Papers
Thu 7 Sep 2023
196 papers
- DGSD: Dynamical Graph Self-Distillation for EEG-Based Auditory Spatial Attention DetectionKnowledge distillation → Distillation for medical imaging
- Evaluation and Enhancement of Semantic Grounding in Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Exploring Sparse MoE in GANs for Text-conditioned Image SynthesisMixture-of-experts → Vision mixture-of-experts
- DiffusionEngine: Diffusion Model is Scalable Data Engine for Object DetectionDiffusion models → Image generation, text-to-image and editing
- Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement LearningOffline RL and imitation learning from data → Real-world robot offline RL
- T2IW: Joint Text to Image & Watermark GenerationLLM safety and security → Watermarking generated content and models
- Enhancing Pipeline-Based Conversational Agents with Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
- Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model AdaptionDiffusion models → Diffusion foundations and sampling
- DiffDefense: Defending against Adversarial Attacks via Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
- Exploring an LM to generate Prolog Predicates from Mathematics QuestionsLLM reasoning → Mathematical reasoning
- Prompt-based Context- and Domain-aware Pretraining for Vision and Language NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Towards Comparable Knowledge Distillation in Semantic Image SegmentationKnowledge distillation → Detection and dense prediction distillation
- Spiking Structured State Space Model for Monaural Speech EnhancementState-space sequence models (S4, Mamba) → Speech and audio SSMs
- Text2Control3D: Controllable 3D Avatar Generation in Neural Radiance Fields using Geometry-Guided Text-to-Image Diffusion ModelDiffusion models → 3D, point cloud and scene generation
- Reuse and Diffuse: Iterative Denoising for Text-to-Video GenerationDiffusion models → Video generation
- SyncDreamer: Generating Multiview-consistent Images from a Single-view ImageDiffusion models → 3D, point cloud and scene generation
- Multimodal Guidance Network for Missing-Modality Inference in Content ModerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip StrategyDiffusion models → Inverse problems and image restoration
- Understanding Data Augmentation from a Robustness Perspective
- Enabling energy-Efficient object detection with surrogate gradient descent in spiking neural networks
- Operator-Based Detecting, Learning, and Stabilizing Unstable Periodic Orbits of Chaotic Attractors
- VeriDIP: Verifying Ownership of Deep Neural Networks through Privacy Leakage Fingerprints
- DeepCrysTet: A Deep Learning Approach Using Tetrahedral Mesh for Predicting Properties of Crystalline Materials
- BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer
- Enabling Intelligent Vehicular Networks Through Distributed Learning in the Non-Terrestrial Networks 6G Vision
- Joint Self-supervised Depth and Optical Flow Estimation towards Dynamic Objects
- Using Curriculum Theory to Inform Approaches to Generative AI in Schools
- Automatically Testing Functional Properties of Code Translation Models
- Discovering Dynamic Effective Connectome of Brain with Bayesian Dynamic DAG Learning
- Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences
- Creating a Systematic ESG (Environmental Social Governance) Scoring System Using Social Network Analysis and Machine Learning for More Sustainable Company Practices
- S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens
- SRN-SZ: Deep Leaning-Based Scientific Error-bounded Lossy Compression with Super-resolution Neural Networks
- Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems
- Brief technical note on linearizing recurrent neural networks (RNNs) before vs after the pointwise nonlinearity
- Algebra and Geometry of Camera Resectioning
- TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Models
- Improving the Accuracy of Beauty Product Recommendations by Assessing Face Illumination Quality
- Evaluation of large language models for discovery of gene set function
- Optimal Transport with Tempered Exponential Measures
- An Element-wise RSAV Algorithm for Unconstrained Optimization Problems
- MMSFormer: Multimodal Transformer for Material and Semantic Segmentation
- Adapting Self-Supervised Representations to Multi-Domain Setups
- ConDA: Contrastive Domain Adaptation for AI-generated Text Detection
- Derivation of Coordinate Descent Algorithms from Optimal Control Theory
- CDFSL-V: Cross-Domain Few-Shot Learning for Videos
- Noisy Computing of the mathsfOR and mathsfMAX Functions
- Separable Self and Mixed Attention Transformers for Efficient Object Tracking
- LanSER: Language-Model Supported Speech Emotion Recognition
- DBsurf: A Discrepancy Based Method for Discrete Stochastic Gradient Estimation
- Automatic Concept Embedding Model (ACEM): No train-time concepts, No issue!
- Improving Resnet-9 Generalization Trained on Small Datasets
- REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation
- SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutions
- BluNF: Blueprint Neural Field
- Random Expert Sampling for Deep Learning Segmentation of Acute Ischemic Stroke on Non-contrast CT
- Large-Scale Automatic Audiobook Creation
- Beyond attention: deriving biologically interpretable insights from weakly-supervised multiple-instance learning models
- Automatic Algorithm Selection for Pseudo-Boolean Optimization with Given Computational Time Limits
- A-Eval: A Benchmark for Cross-Dataset Evaluation of Abdominal Multi-Organ Segmentation
- ImageBind-LLM: Multi-modality Instruction Tuning
- Tracking Anything with Decoupled Video Segmentation
- Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction
- The Making and Breaking of Camouflage
- ProPainter: Improving Propagation and Transformer for Video Inpainting
- InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
- ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation
- FIND: A Function Description Benchmark for Evaluating Interpretability Methods
- Zero-Shot Audio Captioning via Audibility Guidance
- DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
- Large Language Models Are Not Robust Multiple Choice Selectors
- Better Practices for Domain Adaptation
- Introducing "Forecast Utterance" for Conversational Data Science
- OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMs
- Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks
- A Tutorial on the Non-Asymptotic Theory of System Identification
- Text-to-feature diffusion for audio-visual few-shot learning
- FLM-101B: An Open LLM and How to Train It with 100K Budget
- CenTime: Event-Conditional Modelling of Censoring in Survival Analysis
- Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samples
- Gradient-Based Feature Learning under Structured Data
- Early warning indicators via latent stochastic dynamical systems
- Cross-Task Attention Network: Improving Multi-Task Learning for Medical Imaging Applications
- Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching
- Uncovering Drift in Textual Data: An Unsupervised Method for Detecting and Mitigating Drift in Machine Learning Models
- ArtHDR-Net: Perceptually Realistic and Accurate HDR Content Creation
- Prime and Modulate Learning: Generation of forward models with signed back-propagation and environmental cues
- Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization
- Empirical Risk Minimization for Losses without Variance
- AnthroNet: Conditional Generation of Humans via Anthropometrics
- Panoramas from Photons
- SimNP: Learning Self-Similarity Priors Between Neural Points
- Improved theoretical guarantee for rank aggregation via spectral method
- Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck
- FisheyePP4AV: A privacy-preserving method for autonomous vehicles on fisheye camera images
- Conformal Autoregressive Generation: Beam Search with Coverage Guarantees
- Optimal Transport Regularized Divergences: Application to Adversarial Robustness
- USA: Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part of Speech Dataset
- CPU frequency scheduling of real-time applications on embedded devices with temporal encoding-based deep reinforcement learning
- Deep Learning Safety Concerns in Automated Driving Perception
All 196
- Feature Propagation on Knowledge Graphs using Cellular Sheaves
- Neural lasso: a unifying approach of lasso and neural networks
- L2,1-Norm Regularized Quaternion Matrix Completion Using Sparse Representation and Quaternion QR Decomposition
- dacl1k: Real-World Bridge Damage Dataset Putting Open-Source Data to the Test
- M(otion)-mode Based Prediction of Ejection Fraction using Echocardiograms
- Hybrid of representation learning and reinforcement learning for dynamic and complex robotic motion planning
- TSGBench: Time Series Generation Benchmark
- Convergence Analysis of Decentralized ASGD
- Medoid Silhouette clustering with automatic cluster number selection
- PBP: Path-based Trajectory Prediction for Autonomous Driving
- The Daunting Dilemma with Sentence Encoders: Success on Standard Benchmarks, Failure in Capturing Basic Semantic Properties
- Label-efficient Contrastive Learning-based model for nuclei detection and classification in 3D Cardiovascular Immunofluorescent Images
- ClusterFusion: Leveraging Radar Spatial Features for Radar-Camera 3D Object Detection in Autonomous Vehicles
- Using representation balancing to learn conditional-average dose responses from clustered data
- A Causal Perspective on Loan Pricing: Investigating the Impacts of Selection Bias on Identifying Bid-Response Functions
- Interpretable Visual Question Answering via Reasoning Supervision
- A boundary-aware point clustering approach in Euclidean and embedding spaces for roof plane segmentation
- A Natural Gas Consumption Forecasting System for Continual Learning Scenarios based on Hoeffding Trees with Change Point Detection Mechanism
- Word segmentation granularity in Korean
- A State Representation for Diminishing Rewards
- Chat Failures and Troubles: Reasons and Solutions
- A Probabilistic Semi-Supervised Approach with Triplet Markov Chains
- Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory
- Short-Term Load Forecasting Using A Particle-Swarm Optimized Multi-Head Attention-Augmented CNN-LSTM Network
