Papers
Wed 28 Jun 2023
207 papers
- On the Exploitability of Instruction TuningLLM safety and security → Backdoor and data poisoning attacks
- PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image EditingDiffusion models → Image generation, text-to-image and editing
- On Practical Aspects of Aggregation Defenses against Data Poisoning AttacksLLM safety and security → Backdoor and data poisoning attacks
- DiffComplete: Diffusion-based Generative 3D Shape CompletionDiffusion models → 3D, point cloud and scene generation
- DoseDiff: Distance-aware Diffusion Model for Dose Prediction in RadiotherapyDiffusion models → Medical imaging and segmentation
- Inferring the Goals of Communicating Agents from Actions and InstructionsLLM agents and tool use → General LLM agent frameworks and benchmarks
- Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts ArchitectureLLM agents and tool use → Social simulation and multi-agent debate +1
- UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed DataDiffusion models → Audio, speech and music
- SVNR: Spatially-variant Noise Removal with Denoising DiffusionDiffusion models → Diffusion foundations and sampling
- Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and SpecificityMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial UltrasoundLLM safety and security → Audio jailbreaks and speech backdoors
- Accelerating Transducers through Adjacent Token MergingEfficient LLM inference and serving → Audio and omni-modal token compression
- A Dimensional Structure based Knowledge Distillation Method for Cross-Modal LearningKnowledge distillation → Multimodal distillation
- Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving
- Fake the Real: Backdoor Attack on Deep Speech Classification via Voice ConversionLLM safety and security → Audio jailbreaks and speech backdoors
- Evaluation of Reinforcement Learning Techniques for Trading on a Diverse Portfolio
- HIVA: Holographic Intellectual Voice Assistant
- Neural network analysis of neutron and X-ray reflectivity data: Incorporating prior knowledge for tackling the phase problem
- VisText: A Benchmark for Semantically Rich Chart Captioning
- Recommender Systems for Online and Mobile Social Networks: A survey
- Confidence Ranking for CTR Prediction
- EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech
- Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection
- An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs
- Autoregressive with Slack Time Series Model for Forecasting a Partially-Observed Dynamical Time Series
- SeMLaPS: Real-time Semantic Mapping with Latent Prior Networks and Quasi-Planar Segmentation
- Does Saliency-Based Training bring Robustness for Deep Neural Networks in Image Classification?
- Allocating Divisible Resources on Arms with Unknown and Random Rewards
- Finite-Sample Symmetric Mean Estimation with Fisher Information Rate
- Causal inference for the expected number of recurrent events in the presence of a terminal event
- Pareto Optimal Learning for Estimating Large Language Model Errors
- Feature Selection: A perspective on inter-attribute cooperation
- Non-Convex Optimizations for Machine Learning with Theoretical Guarantee: Robust Matrix Completion and Neural Network Learning
- Inter-Rater Uncertainty Quantification in Medical Image Segmentation via Rater-Specific Bayesian Neural Networks
- Learning Fair Classifiers via Min-Max F-divergence Regularization
- Analysis of LiDAR Configurations on Off-road Semantic Segmentation Performance
- UTOPIA: Universally Trainable Optimal Prediction Intervals Aggregation
- Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023
- Multi-Scale Deformable Alignment and Content-Adaptive Inference for Flexible-Rate Bi-Directional Video Compression
- Envisioning a Next Generation Extended Reality Conferencing System with Efficient Photorealistic Human Rendering
- A systematic study of the foreground-background imbalance problem in deep learning for object detection
- CLANet: A Comprehensive Framework for Cross-Batch Cell Line Identification Using Brightfield Images
- ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models
- Prediction of Rapid Early Progression and Survival Risk with Pre-Radiation MRI in WHO Grade 4 Glioma Patients
- Hyena Neural Operator for Partial Differential Equations
- Dimension-Independent Kernel ε-Covers
- Momentum Benefits Non-IID Federated Learning Simply and Provably
- SARC: Soft Actor Retrospective Critic
- Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements
- Event Detection from Social Media Stream: Methods, Datasets and Opportunities
- Towards a Better Theoretical Understanding of Independent Subnetwork Training
- DenseBAM-GI: Attention Augmented DeneseNet with momentum aided GRU for HMER
- Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering
- Increasing Performance And Sample Efficiency With Model-agnostic Interactive Feature Attributions
- DNA-TEQ: An Adaptive Exponential Quantization of Tensors for DNN Inference
- Complex-valued Adaptive System Identification via Low-Rank Tensor Decomposition
- MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning
- Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language
- Efficient and Multiply Robust Risk Estimation under General Forms of Dataset Shift
- Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes
- Towards Measuring the Representation of Subjective Global Opinions in Language Models
- Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses
- Spatiotemporal Besov Priors for Bayesian Inverse Problems
