Papers
Sun 29 Jan 2023
96 papers
- Distilling Internet-Scale Vision-Language Models into Embodied AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
- AudioLDM: Text-to-Audio Generation with Latent Diffusion ModelsDiffusion models → Audio, speech and music
- Debiased Fine-Tuning for Vision-language Models by Prompt RegularizationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Don't Play Favorites: Minority Guidance for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Deep Learning model integrity checking mechanism using watermarking techniqueLLM safety and security → Watermarking generated content and models
- Physarum Inspired Bicycle Lane Network Design in a Congested Mega City
- Multi-video Moment Ranking with Multimodal Clue
- Confidence-Aware Calibration and Scoring Functions for Curriculum Learning
- Development of Machine learning algorithms to identify the Cobb angle in adolescents with idiopathic scoliosis based on lumbosacral joint efforts during gait (Case study)
- Zero-Shot Transfer of Haptics-Based Object Insertion Policies
- Unifying Molecular and Textual Representations via Multi-task Language Modelling
- Intrinsic Bayesian Optimisation on Complex Constrained Domain
- Sample Efficient Deep Reinforcement Learning via Local Planning
- Uncovering Adversarial Risks of Test-Time Adaptation
- Bounded (O(1)) Regret Recommendation Learning via Synthetic Controls Oracle
- A Mental Model Based Framework of Trust
- Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation
- Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation
- A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction
- Simplifying Subgraph Representation Learning for Scalable Link Prediction
- Imbalanced Mixed Linear Regression
- A Deep Reinforcement Learning Framework for Optimizing Congestion Control in Data Centers
- Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing
- Asymptotic Inference for Multi-Stage Stationary Treatment Policy with Variable Selection
- Unlocking Deterministic Robustness Certification on ImageNet
- Global Flood Prediction: a Multimodal Machine Learning Approach
- Supervised and Contrastive Self-Supervised In-Domain Representation Learning for Dense Prediction Problems in Remote Sensing
- Implicit Regularization for Group Sparsity
- On Approximating the Dynamic Response of Synchronous Generators via Operator Learning: A Step Towards Building Deep Operator-based Power Grid Simulators
- Concurrent Shuffle Differential Privacy Under Continual Observation
- Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive
- PhyCV: The First Physics-inspired Computer Vision Library
- G-Rank: Unsupervised Continuous Learn-to-Rank for Edge Devices in a P2P Network
- Sequential Estimation of Gaussian Process-based Deep State-Space Models
- Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification
- Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infilling
- Producing Usable Taxonomies Cheaply and Rapidly at Pinterest Using Discovered Dynamic μ-Topics
- 3D Object Detection in LiDAR Point Clouds using Graph Neural Networks
- LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detection
- Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline
- EMP-EVAL: A Framework for Measuring Empathy in Open Domain Dialogues
- BERT-based Authorship Attribution on the Romanian Dataset called ROST
- Time-Series Pattern Recognition in Smart Manufacturing Systems: A Literature Review and Ontology
- Graph Mixer Networks
- Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds
- StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes
- Large Language Models for Biomedical Knowledge Graph Construction: Information extraction from EMR notes
- Maximising Weather Forecasting Accuracy through the Utilisation of Graph Neural Networks and Dynamic GNNs
- Gesture Control of Micro-drone: A Lightweight-Net with Domain Randomization and Trajectory Generators
- Continual Learning for Predictive Maintenance: Overview and Challenges
- Kernelized Cumulants: Beyond Kernel Mean Embeddings
- Comparing Spoken Languages using Paninian System of Sounds and Finite State Machines
- The Influences of Color and Shape Features in Visual Contrastive Learning
- SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking
- Towards Verifying the Geometric Robustness of Large-scale Neural Networks
- Exploring Attention Map Reuse for Efficient Transformer Neural Networks
- Pipe-BD: Pipelined Parallel Blockwise Distillation
- Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning
- Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022
- Syrupy Mouthfeel and Hints of Chocolate -- Predicting Coffee Review Scores using Text Based Sentiment
- Deep Learning for Human Parsing: A Survey
- Contextual Causal Bayesian Optimisation
- Entropy-driven Fair and Effective Federated Learning
- Decision-Making Context Interaction Network for Click-Through Rate Prediction
- HeroNet: A Hybrid Retrieval-Generation Network for Conversational Bots
- Learning Analytics from Spoken Discussion Dialogs in Flipped Classroom
- DocILE 2023 Teaser: Document Information Localization and Extraction
- On Learning Necessary and Sufficient Causal Graphs
- Plugin estimators for selective classification with out-of-distribution detection
- On Heterogeneous Treatment Effects in Heterogeneous Causal Graphs
- Data-driven intelligent computational design for products: Method, techniques, and applications
- FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering
- Towards Inference Efficient Deep Ensemble Learning
- Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality
- Preserving Fairness in AI under Domain Shift
- Smooth Non-Stationary Bandits
- Fair Decision-making Under Uncertainty
- Graph Harmony: Denoising and Nuclear-Norm Wasserstein Adaptation for Enhanced Domain Transfer in Graph-Structured Data
- ADL-ID: Adversarial Disentanglement Learning for Wireless Device Fingerprinting Temporal Domain Adaptation
- SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits
- Exploiting High Performance Spiking Neural Networks with Efficient Spiking Patterns
- Semantics-enhanced Temporal Graph Networks for Content Popularity Prediction
- On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network
- Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation
- Emerging Synergies in Causality and Deep Generative Models: A Survey
- Long-Term Modeling of Financial Machine Learning for Active Portfolio Management
- Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Model
- Incremental Value and Interpretability of Radiomics Features of Both Lung and Epicardial Adipose Tissue for Detecting the Severity of COVID-19 Infection
- Towards Vision Transformer Unrolling Fixed-Point Algorithm: a Case Study on Image Restoration
- Time out of Mind: Generating Rate of Speech conditioned on emotion and speaker
- Team Resilience under Shock: An Empirical Analysis of GitHub Repositories during Early COVID-19 Pandemic
- Cross-Subject Deep Transfer Models for Evoked Potentials in Brain-Computer Interface
- Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
- Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
- Progressive Prompts: Continual Learning for Language Models
- Adapting Neural Link Predictors for Data-Efficient Complex Query Answering