Papers
Tue 31 Jan 2023
217 papers
- Revisiting Bellman Errors for Offline Model SelectionOffline RL and imitation learning from data → Offline RL algorithms
- Learning Risk-Aware Costmaps via Inverse Reinforcement Learning for Off-Road NavigationOffline RL and imitation learning from data → Imitation and offline RL for driving
- In-Context Retrieval-Augmented Language ModelsRetrieval-augmented generation → Generation and context integration
- Debiasing Vision-Language Models via Biased PromptsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
- Salient Conditional Diffusion for Defending Against Backdoor AttacksDiffusion models → Robustness, privacy and adversarial aspects +1
- Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
- DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion ModelsDiffusion models → Flow matching, time series and science
- Learning Data Representations with Joint Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Anti-Exploration by Random Network DistillationOffline RL and imitation learning from data → Offline RL algorithms
- Zero3D: Semantic-Driven Multi-Category 3D Shape GenerationDiffusion models → 3D, point cloud and scene generation
- Skill Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
- AMD: Adaptive Masked Distillation for Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Learning Vision-based Robotic Manipulation Tasks Sequentially in Offline Reinforcement Learning SettingsOffline RL and imitation learning from data → Real-world robot offline RL
- Faithful Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
- Optimizing DDPM Sampling with Shortcut Fine-TuningDiffusion models → Diffusion foundations and sampling
- Image Guidance for Robot-Assisted Ankle Fracture Repair
- KG-Hub -- Building and Exchanging Biological Knowledge Graphs
- Online estimation methods for irregular autoregressive models
- ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency
- RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion
- Redesigning Electronic Health Record Systems to Support Developing Countries
- A Comprehensive Survey of Continual Learning: Theory, Method and Application
- Generating High Fidelity Synthetic Data via Coreset selection and Entropic Regularization
- Learning Topology-Preserving Data Representations
- Universal Topological Regularity of Syntactic Structures
- Design and Implementation of A Soccer Ball Detection System with Multiple Cameras
- Machine Translation Impact in E-commerce Multilingual Search
- Real Estate Property Valuation using Self-Supervised Vision Transformers
- Learning Universal Policies via Text-Guided Video Generation
- OrthoReg: Improving Graph-regularized MLPs via Orthogonality Regularization
- Distributed sequential federated learning
- Truthful Incentive Mechanism for Federated Learning with Crowdsourced Data Labeling
- Fourier series weight in quantum machine learning
- Online Learning in Dynamically Changing Environments
- Towards Detecting Harmful Agendas in News Articles
- Physics-informed Reduced-Order Learning from the First Principles for Simulation of Quantum Nanostructures
- Learning noisy-OR Bayesian Networks with Max-Product Belief Propagation
- Does Deep Active Learning Work in the Wild?
- The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models
- Large Language Models Can Be Easily Distracted by Irrelevant Context
- Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets
- Adaptive sparseness for correntropy-based robust regression via automatic relevance determination
- GANravel: User-Driven Direction Disentanglement in Generative Adversarial Networks
- Personalized Privacy Auditing and Optimization at Test Time
- Evaluating Temporal Observation-Based Causal Discovery Techniques Applied to Road Driver Behaviour
- Dynamic Flows on Curved Space Generated by Labeled Data
- NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese Networks
- Graph Anomaly Detection in Time Series: A Survey
- Transformers Meet Directed Graphs
- Probabilistic Point Cloud Modeling via Self-Organizing Gaussian Mixture Models
- Neural Control of Parametric Solutions for High-dimensional Evolution PDEs
- Differentially-Private Hierarchical Clustering with Provable Approximation Guarantees
- Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor
- Neuromechanical Autoencoders: Learning to Couple Elastic and Neural Network Nonlinearity
- 3D-Spatiotemporal Forecasting the Expansion of Supernova Shells Using Deep Learning toward High-Resolution Galaxy Simulations
- On the Within-Group Fairness of Screening Classifiers
- Low Complexity Approaches for End-to-End Latency Prediction
- The Power of External Memory in Increasing Predictive Model Capacity
- Reverse engineering adversarial attacks with fingerprints from adversarial examples
- PADL: Language-Directed Physics-Based Character Control
- Mathematical Capabilities of ChatGPT
- From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds
- Learning in POMDPs is Sample-Efficient with Hindsight Observability
- Simplex Random Features
- General Gaussian Noise Mechanisms and Their Optimality for Unbiased Mean Estimation
- Benchmarking Large Language Models for News Summarization
- Interpreting Robustness Proofs of Deep Neural Networks
- Do Multi-Document Summarization Models Synthesize?
- Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
- A Mathematical Model for Curriculum Learning for Parities
- Grounding Language Models to Images for Multimodal Inputs and Outputs
- Complete Neural Networks for Complete Euclidean Graphs
- Patch Gradient Descent: Training Neural Networks on Very Large Images
- Execution-based Code Generation using Deep Reinforcement Learning
- Learning Roles with Emergent Social Value Orientations
- A Prototype System for High Frame Rate Ultrasound Imaging based Prosthetic Arm Control
- Identifying the Hazard Boundary of ML-enabled Autonomous Systems Using Cooperative Co-Evolutionary Search
- Fairness-aware Vision Transformer via Debiased Self-Attention
- Partitioning Distributed Compute Jobs with Reinforcement Learning and Graph Neural Networks
- Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback
- Deep learning-based lung segmentation and automatic regional template in chest X-ray images for pediatric tuberculosis
- FLAME: A small language model for spreadsheet formulas
- Differentially Private Distributed Bayesian Linear Regression with MCMC
- The Touch'e23-ValueEval Dataset for Identifying Human Values behind Arguments
- Multicalibration as Boosting for Regression
- Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification
- Learning, Fast and Slow: A Goal-Directed Memory-Based Approach for Dynamic Environments
- Toward Efficient Gradient-Based Value Estimation
- PAC learning and stabilizing Hedonic Games: towards a unifying approach
- Retrosynthetic Planning with Dual Value Networks
- Dynamic Scheduled Sampling with Imitation Loss for Neural Text Generation
- Multi-Fidelity Covariance Estimation in the Log-Euclidean Geometry
- Archetypal Analysis++: Rethinking the Initialization Strategy
- Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion
- UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
- Self-Consistent Velocity Matching of Probability Flows
- Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design
- A Bayesian Generative Adversarial Network (GAN) to Generate Synthetic Time-Series Data, Application in Combined Sewer Flow Prediction
All 217
- Preserving local densities in low-dimensional embeddings
- A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser
- Convolutional autoencoder for the spatiotemporal latent representation of turbulence
- Towards fully covariant machine learning
- Zero-shot cross-lingual transfer language selection using linguistic similarity
- Physics-constrained 3D Convolutional Neural Networks for Electrodynamics
- Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality
- On the Initialisation of Wide Low-Rank Feedforward Neural Networks
- Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
- Are Defenses for Graph Neural Networks Robust?
- Time Series Forecasting via Semi-Asymmetric Convolutional Architecture with Global Atrous Sliding Window
- The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
- Friend-training: Learning from Models of Different but Related Tasks
- Improved distinct bone segmentation in upper-body CT through multi-resolution networks
- Enhancing Hyper-To-Real Space Projections Through Euclidean Norm Meta-Heuristic Optimization
- What Makes Good Examples for Visual In-Context Learning?
- Towards interpretable quantum machine learning via single-photon quantum walks
- Automated Sentiment and Hate Speech Analysis of Facebook Data by Employing Multilingual Transformer Models
- Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensors
- Spyker: High-performance Library for Spiking Deep Neural Networks
- A Survey and Benchmark of Automatic Surface Reconstruction from Point Clouds
- Exploring QSAR Models for Activity-Cliff Prediction
- An Efficient Solution to s-Rectangular Robust Markov Decision Processes
- Tricking AI chips into Simulating the Human Brain: A Detailed Performance Analysis
- Transport with Support: Data-Conditional Diffusion Bridges
- Active Learning-based Domain Adaptive Localized Polynomial Chaos Expansion
- TopoBERT: Plug and Play Toponym Recognition Module Harnessing Fine-tuned BERT
- Scheduling Inference Workloads on Distributed Edge Clusters with Reinforcement Learning
- Priors are Powerful: Improving a Transformer for Multi-camera 3D Detection with 2D Priors
- Policy Gradient for Rectangular Robust Markov Decision Processes
- Straight-Through meets Sparse Recovery: the Support Exploration Algorithm
- Sport Task: Fine Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2022
- BALANCE: Bayesian Linear Attribution for Root Cause Localization
- NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning
- Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity
- Lidar Upsampling with Sliced Wasserstein Distance
- Purposeful and Operation-based Cognitive System for AGI
- NoiseTransfer: Image Noise Generation with Contrastive Embeddings
- Review of methods for automatic cerebral microbleeds detection
- Holistic Graph-based Motion Prediction
- Low Complexity Adaptive Machine Learning Approaches for End-to-End Latency Prediction
- Population-wise Labeling of Sulcal Graphs using Multi-graph Matching
- Domain-Generalizable Multiple-Domain Clustering
- Kernel Stein Discrepancy thinning: a theoretical perspective of pathologies and a practical fix with regularization
