Papers
Fri 7 Oct 2022
205 papers
- Efficient Diffusion Models for Vision: A SurveyDiffusion models → Diffusion foundations and sampling
- A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on TwitterLLM safety and security → Safety alignment, refusal and guardrails
- BAFFLE: Hiding Backdoors in Offline Reinforcement Learning DatasetsOffline RL and imitation learning from data → Offline RL algorithms
- ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question AnsweringLLM reasoning → Reasoning for agents, planning and code
- Retrieval Augmented Visual Question Answering with Outside KnowledgeRetrieval-augmented generation → Multimodal RAG
- Conservative Bayesian Model-Based Value Expansion for Offline Policy OptimizationOffline RL and imitation learning from data → Offline RL algorithms
- SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Traffic-Aware Autonomous Driving with Differentiable Traffic SimulationEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image ClassificationKnowledge distillation → Distillation for medical imaging
- GoalsEye: Learning High Speed Precision Table Tennis on a Physical RobotOffline RL and imitation learning from data → Imitation learning methods
- C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video RetrievalKnowledge distillation → Knowledge distillation for LLMs
- Automatic Chain of Thought Prompting in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
- IDa-Det: An Information Discrepancy-aware Distillation for 1-bit DetectorsKnowledge distillation → Detection and dense prediction distillation
- Mutual Learning of Single- and Multi-Channel End-to-End Neural DiarizationKnowledge distillation → Speech and audio distillation
- Measuring and Narrowing the Compositionality Gap in Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
- Distillation-Resistant Watermarking for Model Protection in NLPLLM safety and security → Watermarking generated content and models
- Achieving and Understanding Out-of-Distribution Generalization in Systematic Reasoning in Small-Scale TransformersLLM reasoning → Mathematical reasoning
- A Tutorial on Asymptotic Properties for Biostatisticians with Applications to COVID-19 Data
- De-risking geological carbon storage from high resolution time-lapse seismic to explainable leakage detection
- Artificial Life using a Book and Bookmarker
- Using Interventions to Improve Out-of-Distribution Generalization of Text-Matching Recommendation Systems
- CLEAR: Causal Explanations from Attention in Neural Recommenders
- SAICL: Student Modelling with Interaction-level Auxiliary Contrastive Tasks for Knowledge Tracing and Dropout Prediction
- ANFIS-based prediction of power generation for combined cycle power plant
- Who Wrote this? How Smart Replies Impact Language and Agency in the Workplace
- Automatic Discovery of Composite SPMD Partitioning Strategies in PartIR
- Indoor Localization with Robust Global Channel Charting: A Time-Distance-Based Approach
- An Energy-Efficient Spiking Neural Network for Finger Velocity Decoding for Implantable Brain-Machine Interface
- Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules
- Can Artificial Intelligence Reconstruct Ancient Mosaics?
- iMedBot: A Web-based Intelligent Agent for Healthcare Related Prediction and Deep Learning
- Simulating single-photon detector array sensors for depth imaging
- Exploration Policies for On-the-Fly Controller Synthesis: A Reinforcement Learning Approach
- Constructing Prediction Intervals with Neural Networks: An Empirical Evaluation of Bootstrapping and Conformal Inference Methods
- mPSAuth: Privacy-Preserving and Scalable Authentication for Mobile Web Applications
- Over-the-Air Split Machine Learning in Wireless MIMO Networks
- Time Minimization in Hierarchical Federated Learning
- Utilizing Explainable AI for improving the Performance of Neural Networks
- CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure
- EmbryosFormer: Deformable Transformer and Collaborative Encoding-Decoding for Embryos Stage Development Classification
- Information Topology
- Differentially Private Deep Learning with ModelMix
- Mutual Theory of Mind for Human-AI Communication
- Breaking BERT: Evaluating and Optimizing Sparsified Attention
- Learning to embed semantic similarity for joint image-text retrieval
- Self-Supervised Deep Equilibrium Models for Inverse Problems with Theoretical Guarantees
- Early Detection of Bark Beetle Attack Using Remote Sensing and Machine Learning: A Review
- Sampling-Based Decomposition Algorithms for Arbitrary Tensor Networks
- An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation
- See, Plan, Predict: Language-guided Cognitive Planning with Video Prediction
- Is margin all you need? An extensive empirical study of active learning on tabular data
- Large Language Models can Implement Policy Iteration
- The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
- Scene-level Tracking and Reconstruction without Object Priors
- Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative
- Supervised and Unsupervised Learning of Audio Representations for Music Understanding
- Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts
- Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation
- Learning a Visually Grounded Memory Assistant
- Evaluating the Performance of StyleGAN2-ADA on Medical Images
- LOCL: Learning Object-Attribute Composition using Localization
- MRI-based classification of IDH mutation and 1p/19q codeletion status of gliomas using a 2.5D hybrid multi-task convolutional neural network
- In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?
- xDBTagger: Explainable Natural Language Interface to Databases Using Keyword Mappings and Schema Graph
- FedPC: Federated Learning for Language Generation with Personal and Context Preference Embeddings
- Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
- Trustworthiness of Laser-Induced Breakdown Spectroscopy Predictions via Simulation-based Synthetic Data Augmentation and Multitask Learning
- A deep learning approach to solve forward differential problems on graphs
- ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction
- Demystifying Map Space Exploration for NPUs
- SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training
- Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning
- Dynamic Latent Separation for Deep Learning
- Understanding Practices, Challenges, and Opportunities for User-Engaged Algorithm Auditing in Industry Practice
- Class-wise and reduced calibration methods
- LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models
- Multi-Frequency-Aware Patch Adversarial Learning for Neural Point Cloud Rendering
- Compressing Video Calls using Synthetic Talking Heads
- Few-Shot Anaphora Resolution in Scientific Protocols via Mixtures of In-Context Experts
- GENHOP: An Image Generation Method Based on Successive Subspace Learning
- Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation
- Quantitative Metrics for Evaluating Explanations of Video DeepFake Detectors
- Novice Type Error Diagnosis with Natural Language Models
- IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty
- Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts
- Reinforcement Learning Approach for Multi-Agent Flexible Scheduling Problems
- To tree or not to tree? Assessing the impact of smoothing the decision boundaries
- A Closer Look at Hardware-Friendly Weight Quantization
- CommsVAE: Learning the brain's macroscale communication dynamics using coupled sequential VAEs
- Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos
- Understanding the Covariance Structure of Convolutional Filters
- Longtonotes: OntoNotes with Longer Coreference Chains
- How to Enable Uncertainty Estimation in Proximal Policy Optimization
- Learnware: Small Models Do Big
- Leveraging Structure from Motion to Localize Inaccessible Bus Stops
- Artificial Intelligence and Natural Language Processing and Understanding in Space: A Methodological Framework and Four ESA Case Studies
- GraspCaps: A Capsule Network Approach for Familiar 6DoF Object Grasping
- Pose Guided Human Image Synthesis with Partially Decoupled GAN
- The (1+(λ,λ)) Global SEMO Algorithm
- 1st ICLR International Workshop on Privacy, Accountability, Interpretability, Robustness, Reasoning on Structured Data (PAIR^2Struct)
All 205
- Pronunciation Modeling of Foreign Words for Mandarin ASR by Considering the Effect of Language Transfer
- BlanketSet -- A clinical real-world in-bed action recognition and qualitative semi-synchronised MoCap dataset
- Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps
- Label Propagation with Weak Supervision
- Specialized Re-Ranking: A Novel Retrieval-Verification Framework for Cloth Changing Person Re-Identification
- Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery
- Machine Learning Meets The Herbrand Universe
- Understanding Transformer Memorization Recall Through Idioms
- An Investigation into Whitening Loss for Self-supervised Learning
- Learning Social Navigation from Demonstrations with Conditional Neural Processes
- Synthetic Voice Detection and Audio Splicing Detection using SE-Res2Net-Conformer Architecture
- Cloud-based Automatic Speech Recognition Systems for Southeast Asian Languages
- Are Representations Built from the Ground Up? An Empirical Examination of Local Composition in Language Models
- AI-Driven Road Maintenance Inspection v2: Reducing Data Dependency & Quantifying Road Damage
- How Large Language Models are Transforming Machine-Paraphrased Plagiarism
- Automated segmentation and morphological characterization of placental histology images based on a single labeled image
- Empowering Graph Representation Learning with Test-Time Graph Transformation
- A deep learning approach for detection and localization of leaf anomalies
- In-situ Model Downloading to Realize Versatile Edge AI in 6G Mobile Networks
- Treewidth-aware Reductions of Normal ASP to SAT -- Is Normal ASP Harder than SAT after All?
