Papers
Thu 27 Jul 2023
194 papers
- Open Problems and Fundamental Limitations of Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- f-Divergence Minimization for Sequence-Level Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
- Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Universal and Transferable Adversarial Attacks on Aligned Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
- TEDi: Temporally-Entangled Diffusion for Long-Term Motion SynthesisDiffusion models → Video generation
- Thinker: Learning to Plan and ActWorld models → World models for language agents
- S3: Social-network Simulation System with Large Language Model-Empowered AgentsWorld models → World models for language agents
- Weakly Supervised AI for Efficient Analysis of 3D Pathology SamplesState-space sequence models (S4, Mamba) → Mamba for medical image analysis
- Fair Machine Unlearning: Data Removal while Mitigating DisparitiesLLM safety and security → Machine unlearning
- Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence GenerationRetrieval-augmented generation → Multimodal RAG
- Backdoor Attacks for In-Context Learning with Language ModelsLLM safety and security → Backdoor and data poisoning attacks
- LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image EnhancementDiffusion models → Inverse problems and image restoration
- Spatial-Frequency U-Net for Denoising Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- Stochastic Average Gradient : A Simple Empirical Investigation
- On Physical Origins of Learning
- An Ensemble Method of Deep Reinforcement Learning for Automated Cryptocurrency Trading
- When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top-k Multi-Label Learning
- Building RadiologyNET: Unsupervised annotation of a large-scale multimodal medical database
- Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
- Rotation-Invariant Random Features Provide a Strong Baseline for Machine Learning on 3D Point Clouds
- Improved Neural Radiance Fields Using Pseudo-depth and Fusion
- Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signals
- Robust vertebra identification using simultaneous node and edge predicting Graph Neural Networks
- A Multimodal Supervised Machine Learning Approach for Satellite-based Wildfire Identification in Europe
- AI Literature Review Suite
- Designing Fiduciary Artificial Intelligence
- Car-Driver Drowsiness Assessment through 1D Temporal Convolutional Networks
- JusticeBot: A Methodology for Building Augmented Intelligence Tools for Laypeople to Increase Access to Justice
- Sustainable transparency in Recommender Systems: Bayesian Ranking of Images for Explainability
- Approximate Model-Based Shielding for Safe Reinforcement Learning
- LLMediator: GPT-4 Assisted Online Dispute Resolution
- Identifying acute illness phenotypes via deep temporal interpolation and clustering network on physiologic signatures
- Fast Dust Sand Image Enhancement Based on Color Correction and New Membership Function
- Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures
- Reachability Poorman Discrete-Bidding Games
- PCA, SVD, and Centering of Data
- Generative AI for Medical Imaging: extending the MONAI Framework
- PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
- One-shot Joint Extraction, Registration and Segmentation of Neuroimaging Data
- The Marginal Value of Momentum for Small Learning Rate SGD
- Learning in Repeated Multi-Unit Pay-As-Bid Auctions
- Small, but important: Traffic light proposals for detecting small traffic lights and beyond
- Med-Flamingo: a Multimodal Medical Few-shot Learner
- EnSolver: Uncertainty-Aware Ensemble CAPTCHA Solvers with Theoretical Guarantees
- RCT Rejection Sampling for Causal Estimation Evaluation
- Causative Cyberattacks on Online Learning-based Automated Demand Response Systems
- PredictChain: Empowering Collaboration and Data Accessibility for AI in a Decentralized Blockchain-based Marketplace
- VISU at WASSA 2023 Shared Task: Detecting Emotions in Reaction to News Stories Leveraging BERT and Stacked Embeddings
- R-LPIPS: An Adversarially Robust Perceptual Similarity Metric
- A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity
- R-Block: Regularized Block of Dropout for convolutional networks
- Online Clustered Codebook
- Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields
- End-to-end Remote Sensing Change Detection of Unregistered Bi-temporal Images for Natural Disasters
- Detecting Morphing Attacks via Continual Incremental Training
- Detection of Children Abuse by Voice and Audio Classification by Short-Time Fourier Transform Machine Learning implemented on Nvidia Edge GPU device
