Papers
Mon 24 Oct 2022
261 papers
- Inferring Past Human Actions in Homes with Abductive ReasoningLLM reasoning → Multimodal reasoning
- Structure-based Drug Design with Equivariant Diffusion ModelsDiffusion models → Flow matching, time series and science
- Learning by Hallucinating: Vision-Language Pre-training with Weak SupervisionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
- Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge ComputingEfficient LLM inference and serving → Early exit and edge inference
- Dichotomy of Control: Separating What You Can Control from What You CannotOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMsWorld models → World models for language agents
- ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text GenerationEfficient LLM inference and serving → Speculative decoding
- Geometric Knowledge Distillation: Topology Compression for Graph Neural NetworksKnowledge distillation → Graph neural network distillation
- High-Resolution Image Editing via Multi-Stage Blended DiffusionDiffusion models → Image generation, text-to-image and editing
- Correlation of the importances of neural network weights calculated by modern methods of overcoming catastrophic forgetting
- A Machine Learning Approach to Classifying Construction Cost Documents into the International Construction Measurement Standard
- Spiking Variational Graph Auto-Encoders for Efficient Graph Representation Learning
- Unlocking the potential of two-point cells for energy-efficient and resilient training of deep nets
- Efficiently Trained Low-Resource Mongolian Text-to-Speech System Based On FullConv-TTS
- Item-based Variational Auto-encoder for Fair Music Recommendation
- Logic-Based Explainability in Machine Learning
- AI Explainability and Governance in Smart Energy Systems: A Review
- Deep Model Reassembly
- Symbolic Distillation for Learned TCP Congestion Control
- Investigation of chemical structure recognition by encoder-decoder models in learning progress
- A Neural Network Based Automated IFT-20 Sensory Neuron Classifier for Caenorhabditis elegans
- Detection and Prevention Against Poisoning Attacks in Federated Learning
- RulE: Knowledge Graph Reasoning with Rule Embedding
- Perfectly Secure Steganography Using Minimum Entropy Coupling
- SleepMore: Inferring Sleep Duration at Scale via Multi-Device WiFi Sensing
- Atlas flow : compatible local structures on the manifold
- Food Ingredients Recognition through Multi-label Learning
- GlassesGAN: Eyewear Personalization using Synthetic Appearance Discovery and Targeted Subspace Modeling
- OSS Mentor A framework for improving developers contributions via deep reinforcement learning
- Exploring the impact of weather on Metro demand forecasting using machine learning method
- Does Joint Training Really Help Cascaded Speech Translation?
- Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model
- Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano
- Multi-SpacePhish: Extending the Evasion-space of Adversarial Attacks against Phishing Website Detectors using Machine Learning
- Self-Configuring nnU-Nets Detect Clouds in Satellite Images
- Boosting Kidney Stone Identification in Endoscopic Images Using Two-Step Transfer Learning
- An Effective Approach for Multi-label Classification with Missing Labels
- ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs
- Learning to forecast vegetation greenness at fine resolution over Africa with ConvLSTMs
- Temporally Disentangled Representation Learning
- Depth Monocular Estimation with Attention-based Encoder-Decoder Network from Single Image
- MISm: A Medical Image Segmentation Metric for Evaluation of weak labeled Data
- NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields
- Toward an Intelligent Tutoring System for Argument Mining in Legal Texts
- Vitruvio: 3D Building Meshes via Single Perspective Sketches
- On the Robustness of Dataset Inference
- Budget-Constrained Bounds for Mini-Batch Estimation of Optimal Transport
- Predicting Long-Term Citations from Short-Term Linguistic Influence
- VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge
- Deploying a Steered Query Optimizer in Production at Microsoft
- Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook
- Adapters for Enhanced Modeling of Multilingual Knowledge and Text
- Understanding the Evolution of Linear Regions in Deep Reinforcement Learning
- GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction
- The Robustness Limits of SoTA Vision Models to Natural Variation
- Learned Lifted Linearization Applied to Unstable Dynamic Systems Enabled by Koopman Direct Encoding
- Active Learning for Single Neuron Models with Lipschitz Non-Linearities
- LANS: Large-scale Arabic News Summarization Corpus
- Noise Injection as a Probe of Deep Learning Dynamics
- DilatedSegNet: A Deep Dilated Segmentation Network for Polyp Segmentation
- Datavoidant: An AI System for Addressing Political Data Voids on Social Media
- Embodied, Situated, and Grounded Intelligence: Implications for AI
- Learning Latent Structural Causal Models
- Speeding Up Question Answering Task of Language Models via Inverted Index
- Does Self-Rationalization Improve Robustness to Spurious Correlations?
- Conditionally Risk-Averse Contextual Bandits
- Sequential Recommendation with Auxiliary Item Relationships via Multi-Relational Transformer
- Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense Representations
- Characterizing Verbatim Short-Term Memory in Neural Language Models
- I see what you hear: a vision-inspired method to localize words
- Energy Pricing in P2P Energy Systems Using Reinforcement Learning
- Weight Fixing Networks
- Perceptual Image Enhancement for Smartphone Real-Time Applications
- Machine and Deep Learning for IoT Security and Privacy: Applications, Challenges, and Future Directions
- MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling
- Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation
- Video based Object 6D Pose Estimation using Transformers
- Private Online Prediction from Experts: Separations and Faster Rates
- Effective Pre-Training Objectives for Transformer-based Autoencoders
- Human-centered XAI for Burn Depth Characterization
- Classification of Misinformation in New Articles using Natural Language Processing and a Recurrent Neural Network
- Sufficient Invariant Learning for Distribution Shift
- Adaptive Top-K in SGD for Communication-Efficient Distributed Learning
- Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement
- Computational Inference in Cognitive Science: Operational, Societal and Ethical Considerations
- Context-Situated Pun Generation
- ExPUNations: Augmenting Puns with Keywords and Explanations
- Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
- Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance
- Opportunistic Episodic Reinforcement Learning
- Subspace Recovery from Heterogeneous Data with Non-isotropic Noise
- LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations
- textttMangrove: Learning Galaxy Properties from Merger Trees
- Graded-Q Reinforcement Learning with Information-Enhanced State Encoder for Hierarchical Collaborative Multi-Vehicle Pursuit
- Fast and Low-Memory Deep Neural Networks Using Binary Matrix Factorization
- Machine learning-based approach for online fault Diagnosis of Discrete Event System
- MetaFormer Baselines for Vision
- Controlled Text Reduction
- EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain
- Precision Machine Learning
All 261
- Monocular Dynamic View Synthesis: A Reality Check
- Protocols for classically training quantum generative models on probability distributions
- Bridging Machine Learning and Sciences: Opportunities and Challenges
- Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval
- Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models
- High Fidelity Neural Audio Compression
- Towards Better Few-Shot and Finetuning Performance with Forgetful Causal Language Models
- Instruction-Following Agents with Multimodal Transformer
- PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds
- Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds
- A Continuous Convolutional Trainable Filter for Modelling Unstructured Data
- Deep Learning Approach for Dynamic Sampling for Multichannel Mass Spectrometry Imaging
- Thermodynamics-informed neural networks for physically realistic mixed reality
- Contrastive Representation Learning for Gaze Estimation
- Entity-level Sentiment Analysis in Contact Center Telephone Conversations
- Sampling with Mollified Interaction Energy Descent
- Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech
- Offline congestion games: How feedback type affects data coverage requirement
- We need to talk about random seeds
- Explaining Translationese: why are Neural Classifiers Better and what do they Learn?
- On the failure of variational score matching for VAE models
- A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems
- Focused Concatenation for Context-Aware Neural Machine Translation
- Contraction of Locally Differentially Private Mechanisms
- Evaluating Long-Term Memory in 3D Mazes
- Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
- ADLight: A Universal Approach of Traffic Signal Control with Augmented Data Using Reinforcement Learning
- Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions
- System Configuration and Navigation of a Guide Dog Robot: Toward Animal Guide Dog-Level Guiding Work
- Large Batch and Patch Size Training for Medical Image Segmentation
- Don't Discard Fixed-Window Audio Segmentation in Speech-to-Text Translation
- NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks
- Novelty Detection in Time Series via Weak Innovations Representation: A Deep Learning Approach
- Robust Self-Supervised Learning with Lie Groups
- Matching Map Recovery with an Unknown Number of Outliers
- ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition
- Augmenting Task-Oriented Dialogue Systems with Relation Extraction
- Layer-Neighbor Sampling -- Defusing Neighborhood Explosion in GNNs
- Brain Tumor Segmentation using Enhanced U-Net Model with Empirical Analysis
- Real-time Speech Interruption Analysis: From Cloud to Client Deployment
- Theoretical Guarantees for Domain Adaptation with Hierarchical Optimal Transport
- Deep Kronecker Network
- Clean Text and Full-Body Transformer: Microsoft's Submission to the WMT22 Shared Task on Sign Language Translation
- Dual-Pixel Raindrop Removal
- MARS: Meta-Learning as Score Matching in the Function Space
- Learning and Covering Sums of Independent Random Variables with Unbounded Support
- Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning
- Applications of Machine Learning in Pharmacogenomics: Clustering Plasma Concentration-Time Curves
- BoundED: Neural Boundary and Edge Detection in 3D Point Clouds via Local Neighborhood Statistics
- Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysis
- Semantic Image Segmentation with Deep Learning for Vine Leaf Phenotyping
- NVIDIA FLARE: Federated Learning from Simulation to Real-World
- Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses
- Analyzing the Use of Influence Functions for Instance-Specific Data Filtering in Neural Machine Translation
- CompressedScaffnew: The First Theoretical Double Acceleration of Communication from Local Training and Compression in Distributed Optimization
- ECG Artifact Removal from Single-Channel Surface EMG Using Fully Convolutional Networks
- Generating Hierarchical Explanations on Text Classification Without Connecting Rules
- IQUAFLOW: A new framework to measure image quality
- Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation
- Mutual Information Alleviates Hallucinations in Abstractive Summarization
- Post-Selection Confidence Bounds for Prediction Performance
- Langevin dynamics based algorithm e-THvarepsilonO POULA for stochastic optimization problems with discontinuous stochastic gradient
- Simultaneous Improvement of ML Model Fairness and Performance by Identifying Bias in Data
- The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative
- A simple probabilistic neural network for machine understanding
- Proficiency assessment of L2 spoken English using wav2vec 2.0
- Exploring Self-Attention for Crop-type Classification Explainability
- Bilingual Synchronization: Restoring Translational Relationships with Editing Operations
- Towards an Understanding of Long-Tailed Runtimes of SLS Algorithms
- Reachability-Aware Laplacian Representation in Reinforcement Learning
- A PAC-Bayesian Generalization Bound for Equivariant Networks
- Binary Graph Convolutional Network with Capacity Exploration
- Transformers over Directed Acyclic Graphs
- Multilingual Multimodal Learning with Machine Translated Text
- PAC-Bayesian Offline Contextual Bandits With Guarantees
- Facial Soft Biometrics for Recognition in the Wild: Recent Works, Annotation, and COTS Evaluation
- Iris super-resolution using CNNs: is photo-realism important to iris recognition?
- Unsupervised Term Extraction for Highly Technical Domains
- Interactive inference: a multi-agent model of cooperative joint actions
- Federated Learning and Meta Learning: Approaches, Applications, and Directions
- WDA-Net: Weakly-Supervised Domain Adaptive Segmentation of Electron Microscopy
- Heat Demand Forecasting with Multi-Resolutional Representation of Heterogeneous Temporal Ensemble
- Deep Grey-Box Modeling With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models
- Towards an efficient Iris Recognition System on Embedded Devices
- Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models
- Full-Text Argumentation Mining on Scientific Publications
- Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
- Are Deep Sequence Classifiers Good at Non-Trivial Generalization?
- mm-Wave Radar Hand Shape Classification Using Deformable Transformers
- EpipolarNVS: leveraging on Epipolar geometry for single-image Novel View Synthesis
- Towards Unifying Reference Expression Generation and Comprehension
- Hardness in Markov Decision Processes: Theory and Practice
- How Bad is Selfish Driving? Bounding the Inefficiency of Equilibria in Urban Driving Games
- A partial order view of message-passing communication models
- A Unified Framework for Pun Generation with Humor Principles
- PARAFAC2-based Coupled Matrix and Tensor Factorizations
- Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers
- Structural generalization is hard for sequence-to-sequence models
- EXK-SC: A Semantic Communication Model Based on Information Framework Expansion and Knowledge Collision
- Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
- Learning Neural Radiance Fields from Multi-View Geometry
- "Covid vaccine is against Covid but Oxford vaccine is made at Oxford!" Semantic Interpretation of Proper Noun Compounds
- Subspace Representations for Soft Set Operations and Sentence Similarities
- Self-supervised Rewiring of Pre-trained Speech Encoders: Towards Faster Fine-tuning with Less Labels in Speech Processing
- Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models
- Generalised Likelihood Ratio Testing Adversaries through the Differential Privacy Lens
- E-Valuating Classifier Two-Sample Tests
- On the Effectiveness of Automated Metrics for Text Generation Systems
- Investigating the detection of Tortured Phrases in Scientific Literature
- FairGen: Fair Synthetic Data Generation
- Cards Against AI: Predicting Humor in a Fill-in-the-blank Party Game
- CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network
- On Many-Actions Policy Gradient
- Iterative Patch Selection for High-Resolution Image Recognition
- Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment
- Efficient Representation of Natural Image Patches
- An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks
- Modeling Information Change in Science Communication with Semantically Matched Paraphrases
- Are Current Decoding Strategies Capable of Facing the Challenges of Visual Dialogue?
- Optimal activity and battery scheduling algorithm using load and solar generation forecasts
- Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)
- Maknuune: A Large Open Palestinian Arabic Lexicon
- Multi-Type Conversational Question-Answer Generation with Closed-ended and Unanswerable Questions
- Language-free Training for Zero-shot Video Grounding
- Investigating Neuron Disturbing in Fusing Heterogeneous Neural Networks
- Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning
- Non-Contrastive Learning-based Behavioural Biometrics for Smart IoT Devices
- Composition, Attention, or Both?
- On the optimization and pruning for Bayesian deep learning
- Implementation of Trained Factorization Machine Recommendation System on Quantum Annealer
- Ares: A System-Oriented Wargame Framework for Adversarial ML
- Enhancing Label Consistency on Document-level Named Entity Recognition
- IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation
- Revisiting Sparse Convolutional Model for Visual Recognition
- Deep Edge Intelligence: Architecture, Key Features, Enabling Technologies and Challenges
- Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?
- Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method
- Heterogeneous Information Crossing on Graphs for Session-based Recommender Systems
- GradMix for nuclei segmentation and classification in imbalanced pathology image datasets
- Selecting and Composing Learning Rate Policies for Deep Neural Networks
- 360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning
- Multi-Agent Path Finding via Tree LSTM
- Removing Radio Frequency Interference from Auroral Kilometric Radiation with Stacked Autoencoders
- Finding Memo: Extractive Memorization in Constrained Sequence Generation Tasks
- GFlowOut: Dropout with Generative Flow Networks
- Exploring Euphemism Detection in Few-Shot and Zero-Shot Settings
- TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases
- OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks
- BARS: A Benchmark for Airport Runway Segmentation
- Investigating self-supervised, weakly supervised and fully supervised training approaches for multi-domain automatic speech recognition: a study on Bangladeshi Bangla
- Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE
- Robust Ellipse Fitting Based on Maximum Correntropy Criterion With Variable Center
- A Novel Adaptive Causal Sampling Method for Physics-Informed Neural Networks
- Specializing Multi-domain NMT via Penalizing Low Mutual Information
- Predicting the Citation Count and CiteScore of Journals One Year in Advance
- Visualizing the Obvious: A Concreteness-based Ensemble Model for Noun Property Prediction
- Gallery Filter Network for Person Search
- Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation
- SpikeSim: An end-to-end Compute-in-Memory Hardware Evaluation Tool for Benchmarking Spiking Neural Networks
- Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learning
- AACHER: Assorted Actor-Critic Deep Reinforcement Learning with Hindsight Experience Replay