Papers
Wed 13 Sep 2023
188 papers
- A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement LearningOffline RL and imitation learning from data → Real-world robot offline RL
- Limitations of Face Image GenerationDiffusion models → Image generation, text-to-image and editing
- Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion EnhancementDiffusion models → Diffusion foundations and sampling
- Diffusion models for audio semantic communicationDiffusion models → Diffusion for compression and wireless
- RAIN: Your Language Models Can Align Themselves without FinetuningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and EthicsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- UnifiedGesture: A Unified Gesture Synthesis Model for Multiple SkeletonsDiffusion models → Audio, speech and music
- Auto-Regressive Next-Token Predictors are Universal LearnersLLM reasoning → Test-time compute and efficient thinking
- DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- MagiCapture: High-Resolution Multi-Concept Portrait CustomizationDiffusion models → Image generation, text-to-image and editing
- DCTTS: Discrete Diffusion Model with Contrastive Learning for Text-to-speech GenerationDiffusion models → Audio, speech and music
- ZKROWNN: Zero Knowledge Right of Ownership for Neural NetworksLLM safety and security → Watermarking generated content and models
- CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data GenerationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward PassLLM safety and security → Membership inference attacks
- STUPD: A Synthetic Dataset for Spatial and Temporal Relation ReasoningLLM reasoning → Spatial and embodied reasoning +1
- Dissipative Imitation Learning for Discrete Dynamic Output Feedback Control with Sparse Data SetsOffline RL and imitation learning from data → Imitation learning methods
- Statistical Rejection Sampling Improves Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RLLLM reasoning → Prompting and chain-of-thought reasoning
- End-to-end Phase Field Model Discovery Combining Experimentation, Crowdsourcing, Simulation and Learning
- Harnessing Deep Q-Learning for Enhanced Statistical Arbitrage in High-Frequency Trading: A Comprehensive Exploration
- From Deep Filtering to Deep Econometrics
- Privacy-Engineered Value Decomposition Networks for Cooperative Multi-Agent Reinforcement Learning
- Analysis and Detection against Network Attacks in the Overlapping Phenomenon of Behavior Attribute
- CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics
- Improving the Performance of R17 Type-II Codebook with Deep Learning
- An Efficient Intelligent Semi-Automated Warehouse Inventory Stocktaking System
- A Multi-label Classification Approach to Increase Expressivity of EMG-based Gesture Recognition
- Pretraining on the Test Set Is All You Need
- Large Language Models Can Infer Psychological Dispositions of Social Media Users
- Open-vocabulary Keyword-spotting with Adaptive Instance Normalization
- Racing Control Variable Genetic Programming for Symbolic Regression
- Generative AI
- Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer
- Tackling the dimensions in imaging genetics with CLUB-PLS
- Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains
- Efficient quantum recurrent reinforcement learning via quantum reservoir computing
- Learning from Auxiliary Sources in Argumentative Revision Classification
- Reliability-based cleaning of noisy training labels with inductive conformal prediction in multi-modal biomedical data mining
- Automated Assessment of Critical View of Safety in Laparoscopic Cholecystectomy
- textttNePhi: Neural Deformation Fields for Approximately Diffeomorphic Medical Image Registration
- Traveling Words: A Geometric Interpretation of Transformers
- AudioSR: Versatile Audio Super-resolution at Scale
- Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
- Multi-Modal Hybrid Learning and Sequential Training for RGB-T Saliency Detection
- GAN-based Algorithm for Efficient Image Inpainting
- User Training with Error Augmentation for Electromyogram-based Gesture Classification
- Language-Conditioned Observation Models for Visual Object Search
- So you think you can track?
- Safe and Accelerated Deep Reinforcement Learning-based O-RAN Slicing: A Hybrid Transfer Learning Approach
- Simultaneous inference for generalized linear models with unmeasured confounders
- Automated segmentation of rheumatoid arthritis immunohistochemistry stained synovial tissue
- In-Contextual Gender Bias Suppression for Large Language Models
- All you need is spin: SU(2) equivariant variational quantum circuits based on spin networks
- LInKs "Lifting Independent Keypoints" -- Partial Pose Lifting for Occlusion Handling with Improved Accuracy in 2D-3D Human Pose Estimation
- Autotuning Apache TVM-based Scientific Applications Using Bayesian Optimization
- EarthPT: a time series foundation model for Earth Observation
- Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
- Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments
- Attention-based Dynamic Graph Convolutional Recurrent Neural Network for Traffic Flow Prediction in Highway Transportation
- A Robust SINDy Approach by Combining Neural Networks and an Integral Form
- The effect of data augmentation and 3D-CNN depth on Alzheimer's Disease detection
- Learning From Drift: Federated Learning on Non-IID Data via Drift Regularization
- Predicting Survival Time of Ball Bearings in the Presence of Censoring
- Multi-step prediction of chlorophyll concentration based on Adaptive Graph-Temporal Convolutional Network with Series Decomposition
- LCReg: Long-Tailed Image Classification with Latent Categories based Recognition
- A Health Monitoring System Based on Flexible Triboelectric Sensors for Intelligence Medical Internet of Things and its Applications in Virtual Reality
- Text-Guided Generation and Editing of Compositional 3D Avatars
- Tree-Structured Shading Decomposition
- PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
- Getting More for Less: Using Weak Labels and AV-Mixup for Robust Audio-Visual Speaker Verification
- Contrastive Deep Encoding Enables Uncertainty-aware Machine-learning-assisted Histopathology
- Data Augmentation via Subgroup Mixup for Improving Fairness
- Characterizing Speed Performance of Multi-Agent Reinforcement Learning
- Hardening RGB-D Object Recognition Systems against Adversarial Patch Attacks
- Polygon Intersection-over-Union Loss for Viewpoint-Agnostic Monocular 3D Vehicle Detection
- Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding
- RadarLCD: Learnable Radar-based Loop Closure Detection Pipeline
- Developing a Novel Image Marker to Predict the Clinical Outcome of Neoadjuvant Chemotherapy (NACT) for Ovarian Cancer Patients
- Mitigating Group Bias in Federated Learning for Heterogeneous Devices
- SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection
- Can Whisper perform speech-based in-context learning?
- The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning
- FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection
- Physics-informed Bayesian inference of external potentials in classical density-functional theory
- A Comprehensive Analysis of the Role of Artificial Intelligence and Machine Learning in Modern Digital Forensics and Incident Response
- Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments
- Aggregating Nearest Sharp Features via Hybrid Transformers for Video Deblurring
- Pearl's and Jeffrey's Update as Modes of Learning in Probabilistic Programming
- An Extreme Learning Machine-Based Method for Computational PDEs in Higher Dimensions
- SafetyBench: Evaluating the Safety of Large Language Models
- Efficient Reinforcement Learning for Jumping Monopods
- Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting
- Optimal transport distances for directed, weighted graphs: a case study with cell-cell communication networks
- Exploiting Multiple Priors for Neural 3D Indoor Reconstruction
- Beyond original Research Articles Categorization via NLP
- R'esum'e Parsing as Hierarchical Sequence Labeling: An Empirical Study
- OYXOY: A Modern NLP Test Suite for Modern Greek
- Modeling the Evolutionary Trends in Corporate ESG Reporting: A Study based on Knowledge Management Model
- Unsupervised Contrast-Consistent Ranking with Language Models
- Remote Inference of Cognitive Scores in ALS Patients Using a Picture Description
All 188
- Instance Adaptive Prototypical Contrastive Embedding for Generalized Zero Shot Learning
- CARE: Large Precision Matrix Estimation for Compositional Data
- MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems
- Differentiable JPEG: The Devil is in the Details
- DNNShifter: An Efficient DNN Pruning System for Edge Computing
- Setting the Right Expectations: Algorithmic Recourse Over Time
- Towards Reliable Dermatology Evaluation Benchmarks
- PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection
- Neural network-based coronary dominance classification of RCA angiograms
- Implicit Neural Multiple Description for DNA-based data storage
- TransNet: A Transfer Learning-Based Network for Human Action Recognition
- Limited-Angle Tomography Reconstruction via Deep End-To-End Learning on Synthetic Data
- Effect of hyperparameters on variable selection in random forests
- DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision
- Collectionless Artificial Intelligence
- Modeling Dislocation Dynamics Data Using Semantic Web Technologies
- Dynamic Causal Disentanglement Model for Dialogue Emotion Detection
- Contrast-Phys+: Unsupervised and Weakly-supervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast
- Native Language Identification with Big Bird Embeddings
- Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuning
- Investigating the Impact of Action Representations in Policy Gradient Algorithms
- Continual Learning with Dirichlet Generative-based Rehearsal
- Towards the TopMost: A Topic Modeling System Toolkit
- CCSPNet-Joint: Efficient Joint Training Method for Traffic Sign Detection Under Extreme Conditions
- Domain-Aware Augmentations for Unsupervised Online General Continual Learning
- Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?
- OWL Reasoners still useable in 2023
- Autoencoder-Based Visual Anomaly Localization for Manufacturing Quality Control
- ProMap: Datasets for Product Mapping in E-commerce
- Video Infringement Detection via Feature Disentanglement and Mutual Information Maximization
- Dynamic control of self-assembly of quasicrystalline structures through reinforcement learning
- Gpachov at CheckThat! 2023: A Diverse Multi-Approach Ensemble for Subjectivity Detection in News Articles
- On the Local Quadratic Stability of T-S Fuzzy Systems in the Vicinity of the Origin
- Supervised Machine Learning and Physics based Machine Learning approach for prediction of peak temperature distribution in Additive Friction Stir Deposition of Aluminium Alloy
- Safe Reinforcement Learning with Dual Robustness
- UniBrain: Universal Brain MRI Diagnosis with Hierarchical Knowledge-enhanced Pre-training
- Topology-inspired Cross-domain Network for Developmental Cervical Stenosis Quantification
- Beyond Adapting SAM: Towards End-to-End Ultrasound Image Segmentation via Auto Prompting
- Tracking Particles Ejected From Active Asteroid Bennu With Event-Based Vision
- Comparative Analysis of Contextual Relation Extraction based on Deep Learning Models
- Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly
- TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification
- Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation task
- FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization
- Dynamic NeRFs for Soccer Scenes
- Defensive Alliances in Signed Networks
- Uncertainty-aware Traffic Prediction under Missing Data
- When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System
- Cognitive Mirage: A Review of Hallucinations in Large Language Models
- Electricity Demand Forecasting through Natural Language Processing with Long Short-Term Memory Networks
- Motion-Bias-Free Feature-Based SLAM
- Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors
- Fundamental Limits of Deep Learning-Based Binary Classifiers Trained with Hinge Loss
- Scaled Prompt-Tuning for Few-Shot Natural Language Generation
- Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advances
- MFL-YOLO: An Object Detection Model for Damaged Traffic Signs
- Integrating GAN and Texture Synthesis for Enhanced Road Damage Detection
- VEATIC: Video-based Emotion and Affect Tracking in Context Dataset
- MTD: Multi-Timestep Detector for Delayed Streaming Perception
- MCNS: Mining Causal Natural Structures Inside Time Series via A Novel Internal Causality Scheme
- GelFlow: Self-supervised Learning of Optical Flow for Vision-Based Tactile Sensor Displacement Measurement
- Leveraging Foundation models for Unsupervised Audio-Visual Segmentation
- Enhancing Keyphrase Generation by BART Finetuning with Splitting and Shuffling
- Deep Nonparametric Convexified Filtering for Computational Photography, Image Synthesis and Adversarial Defense
- Dynamic Spectrum Mixer for Visual Recognition
- Deep Attentive Time Warping
- TrafficGPT: Viewing, Processing and Interacting with Traffic Foundation Models
- Bias Amplification Enhances Minority Group Performance
- MPI-Flow: Learning Realistic Optical Flow with Multiplane Images
- Crystal structure prediction using neural network potential and age-fitness Pareto genetic algorithm
- Predicting Fatigue Crack Growth via Path Slicing and Re-Weighting
- Simultaneous Machine Translation with Large Language Models
- VLSlice: Interactive Vision-and-Language Slice Discovery
- Transparent Object Tracking with Enhanced Fusion Module
- Benchmarking Procedural Language Understanding for Low-Resource Languages: A Case Study on Turkish
- Tackling the Non-IID Issue in Heterogeneous Federated Learning by Gradient Harmonization
- Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics
- Attention Loss Adjusted Prioritized Experience Replay
- Federated PAC-Bayesian Learning on Non-IID data
- A plug-and-play synthetic data deep learning for undersampled magnetic resonance image reconstruction
- Robust experimental data assimilation for the Spalart-Allmaras turbulence model
- SHARM: Segmented Head Anatomical Reference Models
- ShaDocFormer: A Shadow-Attentive Threshold Detector With Cascaded Fusion Refiner for Document Shadow Removal
- Sound field decomposition based on two-stage neural networks
- Generalizable Neural Fields as Partially Observed Neural Processes
- Out of Distribution Detection via Domain-Informed Gaussian Process State Space Models
- Event-Driven Imaging in Turbid Media: A Confluence of Optoelectronics and Neuromorphic Computation
- ConR: Contrastive Regularizer for Deep Imbalanced Regression