Papers
Fri 8 Sep 2023
153 papers
- AdBooster: Personalized Ad Creative Generation using Stable Diffusion OutpaintingDiffusion models → Image generation, text-to-image and editing
- Decoding visual brain representations from electroencephalography through Knowledge Distillation and latent diffusion modelsDiffusion models → Medical imaging and segmentation
- Knowledge Distillation-Empowered Digital Twin for Anomaly DetectionKnowledge distillation → Detection and dense prediction distillation
- VDFD: Multi-Agent Value Decomposition Framework with Disentangled World ModelWorld models → Latent dynamics models and model-based RL
- A Versatile Graph Learning Approach through LLM-based AgentLLM agents and tool use → Web, search, and research agents
- The Power of Sound (TPoS): Audio Reactive Video Generation with Stable DiffusionDiffusion models → Audio, speech and music
- Measuring and Improving Chain-of-Thought Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
- Create Your World: Lifelong Text-to-Image DiffusionDiffusion models → Image generation, text-to-image and editing
- MaskDiffusion: Boosting Text-to-Image Consistency with Conditional MaskDiffusion models → Image generation, text-to-image and editing
- Language Prompt for Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
- MoEController: Instruction-based Arbitrary Image Manipulation with Mixture-of-Expert ControllersDiffusion models → Image generation, text-to-image and editing +1
- Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-ExpertsMixture-of-experts → Vision mixture-of-experts
- Context-Aware Prompt Tuning for Vision-Language Model with Dual-AlignmentMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Rink-Agnostic Hockey Rink Registration
- A survey of manifold learning and its applications for multimedia
- Originality and the Future of Copyright in an Age of Generative AI
- Data Commons
- Matching Table Metadata with Business Glossaries Using Large Language Models
- Online Infinite-Dimensional Regression: Learning Linear Operators
- Down the Toxicity Rabbit Hole: A Novel Framework to Bias Audit Large Language Models
- Towards Reliable and Fluent Large Language Models: Incorporating Feedback Learning Loops in QA Systems
- Adversarial attacks on hybrid classical-quantum Deep Learning models for Histopathological Cancer Detection
- Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Models
- Circles: Inter-Model Comparison of Multi-Classification Problems with High Number of Classes
- tSPM+; a high-performance algorithm for mining transitive sequential patterns from clinical data
- Few-Shot Learning of Force-Based Motions From Demonstration Through Pre-training of Haptic Representation
- Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?
- Open and reusable deep learning for pathology with WSInfer and QuPath
- Probabilistic Safety Regions Via Finite Families of Scalable Classifiers
- Perceptual adjustment queries and an inverted measurement paradigm for low-rank metric learning
- Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossing
- Style Generation: Image Synthesis based on Coarsely Matched Texts
- Linking Symptom Inventories using Semantic Textual Similarity
- Motif-aware Attribute Masking for Molecular Graph Pre-training
- Dynamic Mesh-Aware Radiance Fields
- EGOFALLS: A visual-audio dataset and benchmark for fall detection using egocentric cameras
- Mask2Anomaly: Mask Transformer for Universal Open-set Segmentation
- When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale
- Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding
- Towards Interpretable Solar Flare Prediction with Attention-based Deep Neural Networks
- Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing
- Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges
- Poster: Making Edge-assisted LiDAR Perceptions Robust to Lossy Point Cloud Compression
- Examining Autoexposure for Challenging Scenes
- Connecting NTK and NNGP: A Unified Theoretical Framework for Wide Neural Network Learning Dynamics
- End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining
- Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks
- Systematic Review of Techniques in Brain Image Synthesis using Deep Learning
- Decreasing the Computing Time of Bayesian Optimization using Generalizable Memory Pruning
- Spatial-Temporal Graph Attention Fuser for Calibration in IoT Air Pollution Monitoring Systems
- Generating drawdown-realistic financial price paths using path signatures
- Unsupervised Gaze-aware Contrastive Learning with Subject-specific Condition
- COVID-19 Detection System: A Comparative Analysis of System Performance Based on Acoustic Features of Cough Audio Signals
- Compositional Learning of Visually-Grounded Concepts Using Reinforcement
- On the Efficacy of Multi-scale Data Samplers for Vision Applications
- Weighted Unsupervised Domain Adaptation Considering Geometry Features and Engineering Performance of 3D Design Data
- On the Actionability of Outcome Prediction
- Generalized Cross-domain Multi-label Few-shot Learning for Chest X-rays
- Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
- WiSARD: A Labeled Visual and Thermal Image Dataset for Wilderness Search and Rescue
- Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networks
- Impact of Blur and Resolution on Demographic Disparities in 1-to-Many Facial Identification
- Comparative Study of Visual SLAM-Based Mobile Robot Localization Using Fiducial Markers
- Single View Refractive Index Tomography with Neural Fields
- Physics-Informed Neural Networks for an optimal counterdiabatic quantum computation
- Variations and Relaxations of Normalizing Flows
- Soft Quantization using Entropic Regularization
- Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach
- Advanced Computing and Related Applications Leveraging Brain-inspired Spiking Neural Networks
- Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving
- SynthoGestures: A Novel Framework for Synthetic Dynamic Hand Gesture Generation for Driving Scenarios
- Parallel and Limited Data Voice Conversion Using Stochastic Variational Deep Kernel Learning
- DeformToon3D: Deformable 3D Toonification from Neural Radiance Fields
- CSPRD: A Financial Policy Retrieval Dataset for Chinese Stock Market
- Emergent learning in physical systems as feedback-based aging in a glassy landscape
- Generalization Bounds: Perspectives from Information Theory and PAC-Bayes
- Seeing-Eye Quadruped Navigation with Force Responsive Locomotion Control
- Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation
- Active Learning for Classifying 2D Grid-Based Level Completability
- CNN Injected Transformer for Image Exposure Correction
- Learning from Power Signals: An Automated Approach to Electrical Disturbance Identification Within a Power Transmission System
- SSIG: A Visually-Guided Graph Edit Distance for Floor Plan Similarity
- Value-Compressed Sparse Column (VCSC): Sparse Matrix Storage for Redundant Data
- Zero-Shot Robustification of Zero-Shot Models
- Revealing the preference for correcting separated aberrations in joint optic-image design
- Online Submodular Maximization via Online Convex Optimization
- Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens
- Graph Neural Networks Use Graphs When They Shouldn't
- Leveraging Model Fusion for Improved License Plate Recognition
- Generating the Ground Truth: Synthetic Data for Soft Label and Label Noise Research
- Actor critic learning algorithms for mean-field control with moment neural networks
- Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models
- AMLP: Adjustable Masking Lesion Patches for Self-Supervised Medical Image Segmentation
- Federated Learning for Early Dropout Prediction on Healthy Ageing Applications
- Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes
- Navigating Out-of-Distribution Electricity Load Forecasting during COVID-19: Benchmarking energy load forecasting models without and with continual learning
- FIMO: A Challenge Formal Dataset for Automated Theorem Proving
- How Can We Tame the Long-Tail of Chest X-ray Datasets?
- Fuzzy Fingerprinting Transformer Language-Models for Emotion Recognition in Conversations
All 153
- Sequential Semantic Generative Communication for Progressive Text-to-Image Generation
- Viewing the process of generating counterfactuals as a source of knowledge: a new approach for explaining classifiers
- Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence
- From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
- Optimal Rate of Kernel Regression in Large Dimensions
- LLMCad: Fast and Scalable On-device Large Language Model Inference
- Towards Practical Capture of High-Fidelity Relightable Avatars
- Adaptive Distributed Kernel Ridge Regression: A Feasible Distributed Learning Scheme for Data Silos
- FIVA: Facial Image and Video Anonymization and Anonymization Defense
- Long-Range Correlation Supervision for Land-Cover Classification from Remote Sensing Images
- Offline Recommender System Evaluation under Unobserved Confounding
- Concomitant Group Testing
- Score-PA: Score-based 3D Part Assembly
- UQ at #SMM4H 2023: ALEX for Public Health Analysis with Social Media
- Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse
- Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain
- Towards Mitigating Architecture Overfitting on Distilled Datasets
- SegmentAnything helps microscopy images based automatic and quantitative organoid detection and analysis
- Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality
- Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese
- Manifold-based Verbalizer Space Re-embedding for Tuning-free Prompt-based Classification
- Unsupervised Object Localization with Representer Point Selection
- PRISTA-Net: Deep Iterative Shrinkage Thresholding Network for Coded Diffraction Patterns Phase Retrieval
- Grouping Boundary Proposals for Fast Interactive Image Segmentation
- GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue
- PRISM: Mitigating EHR Data Sparsity via Learning from Missing Feature Calibrated Prototype Patient Representations
- Cross-Utterance Conditioned VAE for Speech Generation
- Mapping EEG Signals to Visual Stimuli: A Deep Learning Approach to Match vs. Mismatch Classification
- Representation Synthesis by Probabilistic Many-Valued Logic Operation in Self-Supervised Learning
- Robot Localization and Mapping Final Report -- Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry
- NESTLE: a No-Code Tool for Statistical Analysis of Legal Corpus
- Depth Completion with Multiple Balanced Bases and Confidence for Dense Monocular SLAM
- Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps
- RST-style Discourse Parsing Guided by Document-level Content Structures
- Proprioceptive External Torque Learning for Floating Base Robot and its Applications to Humanoid Locomotion
- Meta predictive learning model of languages in neural circuits
- Weakly Supervised Point Clouds Transformer for 3D Object Detection
- Preserved Edge Convolutional Neural Network for Sensitivity Enhancement of Deuterium Metabolic Imaging (DMI)
- Toward Sufficient Spatial-Frequency Interaction for Gradient-aware Underwater Image Enhancement
- Data-driven classification of low-power communication signals by an unauthenticated user using a software-defined radio
- Unsupervised Multi-document Summarization with Holistic Inference
- ECoDe: A Sample-Efficient Method for Co-Design of Robotic Agents
- Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation
- Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning
- UER: A Heuristic Bias Addressing Approach for Online Continual Learning
- Enabling the Evaluation of Driver Physiology Via Vehicle Dynamics
- SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments
- Computationally Efficient Data-Driven Discovery and Linear Representation of Nonlinear Systems For Control
- Riemannian Langevin Monte Carlo schemes for sampling PSD matrices with fixed rank
- Enhancing Hierarchical Transformers for Whole Brain Segmentation with Intracranial Measurements Integration
- Inferring physical laws by artificial intelligence based causal models
- INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalization
- 3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation