Papers
Mon 8 May 2023
201 papers
- Accessible Instruction-Following AgentLLM agents and tool use → Multimodal and embodied agents
- Knowledge-enhanced Agents for Interactive Text GamesLLM agents and tool use → Reinforcement learning for LLM agents
- Atmospheric Turbulence Correction via Variational Deep DiffusionDiffusion models → Inverse problems and image restoration
- Web Content Filtering through knowledge distillation of Large Language ModelsKnowledge distillation → Knowledge distillation for LLMs
- Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- NeuroComparatives: Neuro-Symbolic Distillation of Comparative KnowledgeKnowledge distillation → Knowledge distillation for LLMs
- DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion ModelsDiffusion models → Audio, speech and music
- How Do In-Context Examples Affect Compositional Generalization?LLM reasoning → Reasoning benchmarks and evaluation
- CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Sense, Imagine, Act: Multimodal Perception Improves Model-Based Reinforcement Learning for Head-to-Head Autonomous RacingWorld models → Latent dynamics models and model-based RL
- ReGeneration Learning of Diffusion Models with Rich Prompts for Zero-Shot Image TranslationDiffusion models → Image generation, text-to-image and editing
- Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or BiasLLM safety and security → Backdoor and data poisoning attacks
- A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual CluesLLM reasoning → Multimodal reasoning
- Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question AnsweringLLM reasoning → Reasoning benchmarks and evaluation
- DiffBFR: Bootstrapping Diffusion Model Towards Blind Face RestorationDiffusion models → Inverse problems and image restoration
- Can Diffusion Model Achieve Better Performance in Text Generation? Bridging the Gap between Training and Inference!Diffusion models → Discrete and text diffusion
- Real-World Denoising via Diffusion ModelDiffusion models → Diffusion foundations and sampling
- Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and PriorsEnd-to-end autonomous driving → Reinforcement learning for driving
- The impact and applications of ChatGPT: a systematic review of literature reviews
- ChatGPT: Vision and Challenges
- Distribution-aware Fairness Test Generation
- Deep Learning and Image Super-Resolution-Guided Beam and Power Allocation for mmWave Networks
- KineticNet: Deep learning a transferable kinetic energy functional for orbital-free density functional theory
- Vulnerability Detection Using Two-Stage Deep Learning Models
- Unjustified Sample Sizes and Generalizations in Explainable AI Research: Principles for More Inclusive User Studies
- Imitation versus Innovation: What children can do that large language and language-and-vision models cannot (yet)?
- A Comprehensive Survey on Affective Computing; Challenges, Trends, Applications, and Future Directions
- Risk-limiting Financial Audits via Weighted Sampling without Replacement
- Information Design in Multi-Agent Reinforcement Learning
- ComputeGPT: A computational chat model for numerical problems
- Multi-Task End-to-End Training Improves Conversational Recommendation
- Leveraging Machine Learning to Gain Insights on Quantum Thermodynamic Entropy
- Algebra Error Classification with Large Language Models
- Enhancing Road Safety through Accurate Detection of Hazardous Driving Behaviors with Graph Convolutional Recurrent Networks
- Modelling Concurrency Bugs Using Machine Learning
- Exploring a Gradient-based Explainable AI Technique for Time-Series Data: A Case Study of Assessing Stroke Rehabilitation Exercises
- Privacy-preserving Adversarial Facial Features
- Code Execution with Pre-trained Language Models
- Self-Repellent Random Walks on General Graphs -- Achieving Minimal Sampling Variance via Nonlinear Markov Chains
- Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness
- Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections
- Artificial Intelligence in 3GPP 5G-Advanced: A Survey
- Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts
- Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks
- Large-Scale Study of Temporal Shift in Health Insurance Claims
- A Unifying Framework of Attention-based Neural Load Forecasting
- Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey
- A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution
- SECRETS: Subject-Efficient Clinical Randomized Controlled Trials using Synthetic Intervention
- Recommender Systems with Generative Retrieval
- A Feasibility Study on Indoor Localization and Multi-person Tracking Using Sparsely Distributed Camera Network with Edge Computing
- Coherent Wave Dynamics and Language Generation of a Generative Pre-trained Transformer
- Crack Detection of Asphalt Concrete Using Combined Fracture Mechanics and Digital Image Correlation
- Dreams Are More "Predictable'' Than You Think
- ANALOGICAL -- A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models
- Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding
- Domain Agnostic Image-to-image Translation using Low-Resolution Conditioning
- Domain independent post-processing with graph U-nets: Applications to Electrical Impedance Tomographic Imaging
- Solving Linear Inverse Problems using Higher-Order Annealed Langevin Diffusion
- Synthesis of Annotated Colorectal Cancer Tissue Images from Gland Layout
- Revisiting Relation Extraction in the era of Large Language Models
- GersteinLab at MEDIQA-Chat 2023: Clinical Note Summarization from Doctor-Patient Conversations through Fine-tuning and In-context Learning
- Crop identification using deep learning on LUCAS crop cover photos
- Autoencoder-based prediction of ICU clinical codes
- Explanation-based Finetuning Makes Models More Robust to Spurious Cues
- Knowledge Graph Guided Semantic Evaluation of Language Models For User Trust
- FedHB: Hierarchical Bayesian Federated Learning
- LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization
- UQ for Credit Risk Management: A deep evidence regression approach
- NerfAcc: Efficient Sampling Accelerates NeRFs
- From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks
- Error Analysis of Kernel/GP Methods for Nonlinear and Parametric PDEs
- Joint Moment Retrieval and Highlight Detection Via Natural Language Queries
- The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification
- RelPose++: Recovering 6D Poses from Sparse-view Observations
- PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds
- Learning to Evaluate the Artness of AI-generated Images
- On User-Level Private Convex Optimization
- What Do Patients Say About Their Disease Symptoms? Deep Multilabel Text Classification With Human-in-the-Loop Curation for Automatic Labeling of Patient Self Reports of Problems
- Explainable Parallel RCNN with Novel Feature Representation for Time Series Forecasting
- Gaussian process deconvolution
- SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding
- A Frustratingly Easy Improvement for Position Embeddings via Random Padding
- The Current State of Summarization
- CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
- SR+Codec: a Benchmark of Super-Resolution for Video Compression Bitrate Reduction
- Reinforcement Learning for Topic Models
- Scalable Optimal Margin Distribution Machine
- Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video
- Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning
- Influence of External Information on Large Language Models Mirrors Social Cognitive Patterns
- Mlinear: Rethink the Linear Model for Time-series Forecasting
- Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data
- MultiModal-GPT: A Vision and Language Model for Dialogue with Humans
- AvatarReX: Real-time Expressive Full-body Avatars
- HistAlign: Improving Context Dependency in Language Generation by Aligning with History
- BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning
- OSTA: One-shot Task-adaptive Channel Selection for Semantic Segmentation of Multichannel Images
- Large-scale and Efficient Texture Mapping Algorithm via Loopy Belief Propagation
All 201
- Augmented Large Language Models with Parametric Knowledge Guiding
- Is AUC the best measure for practical comparison of anomaly detectors?
- Toeplitz Neural Network for Sequence Modeling
- Understanding Noise-Augmented Training for Randomized Smoothing
- Controllable Light Diffusion for Portraits
- SkillQG: Learning to Generate Question for Reading Comprehension Assessment
- DEFENDER: DTW-Based Episode Filtering Using Demonstrations for Enhancing RL Safety
- Strategy for Rapid Diabetic Retinopathy Exposure Based on Enhanced Feature Extraction Processing
- Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields
- DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation
- Learning to Generate Poetic Chinese Landscape Painting with Calligraphy
- The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation
- High-Dimensional Smoothed Entropy Estimation via Dimensionality Reduction
- ElasticHash: Semantic Image Similarity Search by Deep Hashing with Elasticsearch
- Differentially Private Attention Computation
- Runtime Monitoring of Dynamic Fairness Properties
- Anticipatory Planning: Improving Long-Lived Planning by Estimating Expected Cost of Future Tasks
- Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey
- ASDL: A Unified Interface for Gradient Preconditioning in PyTorch
- Enhancing Knowledge Graph Construction Using Large Language Models
- Predicting nuclear masses with product-unit networks
- PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
- Analysis of Numerical Integration in RNN-Based Residuals for Fault Diagnosis of Dynamic Systems
- Riesz networks: scale invariant neural networks in a single forward pass
- CSGCL: Community-Strength-Enhanced Graph Contrastive Learning
- CURTAINs Flows For Flows: Constructing Unobserved Regions with Maximum Likelihood Estimation
- Learning Good Interventions in Causal Graphs via Covering
- Enhancing Continual Relation Extraction via Classifier Decomposition
- Neural Likelihood Surfaces for Spatial Processes with Computationally Intensive or Intractable Likelihoods
- XAI in Computational Linguistics: Understanding Political Leanings in the Slovenian Parliament
- Federated Learning in Wireless Networks via Over-the-Air Computations
- Target-driven One-Shot Unsupervised Domain Adaptation
- The Signature Kernel
- Graph Masked Autoencoder for Sequential Recommendation
- A LSTM and Cost-Sensitive Learning-Based Real-Time Warning for Civil Aviation Over-limit
- SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation
- Development of a Vision System to Enhance the Reliability of the Pick-and-Place Robot for Autonomous Testing of Camera Module used in Smartphones
- Privacy-Preserving Representations are not Enough -- Recovering Scene Content from Camera Poses
- Cone: Unsupervised Contrastive Opinion Extraction
- First-Choice Maximality Meets Ex-ante and Ex-post Fairness
- MultiTACRED: A Multilingual Version of the TAC Relation Extraction Dataset
- TAPS: Connecting Certified and Adversarial Training
- HiFi: High-Information Attention Heads Hold for Parameter-Efficient Model Adaptation
- Putting Natural in Natural Language Processing
- Multi-source Education Knowledge Graph Construction and Fusion for College Curricula
- Boosting Radiology Report Generation by Infusing Comparison Prior
- Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach
- Toward Adversarial Training on Contextualized Language Representation
- Non-Autoregressive Math Word Problem Solver with Unified Tree Structure
- Larger Offspring Populations Help the (1 + (λ, λ)) Genetic Algorithm to Overcome the Noise
- Multi-Temporal Lip-Audio Memory for Visual Speech Recognition
- High Quality Large-Scale 3-D Urban Mapping with Multi-Master TomoSAR
- Q&A Label Learning
- LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition
- Smart Home Device Detection Algorithm Based on FSA-YOLOv5
- Prompted LLMs as Chatbot Modules for Long Open-domain Conversation
- Recent Trends in Artificial Intelligence Technology: A Scoping Review
- CrAFT: Compression-Aware Fine-Tuning for Efficient Visual Task Adaptation
- Scene Text Recognition with Image-Text Matching-guided Dictionary
- Sparks of Artificial General Recommender (AGR): Early Experiments with ChatGPT
- Robust Traffic Light Detection Using Salience-Sensitive Loss: Computational Framework and Evaluations
- Blockchained Federated Learning for Internet of Things: A Comprehensive Survey
- FedZKP: Federated Model Ownership Verification with Zero-knowledge Proof
- Pedestrian Behavior Maps for Safety Advisories: CHAMP Framework and Real-World Data Analysis
- Target-Side Augmentation for Document-Level Machine Translation
- MO-DEHB: Evolutionary-based Hyperband for Multi-Objective Optimization
- SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
- Building Footprint Extraction with Graph Convolutional Network
- Leveraging Deep Learning and Digital Twins to Improve Energy Performance of Buildings
- IIITD-20K: Dense captioning for Text-Image ReID
- Token-Level Fitting Issues of Seq2seq Models
- MGR: Multi-generator Based Rationalization
- Axiomatization of Interventional Probability Distributions
- Behavior Contrastive Learning for Unsupervised Skill Discovery
- AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment
- Adaptive Learning Path Navigation Based on Knowledge Tracing and Reinforcement Learning
- TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection
- Video Object Segmentation in Panoptic Wild Scenes
- AnomalyBERT: Self-Supervised Transformer for Time Series Anomaly Detection using Data Degradation Scheme
- Generalized Universal Domain Adaptation with Generative Flow Networks
- Locally Attentional SDF Diffusion for Controllable 3D Shape Generation
- Language Independent Neuro-Symbolic Semantic Parsing for Form Understanding
- FashionTex: Controllable Virtual Try-on with Text and Texture
- DeformerNet: Learning Bimanual Manipulation of 3D Deformable Objects
- Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks
- New metrics and search algorithms for weighted causal DAGs
- Towards Accurate Human Motion Prediction via Iterative Refinement
- Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting
- Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization
- Accelerated Algorithms for a Class of Optimization Problems with Equality and Box Constraints
- Goal-oriented inference of environment from redundant observations
- Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt
- Improving Cross-Task Generalization with Step-by-Step Instructions
- Improving 2D face recognition via fine-level facial depth generation and RGB-D complementary feature learning
- Multivariate Analysis on Performance Gaps of Artificial Intelligence Models in Screening Mammography
- Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts
- A-ePA*SE: Anytime Edge-Based Parallel A* for Slow Evaluations
- TaLU: A Hybrid Activation Function Combining Tanh and Rectified Linear Unit to Enhance Neural Networks
- Few Shot Learning for Medical Imaging: A Comparative Analysis of Methodologies and Formal Mathematical Framework
- Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5
- SegGPT Meets Co-Saliency Scene