- Lagrangian based A* algorithm for automated reasoning
- Multi-Site Clinical Federated Learning using Recursive and Attentive Models and NVFlare
- Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
- Theater Aid System for the Visually Impaired Through Transfer Learning of Spatio-Temporal Graph Convolution Networks
- cuSLINK: Single-linkage Agglomerative Clustering on the GPU
- Information-Computation Tradeoffs for Learning Margin Halfspaces with Random Classification Noise
- Emulating the dynamics of complex systems using autoregressive models on manifolds (mNARX)
- On the Identifiability of Quantized Factors
- Representation Learning via Variational Bayesian Networks
- Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models
- An Adversarial Multi-Task Learning Method for Chinese Text Correction with Semantic Detection
- Gaussian random field approximation via Stein's method with applications to wide random neural networks
- Point2Point : A Framework for Efficient Deep Learning on Hilbert sorted Point Clouds with applications in Spatio-Temporal Occupancy Prediction
- Social World Knowledge: Modeling and Applications
- A Meta-Learning Method for Estimation of Causal Excursion Effects to Assess Time-Varying Moderation
- Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruning
- Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many Synthesis
- Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting
- S2SNet: A Pretrained Neural Network for Superconductivity Discovery
- RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model
- Emotion Analysis of Tweets Banning Education in Afghanistan
- Deep Unfolded Simulated Bifurcation for Massive MIMO Signal Detection
- Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery
- Latent SDEs on Homogeneous Spaces
- CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models
- Continuous-time q-learning for mean-field control problems
- Towards a Better Understanding of Learning with Multiagent Teams
- Low-Confidence Samples Mining for Semi-supervised Object Detection
- Multi-IMU with Online Self-Consistency for Freehand 3D Ultrasound Reconstruction
- Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation
- Effective Transfer of Pretrained Large Visual Model for Fabric Defect Segmentation via Specifc Knowledge Injection
- Learning to Pan-sharpening with Memories of Spatial Details
- Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification
- Defining data science: a new field of inquiry
- SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills
- C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection
All 207
- A systematic literature review on source code similarity measurement and clone detection: techniques, applications, and challenges
- Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation
- Recent Advances in Optimal Transport for Machine Learning
- Generative User-Experience Research for Developing Domain-specific Natural Language Processing Applications
- Neural directional distance field object representation for uni-directional path-traced rendering
- Training Deep Surrogate Models with Large Scale Online Learning
- High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error Refinement
- Distributional Modeling for Location-Aware Adversarial Patches
- MLSMM: Machine Learning Security Maturity Model
- More efficient manual review of automatically transcribed tabular data
- A Framework for Identifying Depression on Social Media: MentalRiskES@IberLEF 2023
- Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination Methods
- Real-World Performance of Autonomously Reporting Normal Chest Radiographs in NHS Trusts Using a Deep-Learning Algorithm on the GP Pathway
- Time Regularization in Optimal Time Variable Learning
- Fast Marching Energy CNN
- Is ChatGPT a Biomedical Expert? -- Exploring the Zero-Shot Performance of Current GPT Models in Biomedical Tasks
- 1M parameters are enough? A lightweight CNN-based model for medical image segmentation
- Chan-Vese Attention U-Net: An attention mechanism for robust segmentation
- Sparse Representations, Inference and Learning
- Empirical Loss Landscape Analysis of Neural Network Activation Functions
- Mastering Nordschleife -- A comprehensive race simulation for AI strategy decision-making in motorsports
- Lifelong Change Detection: Continuous Domain Adaptation for Small Object Change Detection in Every Robot Navigation
- Mass Spectra Prediction with Structural Motif-based Graph Neural Networks
- A serial dual-channel library occupancy detection system based on Faster RCNN
- Secure and Fast Asynchronous Vertical Federated Learning via Cascaded Hybrid Optimization
- Long-term Conversation Analysis: Exploring Utility and Privacy
- Federated Generative Learning with Foundation Models
- MRHER: Model-based Relay Hindsight Experience Replay for Sequential Object Manipulation Tasks with Sparse Rewards
- Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing
- DUET: 2D Structured and Approximately Equivariant Representations
- Improving Primate Sounds Classification using Binary Presorting for Deep Learning
- Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
- What Sentiment and Fun Facts We Learnt Before FIFA World Cup Qatar 2022 Using Twitter and AI
- OpenNDD: Open Set Recognition for Neurodevelopmental Disorders Detection
- A Cascaded Approach for ultraly High Performance Lesion Detection and False Positive Removal in Liver CT Scans
- Stone Needle: A General Multimodal Large-scale Model Framework towards Healthcare
