Papers
Sat 1 Jul 2023
97 papers
- ProbVLM: Probabilistic Adapter for Frozen Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
- Single Sequence Prediction over Reasoning Graphs for Multi-hop QALLM reasoning → Knowledge- and tool-augmented reasoning
- DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution MisalignmentLLM reasoning → Spatial and embodied reasoning
- Let Me Teach You: Pedagogical Foundations of Feedback for Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- CephGPT-4: An Interactive Multimodal Cephalometric Measurement and Diagnostic System with Visual Large Language Model
- Causing is Achieving -- A solution to the problem of causation
- Data-Driven Design for Metamaterials and Multiscale Systems: A Review
- Q-YOLO: Efficient Inference for Real-time Object Detection
- Understanding Counterspeech for Online Harm Mitigation
- Finding differences in perspectives between designers and engineers to develop trustworthy AI for autonomous cars
- FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
- Discovering Patterns of Definitions and Methods from Scientific Documents
- Automatic Counterfactual Augmentation for Robust Text Classification Based on Word-Group Search
- An Adaptive Optimization Approach to Personalized Financial Incentives in Mobile Behavioral Weight Loss Interventions
- Weighted Anisotropic-Isotropic Total Variation for Poisson Denoising
- Towards Resource-Efficient Streaming of Large-Scale Medical Image Datasets for Deep Learning
- WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution
- Sparsity-aware generalization theory for deep neural networks
- Adaptive Algorithms for Relaxed Pareto Set Identification
- JoinBoost: Grow Trees Over Normalized Data Using Only SQL
- Brightness-Restricted Adversarial Attack Patch
- Applications of Binary Similarity and Distance Measures
- WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting
- Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
- Improving CNN-based Person Re-identification using score Normalization
- MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications
- CasTGAN: Cascaded Generative Adversarial Network for Realistic Tabular Data Synthesis
- Low-Resource Cross-Lingual Adaptive Training for Nigerian Pidgin
- Effective Matching of Patients to Clinical Trials using Entity Extraction and Neural Re-ranking
- Residual-based attention in physics-informed neural networks
- Revisiting Sample Size Determination in Natural Language Understanding
- Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation
- Improving Text Matching in E-Commerce Search with A Rationalizable, Intervenable and Fast Entity-Based Relevance Model
- Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training
- Understanding recent deep-learning techniques for identifying collective variables of molecular dynamics
- The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations
- A Comparative Study of Machine Learning Algorithms for Anomaly Detection in Industrial Environments: Performance and Environmental Impact
- BatGPT: A Bidirectional Autoregessive Talker from Generative Pre-trained Transformer
- When Synthetic Data Met Regulation
- Fedward: Flexible Federated Backdoor Defense Framework with Non-IID Data
- Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection
- Sparse-Input Neural Network using Group Concave Regularization
- Improving Multitask Retrieval by Promoting Task Specialization
- Recursive Algorithmic Reasoning
- Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
- SDRCNN: A single-scale dense residual connected convolutional neural network for pansharpening
- DeepMediX: A Deep Learning-Driven Resource-Efficient Medical Diagnosis Across the Spectrum
- Automatic Solver Generator for Systems of Laurent Polynomial Equations
- SHARCS: Shared Concept Space for Explainable Multimodal Learning
- Detection of River Sandbank for Sand Mining with the Presence of Other High Mineral Content Regions Using Multi-spectral Images
- PM-DETR: Domain Adaptive Prompt Memory for Object Detection with Transformers
- Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
- Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey
- SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimation
- Applied Bayesian Structural Health Monitoring: inclinometer data anomaly detection and forecasting
- DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation
- Accelerated primal-dual methods with enlarged step sizes and operator learning for nonsmooth optimal control problems
- AutoST: Training-free Neural Architecture Search for Spiking Transformers
- All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning
- CMA-ES for Post Hoc Ensembling in AutoML: A Great Success and Salvageable Failure
- Assembled-OpenML: Creating Efficient Benchmarks for Ensembles in AutoML with OpenML
- SysNoise: Exploring and Benchmarking Training-Deployment System Inconsistency
- Common Knowledge Learning for Generating Transferable Adversarial Examples
- Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentation
- AE-RED: A Hyperspectral Unmixing Framework Powered by Deep Autoencoder and Regularization by Denoising
- Hiding in Plain Sight: Differential Privacy Noise Exploitation for Evasion-resilient Localized Poisoning Attacks in Multiagent Reinforcement Learning
- Hierarchical Pretraining for Biomedical Term Embeddings
- Bootstrapping the Cross-Validation Estimate
- InstructEval: Systematic Evaluation of Instruction Selection Methods
- Efficient Subclass Segmentation in Medical Images
- An ML approach to resolution of singularities
- THUIR2 at NTCIR-16 Session Search (SS) Task
- Safe Screening for Unbalanced Optimal Transport
- On a Relation Between the Rate-Distortion Function and Optimal Transport
- Deep Angiogram: Trivializing Retinal Vessel Segmentation
- VesselMorph: Domain-Generalized Retinal Vessel Segmentation via Shape-Aware Representation
- Unified Transfer Learning Models in High-Dimensional Linear Regression
- Hierarchical Federated Learning Incentivization for Gas Usage Estimation
- Forward-Forward Algorithm for Hyperspectral Image Classification: A Preliminary Study
- InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphs
- Causal Structure Learning by Using Intersection of Markov Blankets
- S-Omninet: Structured Data Enhanced Universal Multimodal Learning Architecture
- StyleStegan: Leak-free Style Transfer Based on Feature Steganography
- Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals
- A Constructive Approach to Function Realization by Neural Stochastic Differential Equations
- More for Less: Compact Convolutional Transformers Enable Robust Medical Image Classification with Limited Data
- Internal-External Boundary Attention Fusion for Glass Surface Segmentation
- AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondence
- Image Matters: A New Dataset and Empirical Study for Multimodal Hyperbole Detection
- Rearrangement Planning for General Part Assembly
- Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
- How far is Language Model from 100% Few-shot Named Entity Recognition in Medical Domain
- Interpretable Neural Networks with Random Constructive Algorithm
- Personality Traits in Large Language Models
- Long-Tailed Continual Learning For Visual Food Recognition
- Single-Stage Heavy-Tailed Food Classification
- Unsupervised Coordinate-Based Video Denoising