Papers
Mon 17 Oct 2022
235 papers
- UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single ImageDiffusion models → Image generation, text-to-image and editing
- Token Merging: Your ViT But FasterEfficient LLM inference and serving → Token pruning and merging for ViTs
- Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated LearningLLM safety and security → Federated unlearning and poisoning
- Imagic: Text-Based Real Image Editing with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Vision-Language Pre-training: Basics, Recent Advances, and Future TrendsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve ThemLLM reasoning → Prompting and chain-of-thought reasoning
- Boosting Offline Reinforcement Learning via Data RebalancingOffline RL and imitation learning from data → Offline RL algorithms
- Model Predictive Control via On-Policy Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Symbol Guided Hindsight Priors for Reward Learning from Human PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Verifiable and Provably Secure Machine UnlearningLLM safety and security → Machine unlearning
- Distilling Object Detectors With Global KnowledgeKnowledge distillation → Detection and dense prediction distillation
- Heterogeneous Feature Distillation Network for SAR Image Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
- A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks InformationLLM safety and security → Membership inference attacks
- Meta-Learning via Classifier(-free) Diffusion GuidanceDiffusion models → Diffusion foundations and sampling
- DiffuSeq: Sequence to Sequence Text Generation with Diffusion ModelsDiffusion models → Discrete and text diffusion
- Forget Unlearning: Towards True Data-Deletion in Machine LearningLLM safety and security → Machine unlearning
- Inferring Versatile Behavior from Demonstrations by Matching Geometric DescriptorsOffline RL and imitation learning from data → Robot manipulation imitation learning
- Fine-tuned Sentiment Analysis of COVID-19 Vaccine-Related Social Media Data: Comparative Study
- Routine Usage of AI-based Chest X-ray Reading Support in a Multi-site Medical Supply Center
- Review of the state of the art in autonomous artificial intelligence
- Overlap-guided Gaussian Mixture Models for Point Cloud Registration
- When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and A New Benchmark
- Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation
- FIMP: Foundation Model-Informed Message Passing for Graph Neural Networks
- Leveraging Non-dialogue Summaries for Dialogue Summarization
- Multi-granularity Argument Mining in Legal Texts
- Adversarial and Safely Scaled Question Generation
- Anisotropic Multi-Scale Graph Convolutional Network for Dense Shape Correspondence
- Understanding CNN Fragility When Learning With Imbalanced Data
- Morig: Motion-aware rigging of character meshes from point clouds
- Extensible Proxy for Efficient NAS
- Track Targets by Dense Spatio-Temporal Position Encoding
- Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning
- Early Diagnosis of Retinal Blood Vessel Damage via Deep Learning-Powered Collective Intelligence Models
- Deformably-Scaled Transposed Convolution
- A tradeoff between universality of equivariant models and learnability of symmetries
- Real-Time Driver Monitoring Systems through Modality and View Analysis
- Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraints
- CAN-BERT do it? Controller Area Network Intrusion Detection System based on BERT Language Model
- Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy
- Modelling Emotion Dynamics in Song Lyrics with State Space Models
- Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization
- A Pilot Study on Teacher-Facing Real-Time Classroom Game Dashboards
- Deepfake Text Detection: Limitations and Opportunities
- Differentiable Physics Simulation of Dynamics-Augmented Neural Objects
- Sufficient Exploration for Convex Q-learning
- Towards Generating Adversarial Examples on Mixed-type Data
- Measures of Information Reflect Memorization Patterns
- A Transfer Learning Based Approach for Classification of COVID-19 and Pneumonia in CT Scan Imaging
- Probabilistic Forecasting Methods for System-Level Electricity Load Forecasting
- Affective Idiosyncratic Responses to Music
- Review learning: Real world validation of privacy preserving continual learning across medical institutions
- Potrika: Raw and Balanced Newspaper Datasets in the Bangla Language with Eight Topics and Five Attributes
- Adaptive Oracle-Efficient Online Learning
- Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems
- Learning Diversified Feature Representations for Facial Expression Recognition in the Wild
- Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation
- 6th Place Solution to Google Universal Image Embedding
- On Accelerated Perceptrons and Beyond
- Bridging the Gap between Artificial Intelligence and Artificial General Intelligence: A Ten Commandment Framework for Human-Like Intelligence
- Probabilistic Categorical Adversarial Attack & Adversarial Training
- A Mixing Time Lower Bound for a Simplified Version of BART
- CrossRE: A Cross-Domain Dataset for Relation Extraction
- Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection
- Deep Bidirectional Language-Knowledge Graph Pretraining
- Robust Imitation of a Few Demonstrations with a Backwards Model
- TorchDIVA: An Extensible Computational Model of Speech Production built on an Open-Source Machine Learning Library
- Mitigating Covertly Unsafe Text within Natural Language Systems
- Non-Contrastive Learning Meets Language-Image Pre-Training
- What Makes Convolutional Models Great on Long Sequence Modeling?
- Neural Contact Fields: Tracking Extrinsic Contact with Tactile Sensing
- Unsupervised Optimal Power Flow Using Graph Neural Networks
- CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection
- Predicting Dynamic Stability from Static Features in Power Grid Models using Machine Learning
- Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers
- On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning
- A Unified Algorithm for Stochastic Path Problems
- Provable Phase Retrieval with Mirror Descent
- Contact2Grasp: 3D Grasp Synthesis via Hand-Object Contact Constraint
- ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization
- Improving Contrastive Learning on Visually Homogeneous Mars Rover Images
- Confound-leakage: Confound Removal in Machine Learning Leads to Leakage
- A Model-Consistent Data-Driven Computational Strategy for PDE Joint Inversion Problems
- Self-Supervised Learning Through Efference Copies
- A Saccaded Visual Transformer for General Object Spotting
- Conditional Neural Processes for Molecules
- ArtFacePoints: High-resolution Facial Landmark Detection in Paintings and Prints
- Pixel-Aligned Non-parametric Hand Mesh Reconstruction
- On the Impact of Temporal Concept Drift on Model Explanations
- Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class
- Sub-8-bit quantization for on-device speech recognition: a regularization-free approach
- Implicit models, latent compression, intrinsic biases, and cheap lunches in community detection
- Packed-Ensembles for Efficient Uncertainty Estimation
- Zero-Shot Ranking Socio-Political Texts with Transformer Language Models to Reduce Close Reading Time
- Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization
- Data-driven Modeling of Mach-Zehnder Interferometer-based Optical Matrix Multipliers
- Spatially scalable recursive estimation of Gaussian process terrain maps using local basis functions
- How do we get there? Evaluating transformer neural networks as cognitive models for English past tense inflection
- KPI-EDGAR: A Novel Dataset and Accompanying Metric for Relation Extraction from Financial Documents
- Table-To-Text generation and pre-training with TabT5
All 235
- Statistical, Robustness, and Computational Guarantees for Sliced Wasserstein Distances
- Face Pasting Attack
- Prompting GPT-3 To Be Reliable
- Pruning-based Topology Refinement of 3D Mesh using a 2D Alpha Mask
- PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks
- Data Subsampling for Bayesian Neural Networks
- An Open-source Benchmark of Deep Learning Models for Audio-visual Apparent and Self-reported Personality Recognition
- Gated Recurrent Unit for Video Denoising
- Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimization
- Pseudo-OOD training for robust language models
- Sparse Kronecker Product Decomposition: A General Framework of Signal Region Detection in Image Regression
- ISEE.U: Distributed online active target localization with unpredictable targets
- Advanced Characterization-Informed Framework and Quantitative Insight to Irradiated Annular U-10Zr Metallic Fuels
- Cutting-Splicing data augmentation: A novel technology for medical image segmentation
- Modeling the Lighting in Scenes as Style for Auto White-Balance Correction
- Multi-Agent Automated Machine Learning
- Nish: A Novel Negative Stimulated Hybrid Activation Function
- A Solver-Free Framework for Scalable Learning in Neural ILP Architectures
- Asymptotic-Preserving Neural Networks for hyperbolic systems with diffusive scaling
- Machine Learning Technique Predicting Video Streaming Views to Reduce Cost of Cloud Services
- Reversing Image Signal Processors by Reverse Style Transferring
- Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
- Forward-Backward Latent State Inference for Hidden Continuous-Time semi-Markov Chains
- SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition
- Natural Scene Image Annotation Using Local Semantic Concepts and Spatial Bag of Visual Words
- Attribute Inference Attacks in Online Multiplayer Video Games: a Case Study on Dota2
- Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak Labels
- Defects of Convolutional Decoder Networks in Frequency Representation
- Explaining Image Classification with Visual Debates
- A Symbolic Representation of Human Posture for Interpretable Learning and Reasoning
- AIM 2022 Challenge on Instagram Filter Removal: Methods and Results
- Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognition
- Improving Object-centric Learning with Query Optimization
- Flipped Classroom: Effective Teaching for Time Series Forecasting
- Weakly Supervised Face Naming with Symmetry-Enhanced Contrastive Loss
- Predicting Dense and Context-aware Cost Maps for Semantic Robot Navigation
- Approximating Continuous Convolutions for Deep Network Compression
- S3-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint
- DE-CROP: Data-efficient Certified Robustness for Pretrained Classifiers
- Event-based Stereo Depth Estimation from Ego-motion using Ray Density Fusion
- Joint Multilingual Knowledge Graph Completion and Alignment
- A Treatise On FST Lattice Based MMI Training
- Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialog
- Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery
- Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval
- A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities
- Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations
- Contrastive Language-Image Pre-Training with Knowledge Graphs
- Learning Decentralized Linear Quadratic Regulators with √T Regret
- Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving
- HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks
- Robust Planning for Human-Robot Joint Tasks with Explicit Reasoning on Human Mental State
- Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
- Bridging the Gap between Local Semantic Concepts and Bag of Visual Words for Natural Scene Image Retrieval
- Probabilities of Causation: Role of Observational Data
- Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
- PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning
- Industry-Scale Orchestrated Federated Learning for Drug Discovery
- Differential Evolution based Dual Adversarial Camouflage: Fooling Human Eyes and Object Detectors
- Cerebrovascular Segmentation via Vessel Oriented Filtering Network
- Deep Learning Aided Laplace Based Bayesian Inference for Epidemiological Systems
- Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks
- You Only Live Once: Single-Life Reinforcement Learning
- A Unitary Transform Based Generalized Approximate Message Passing
- Automatic Analysis of Human Body Representations in Western Art
- Social Biases in Automatic Evaluation Metrics for NLG
- On the convergence of policy gradient methods to Nash equilibria in general stochastic games
- TIVE: A Toolbox for Identifying Video Instance Segmentation Errors
- PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks
- tegdet: An extensible Python Library for Anomaly Detection using Time-Evolving Graphs
- MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification
- Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning
- Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels
- Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
- MoSE: Modality Split and Ensemble for Multimodal Knowledge Graph Completion
- Correlation between Alignment-Uniformity and Performance of Dense Contrastive Representations
- PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance
- Test-Time Training for Graph Neural Networks
- ITSRN++: Stronger and Better Implicit Transformer Network for Continuous Screen Content Image Super-Resolution
- CS-MLGCN : Multiplex Graph Convolutional Networks for Community Search in Multiplex Networks
- Effective and Efficient Query-aware Snippet Extraction for Web Search
- Towards Robust k-Nearest-Neighbor Machine Translation
- HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold
- A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation Models
- Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference
- Sequential Topic Selection Model with Latent Variable for Topic-Grounded Dialogue
- Cluster Explanation via Polyhedral Descriptions
- Break The Spell Of Total Correlation In betaTCVAE
- Rethinking Trajectory Prediction via "Team Game"
- Unifying Graph Contrastive Learning with Flexible Contextual Scopes
- EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle
- Exposing Influence Campaigns in the Age of LLMs: A Behavioral-Based AI Approach to Detecting State-Sponsored Trolls
- Cross-layer Attention Network for Fine-grained Visual Categorization
- Stochastic Differentially Private and Fair Learning
- Towards Summary Candidates Fusion
- Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
- Signal Processing for Implicit Neural Representations
- N-pad : Neighboring Pixel-based Industrial Anomaly Detection
- ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains
- Protein Sequence and Structure Co-Design with Equivariant Translation
- Towards Relation Extraction From Speech
- Systematic Evaluation of Predictive Fairness
- MCP: Self-supervised Pre-training for Personalized Chatbots with Multi-level Contrastive Sampling
- Use of a smartphone camera to determine the focal length of a thin lens by finding the transverse magnification of the virtual image of an object
- Keep Me Updated! Memory Management in Long-term Conversations
- A Transformer-based Generative Model for De Novo Molecular Design
- Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving
- Row-wise LiDAR Lane Detection Network with Lane Correlation Refinement
- Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task
- Risk-Sensitive Markov Decision Processes with Long-Run CVaR Criterion
- PCGen: Point Cloud Generator for LiDAR Simulation
- Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows
- 2nd Place Solution to Google Universal Image Embedding
- How many radiographs are needed to re-train a deep learning system for object detection?
- Forecasting Human Trajectory from Scene History
- Evaluation of Pedestrian Safety in a High-Fidelity Simulation Environment Framework
- RARR: Researching and Revising What Language Models Say, Using Language Models
- RbX: Region-based explanations of prediction models
- ReAFFPN: Rotation-equivariant Attention Feature Fusion Pyramid Networks for Aerial Object Detection
- Selective Query-guided Debiasing for Video Corpus Moment Retrieval
- Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation
- Continuous Pseudo-Labeling from the Start
- Handling Label Uncertainty for Camera Incremental Person Re-Identification
- A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling
- Teacher Forcing Recovers Reward Functions for Text Generation
- ODG-Q: Robust Quantization via Online Domain Generalization
- ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction
- A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems
- GeoThermalCloud: Machine Learning for Geothermal Resource Exploration
- Regularized Data Programming with Automated Bayesian Prior Selection
- Scale-Agnostic Super-Resolution in MRI using Feature-Based Coordinate Networks
- SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation
- Scaling up Trustless DNN Inference with Zero-Knowledge Proofs
- Decision-Making Among Bounded Rational Agents
- Temporal-Spatial dependencies ENhanced deep learning model (TSEN) for household leverage series forecasting