- Clustering of illustrations by atmosphere using a combination of supervised and unsupervised learning
- Self-Supervised Learning for Improved Synthetic Aperture Sonar Target Recognition
- Cascaded Cross-Modal Transformer for Request and Complaint Detection
- Cortex Inspired Learning to Recover Damaged Signal Modality with ReD-SOM Model
- A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
- Understanding Forward Process of Convolutional Neural Network
- Self-Supervised Visual Acoustic Matching
- To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation
- The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
- MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving
- PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking
- A Geometric Notion of Causal Probing
- On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-n Recommendation
- Learning Depth Estimation for Transparent and Mirror Surfaces
- Matching Patients to Clinical Trials with Large Language Models
- A Transformer-based Approach for Arabic Offline Handwritten Text Recognition
- Guaranteed Approximation Bounds for Mixed-Precision Neural Operators
- Diverse Inpainting and Editing with GAN Inversion
- Adaptive Segmentation Network for Scene Text Detection
- SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark
- Self-Supervised Graph Transformer for Deepfake Detection
- Samplable Anonymous Aggregation for Private Federated Data Analysis
- How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges
- Harnessing Synthetic Active Particles for Physical Reservoir Computing
- Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
- Gzip versus bag-of-words for text classification
- TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer
- Multilingual Code Co-Evolution Using Large Language Models
- Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs
- MapNeRF: Incorporating Map Priors into Neural Radiance Fields for Driving View Simulation
- Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models
- Learning locally dominant force balances in active particle systems
- Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image Classification
- Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space
- Network Fault-tolerant and Byzantine-resilient Social Learning via Collaborative Hierarchical Non-Bayesian Learning
- A Self-Adaptive Penalty Method for Integrating Prior Knowledge Constraints into Neural ODEs
- Efficient Interaction-Aware Interval Analysis of Neural Network Feedback Loops
- PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
- Solving Data Quality Problems with Desbordante: a Demo
- Graph-based Polyphonic Multitrack Music Generation
- Benchmarking Performance of Deep Learning Model for Material Segmentation on Two HPC Systems
- GET3D--: Learning GET3D from Unconstrained Image Collections
- NSA: Naturalistic Support Artifact to Boost Network Confidence
- ARC-NLP at PAN 2023: Transition-Focused Natural Language Inference for Writing Style Detection
All 194
- ARC-NLP at PAN 2023: Hierarchical Long Text Classification for Trigger Detection
- Scaling Session-Based Transformer Recommendations using Optimized Negative Sampling and Loss Functions
- CodeLens: An Interactive Tool for Visualizing Code Representations
- Text-guided Foundation Model Adaptation for Pathological Image Classification
- Retrieval-based Text Selection for Addressing Class-Imbalanced Data in Classification
- Mixture of Self-Supervised Learning
- Base-based Model Checking for Multi-Agent Only Believing (long version)
- Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Driving
- MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entities
- Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration
- A full-resolution training framework for Sentinel-2 image fusion
- IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer
- Comparative Evaluation of Digital and Analog Chest Radiographs to Identify Tuberculosis using Deep Learning Model
- Generative convective parametrization of dry atmospheric boundary layer
- Exploiting the Potential of Seq2Seq Models as Robust Few-Shot Learners
- ArcGPT: A Large Language Model Tailored for Real-world Archival Applications
- Turkish Native Language Identification V2
- Counterfactual Explanations for Graph Classification Through the Lenses of Density
- Kernelised Normalising Flows
- Simplified Concrete Dropout -- Improving the Generation of Attribution Masks for Fine-grained Classification
- Fading memory as inductive bias in residual recurrent networks
- What Makes a Good Paraphrase: Do Automated Evaluations Work?
- Models of reference production: How do they withstand the test of time?