- MS-UNet-v2: Adaptive Denoising Method and Training Strategy for Medical Image Segmentation with Small Training Data
- PyGraft: Configurable Generation of Synthetic Schemas and Knowledge Graphs at Your Fingertips
- A computationally lightweight safe learning algorithm
- Dataset Generation and Bonobo Classification from Weakly Labelled Videos
- How adversarial attacks can disrupt seemingly stable accurate classifiers
- Alzheimer Disease Detection from Raman Spectroscopy of the Cerebrospinal Fluid via Topological Machine Learning
- BNS-Net: A Dual-channel Sarcasm Detection Method Considering Behavior-level and Sentence-level Conflicts
- Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection
- Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments
- Promoting Fairness in GNNs: A Characterization of Stability
- VideolandGPT: A User Study on a Conversational Recommender System
- Context-Aware 3D Object Localization from Single Calibrated Images: A Study of Basketballs
- Beyond XAI:Obstacles Towards Responsible AI
- Insights Into the Inner Workings of Transformer Models for Protein Function Prediction
- Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction
- NeuroCodeBench: a plain C neural network benchmark for software verification
- Filtration Surfaces for Dynamic Graph Classification
- Evaluating ChatGPT as a Recommender System: A Rigorous Approach
- Your Battery Is a Blast! Safeguarding Against Counterfeit Batteries with Authentication
- Chasing Consistency in Text-to-3D Generation from a Single Image
- Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning
- Loquacity and Visible Emotion: ChatGPT as a Policy Advisor
- Spatial encoding of BOLD fMRI time series for categorizing static images across visual datasets: A pilot study on human vision
- Interactive Hyperparameter Optimization in Multi-Objective Problems via Preference Learning
- DTW+S: Shape-based Comparison of Time-series with Ordered Local Trend
- DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
- Toward High Quality Facial Representation Learning
- Sparse Federated Training of Object Detection in the Internet of Vehicles
- Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media
- All Labels Together: Low-shot Intent Detection with an Efficient Label Semantic Encoding Paradigm
- Trinary Decision Trees for handling missing data
- An Anchor Learning Approach for Citation Field Learning
- Region Generation and Assessment Network for Occluded Person Re-Identification
- On the dynamics of multi agent nonlinear filtering and learning
- Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation
- MVD:A Novel Methodology and Dataset for Acoustic Vehicle Type Classification
- Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction
- YOLO series target detection algorithms for underwater environments
- Data-Adaptive Graph Framelets with Generalized Vanishing Moments for Graph Machine Learning
- Feature Enhancer Segmentation Network (FES-Net) for Vessel Segmentation
- A Robust Negative Learning Approach to Partial Domain Adaptation Using Source Prototypes
- Efficient Single Object Detection on Image Patches with Early Exit Enhanced High-Precision CNNs
- DGC: Training Dynamic Graphs with Spatio-Temporal Non-Uniformity using Graph Partitioning by Chunks
- Parameterized Aspects of Distinct Kemeny Rank Aggregation
- BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications
- Dynamic Frame Interpolation in Wavelet Domain
- Towards Robust Natural-Looking Mammography Lesion Synthesis on Ipsilateral Dual-Views Breast Cancer Analysis
- Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region
- Instance Segmentation of Dislocations in TEM Images
- Evaluating Deep Learning-based Melanoma Classification using Immunohistochemistry and Routine Histology: A Three Center Study
- SAM3D: Segment Anything Model in Volumetric Medical Images
- Privacy-preserving Continual Federated Clustering via Adaptive Resonance Theory
- DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners
- TSI-Net: A Timing Sequence Image Segmentation Network for Intracranial Artery Segmentation in Digital Subtraction Angiography
- InteractionNet: Joint Planning and Prediction for Autonomous Driving with Transformers
- Temporal Collection and Distribution for Referring Video Object Segmentation
- Perceptual Quality Assessment of 360^circ Images Based on Generative Scanpath Representation
- Machine Learning for Tangible Effects: Natural Language Processing for Uncovering the Illicit Massage Industry & Computer Vision for Tactile Sensing
- Fast FixMatch: Faster Semi-Supervised Learning with Curriculum Batch Size
- Support-Set Context Matters for Bongard Problems
- Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation
- Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Data
- Cross-domain Sound Recognition for Efficient Underwater Data Analysis
- XGen-7B Technical Report
- Broadband Ground Motion Synthesis via Generative Adversarial Neural Operators: Development and Validation
- Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning
- Personalized Tucker Decomposition: Modeling Commonality and Peculiarity on Tensor Data
- Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacy
- Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty
- Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
- From Base to Conversational: Japanese Instruction Dataset and Tuning Large Language Models
- Large Language Models as Optimizers