Papers
Wed 16 Aug 2023
186 papers
- Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language ModelsLLM safety and security → Jailbreaking
- FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMsMixture-of-experts → MoE large language models
- Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
- TeCH: Text-guided Reconstruction of Lifelike Clothed HumansDiffusion models → 3D, point cloud and scene generation
- Two-and-a-half Order Score-based Model for Solving 3D Ill-posed Inverse ProblemsDiffusion models → Medical imaging and segmentation
- Diff-CAPTCHA: An Image-based CAPTCHA with Security Enhanced by Denoising Diffusion ModelDiffusion models → Image generation, text-to-image and editing
- Denoising Diffusion Probabilistic Model for Retinal Image Generation and SegmentationDiffusion models → Medical imaging and segmentation
- Dual-Stream Diffusion Net for Text-to-Video GenerationDiffusion models → Video generation
- MEDOE: A Multi-Expert Decoder and Output Ensemble Framework for Long-tailed Semantic SegmentationMixture-of-experts → Vision mixture-of-experts
- RSpell: Retrieval-augmented Framework for Domain Adaptive Chinese Spelling CheckRetrieval-augmented generation → Generation and context integration
- Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented SystemRetrieval-augmented generation → Conversational and speech RAG
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent ConversationLLM agents and tool use → Software engineering coding agents
- ChatLogo: A Large Language Model-Driven Hybrid Natural-Programming Language Interface for Agent-based Modeling and ProgrammingLLM agents and tool use → General LLM agent frameworks and benchmarks
- Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module OperationLLM safety and security → Machine unlearning
- Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme DetectionMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Deep Learning based Tomato Disease Detection and Remedy Suggestions using Mobile Application
- Memories in the Making: Predicting Video Memorability with Encoding Phase EEG
- Prediction and Interpretation of Vehicle Trajectories in the Graph Spectral Domain
- Adaptive mitigation of time-varying quantum noise
- A Preliminary Study on a Conceptual Game Feature Generation and Recommendation System
- STEM: Unleashing the Power of Embeddings for Multi-task Recommendation
- An Empirical Study on Fault Detection and Root Cause Analysis of Indium Tin Oxide Electrodes by Processing S-parameter Patterns
- AI For Fraud Awareness
- Leveraging Explainable AI to Analyze Researchers' Aspect-Based Sentiment about ChatGPT
- Atom-by-atom protein generation and beyond with language models
- Partially Observable Multi-Agent Reinforcement Learning with Information Sharing
- Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment
- AI planning in the imagination: High-level planning on learned abstract search spaces
- Lightweight Adaptation of Neural Language Models via Subspace Embedding
- Quantifying Overfitting: Introducing the Overfitting Index
- SkinDistilViT: Lightweight Vision Transformer for Skin Lesion Classification
- BREATHE: Second-Order Gradients and Heteroscedastic Emulation based Design Space Exploration
- Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions
- Large Language Models for Granularized Barrett's Esophagus Diagnosis Classification
- A Data-Theoretic Approach to Identifying Violent Facial Expressions in Social Crime Contexts
- Flickr Africa: Examining Geo-Diversity in Large-Scale, Human-Centric Visual Data
- Physics Informed Recurrent Neural Networks for Seismic Response Evaluation of Nonlinear Systems
- Reproducing Kernel Hilbert Space Pruning for Sparse Hyperspectral Abundance Prediction
- Towards Zero Memory Footprint Spiking Neural Network Training
- Towards Personalized Federated Learning via Heterogeneous Model Reassembly
- Non-monotone Sequential Submodular Maximization
- Fair GANs through model rebalancing for extremely imbalanced class distributions
- FedPop: Federated Population-based Hyperparameter Tuning
- Learning the meanings of function words from grounded language using a visual question answering model
- BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognition
- LSTM-Based Forecasting Model for GRACE Accelerometer Data
- Integrating Renewable Energy in Agriculture: A Deep Reinforcement Learning-based Approach
- FootGPT : A Large Language Model Development Experiment on a Minimal Setting
- On the Augmentation of Cognitive Accuracy and Cognitive Precision in Human/Cog Ensembles
- PEvoLM: Protein Sequence Evolutionary Information Language Model
- AffectEcho: Speaker Independent and Language-Agnostic Emotion and Affect Transfer for Speech Synthesis
- MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions
- InsMapper: Exploring Inner-instance Information for Vectorized HD Mapping
- Proprioceptive Learning with Soft Polyhedral Networks
- Can Transformers Learn Optimal Filtering for Unknown Systems?
