Papers
Wed 26 Jul 2023
200 papers
- Three Bricks to Consolidate Watermarks for Large Language ModelsLLM safety and security → Watermarking generated content and models
- Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
- Diff-E: Diffusion-based Learning for Decoding Imagined Speech EEGDiffusion models → Medical imaging and segmentation
- Waypoint-Based Imitation Learning for Robotic ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
- Founding a mathematical diffusion model in linguistics. The case study of German syntactic features in the North-Eastern Italian dialectsDiffusion models → Discrete and text diffusion
- Artifact Restoration in Histology Images with Diffusion Probabilistic ModelsDiffusion models → Medical imaging and segmentation
- VideoControlNet: A Motion-Guided Video-to-Video Translation Framework by Using Diffusion Model with ControlNetDiffusion models → Video generation
- Pre-Training with Diffusion models for Dental Radiography segmentationDiffusion models → Medical imaging and segmentation
- ECO: Ensembling Context Optimization for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
- MCMC-Correction of Score-Based Diffusion Models for Model CompositionDiffusion models → Diffusion foundations and sampling
- Causal reasoning in typical computer vision tasksLLM reasoning → Multimodal reasoning
- How Does Diffusion Influence Pretrained Language Models on Out-of-Distribution Data?Diffusion models → Discrete and text diffusion
- Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D GenerationDiffusion models → 3D, point cloud and scene generation
- LieDetect: Detection of representation orbits of compact Lie groups from point clouds
- Observe Locally, Classify Globally: Using GNNs to Identify Sparse Matrix Structure
- Visual Saliency Detection in Advanced Driver Assistance Systems
- Differentiable short-time Fourier transform with respect to the hop length
- Differentiable adaptive short-time Fourier transform with respect to the window length
- Flexible Differentially Private Vertical Federated Learning with Adaptive Feature Embeddings
- Acceptable risks in Europe's proposed AI Act: Reasonableness and other principles for deciding how much risk management is enough
- A Sentence is Worth a Thousand Pictures: Can Large Language Models Understand Hum4n L4ngu4ge and the W0rld behind W0rds?
- DPBERT: Efficient Inference for BERT based on Dynamic Planning
- How User Language Affects Conflict Fatality Estimates in ChatGPT
- Data Augmentation for Neural Machine Translation using Generative Language Model
- The flow of ideas in word embeddings
- Building and Testing a General Intelligence Embodied in a Humanoid Robot
- Utilizing Large Language Models for Natural Interface to Pharmacology Databases
- A new algorithm for Subgroup Set Discovery based on Information Gain
- Equitable Time-Varying Pricing Tariff Design: A Joint Learning and Optimization Approach
- Mathematical Modeling of BCG-based Bladder Cancer Treatment Using Socio-Demographics
- Speed Reading Tool Powered by Artificial Intelligence for Students with ADHD, Dyslexia, and Short Attention Span
- Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum
- Optimal Noise Reduction in Dense Mixed-Membership Stochastic Block Models under Diverging Spiked Eigenvalues Condition
- Function Value Learning: Adaptive Learning Rates Based on the Polyak Stepsize and Function Splitting in ERM
- Open Problems in Computer Vision for Wilderness SAR and The Search for Patricia Wu-Murad
- Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning
- CliniDigest: A Case Study in Large Language Model Based Large-Scale Summarization of Clinical Trial Descriptions
- Patterns of Vehicle Lights: Addressing Complexities in Curation and Annotation of Camera-Based Vehicle Light Datasets and Metrics
- FocalErrorNet: Uncertainty-aware focal modulation network for inter-modal registration error estimation in ultrasound-guided neurosurgery
- The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers
- Bug Characterization in Machine Learning-based Systems
- Words That Stick: Predicting Decision Making and Synonym Engagement Using Cognitive Biases and Computational Linguistics
- Attention for Robot Touch: Tactile Saliency Prediction for Robust Sim-to-Real Tactile Control
- Improving Reliable Navigation under Uncertainty via Predictions Informed by Non-Local Information
- A Predictive Model of Digital Information Engagement: Forecasting User Engagement With English Words by Incorporating Cognitive Biases, Computational Linguistics and Natural Language Processing
- HUGE: Huge Unsupervised Graph Embeddings with TPUs
- SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpainting
- Technical note: ShinyAnimalCV: open-source cloud-based web application for object detection, segmentation, and three-dimensional visualization of animals using computer vision
- Role of Image Acquisition and Patient Phenotype Variations in Automatic Segmentation Model Generalization
- Restrictions on Physical Stochastic Reservoir Computers
- What Kinds of Contracts Do ML APIs Need?
- Single Channel Speech Enhancement Using U-Net Spiking Neural Networks
- MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
- Training Quantum Boltzmann Machines with Coresets
- Predictive Maintenance of Armoured Vehicles using Machine Learning Approaches
- VISPUR: Visual Aids for Identifying and Interpreting Spurious Associations in Data-Driven Decisions
- Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach
- Neural Schr"odinger Bridge with Sinkhorn Losses: Application to Data-driven Minimum Effort Control of Colloidal Self-assembly
- Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking
- Fixed Integral Neural Networks
- Phenotype-preserving metric design for high-content image reconstruction by generative inpainting
- ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography
- Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models
- Unsupervised Deep Learning-based Pansharpening with Jointly-Enhanced Spectral and Spatial Fidelity
- Non-Linear Self Augmentation Deep Pipeline for Cancer Treatment outcome Prediction
- A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot
- Learning to simulate partially known spatio-temporal dynamics with trainable difference operators
- Hypergraph Isomorphism Computation
- Human-centric Scene Understanding for 3D Large-scale Scenarios
- Coupled-Space Attacks against Random-Walk-based Anomaly Detection
- Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data
- HyperFed: Hyperbolic Prototypes Exploration with Consistent Aggregation for Non-IID Data in Federated Learning
- Virtual Mirrors: Non-Line-of-Sight Imaging Beyond the Third Bounce
- TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023
- MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation
- WavJourney: Compositional Audio Creation with Large Language Models
- Towards Generalist Biomedical AI
- Event-based Vision for Early Prediction of Manipulation Actions
- Visual Instruction Inversion: Image Editing via Visual Prompting
- Evaluating the Moral Beliefs Encoded in LLMs
- Reinforcement Learning by Guided Safe Exploration
- Comparative Analysis of Libraries for the Sentimental Analysis
- Automatically Evaluating Opinion Prevalence in Opinion Summarization
- A Constraint Enforcement Deep Reinforcement Learning Framework for Optimal Energy Storage Systems Dispatch
- ChatGPT and Persuasive Technologies for the Management and Delivery of Personalized Recommendations in Hotel Hospitality
- Unraveling the Complexity of Splitting Sequential Data: Tackling Challenges in Video and Time Series Analysis
- US & MRI Image Fusion Based on Markerless Skin Registration
- Emerging Statistical Machine Learning Techniques for Extreme Temperature Forecasting in U.S. Cities
- General Purpose Artificial Intelligence Systems (GPAIS): Properties, Definition, Taxonomy, Societal Implications and Responsible Governance
- Large-scale Fully-Unsupervised Re-Identification
- G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory
- Deepfake Image Generation for Improved Brain Tumor Segmentation
- Improving International Climate Policy via Mutually Conditional Binding Commitments
- Improving International Climate Policy via Mutually Conditional Binding Commitments
- Sparse Double Descent in Vision Transformers: real or phantom threat?
- A New Perspective on Evaluation Methods for Explainable Artificial Intelligence (XAI)
- Fluorescent Neuronal Cells v2: Multi-Task, Multi-Format Annotations for Deep Learning in Microscopy
- Defending Adversarial Patches via Joint Region Localizing and Inpainting
- DisguisOR: Holistic Face Anonymization for the Operating Room
All 200
- Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI)
- Evolving Multi-Objective Neural Network Controllers for Robot Swarms
- UnScientify: Detecting Scientific Uncertainty in Scholarly Full Text
- Sources of Opacity in Computer Systems: Towards a Comprehensive Taxonomy
- Computational Approaches for Traditional Chinese Painting: From the "Six Principles of Painting" Perspective
- Explore the possibility of advancing climate negotiations on the basis of regional trade organizations: A study based on RICE-N
- Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences
- Online Modeling and Monitoring of Dependent Processes under Resource Constraints
- AI and Education: An Investigation into the Use of ChatGPT for Systems Thinking
- Application of Random Forest and Support Vector Machine for Investigation of Pressure Filtration Performance, a Zinc Plant Filter Cake Modeling
- Efficient Learning of Discrete-Continuous Computation Graphs
- Unveiling Security, Privacy, and Ethical Concerns of ChatGPT
- ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation
- A comparison of machine learning surrogate models of street-scale flooding in Norfolk, Virginia
- Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks
- High-definition event frame generation using SoC FPGA devices
- Learning Disentangled Discrete Representations
- Toward Design of Synthetic Active Inference Agents by Mere Mortals
- LOIS: Looking Out of Instance Semantics for Visual Question Answering
- Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewards
- Developing and Evaluating Tiny to Medium-Sized Turkish BERT Models
- CIF-T: A Novel CIF-based Transducer Architecture for Automatic Speech Recognition
- Creative Birds: Self-Supervised Single-View 3D Style Transfer
- Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling
- Memory-Efficient Graph Convolutional Networks for Object Classification and Detection with Event Cameras
- Calculating the maximum number of maximum cliques for simple graphs