- Exploring Spatial-Temporal Variations of Public Discourse on Social Media: A Case Study on the First Wave of the Coronavirus Pandemic in Italy
- Lightweight Modeling of User Context Combining Physical and Virtual Sensor Data
- Exponential separations between classical and quantum learners
- A Distributed Computation Model Based on Federated Learning Integrates Heterogeneous models and Consortium Blockchain for Solving Time-Varying Problems
- Structure in Deep Reinforcement Learning: A Survey and Open Problems
- Points for Energy Renovation (PointER): A LiDAR-Derived Point Cloud Dataset of One Million English Buildings Linked to Energy Characteristics
- Fast Recognition of birds in offshore wind farms based on an improved deep learning model
- Positive Label Is All You Need for Multi-Label Classification
- BayesFlow: Amortized Bayesian Workflows With Neural Networks
- Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition
- Query Understanding in the Age of Large Language Models
- Text-driven Talking Face Synthesis by Reprogramming Audio-driven Models
- Streamlining Social Media Information Retrieval for COVID-19 Research with Deep Learning
- Systematic analysis of the impact of label noise correction on ML Fairness
- MyDigitalFootprint: an extensive context dataset for pervasive computing applications at the edge
- Tensorformer: Normalized Matrix Attention Transformer for High-quality Point Cloud Reconstruction
- AFPN: Asymptotic Feature Pyramid Network for Object Detection
- Sentence-to-Label Generation Framework for Multi-task Learning of Japanese Sentence Classification and Named Entity Recognition
- Reconstructing the Hemodynamic Response Function via a Bimodal Transformer
- Separable Physics-Informed Neural Networks
- Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications
- Understanding Prompt Tuning for V-L Models Through the Lens of Neural Collapse
- Angle Sensitive Pixels for Lensless Imaging on Spherical Sensors
- Reduce Computational Complexity for Convolutional Layers by Skipping Zeros
- Knowledge-Enhanced Hierarchical Information Correlation Learning for Multi-Modal Rumor Detection
- Pb-Hash: Partitioned b-bit Hashing
- No Transfers Required: Integrating Last Mile with Public Transit Using Opti-Mile
- Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction
- Interpretable Anomaly Detection in Cellular Networks by Learning Concepts in Variational Autoencoders
- Curious Replay for Model-based Adaptation
- You Can Generate It Again: Data-to-Text Generation with Verification and Correction Prompting
- NIPD: A Federated Learning Person Detection Benchmark Based on Real-World Non-IID Data
- Boosting Adversarial Transferability with Learnable Patch-wise Masks
- Multi-network Contrastive Learning Based on Global and Local Representations
- Reducing Redundant Work in Jump Point Search
- Learning Dynamic Graphs from All Contextual Information for Accurate Point-of-Interest Visit Forecasting
- Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio
- Subclass-balancing Contrastive Learning for Long-tailed Recognition
- The Parametric Complexity of Operator Learning
- Fine-grained 3D object recognition: an approach and experiments
- On information captured by neural networks: connections with memorization and generalization
- Confidence-Calibrated Ensemble Dense Phrase Retrieval
- Transfer Learning with Random Coefficient Ridge Regression
- The 2nd Place Solution for 2023 Waymo Open Sim Agents Challenge
- DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces
- Incremental Learning on Food Instance Segmentation
- RL3: Boosting Meta Reinforcement Learning via RL inside RL2
- Deep Learning Models for Flood Predictions in South Florida
- Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering
- Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs
- Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization
- Pseudo-Labeling Enhanced by Privileged Information and Its Application to In Situ Sequencing Images
- Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias
- Capturing the Diffusive Behavior of the Multiscale Linear Transport Equations by Asymptotic-Preserving Convolutional DeepONets
- A Unified View of Deep Learning for Reaction and Retrosynthesis Prediction: Current Status and Future Challenges
- Beyond the Hype: Assessing the Performance, Trustworthiness, and Clinical Suitability of GPT3.5
- Sequential Attention Source Identification Based on Feature Representation
- Toward Real Flare Removal: A Comprehensive Pipeline and A New Benchmark
- Blockwise Feature Interaction in Recommendation Systems
- Towards Open Vocabulary Learning: A Survey
- Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners
- Discovering stochastic partial differential equations from limited data using variational Bayes inference
- Let Segment Anything Help Image Dehaze
- GraSS: Contrastive Learning with Gradient Guided Sampling Strategy for Remote Sensing Image Semantic Segmentation
- Differentially Private Distributed Estimation and Learning
- Hierarchical Graph Neural Networks for Proprioceptive 6D Pose Estimation of In-hand Objects
- Pure exploration in multi-armed bandits with low rank structure using oblivious sampler
- GoalieNet: A Multi-Stage Network for Joint Goalie, Equipment, and Net Pose Estimation in Ice Hockey
- Action-conditioned Deep Visual Prediction with RoAM, a new Indoor Human Motion Dataset for Autonomous Robots
- SpotEM: Efficient Video Search for Episodic Memory
- Ordering for Non-Replacement SGD