- Ref-DVGO: Reflection-Aware Direct Voxel Grid Optimization for an Improved Quality-Efficiency Trade-Off in Reflective Scene Reconstruction
- Diagnosing Human-object Interaction Detectors
- Likelihood-Based Text-to-Image Evaluation with Patch-Level Perceptual and Semantic Credit Assignment
- Painter: Teaching Auto-regressive Language Models to Draw Sketches
- Exploiting Point-Wise Attention in 6D Object Pose Estimation Based on Bidirectional Prediction
- Autoencoding a Soft Touch to Learn Grasping from On-land to Underwater
- ResBuilder: Automated Learning of Depth with Residual Structures
- Self-Supervised Online Camera Calibration for Automated Driving and Parking Applications
- Time Travel in LLMs: Tracing Data Contamination in Large Language Models
- Label Propagation Techniques for Artifact Detection in Imbalanced Classes using Photoplethysmogram Signals
- DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching
- Classification Committee for Active Deep Object Detection
- LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters
- An Expert's Guide to Training Physics-informed Neural Networks
- On Neural Quantum Support Vector Machines
- Hierarchical Uncertainty Estimation for Medical Image Segmentation Networks
- Learning to Distill Global Representation for Sparse-View CT
- High-Fidelity Lake Extraction via Two-Stage Prompt Enhancement: Establishing a Novel Baseline and Benchmark
- Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction
- Accurate synthesis of Dysarthric Speech for ASR data augmentation
- Integrating Visual and Semantic Similarity Using Hierarchies for Image Retrieval
- ALIP: Adaptive Language-Image Pre-training with Synthetic Caption
- Eliciting Risk Aversion with Inverse Reinforcement Learning via Interactive Questioning
- Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer
- Knowledge-Enhanced Multi-Label Few-Shot Product Attribute-Value Extraction
- Digital twinning of cardiac electrophysiology models from the surface ECG: a geodesic backpropagation approach
- Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities
- Content-based Recommendation Engine for Video Streaming Platform
- Prediction of post-radiotherapy recurrence volumes in head and neck squamous cell carcinoma using 3D U-Net segmentation
- SIGMA: Scale-Invariant Global Sparse Shape Matching
- Fast Uncertainty Quantification of Spent Nuclear Fuel with Neural Networks
- Continuous Sweep for Binary Quantification Learning
- Precision and Recall Reject Curves for Classification
- Robust Autonomous Vehicle Pursuit without Expert Steering Labels
- A distributed neural network architecture for dynamic sensor selection with application to bandwidth-constrained body-sensor networks
- Advancing continual lifelong learning in neural information retrieval: definition, dataset, framework, and empirical evaluation
- Automated Semiconductor Defect Inspection in Scanning Electron Microscope Images: a Systematic Review
- PDPK: A Framework to Synthesise Process Data and Corresponding Procedural Knowledge for Manufacturing
- Agglomerative Transformer for Human-Object Interaction Detection
- Dual-Branch Temperature Scaling Calibration for Long-Tailed Recognition
- DeepContrast: Deep Tissue Contrast Enhancement using Synthetic Data Degradations and OOD Model Predictions
- SummHelper: Collaborative Human-Computer Summarization
- KernelWarehouse: Towards Parameter-Efficient Dynamic Convolution
- Independent Distribution Regularization for Private Graph Embedding
- Membrane Potential Batch Normalization for Spiking Neural Networks
All 186
- Convergence of Two-Layer Regression with Nonlinear Units
- Is Meta-Learning the Right Approach for the Cold-Start Problem in Recommender Systems?
- GAEI-UNet: Global Attention and Elastic Interaction U-Net for Vessel Image Segmentation
- Graph Out-of-Distribution Generalization with Controllable Data Augmentation
- Learning logic programs by discovering higher-order abstractions
- Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN
- AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition
- Visually-Aware Context Modeling for News Image Captioning
- Stable and Causal Inference for Discriminative Self-supervised Deep Visual Representations
- ECPC-IDS:A benchmark endometrail cancer PET/CT image dataset for evaluation of semantic segmentation and detection of hypermetabolic regions
- A Framework for Data-Driven Explainability in Mathematical Optimization
- Integrating cognitive map learning and active inference for planning in ambiguous environments
- Warped geometric information on the optimisation of Euclidean functions
- Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos
- CMD: a framework for Context-aware Model self-Detoxification
- Robust Bayesian Satisficing
- DFedADMM: Dual Constraints Controlled Model Inconsistency for Decentralized Federated Learning
- Improving Audio-Visual Segmentation with Bidirectional Generation
- Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval
- CARE: A Large Scale CT Image Dataset and Clinical Applicable Benchmark Model for Rectal Cancer Segmentation
- Computer vision-enriched discrete choice models, with an application to residential location choice
- Detecting Olives with Synthetic or Real Data? Olive the Above
- OnUVS: Online Feature Decoupling Framework for High-Fidelity Ultrasound Video Synthesis
- It Ain't That Bad: Understanding the Mysterious Performance Drop in OOD Generalization for Generative Transformer Models
- Graph Relation Aware Continual Learning
- SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes
- MultiMediate'23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions
- Benchmarking Neural Network Generalization for Grammar Induction
- Description Logics Go Second-Order -- Extending EL with Universally Quantified Concepts
- Fast and Multiphase Rates for Nearest Neighbor Classifiers
- Contrastive Learning for Lane Detection via cross-similarity
- TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
- MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation
- The Expressive Power of Graph Neural Networks: A Survey
- Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Survey
- SCQPTH: an efficient differentiable splitting method for convex quadratic programming
- DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field
- Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerance
- Inherent Redundancy in Spiking Neural Networks
- How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learning
- HyperSNN: A new efficient and robust deep learning model for resource constrained control applications
- Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network
- Neural Spherical Harmonics for structurally coherent continuous representation of diffusion MRI signal
- Explainable Multi-View Deep Networks Methodology for Experimental Physics
- MoCoSA: Momentum Contrast for Knowledge Graph Completion with Structure-Augmented Pre-trained Language Models
- Epicure: Distilling Sequence Model Predictions into Patterns
- Towards Ontology-Mediated Planning with OWL DL Ontologies (Extended Version)
- DeSCo: Towards Generalizable and Scalable Deep Subgraph Counting
- Self-Reference Deep Adaptive Curve Estimation for Low-Light Image Enhancement
- Automatic Vision-Based Parking Slot Detection and Occupancy Classification
- Modelling the Spread of COVID-19 in Indoor Spaces using Automated Probabilistic Planning
- Endogenous Macrodynamics in Algorithmic Recourse
- Unsupervised Domain Adaptive Detection with Network Stability Analysis
- ChinaTelecom System Description to VoxCeleb Speaker Recognition Challenge 2023
- Accelerating Generic Graph Neural Networks via Architecture, Compiler, Partition Method Co-Design
- Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
- AATCT-IDS: A Benchmark Abdominal Adipose Tissue CT Image Dataset for Image Denoising, Semantic Segmentation, and Radiomics Evaluation
- A Quantum Approximation Scheme for k-Means
- Stochastic Controlled Averaging for Federated Learning with Communication Compression
- Characteristics of networks generated by kernel growing neural gas
- Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations
- Benchmarking Adversarial Robustness of Compressed Deep Learning Models
- Deep Generative Imputation Model for Missing Not At Random Data
- Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis
- Sarcasm Detection in a Disaster Context
- Conditional Perceptual Quality Preserving Image Compression
- Fast Training of NMT Model with Data Sorting
- Hierarchical Topological Ordering with Conditional Independence Test for Limited Time Series
- MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluation
- IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation
- S2R: Exploring a Double-Win Transformer-Based Framework for Ideal and Blind Super-Resolution
- GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds
- Data-Driven Adversarial Online Control for Unknown Linear Systems
- SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device
- Microstructure-Empowered Stock Factor Extraction and Utilization
- Ranking-aware Uncertainty for Text-guided Image Retrieval
- Is Self-Supervised Pretraining Good for Extrapolation in Molecular Property Prediction?
- How to Mask in Error Correction Code Transformer: Systematic and Double Masking
- Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals
- OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution
- View Consistent Purification for Accurate Cross-View Localization
- S-Mixup: Structural Mixup for Graph Neural Networks
- Snapshot High Dynamic Range Imaging with a Polarization Camera
- DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory
- Safety Filter Design for Neural Network Systems via Convex Optimization
- Rigid Transformations for Stabilized Lower Dimensional Space to Support Subsurface Uncertainty Quantification and Interpretation