- A semantics-driven methodology for high-quality image annotation
- Leveraging Implicit Feedback from Deployment Data in Dialogue
- Periocular biometrics: databases, algorithms and directions
- GraphRNN Revisited: An Ablation Study and Extensions for Directed Acyclic Graphs
- Decoding ChatGPT: A Taxonomy of Existing Research, Current Challenges, and Possible Future Directions
- Actions Speak What You Want: Provably Sample-Efficient Reinforcement Learning of the Quantal Stackelberg Equilibrium from Strategic Feedbacks
- Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching
- PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions
- Dynamic Domain Discrepancy Adjustment for Active Multi-Domain Adaptation
- Machine Learning Applications In Healthcare: The State Of Knowledge and Future Directions
- Towards Establishing Systematic Classification Requirements for Automated Driving
- Open Image Content Disarm And Reconstruction
- Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation
- 3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability
- Controllable Guide-Space for Generalizable Face Forgery Detection
- Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems
- Consensus-Adaptive RANSAC
- Topological Inductive Bias fosters Multiple Instance Learning in Data-Scarce Scenarios
- Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
- Retinotopy Inspired Brain Encoding Model and the All-for-One Training Recipe
- One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration
- RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition
- ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution
- Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images
- Adaptive Frequency Filters As Efficient Global Token Mixers
- Learning Snippet-to-Motion Progression for Skeleton-based Human Motion Prediction
- Unsupervised extraction of local and global keywords from a single text
- Affective Natural Language Generation of Event Descriptions through Fine-grained Appraisal Conditions
- Fast algorithms for k-submodular maximization subject to a matroid constraint
- Take Your Pick: Enabling Effective Personalized Federated Learning within Low-dimensional Feature Space
- BovineTalk: Machine Learning for Vocalization Analysis of Dairy Cattle under Negative Affective States
- METAVerse: Meta-Learning Traversability Cost Map for Off-Road Navigation
- This is not correct! Negation-aware Evaluation of Language Generation Systems
- Hybrid Representation-Enhanced Sampling for Bayesian Active Learning in Musculoskeletal Segmentation of Lower Extremities
- Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Models
- Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models
- Controlling the Latent Space of GANs through Reinforcement Learning: A Case Study on Task-based Image-to-Image Translation
- Tracking Anything in High Quality
- Understanding Deep Neural Networks via Linear Separability of Hidden Layers
- Visual Prompt Flexible-Modal Face Anti-Spoofing
- Heterogeneous Embodied Multi-Agent Collaboration
- The Hidden Dance of Phonemes and Visage: Unveiling the Enigmatic Link between Phonemes and Facial Features
- Rethinking Voice-Face Correlation: A Geometry View
- Centroid-aware feature recalibration for cancer grading in pathology images
- Learning-based Control for PMSM Using Distributed Gaussian Processes with Optimal Aggregation Strategy
- Entropy Neural Estimation for Graph Contrastive Learning
- Topology-aware Robust Optimization for Out-of-distribution Generalization
- Improving Semi-Supervised Semantic Segmentation with Dual-Level Siamese Structure Network
- AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception
- Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception
- DFR-Net: Density Feature Refinement Network for Image Dehazing Utilizing Haze Density Difference
- EasyNet: An Easy Network for 3D Industrial Anomaly Detection
- trajdata: A Unified Interface to Multiple Human Trajectory Datasets
- GrammarGPT: Exploring Open-Source LLMs for Native Chinese Grammatical Error Correction with Supervised Fine-Tuning
- Stability of Multi-Agent Learning: Convergence in Network Games with Many Players
- Simulation-based Inference for Cardiovascular Models
- BayesDAG: Gradient-Based Posterior Inference for Causal Discovery
- Online learning in bandits with predicted context
- Embedding Democratic Values into Social Media AIs via Societal Objective Functions
- Graph Neural Networks-based Hybrid Framework For Predicting Particle Crushing Strength
- Robustness Verification of Deep Neural Networks using Star-Based Reachability Analysis with Variable-Length Time Series Input
- Corruption-Robust Lipschitz Contextual Search
- YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems
- FinTree: Financial Dataset Pretrain Transformer Encoder for Relation Extraction
- Regularizing Neural Networks with Meta-Learning Generative Models
- AViT: Adapting Vision Transformers for Small Skin Lesion Segmentation Datasets
- AI4GCC - Team: Below Sea Level: Critiques and Improvements
- Dynamic Grouping for Climate Change Negotiation: Facilitating Cooperation and Balancing Interests through Effective Strategies
- AI4GCC-Team -- Below Sea Level: Score and Real World Relevance
- Dynamic Grouping for Climate Change Negotiation: Facilitating Cooperation and Balancing Interests through Effective Strategies
- Characterizing Data Point Vulnerability via Average-Case Robustness
- ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
- Number Theoretic Accelerated Learning of Physics-Informed Neural Networks
- Learning sources of variability from high-dimensional observational studies