor Network for Human Activity Recognition
- MOSPAT: AutoML based Model Selection and Parameter Tuning for Time Series Anomaly Detection
- Deep Learning-based automated classification of Chinese Speech Sound Disorders
- BabyBear: Cheap inference triage for expensive language models
- Alleviating Robust Overfitting of Adversarial Training With Consistency Regularization
- Demand Response Method Considering Multiple Types of Flexible Loads in Industrial Parks
- Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code
- Adaptive Few-Shot Learning Algorithm for Rare Sound Event Detection
- PERT: A New Solution to Pinyin to Character Conversion Task
- Towards a Defense Against Federated Backdoor Attacks Under Continuous Training
- Soft-SVM Regression For Binary Classification
- Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images
- From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering
- ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest
- On the Role of Bidirectionality in Language Model Pre-Training
- A Survey on Neural Open Information Extraction: Current Status and Future Directions
- Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments
- ENS-t-SNE: Embedding Neighborhoods Simultaneously t-SNE
- Semi-Parametric Inducing Point Networks and Neural Processes
- Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable
- Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations
- SCVRL: Shuffled Contrastive Video Representation Learning
- M6-Fashion: High-Fidelity Multi-modal Image Generation and Editing
- Functional Network: A Novel Framework for Interpretability of Deep Neural Networks
- RCC-GAN: Regularized Compound Conditional GAN for Large-Scale Tabular Data Synthesis
- TAILOR: Teaching with Active and Incremental Learning for Object Registration
- High-Order Pooling for Graph Neural Networks with Tensor Decomposition
- Workflow Discovery from Dialogues in the Low Data Regime
- On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
- HiPAL: A Deep Framework for Physician Burnout Prediction Using Activity Logs in Electronic Health Records
- Semi-Supervised Clustering of Sparse Graphs: Crossing the Information-Theoretic Threshold
- Learning multi-scale functional representations of proteins from single-cell microscopy data