- Real-Time Outlier Detection with Dynamic Process Limits
- Quantum contextual bandits and recommender systems for quantum data
- Recurrences reveal shared causal drivers of complex time series
- Fourier Sensitivity and Regularization of Computer Vision Models
- 3D Former: Monocular Scene Reconstruction with 3D SDF Transformers
- An Analysis of Classification Approaches for Hit Song Prediction using Engineered Metadata Features with Lyrics and Audio Features
- Supporting Safety Analysis of Image-processing DNNs through Clustering-based Approaches
- Transfer Learning and Class Decomposition for Detecting the Cognitive Decline of Alzheimer Disease
- Auxiliary Learning as an Asymmetric Bargaining Game
- Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks
- Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks
- Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond
- Archive TimeLine Summarization (ATLS): Conceptual Framework for Timeline Generation over Historical Document Collections
- An investigation of challenges encountered when specifying training data and runtime monitors for safety critical ML applications
- CRC-RL: A Novel Visual Feature Representation Architecture for Unsupervised Reinforcement Learning
- GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning
- Training with Mixed-Precision Floating-Point Assignments
- Towards Learned Emulation of Interannual Water Isotopologue Variations in General Circulation Models
- Learning Generalized Hybrid Proximity Representation for Image Recognition
- ZhichunRoad at Amazon KDD Cup 2022: MultiTask Pre-Training for E-Commerce Product Search
- Compliance Costs of AI Technology Commercialization: A Field Deployment Perspective
- Benchmarking Model Predictive Control Algorithms in Building Optimization Testing Framework (BOPTEST)
- Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
- A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics
- Rethinking Soft Label in Label Distribution Learning Perspective
- Retiring DeltaDP: New Distribution-Level Metrics for Demographic Parity
- Scaling laws for single-agent reinforcement learning
- CMLCompiler: A Unified Compiler for Classical Machine Learning
- GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis
- Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain Adaptation
- Anomaly Segmentation for High-Resolution Remote Sensing Images Based on Pixel Descriptors
- Superhuman Fairness
- Recurrent Structure Attention Guidance for Depth Super-Resolution
- BRAIxDet: Learning to Detect Malignant Breast Lesion with Incomplete Annotations
- Structure Flow-Guided Network for Real Depth Super-Resolution
- LogAI: A Library for Log Analytics and Intelligence
- Fine Robotic Manipulation without Force/Torque Sensor
- Few-Shot Object Detection via Variational Feature Aggregation
- A Modular Multi-stage Lightweight Graph Transformer Network for Human Pose and Shape Estimation from 2D Human Pose
- ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing
- Classified as unknown: A novel Bayesian neural network
- Sequential Strategic Screening
- Differentiating Through Integer Linear Programs with Quadratic Regularization and Davis-Yin Splitting
- Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
- Combinatorial Causal Bandits without Graph Skeleton
- Differentially Private Kernel Inducing Points using features from ScatterNets (DP-KIP-ScatterNet) for Privacy Preserving Data Distillation
- Large Music Recommendation Studies for Small Teams
- Deep Learning for Reference-Free Geolocation for Poplar Trees
- Fisheye traffic data set of point center markers
- GaitSADA: Self-Aligned Domain Adaptation for mmWave Gait Recognition
- An Comparative Analysis of Different Pitch and Metrical Grid Encoding Methods in the Task of Sequential Music Generation
- Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Models
- When Source-Free Domain Adaptation Meets Learning with Noisy Labels
- Automated Time-frequency Domain Audio Crossfades using Graph Cuts
- Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance
- Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees
- Improving Open-Domain Dialogue Evaluation with a Causal Inference Model
- Demystifying Disagreement-on-the-Line in High Dimensions
- On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters
- Misspecification-robust Sequential Neural Likelihood for Simulation-based Inference
- CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects
- Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation
- Skeleton-based Human Action Recognition via Convolutional Neural Networks (CNN)
- IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing
- Hierarchical Disentangled Representation for Invertible Image Denoising and Beyond
- Inference Time Evidences of Adversarial Attacks for Forensic on Transformers
- Sentence Identification with BOS and EOS Label Combinations
- Unconstrained Dynamic Regret via Sparse Coding
- A Reinforcement Learning Framework for Dynamic Mediation Analysis
- Differentiable Entailment for Parameter Efficient Few Shot Learning
- Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning
- Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning
- Continuous Spatiotemporal Transformers