- Instance Segmentation of Dense and Overlapping Objects via Layering
- Time-Space Transformers for Video Panoptic Segmentation
- A2: Efficient Automated Attacker for Boosting Adversarial Training
- Do We Need Explainable AI in Companies? Investigation of Challenges, Expectations, and Chances from Employees' Perspective
- An Empirical Study on How the Developers Discussed about Pandas Topics
- Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes
- Learning to Learn and Sample BRDFs
- What Do End-Users Really Want? Investigation of Human-Centered XAI for Mobile Health Apps
- Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components
- Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement
- When one Logic is Not Enough: Integrating First-order Annotations in OWL Ontologies
- PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation
- Multi-objective and multi-fidelity Bayesian optimization of laser-plasma acceleration
- CLAD: A realistic Continual Learning benchmark for Autonomous Driving
- Neighbor Regularized Bayesian Optimization for Hyperparameter Optimization
- Hate Speech and Offensive Language Detection in Bengali
- Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
- Algorithmic Trading Using Continuous Action Space Deep Reinforcement Learning
- Latent Neural ODEs with Sparse Bayesian Multiple Shooting
- FastCLIPstyler: Optimisation-free Text-based Image Style Transfer Using Style Representations
- Flexible Alignment Super-Resolution Network for Multi-Contrast MRI
- Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loop
- DABERT: Dual Attention Enhanced BERT for Semantic Matching
- Key Information Extraction in Purchase Documents using Deep Learning and Rule-based Corrections
- Depersonalized Federated Learning: Tackling Statistical Heterogeneity by Alternating Stochastic Gradient Descent
- PCKRF: Point Cloud Completion and Keypoint Refinement With Fusion Data for 6D Pose Estimation
- Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking
- IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels
- PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Search
- Monitoring MBE substrate deoxidation via RHEED image-sequence analysis by deep learning
- Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEs
- Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality
- Generating Quizzes to Support Training on Quality Management and Assurance in Space Science and Engineering
- Certified machine learning: Rigorous a posteriori error bounds for PDE defined PINNs
- SpaceQA: Answering Questions about the Design of Space Missions and Space Craft Concepts
- Event Extraction: A Survey
- A Simple Plugin for Transforming Images to Arbitrary Scales
- Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding
- PARAGEN : A Parallel Generation Toolkit
- Quantifying Political Bias in News Articles
- TAN Without a Burn: Scaling Laws of DP-SGD
- Research on Self-adaptive Online Vehicle Velocity Prediction Strategy Considering Traffic Information Fusion
- Computational imaging with the human brain
- Mars Rover Localization Based on A2G Obstacle Distribution Pattern Matching
- Latent Matrices for Tensor Network Decomposition and to Tensor Completion
- Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity Recognition
- Zero-shot stance detection based on cross-domain feature enhancement by contrastive learning
- Geomagnetic Survey Interpolation with the Machine Learning Approach
- UU-Tax at SemEval-2022 Task 3: Improving the generalizability of language models for taxonomy classification through data augmentation
- Pre-trained Adversarial Perturbations
- GNM: A General Navigation Model to Drive Any Robot
- Multiple Object Tracking from appearance by hierarchically clustering tracklets
- Adversarial network training using higher-order moments in a modified Wasserstein distance
- The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphs
- The Ethical Risks of Analyzing Crisis Events on Social Media with Machine Learning
- Game-Theoretic Understanding of Misclassification
- Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
- Dual Clustering Co-teaching with Consistent Sample Mining for Unsupervised Person Re-Identification
- A Unified Framework for Multi-intent Spoken Language Understanding with prompting
- A Keypoint Based Enhancement Method for Audio Driven Free View Talking Head Synthesis
- Explainable AI based Glaucoma Detection using Transfer Learning and LIME
- Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling
- Calibrating Factual Knowledge in Pretrained Language Models
- Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks
- AutoML for Climate Change: A Call to Action
- Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation
- Scaling Forward Gradient With Local Losses
- Generative Augmented Flow Networks
- Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding
- Data-driven Approach to Differentiating between Depression and Dementia from Noisy Speech and Language Data
- GOLLIC: Learning Global Context beyond Patches for Lossless High-Resolution Image Compression
- A Learning-based Framework for Topology-Preserving Segmentation using Quasiconformal Mappings
- Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems
- GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow
- Understanding Edge-of-Stability Training Dynamics with a Minimalist Example
- Scalable Self-Supervised Representation Learning from Spatiotemporal Motion Trajectories for Multimodal Computer Vision
- Design Amortization for Bayesian Optimal Experimental Design
- Set2Box: Similarity Preserving Representation Learning of Sets
- Rethinking Normalization Methods in Federated Learning
- TCNL: Transparent and Controllable Network Learning Via Embedding Human-Guided Concepts
- A Unified Encoder-Decoder Framework with Entity Memory
- TRADE: Object Tracking with 3D Trajectory and Ground Depth Estimates for UAVs
- Multi-agent Deep Covering Skill Discovery
- Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks
- Unsupervised Neural Stylistic Text Generation using Transfer learning and Adapters