Papers
Fri 23 Jun 2023
156 papers
- Zero-shot spatial layout conditioning for text-to-image diffusion modelsDiffusion models → Image generation, text-to-image and editing
- Simultaneous Image-to-Zero and Zero-to-Noise: Diffusion Models with Analytical Image AttenuationDiffusion models → Diffusion foundations and sampling
- Exploring the Potential of AI-Generated Synthetic Datasets: A Case Study on Telematics Data with ChatGPTSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- On-Policy Distillation of Language Models: Learning from Self-Generated MistakesSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training +1
- Offline Skill Graph (OSG): A Framework for Learning and Planning using Offline Reinforcement Learning SkillsOffline RL and imitation learning from data → Offline RL algorithms
- System-Level Natural Language FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy ImitationOffline RL and imitation learning from data → Imitation learning methods
- A Survey on Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrievalRetrieval-augmented generation → Generation and context integration
- CLUE: Calibrated Latent Guidance for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in HistopathologyDiffusion models → Medical imaging and segmentation
- ToolQA: A Dataset for LLM Question Answering with External ToolsLLM agents and tool use → Tool learning and function calling
- An Overview about Emerging Technologies of Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- Exploring Cognitive Paradoxes in Video Games: A Quantum Mechanical Perspective
- An Intelligent Mechanism for Monitoring and Detecting Intrusions in IoT Devices
- Blockchain-based Federated Learning for Decentralized Energy Management Systems
- Multimodal Search on Iconclass using Vision-Language Pre-Trained Models
- ChatGPT may excel in States Medical Licensing Examination but falters in basic Linear Algebra
- Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
- Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning
- Implementing contextual biasing in GPU decoder for online ASR
- LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding
- Product Information Extraction using ChatGPT
- A Cosine Similarity-based Method for Out-of-Distribution Detection
- Evolutionary approaches to explainable machine learning
- AR2-D2:Training a Robot Without a Robot
- The Double Helix inside the NLP Transformer
- Upscaling Global Hourly GPP with Temporal Fusion Transformer (TFT)
- BatchGNN: Efficient CPU-Based Distributed GNN Training on Very Large Graphs
- DualAttNet: Synergistic Fusion of Image-level and Fine-Grained Disease Attention for Multi-Label Lesion Detection in Chest X-rays
- Maintaining Plasticity in Deep Continual Learning
- Potential Benefits of Employing Large Language Models in Research in Moral Education and Development
- Cross-Language Speech Emotion Recognition Using Multimodal Dual Attention Transformers
- Elephants and Algorithms: A Review of the Current and Future Role of AI in Elephant Monitoring
- A First Order Meta Stackelberg Method for Robust Federated Learning
- An analysis of vaccine-related sentiments from development to deployment of COVID-19 vaccines
- On Learning Latent Models with Multi-Instance Weak Supervision
- Tensor Dirichlet Process Multinomial Mixture Model for Passenger Trajectory Clustering
- QNNRepair: Quantized Neural Network Repair
- Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models
- A new approach to generalisation error of machine learning algorithms: Estimates and convergence
- Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition
- Achieving Diversity in Objective Space for Sample-efficient Search of Multiobjective Optimization Problems
- Swin-Free: Achieving Better Cross-Window Attention and Efficiency with Size-varying Window
- Resume Information Extraction via Post-OCR Text Processing
- Nearest Neighbour with Bandit Feedback
- CeBed: A Benchmark for Deep Data-Driven OFDM Channel Estimation
- Task-Driven Graph Attention for Hierarchical Relational Object Navigation
- Incremental Profit per Conversion: a Response Transformation for Uplift Modeling in E-Commerce Promotions
- Four Axiomatic Characterizations of the Integrated Gradients Attribution Method
- Analyzing scRNA-seq data by CCP-assisted UMAP and t-SNE
- Revisiting inference after prediction
- Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraints
- Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity
- The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios
- Reinforcement Learning with Temporal-Logic-Based Causal Diagrams
- How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images
- Improving Panoptic Segmentation for Nighttime or Low-Illumination Urban Driving Scenes
- Review of compressed embedding layers and their applications for recommender systems
- Human-AI Coevolution
- Use case cards: a use case reporting framework inspired by the European AI Act
- Curvature-enhanced Graph Convolutional Network for Biomolecular Interaction Prediction
- Phase Unwrapping of Color Doppler Echocardiography using Deep Learning
- ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration
- Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
- LightGlue: Local Feature Matching at Light Speed
- A New Paradigm for Generative Adversarial Networks based on Randomized Decision Rules
- Constrained optimization of sensor placement for nuclear digital twins
- OpenMask3D: Open-Vocabulary 3D Instance Segmentation
- Adversarial Robustness Certification for Bayesian Neural Networks
- Machine Learning methods for simulating particle response in the Zero Degree Calorimeter at the ALICE experiment, CERN
- Active Coverage for PAC Reinforcement Learning
