Papers
Tue 2 May 2023
184 papers
- Bilingual analogical proportions via hedgesLLM reasoning → Reasoning benchmarks and evaluation
- Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in HealthcareOffline RL and imitation learning from data → Offline RL algorithms
- Visual Reasoning: from State to TransformationLLM reasoning → Multimodal reasoning
- Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual NoiseRetrieval-augmented generation → RAG robustness and adaptive retrieval
- Accelerating Neural Self-Improvement via BootstrappingSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
- Get Back Here: Robust Imitation by Return-to-Distribution PlanningOffline RL and imitation learning from data → Imitation learning methods
- VPGTrans: Transfer Visual Prompt Generator across LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- The Role of Summarization in Generative Agents: A Preliminary PerspectiveLLM agents and tool use → Social simulation and multi-agent debate
- Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language ModelsLLM safety and security → Backdoor and data poisoning attacks
- Chronosymbolic Learning: Efficient CHC Solving with Symbolic Reasoning and Inductive LearningLLM reasoning → Mathematical reasoning
- Solving Inverse Problems with Score-Based Generative Priors learned from Noisy DataDiffusion models → Inverse problems and image restoration
- Complex Logical Reasoning over Knowledge Graphs using Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
- Geometric Latent Diffusion Models for 3D Molecule GenerationDiffusion models → Flow matching, time series and science
- High-Fidelity Image Synthesis from Pulmonary Nodule Lesion Maps using Semantic Diffusion ModelDiffusion models → Medical imaging and segmentation
- mAedesID: Android Application for Aedes Mosquito Species Identification using Convolutional Neural Network
- Shared Latent Space by Both Languages in Non-Autoregressive Neural Machine Translation
- Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment
- Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence
- Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction
- Improving Cancer Hallmark Classification with BERT-based Deep Learning Approach
- Deep Learning-Assisted Simultaneous Targets Sensing and Super-Resolution Imaging
- Automated Code generation for Information Technology Tasks in YAML through Large Language Models
- Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation
- Multi-Head Graph Convolutional Network for Structural Connectome Classification
- CALM: Conditional Adversarial Latent Models for Directable Virtual Characters
- Cortical analysis of heterogeneous clinical brain MRI scans for large-scale neuroimaging studies
- Out-of-distribution detection algorithms for robust insect classification
- Unpaired Downscaling of Fluid Flows with Diffusion Bridges
- Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA
- KEPLET: Knowledge-Enhanced Pretrained Language Model with Topic Entity Awareness
- Hamming Similarity and Graph Laplacians for Class Partitioning and Adversarial Image Detection
- Transferability of coVariance Neural Networks and Application to Interpretable Brain Age Prediction using Anatomical Features
- When Newer is Not Better: Does Deep Learning Really Benefit Recommendation From Implicit Feedback?
- Energy-dependent barren plateau in bosonic variational quantum circuits
- Multimodal Procedural Planning via Dual Text-Image Prompting
- MISNN: Multiple Imputation via Semi-parametric Neural Networks
- Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information
- Fairness and representation in satellite-based poverty maps: Evidence of urban-rural disparities and their impacts on downstream policy
- SLTUNET: A Simple Unified Model for Sign Language Translation
- Representation Learning via Manifold Flattening and Reconstruction
- Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems
- DeCom: Deep Coupled-Factorization Machine for Post COVID-19 Respiratory Syncytial Virus Prediction with Nonpharmaceutical Interventions Awareness
- Psychologically-Inspired Causal Prompts
- Spatial-Temporal Networks for Antibiogram Pattern Prediction
- Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
- Few-shot In-context Learning for Knowledge Base Question Answering
- Expectation Maximization Pseudo Labels
- Photonic Advantage of Optical Encoders
- DiffuSum: Generation Enhanced Extractive Summarization with Diffusion
- Cross-view Action Recognition via Contrastive View-invariant Representation
- High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimation
- Expressive Mortality Models through Gaussian Process Kernels
- Slow Kill for Big Data Learning
- Stance Detection: A Practical Guide to Classifying Political Beliefs in Text
- Construction of Decision Trees and Acyclic Decision Graphs from Decision Rule Systems
- Outlier galaxy images in the Dark Energy Survey and their identification with unsupervised machine learning
- Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks
- Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner
- From Stars to Insights: Exploration and Implementation of Unified Sentiment Analysis with Distant Supervision
- DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation
- Fears about AI-mediated communication are grounded in different expectations for one's own versus others' use
- Predict NAS Multi-Task by Stacking Ensemble Models using GP-NAS
- BrainNPT: Pre-training of Transformer networks for brain network classification
- A Novel Deep Learning based Model for Erythrocytes Classification and Quantification in Sickle Cell Disease
- Integrating spoken instructions into flight trajectory prediction to optimize automation in air traffic control
- Data valuation: The partial ordinal Shapley value for machine learning
- A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework with Gray Code Representation
- Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflection
- Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge
- Generalizing Dataset Distillation via Deep Generative Prior
- Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models
- Key-Locked Rank One Editing for Text-to-Image Personalization
- Neural LiDAR Fields for Novel View Synthesis
- Privacy-Preserving In-Context Learning for Large Language Models
- Sequence Modeling with Multiresolution Convolutional Memory
- Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
- The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers
- Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks
- Unlimiformer: Long-Range Transformers with Unlimited Length Input
- UNTER: A Unified Knowledge Interface for Enhancing Pre-trained Language Models
- FlowMap: Path Generation for Automated Vehicles in Open Space Using Traffic Flow
- A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge
- ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation
- FreeLM: Fine-Tuning-Free Language Model
- AutoColor: Learned Light Power Control for Multi-Color Holograms
- Finding Neurons in a Haystack: Case Studies with Sparse Probing
- The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
- EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensors
- From Words to Code: Harnessing Data for Program Synthesis from Natural Language
- On the Impact of Data Quality on Image Classification Fairness
- Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees
- An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
- Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
- Self-supervised learning for infant cry analysis
- Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
- OTIEA:Ontology-enhanced Triple Intrinsic-Correlation for Cross-lingual Entity Alignment
- Type-enhanced Ensemble Triple Representation via Triple-aware Attention for Cross-lingual Entity Alignment
- How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?
- Mitigating Approximate Memorization in Language Models via Dissimilarity Learned Policy
- Jacobian-Scaled K-means Clustering for Physics-Informed Segmentation of Reacting Flows
All 184
- FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information
- Huatuo-26M, a Large-scale Chinese Medical QA Dataset
- Unlocking the Power of Representations in Long-term Novelty-based Exploration
- Discovering the Effectiveness of Pre-Training in a Large-scale Car-sharing Platform
- Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation
- ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression Learning
- Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement
- On the properties of Gaussian Copula Mixture Models
- Stochastic Contextual Bandits with Graph-based Contexts
- Mixed-Integer Optimal Control via Reinforcement Learning: A Case Study on Hybrid Electric Vehicle Energy Management
- Memory of recurrent networks: Do we compute it right?
- Forecast reconciliation for vaccine supply chain optimization
- Multimodal Neural Databases
- Scalable Mask Annotation for Video Text Spotting
- Sentiment Perception Adversarial Attacks on Neural Machine Translation Systems
- Unsupervised Feature Based Algorithms for Time Series Extrinsic Regression
- From Local to Global: Navigating Linguistic Diversity in the African Context
- Uncertain Machine Ethical Decisions Using Hypothetical Retrospection
- Absolute integrability of Mercer kernels is only sufficient for RKHS stability
- Stress and heat flux via automatic differentiation
- Are demographically invariant models and representations in medical imaging fair?
- Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing
- Oil Spill Segmentation using Deep Encoder-Decoder models
- Class based Influence Functions for Error Detection
- Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees
- LogSpecT: Feasible Graph Learning Model from Stationary Signals with Recovery Guarantees
- Random Function Descent
- Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature
- Self-supervised arbitrary scale super-resolution framework for anisotropic MRI
- Physics-Informed Learning Using Hamiltonian Neural Networks with Output Error Noise Models
- Validation of massively-parallel adaptive testing using dynamic control matching
- Projection-Free Online Convex Optimization with Stochastic Constraints
- Turning Flowchart into Dialog: Augmenting Flowchart-grounded Troubleshooting Dialogs via Synthetic Data Generation
- An Autonomous Non-monolithic Agent with Multi-mode Exploration based on Options Framework
- Long-Term Rhythmic Video Soundtracker
- Geometric Prior Based Deep Human Point Cloud Geometry Compression
- An Improved Yaw Control Algorithm for Wind Turbines via Reinforcement Learning
- Differential Newborn Face Morphing Attack Detection using Wavelet Scatter Network
- Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
- AxWin Transformer: A Context-Aware Vision Transformer Backbone with Axial Windows
- Exploring vision transformer layer choosing for semantic segmentation
- Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation
- DABS: Data-Agnostic Backdoor attack at the Server in Federated Learning
- How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence
- DreamPaint: Few-Shot Inpainting of E-Commerce Items for Virtual Try-On without 3D Modeling
- RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation
- HTPS: Heterogeneous Transferring Prediction System for Healthcare Datasets
- Reverse Engineering of Temporal Queries Mediated by LTL Ontologies
- MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognition
- Invertible Coarse Graining with Physics-Informed Generative Artificial Intelligence
- AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis
- DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning
- Dynamic Scheduling for Federated Edge Learning with Streaming Data
- CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario
- On Uni-Modal Feature Learning in Supervised Multi-Modal Learning
- A Survey of Methods for Converting Unstructured Data to CSG Models
- MultiLegalSBD: A Multilingual Legal Sentence Boundary Detection Dataset
- Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
- Exploration of Unranked Items in Safe Online Learning to Re-Rank
- Topic Shift Detection in Chinese Dialogues: Corpus and Benchmark
- The Pipeline System of ASR and NLU with MLM-based Data Augmentation toward STOP Low-resource Challenge
- EasyHeC: Accurate and Automatic Hand-eye Calibration via Differentiable Rendering and Space Exploration
- LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar
- Deconstructing Student Perceptions of Generative AI (GenAI) through an Expectancy Value Theory (EVT)-based Instrument
- Faster OreFSDet : A Lightweight and Effective Few-shot Object Detector for Ore Images
- A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models
- Unbounded Differentially Private Quantile and Maximum Estimation
- Hybrid model for Single-Stage Multi-Person Pose Estimation
- Self-similarity-based super-resolution of photoacoustic angiography from hand-drawn doodles
- Federated Neural Radiance Fields
- Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
- Lessons Learned in ATCO2: 5000 hours of Air Traffic Control Communications for Robust Automatic Speech Recognition and Understanding
- FedAVO: Improving Communication Efficiency in Federated Learning with African Vultures Optimizer
- Early Classifying Multimodal Sequences
- PU-EdgeFormer: Edge Transformer for Dense Prediction in Point Cloud Upsampling
- Ripple Knowledge Graph Convolutional Networks For Recommendation Systems
- RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models
- ADVISE: AI-accelerated Design of Evidence Synthesis for Global Development
- Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective
- Stratified Adversarial Robustness with Rejection
- PGrad: Learning Principal Gradients For Domain Generalization
- Analysis of different temporal graph neural network configurations on dynamic graphs
- Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making
- TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis