Papers
Sun 24 Mar 2024
147 papers
- Is The Watermarking Of LLM-Generated Code Robust?LLM safety and security → Watermarking generated content and models
- The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR SummarizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Interpretable Modeling of Deep Reinforcement Learning Driven SchedulingDeep reinforcement learning methods → Interpretable and logic-guided RL
- Engineering Safety Requirements for Autonomous Driving with Large Language ModelsEnd-to-end autonomous driving → Large language models for driving
- Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
- Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated SynthesisDiffusion models → Diffusion for compression and wireless
- Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token UnlearningLLM safety and security → Backdoor and data poisoning attacks
- Partially Blinded Unlearning: Class Unlearning for Deep Networks a Bayesian PerspectiveLLM safety and security → Machine unlearning
- Diffusion Model is a Good Pose Estimator from 3D RF-VisionDiffusion models → 3D, point cloud and scene generation
- Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark DiscoveryDiffusion models → 3D, point cloud and scene generation
- Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation EnhancementMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
- Ultra Low-Cost Two-Stage Multimodal System for Non-Normative Behavior DetectionLLM safety and security → Safety alignment, refusal and guardrails
- EVA: Zero-shot Accurate Attributes and Multi-Object Video EditingDiffusion models → Video generation
- Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gapEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution HistoryOffline RL and imitation learning from data → Imitation learning methods
- Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with JustificationsLLM agents and tool use → Agent threats, guardrails and governance
- Adversarial Guided Diffusion Models for Adversarial PurificationDiffusion models → Robustness, privacy and adversarial aspects
- A Unified Module for Accelerating STABLE-DIFFUSION: LCM-LORADiffusion models → Diffusion foundations and sampling
- Fill in the ____ (a Diffusion-based Image Inpainting Pipeline)Diffusion models → 3D, point cloud and scene generation
- SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object TrackingKnowledge distillation → Detection and dense prediction distillation
- Configurable Holography: Towards Display and Scene Adaptation
- Towards Large-Scale Training of Pathology Foundation Models
- Transformer-based Joint Modelling for Automatic Essay Scoring and Off-Topic Detection
- Machine Learning-based Approach for Ex-post Assessment of Community Risk and Resilience Based on Coupled Human-infrastructure Systems Performance
- An efficient domain-independent approach for supervised keyphrase extraction and ranking
- A Python Framework for Neutrosophic Sets and Mappings
- Improve accessibility for Low Vision and Blind people using Machine Learning and Computer Vision
- Stochastic Optimization with Constraints: A Non-asymptotic Instance-Dependent Analysis
- MicroHD: An Accuracy-Driven Optimization of Hyperdimensional Computing Algorithms for TinyML systems
- Interpretable Machine Learning for Weather and Climate Prediction: A Survey
- Markov chain models for inspecting response dynamics in psychological testing
- EG-ConMix: An Intrusion Detection Method based on Graph Contrastive Learning
- Stochastic parameter reduced-order model based on hybrid machine learning approaches
- Modeling Analog Dynamic Range Compressors using Deep Learning and State-space Models
- Artificial Neural Microcircuits as Building Blocks: Concept and Challenges
- AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans
- Optimization on a Finer Scale: Bounded Local Subgradient Variation Perspective
- Large Language Models in Biomedical and Health Informatics: A Review with Bibliometric Analysis
- LexDrafter: Terminology Drafting for Legislative Documents using Retrieval Augmented Generation
- latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction
- Guessing human intentions to avoid dangerous situations in caregiving robots
- HemoSet: The First Blood Segmentation Dataset for Automation of Hemostasis Management
- The Evolution of Football Betting- A Machine Learning Approach to Match Outcome Forecasting and Bookmaker Odds Estimation
- L-MAE: Longitudinal masked auto-encoder with time and severity-aware encoding for diabetic retinopathy progression prediction
- Object Detectors in the Open Environment: Challenges, Solutions, and Outlook
- Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Data
- Connecting the Dots: Inferring Patent Phrase Similarity with Retrieved Phrase Graphs
- Emotion Recognition from the perspective of Activity Recognition
- Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble
- Large Language Models Offer an Alternative to the Traditional Approach of Topic Modelling
- Improving Sequence-to-Sequence Models for Abstractive Text Summarization Using Meta Heuristic Approaches
- On the Equivalency, Substitutability, and Flexibility of Synthetic Data
- Adversarially Masked Video Consistency for Unsupervised Domain Adaptation
- Low Rank Groupwise Deformations for Motion Tracking in Cardiac Cine MRI
- An early warning indicator trained on stochastic disease-spreading models with different noises
- On machine learning analysis of atomic force microscopy images for image classification, sample surface recognition
- Dual-modal Prior Semantic Guided Infrared and Visible Image Fusion for Intelligent Transportation System
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields
- Cyber-Security Knowledge Graph Generation by Hierarchical Nonnegative Matrix Factorization
- Exemplar-Free Class Incremental Learning via Incremental Representation
- CoverUp: Effective High Coverage Test Generation for Python
- Systematic construction of continuous-time neural networks for linear dynamical systems