- Max-Margin Token Selection in Attention Mechanism
- Autoencoders for Real-Time SUEP Detection
- TACOformer:Token-channel compounded Cross Attention for Multimodal Emotion Recognition
- Creating Valid Adversarial Examples of Malware
- NetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep Giants
- A Semi-Paired Approach For Label-to-Image Translation
- Lower Complexity Adaptation for Empirical Entropic Optimal Transport
- Penalty Gradient Normalization for Generative Adversarial Networks
- Scaling MLPs: A Tale of Inductive Bias
- Thoughts on Architecture
- The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Prediction
- Estimating Residential Solar Potential Using Aerial Data
- Efficient Model Selection for Predictive Pattern Mining Model by Safe Pattern Pruning
- FPGA Implementation of Convolutional Neural Network for Real-Time Handwriting Recognition
- Inferring Hierarchical Structure in Multi-Room Maze Environments
- Manifold Contrastive Learning with Variational Lie Group Operators
- Torsion Graph Neural Networks
- PathMLP: Smooth Path Towards High-order Homophily
- WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes
- Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images
- On the Convergence Rate of Gaussianization with Random Rotations
- Segmentation and Tracking of Vegetable Plants by Exploiting Vegetable Shape Feature for Precision Spray of Agricultural Robots
- Binary domain generalization for sparsifying binary neural networks
- DISCO-10M: A Large-Scale Music Dataset
- Exploring AI-enhanced Shared Control for an Assistive Robotic Arm
- Two derivations of Principal Component Analysis on datasets of distributions
- Knowledge-Infused Self Attention Transformers
All 156
- Cascade Subspace Clustering for Outlier Detection
- Retrieval of Boost Invariant Symbolic Observables via Feature Importance
- Adaptive Planning Search Algorithm for Analog Circuit Verification
- Efficient Online Processing with Deep Neural Networks
- Prediction under Latent Subgroup Shifts with High-Dimensional Observations
- Incorporating Graph Information in Transformer-based AMR Parsing
- 3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation
- Understanding quantum machine learning also requires rethinking generalization
- Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation
- Enhanced Dengue Outbreak Prediction in Tamilnadu using Meteorological and Entomological data
- DreamEditor: Text-Driven 3D Scene Editing with Neural Fields
- A Graph Neural Network Approach for Temporal Mesh Blending and Correspondence
- Dermoscopic Dark Corner Artifacts Removal: Friend or Foe?
- Minibatch training of neural network ensembles via trajectory sampling
- Trading-off price for data quality to achieve fair online allocation
- On tracking varying bounds when forecasting bounded time series
- A Weighted Autoencoder-Based Approach to Downlink NOMA Constellation Design
- Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation
- PP-GAN : Style Transfer from Korean Portraits to ID Photos Using Landmark Extractor with GAN
- Neural Algorithmic Reasoning Without Intermediate Supervision
- Explainable Lifelong Stream Learning Based on "Glocal" Pairwise Fusion
- Higher-order Motif-based Time Series Classification for Forced Oscillation Source Location in Power Grids
- Physics-informed neural networks modeling for systems with moving immersed boundaries: application to an unsteady flow past a plunging foil
- Co-creating a globally interpretable model with human input
- First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment
- Stress Testing BERT Anaphora Resolution Models for Reaction Extraction in Chemical Patents
- Physics-constrained Random Forests for Turbulence Model Uncertainty Estimation
- Lesion Detection on Leaves using Class Activation Maps
- Neural 360^circ Structured Light with Learned Metasurfaces
- Catching Image Retrieval Generalization
- Accurate melting point prediction through autonomous physics-informed learning
- TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support
- Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning
- Energy Optimization for HVAC Systems in Multi-VAV Open Offices: A Deep Reinforcement Learning Approach
- Unsupervised Deformable Image Registration for Respiratory Motion Compensation in Ultrasound Images
- Unsupervised Deformable Ultrasound Image Registration and Its Application for Vessel Segmentation
- Differentiable Display Photometric Stereo
- Automated Automotive Radar Calibration With Intelligent Vehicles
- Abstractive Text Summarization for Resumes With Cutting Edge NLP Transformers and LSTM
- Mutually Guided Few-shot Learning for Relational Triple Extraction
- Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems
- Deep Omni-supervised Learning for Rib Fracture Detection from Chest Radiology Images
- Exploring Qualitative Research Using LLMs
- Variance-Covariance Regularization Improves Representation Learning
- Robustness of Segment Anything Model (SAM) for Autonomous Driving in Adverse Weather Conditions
- Learning Scene Flow With Skeleton Guidance For 3D Action Recognition
- Correcting discount-factor mismatch in on-policy policy gradient methods
- On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis
- On The Relationship Between Continual Learning and Long-Tailed Recognition
- Variational Counterfactual Prediction under Runtime Domain Corruption
- Shape-Constraint Recurrent Flow for 6D Object Pose Estimation
- FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning
- Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity
- Fast Maximum k-Plex Algorithms Parameterized by Small Degeneracy Gaps
- Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models
- Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok