Papers
Wed 26 Oct 2022
236 papers
- Environment Design for Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning AbilityLLM reasoning → Multimodal reasoning
- DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative ModelsDiffusion models → Image generation, text-to-image and editing
- M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designMixture-of-experts → Vision mixture-of-experts
- Categorical SDEs with Simplex DiffusionDiffusion models → Diffusion foundations and sampling
- Fast Yet Effective Speech Emotion Recognition with Self-distillationKnowledge distillation → Multimodal distillation
- Towards the Detection of Diffusion Model DeepfakesDiffusion models → Image generation, text-to-image and editing
- Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Eeny, meeny, miny, moe. How to choose data for morphological inflectionMixture-of-experts → MoE large language models
- The NPU-ASLP System for The ISCSLP 2022 Magichub Code-Swiching ASR ChallengeMixture-of-experts → Multimodal MoE models
- D-Shape: Demonstration-Shaped Reinforcement Learning via Goal ConditioningOffline RL and imitation learning from data → Imitation learning methods
- Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design
- Multimodal Generative Models for Bankruptcy Prediction Using Textual Data
- Non-Linear Coordination Graphs
- Active Learning Framework to Automate NetworkTraffic Classification
- Multilevel Transformer For Multimodal Emotion Recognition
- End-to-End Speech to Intent Prediction to improve E-commerce Customer Support Voicebot in Hindi and English
- Incongruity Detection between Bangla News Headline and Body Content through Graph Neural Network
- A Sign That Spells: DALL-E 2, Invisual Images and The Racial Politics of Feature Space
- Exploring Robustness of Prefix Tuning in Noisy Data: A Case Study in Financial Sentiment Analysis
- Toward automatic generation of control structures for process flow diagrams with large language models
- Graph-Regularized Tensor Regression: A Domain-Aware Framework for Interpretable Multi-Way Financial Modelling
- Will we run out of data? Limits of LLM scaling based on human-generated data
- Multi-view Multi-label Fine-grained Emotion Decoding from Human Brain Activity
- Network Aware Compute and Memory Allocation in Optically Composable Data Centres with Deep Reinforcement Learning and Graph Neural Networks
- Learning to Configure Computer Networks with Neural Algorithmic Reasoning
- A Transformer-based Framework for POI-level Social Post Geolocation
- ERL-Re2: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation
- There is more than one kind of robustness: Fooling Whisper with adversarial examples
- A deep scalable neural architecture for soil properties estimation from spectral information
- DiscreteCommunication and ControlUpdating in Event-Triggered Consensus
- SeaDroneSim: Simulation of Aerial Images for Detection of Objects Above Water
- Knowledge-Guided Exploration in Deep Reinforcement Learning
- Automatic extraction of materials and properties from superconductors scientific literature
- Low-Rank Modular Reinforcement Learning via Muscle Synergy
- LP-BFGS attack: An adversarial attack based on the Hessian with limited pixels
- Efficient Utilization of Large Pre-Trained Models for Low Resource ASR
- Learning versus Refutation in Noninteractive Local Differential Privacy
- Grokking phase transitions in learning local rules with gradient descent
- HEiMDaL: Highly Efficient Method for Detection and Localization of wake-words
- Local Graph-homomorphic Processing for Privatized Distributed Systems
- Deep Learning is Provably Robust to Symmetric Label Noise
- Bayesian Hyperbolic Multidimensional Scaling
- The Inconvenient Truths of Ground Truth for Binary Analysis
- IDEAL: Improved DEnse locAL Contrastive Learning for Semi-Supervised Medical Image Segmentation
- Hierarchical quantum circuit representations for neural architecture search
- Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweighting
- arXivEdits: Understanding the Human Revision Process in Scientific Writing
- Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition
- Optimal Sub-sampling to Boost Power of Kernel Sequential Change-point Detection
- Automated Reconstruction of 3D Open Surfaces from Sparse Point Clouds
- Tangent Bundle Filters and Neural Networks: from Manifolds to Cellular Sheaves and Back
- UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
- Federated Continual Learning to Detect Accounting Anomalies in Financial Auditing
- TILDE-Q: A Transformation Invariant Loss Function for Time-Series Forecasting
- DyREx: Dynamic Query Representation for Extractive Question Answering
- Generative modeling of the enteric nervous system employing point pattern analysis and graph construction
- Privately Fine-Tuning Large Language Models with Differential Privacy
- PERGAMO: Personalized 3D Garments from Monocular Video
- Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems
- Multi-Scale Structural-aware Exposure Correction for Endoscopic Imaging
- Characterizing Datapoints via Second-Split Forgetting
- A Hierarchical Approach to Conditional Random Fields for System Anomaly Detection
- FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning
- A novel information gain-based approach for classification and dimensionality reduction of hyperspectral images
- Addressing Heterogeneity in Federated Learning via Distributional Transformation
- Automatic Assessment of Infant Face and Upper-Body Symmetry as Early Signs of Torticollis
- Hypergraph Artificial Benchmark for Community Detection (h-ABCD)
- High-dimensional Measurement Error Models for Lipschitz Loss
- Trade-off between reconstruction loss and feature alignment for domain generalization
- One Arrow, Two Kills: An Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits
- LiDAR-guided object search and detection in Subterranean Environments
- Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems
- The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
- Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racing
- Fast and Efficient Scene Categorization for Autonomous Driving using VAEs
- Interstellar Object Accessibility and Mission Design
- Robust Domain Adaptation for Pre-trained Multilingual Neural Machine Translation Models
- Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured Learning
- MABEL: Attenuating Gender Bias using Textual Entailment Data
- SINCO: A Novel structural regularizer for image compression using implicit neural representations
- What's Different between Visual Question Answering for Machine "Understanding" Versus for Accessibility?
- Disentangled Text Representation Learning with Information-Theoretic Perspective for Adversarial Robustness
- A super-polynomial quantum-classical separation for density modelling
- AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection
- The eyes and hearts of UAV pilots: observations of physiological responses in real-life scenarios
- Automated Diagnosis of Cardiovascular Diseases from Cardiac Magnetic Resonance Imaging Using Deep Learning Models: A Review
- Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds
- CU-Net: LiDAR Depth-Only Completion With Coupled U-Net
- Searching Dense Point Correspondences via Permutation Matrix Learning
- Learning to predict arbitrary quantum processes
- Broken Neural Scaling Laws
- Quantum deep recurrent reinforcement learning
- Anisotropic multiresolution analyses for deepfake detection
- Multi-lingual Evaluation of Code Generation Models
- Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning
- Visual Semantic Parsing: From Images to Abstract Meaning Representation
- Multi-level Data Representation For Training Deep Helmholtz Machines
- Causality Detection using Multiple Annotation Decisions
- ProVe: A Pipeline for Automated Provenance Verification of Knowledge Graphs against Textual Sources
All 236
- Synthetic Tumors Make AI Segment Tumors Better
- TuneUp: A Simple Improved Training Strategy for Graph Neural Networks
- NeuralSearchX: Serving a Multi-billion-parameter Reranker for Multilingual Metasearch at a Low Cost
- Streaming Radiance Fields for 3D Video Synthesis
- Personalized Federated Learning via Heterogeneous Modular Networks
- tf.data service: A Case for Disaggregating ML Input Data Processing
- Visual Answer Localization with Cross-modal Mutual Knowledge Transfer
- Deep Subspace Encoders for Nonlinear System Identification
- On the Curious Case of ℓ2 norm of Sense Embeddings
- BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples
- HyperEF: Spectral Hypergraph Coarsening by Effective-Resistance Clustering
- Don't Prompt, Search! Mining-based Zero-Shot Learning with Language Models
- Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification
- Is Multi-Task Learning an Upper Bound for Continual Learning?
- AD-DMKDE: Anomaly Detection through Density Matrices and Fourier Features
- ViNL: Visual Navigation and Locomotion Over Obstacles
- Decoupled Mixup for Generalized Visual Recognition
- Coordinate Descent for SLOPE
- Evaluation of Synthetically Generated CT for use in Transcranial Focused Ultrasound Procedures
- Unknown area exploration for robots with energy constraints using a modified Butterfly Optimization Algorithm
- Rapid and robust endoscopic content area estimation: A lean GPU-based pipeline and curated benchmark dataset
- Towards a machine learning pipeline in reduced order modelling for inverse problems: neural networks for boundary parametrization, dimensionality reduction and solution manifold approximation
- ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholds
- A New Task: Deriving Semantic Class Targets for the Physical Sciences
- Maximum Likelihood Learning of Unnormalized Models for Simulation-Based Inference
- Hybrid HMM Decoder For Convolutional Codes By Joint Trellis-Like Structure and Channel Prior
- Long-tailed Food Classification
- Monotonic segmental attention for automatic speech recognition
- A Case for Business Process-Specific Foundation Models
- Distribution-Free Finite-Sample Guarantees and Split Conformal Prediction
- Pretrained audio neural networks for Speech emotion recognition in Portuguese
- TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction
- Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks
- Learning on Large-scale Text-attributed Graphs via Variational Inference
- Is Out-of-Distribution Detection Learnable?
- Rhino: Deep Causal Temporal Relationship Learning With History-dependent Noise
- ClipBot: an educational, physically impaired robot that learns to walk via genetic algorithm optimization
- Piloting Copilot, Codex, and StarCoder2: Hot Temperature, Cold Prompts, or Black Magic?
- Autoregressive Structured Prediction with Language Models
- Pronunciation Generation for Foreign Language Words in Intra-Sentential Code-Switching Speech Recognition
- Which is the best model for my data?
- Leveraging Demonstrations with Latent Space Priors
- In search of strong embedding extractors for speaker diarisation
- Investigating the Role of Centering Theory in the Context of Neural Coreference Resolution Systems
- How precise are performance estimates for typical medical image segmentation tasks?
- Comparison of neural closure models for discretised PDEs
- Sparsity in Continuous-Depth Neural Networks
- Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations
- A Bilingual Parallel Corpus with Discourse Annotations
- Desiderata for next generation of ML model serving
- Coresets for Vertical Federated Learning: Regularized Linear Regression and K-Means Clustering
- Full-band General Audio Synthesis with Score-based Diffusion
- TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge
- MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective
- Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input
- Super-Resolution Based Patch-Free 3D Image Segmentation with High-Frequency Guidance
- HSVI can solve zero-sum Partially Observable Stochastic Games
- Graph Filter Transfer via Probability Density Ratio Weighting
- RapidAI4EO: Mono- and Multi-temporal Deep Learning models for Updating the CORINE Land Cover Product
- A new band selection approach based on information theory and support vector machine for hyperspectral images reduction and classification
- SemFormer: Semantic Guided Activation Transformer for Weakly Supervised Semantic Segmentation
- A Late Multi-Modal Fusion Model for Detecting Hybrid Spam E-mail
- Analyzing Deep Learning Representations of Point Clouds for Real-Time In-Vehicle LiDAR Perception
- Automatic Diagnosis of Myocarditis Disease in Cardiac MRI Modality using Deep Transformers and Explainable Artificial Intelligence
- A novel filter based on three variables mutual information for dimensionality reduction and classification of hyperspectral images
- A practical method for occupational skills detection in Vietnamese job listings
- Analyzing Multi-Task Learning for Abstractive Text Summarization
- Predicting the State of Synchronization of Financial Time Series using Cross Recurrence Plots
- End-to-end Tracking with a Multi-query Transformer
- Manifold Gaussian Variational Bayes on the Precision Matrix
- A Stronger Baseline For Automatic Pfirrmann Grading Of Lumbar Spine MRI Using Deep Learning
- Scaling Knowledge Graphs for Automating AI of Digital Twins
- Scaling Laws Beyond Backpropagation
- Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance
- Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models
- Uncertainty Sentence Sampling by Virtual Adversarial Perturbation
- Learning Causal Graphs in Manufacturing Domains using Structural Equation Models
- AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination
- FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization
- Hierarchical Federated Learning with Momentum Acceleration in Multi-Tier Networks
- Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis
- A Robust Bias Mitigation Procedure Based on the Stereotype Content Model
- Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inference
- Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering
- Position tracking of a varying number of sound sources with sliding permutation invariant training
- Uncertainty-based Meta-Reinforcement Learning for Robust Radar Tracking
- Unifying Data Perspectivism and Personalization: An Application to Social Norms
- RGB-T Semantic Segmentation with Location, Activation, and Sharpening
- Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulator
- A Bibliometric Analysis and Review on Reinforcement Learning for Transportation Applications
- OTSeq2Set: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification
- Improving Speech-to-Speech Translation Through Unlabeled Text
- End-to-End Multimodal Representation Learning for Video Dialog
- Multi-Environment based Meta-Learning with CSI Fingerprints for Radio Based Positioning
- Parallel Gated Neural Network With Attention Mechanism For Speech Enhancement
- SimpleDG: Simple Domain Generalization Baseline without Bells and Whistles
- SentBS: Sentence-level Beam Search for Controllable Summarization
- CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming Course
- Provable Safe Reinforcement Learning with Binary Feedback
- History-Based, Bayesian, Closure for Stochastic Parameterization: Application to Lorenz '96
- Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding
- Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection
- Imputation of missing values in multi-view data
- Robust Contextual Linear Bandits
- SPQR: An R Package for Semi-Parametric Density and Quantile Regression
- Meta-node: A Concise Approach to Effectively Learn Complex Relationships in Heterogeneous Graphs
- SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks
- Benchmarking Language Models for Code Syntax Understanding
- Sinhala Sentence Embedding: A Two-Tiered Structure for Low-Resource Languages
- Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning
- Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts
- TPFNet: A Novel Text In-painting Transformer for Text Removal
- PredNAS: A Universal and Sample Efficient Neural Architecture Search Framework
- Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
- Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension
- Short Paper: Static and Microarchitectural ML-Based Approaches For Detecting Spectre Vulnerabilities and Attacks
- Discovering Design Concepts for CAD Sketches
- Smart Speech Segmentation using Acousto-Linguistic Features with look-ahead
- N-gram Is Back: Residual Learning of Neural Text Generation with n-gram Language Model
- ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select
- Geographic Citation Gaps in NLP Research
- Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach
- Discourse-Aware Emotion Cause Extraction in Conversations
- Residual Back Projection With Untrained Neural Networks
- Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes
- Modeling the Graphotactics of Low-Resource Languages Using Sequential GANs
- An Attention-based Long Short-Term Memory Framework for Detection of Bitcoin Scams
- RedPen: Region- and Reason-Annotated Dataset of Unnatural Speech
- Adversarially Robust Medical Classification via Attentive Convolutional Neural Networks
- Adversarial Purification with the Manifold Hypothesis
- Adaptive deep density approximation for fractional Fokker-Planck equations
- FeDXL: Provable Federated Learning for Deep X-Risk Optimization
- IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text
- Federated Fuzzy Neural Network with Evolutionary Rule Learning
- Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization
- Can Transformer Attention Spread Give Insights Into Uncertainty of Detected and Tracked Objects?