- Leveraging Deep Learning and Xception Architecture for High-Accuracy MRI Classification in Alzheimer Diagnosis
- Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane
- Image Captioning in news report scenario
- Convergence analysis of OT-Flow for sample generation
- Skull-to-Face: Anatomy-Guided 3D Facial Reconstruction and Editing
- Rumor Detection with a novel graph neural network approach
- Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains
- SQL-Encoder: Improving NL2SQL In-Context Learning Through a Context-Aware Encoder
- FH-SSTNet: Forehead Creases based User Verification using Spatio-Spatial Temporal Network
- From Discrete to Continuous: Deep Fair Clustering With Transferable Representations
- Logic-based Explanations for Linear Support Vector Classifiers with Reject Option
- Cross-domain Multi-modal Few-shot Object Detection via Rich Text
- ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models
- EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World
- Mixed-Initiative Human-Robot Teaming under Suboptimality with Online Bayesian Adaptation
- Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals
- Enhancing MRI-Based Classification of Alzheimer's Disease with Explainable 3D Hybrid Compact Convolutional Transformers
- Fusion of Minutia Cylinder Codes and Minutia Patch Embeddings for Latent Fingerprint Recognition
- Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method
- An Analytic Solution to Covariance Propagation in Neural Networks
- Multi-Task Learning with Multi-Task Optimization
- Towards Online Real-Time Memory-based Video Inpainting Transformers
- Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition
- One Masked Model is All You Need for Sensor Fault Detection, Isolation and Accommodation
- Analyzing Consumer IoT Traffic from Security and Privacy Perspectives: a Comprehensive Survey
- Realtime Robust Shape Estimation of Deformable Linear Object
- Predicting Energy Budgets in Droplet Dynamics: A Recurrent Neural Network Approach
- CFAT: Unleashing TriangularWindows for Image Super-resolution
- What Happens to a Dataset Transformed by a Projection-based Concept Removal Method?
- Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes
- A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish
- A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
- Complementary Recommendation in E-commerce: Definition, Approaches, and Future Directions
- SSHPool: The Separated Subgraph-based Hierarchical Pooling
- Runtime Monitoring and Fault Detection for Neural Network-Controlled Systems
- Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
- AKBR: Learning Adaptive Kernel-based Representations for Graph Classification
All 147
- A Survey on Lexical Ambiguity Detection and Word Sense Disambiguation
- Enhancing Video Transformers for Action Understanding with VLM-aided Training
- WangchanLion and WangchanX MRC Eval
- Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design
- Enhancing Visual Continual Learning with Language-Guided Supervision
- Self-Supervised Multi-Frame Neural Scene Flow
- Opportunities and challenges in the application of large artificial intelligence models in radiology
- A Transformer approach for Electricity Price Forecasting
- Public Perceptions of Fairness Metrics Across Borders
- Specifying Agent Ethics (Blue Sky Ideas)
- A Multi-Label Dataset of French Fake News: Human and Machine Insights
- Can Language Models Pretend Solvers? Logic Code Simulation with LLMs
- CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field
- LLMs as Compiler for Arabic Programming Language
- Argument Quality Assessment in the Age of Instruction-Following Large Language Models
- The Interplay of Learning, Analytics, and Artificial Intelligence in Education: A Vision for Hybrid Intelligence
- PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling
- Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization
- A Temporal Graph Network Framework for Dynamic Recommendation
- Manifold Regularization Classification Model Based On Improved Diffusion Map
- Qibo: A Large Language Model for Traditional Chinese Medicine
- Segment Anything Model for Road Network Graph Extraction
- Heterogeneous Federated Learning with Splited Language Model
- Improving Demand Forecasting in Open Systems with Cartogram-Enhanced Deep Learning
- Edit3K: Universal Representation Learning for Video Editing Components
- Semantic Is Enough: Only Semantic Information For NeRF Reconstruction
- Monotonic Paraphrasing Improves Generalization of Language Model Prompting
- V2X-Real: a Large-Scale Dataset for Vehicle-to-Everything Cooperative Perception
- Node Classification via Semantic-Structural Attention-Enhanced Graph Convolutional Networks
- Learning Directed Acyclic Graphs from Partial Orderings
- VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections
- Exploring the Impact of Dataset Bias on Dataset Distillation
- RPMArt: Towards Robust Perception and Manipulation for Articulated Objects
- PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference
- SM2C: Boost the Semi-supervised Segmentation for Medical Image by using Meta Pseudo Labels and Mixed Images
- CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering
- Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval
- A Federated Parameter Aggregation Method for Node Classification Tasks with Different Graph Network Structures
- Diverse Representation Embedding for Lifelong Person Re-Identification
- Near-Optimal differentially private low-rank trace regression with guaranteed private initialization
- Multi-Scale Spatio-Temporal Graph Convolutional Network for Facial Expression Spotting
- BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval
- Mars Spectrometry 2: Gas Chromatography -- Second place solution
- Knowledge-guided Machine Learning: Current Trends and Future Prospects
- Exploring Accurate 3D Phenotyping in Greenhouse through Neural Radiance Fields
- Towards Two-Stream Foveation-based Active Vision Learning
- CBGT-Net: A Neuromimetic Architecture for Robust Classification of Streaming Data