- Hybrid ASP-based multi-objective scheduling of semiconductor manufacturing processes (Extended version)
- Likely, Light, and Accurate Context-Free Clusters-based Trajectory Prediction
- Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning
- Improving Aspect-Based Sentiment with End-to-End Semantic Role Labeling Model
- Emotion4MIDI: a Lyrics-based Emotion-Labeled Symbolic Music Dataset
- Contrastive Knowledge Amalgamation for Unsupervised Image Classification
- MATNilm: Multi-appliance-task Non-intrusive Load Monitoring with Limited Labeled Data
- pCTFusion: Point Convolution-Transformer Fusion with Semantic Aware Loss for Outdoor LiDAR Point Cloud Segmentation
- 3DPortraitGAN: Learning One-Quarter Headshot 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses
- Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining
- Towards Practicable Sequential Shift Detectors
- FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Masks
- Semantic Image Completion and Enhancement using GANs
- Turning Whisper into Real-Time Transcription System
- New Interaction Paradigm for Complex EDA Software Leveraging GPT
- Test Time Adaptation for Blind Image Quality Assessment
- A Strategic Framework for Optimal Decisions in Football 1-vs-1 Shot-Taking Situations: An Integrated Approach of Machine Learning, Theory-Based Modeling, and Game Theory
- Understanding Silent Failures in Medical Image Classification
- P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds
- vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical Images
- EFLNet: Enhancing Feature Learning for Infrared Small Target Detection
- GaitMorph: Transforming Gait by Optimally Transporting Discrete Codes
- Evaluating Generative Models for Graph-to-Text Generation
- Pre-training Vision Transformers with Very Limited Synthesized Images
- Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation
- High Dynamic Range Imaging via Visual Attention Modules
- MIM-OOD: Generative Masked Image Modelling for Out-of-Distribution Detection in Medical Images
- Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World
- TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting
- Prediction of wind turbines power with physics-informed neural networks and evidential uncertainty quantification
- Fuzzy order-sorted feature logic
- Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustment
- Improving Natural Language Inference in Arabic using Transformer Models and Linguistically Informed Pre-Training
- Multi-Valued Partial Order Plans in Numeric Planning
- Decoding the Secrets of Machine Learning in Malware Classification: A Deep Dive into Datasets, Feature Extraction, and Model Performance
- Machine Learning based Parameter Sensitivity of Regional Climate Models -- A Case Study of the WRF Model for Heat Extremes over Southeast Australia
- Speed Limits for Deep Learning
- MVMR-FS : Non-parametric feature selection algorithm based on Maximum inter-class Variation and Minimum Redundancy
- Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?
- EqGAN: Feature Equalization Fusion for Few-shot Image Generation
- HTNet for micro-expression recognition
- Fact-Checking of AI-Generated Reports
- Metric-Based In-context Learning: A Case Study in Text Simplification
- 360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking
- Rapid and Scalable Bayesian AB Testing
- FS-Depth: Focal-and-Scale Depth Estimation from a Single Image in Unseen Indoor Scene
- BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning
- NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
- Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior
- Multiscale Dynamic Graph Representation for Biometric Recognition with Occlusions
- Self-Contrastive Graph Diffusion Network
- GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensing
- TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation
- Complete and separate: Conditional separation with missing target source attribute completion
- Clustering based Point Cloud Representation Learning for 3D Analysis
- A Weakly Supervised Segmentation Network Embedding Cross-scale Attention Guidance and Noise-sensitive Constraint for Detecting Tertiary Lymphoid Structures of Pancreatic Tumors
- HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting
- FakeTracer: Catching Face-swap DeepFakes via Implanting Traces in Training
- The detection and rectification for identity-switch based on unfalsified control
- MCPA: Multi-scale Cross Perceptron Attention Network for 2D Medical Image Segmentation
- Explainable Techniques for Analyzing Flow Cytometry Cell Transformers
- Neural Representation-Based Method for Metal-induced Artifact Reduction in Dental CBCT Imaging
- Distillation-guided Representation Learning for Unconstrained Gait Recognition
- A Memory-Augmented Multi-Task Collaborative Framework for Unsupervised Traffic Accident Detection in Driving Videos
- Robust Detection, Association, and Localization of Vehicle Lights: A Context-Based Cascaded CNN Approach and Evaluations
- Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach
- Evaluation of Safety Constraints in Autonomous Navigation with Deep Reinforcement Learning
- Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples
- Reinforcement learning guided fuzz testing for a browser's HTML rendering engine
- Adversarial Sleeping Bandit Problems with Multiple Plays: Algorithm and Ranking Application
- The Effect of Spoken Language on Speech Enhancement using Self-Supervised Speech Representation Loss Functions