Papers
Tue 4 Jul 2023
183 papers
- Garbage in, garbage out: Zero-shot detection of crime using Large Language ModelsLLM reasoning → Chain-of-thought reasoning for driving
- Collaborative Score Distillation for Consistent Visual SynthesisDiffusion models → Image generation, text-to-image and editing
- Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning AttacksLLM safety and security → Federated unlearning and poisoning
- Math Agents: Computational Infrastructure, Mathematical Embedding, and GenomicsLLM agents and tool use → Educational agents and math problem solving
- mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document UnderstandingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDiffusion models → Diffusion foundations and sampling
- Robots That Ask For Help: Uncertainty Alignment for Large Language Model PlannersLLM reasoning → Spatial and embodied reasoning +1
- ProtoDiffusion: Classifier-Free Diffusion Guidance with Prototype LearningDiffusion models → Diffusion foundations and sampling
- KDSTM: Neural Semi-supervised Topic Modeling with Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
- Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised LearningDiffusion models → Diffusion and flow policies for robotics +1
- DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape GenerationDiffusion models → 3D, point cloud and scene generation
- The Inner Sentiments of a ThoughtLLM reasoning → Audio-language model reasoning
- Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic dataLLM safety and security → Membership inference attacks
- SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph GenerationDiffusion models → Flow matching, time series and science
- Insert-expansions for Tool-enabled Conversational AgentsLLM reasoning → Reasoning benchmarks and evaluation +1
- Chain of Thought Prompting Elicits Knowledge AugmentationLLM reasoning → Prompting and chain-of-thought reasoning
- Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident PredictionLLM safety and security → Membership inference attacks
- Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion RepresentationsDiffusion models → Flow matching, time series and science
- FB-OCC: 3D Occupancy Prediction based on Forward-Backward View TransformationEnd-to-end autonomous driving → Generative simulation for driving
- Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RLDiffusion models → Diffusion and flow policies for robotics +1
- Diverse Retrieval-Augmented In-Context Learning for Dialogue State TrackingRetrieval-augmented generation → Conversational and speech RAG
- A Bibliographic Study on Artificial Intelligence Research: Global Panorama and Indian Appearance
- Strictly Low Rank Constraint Optimization -- An Asymptotically O(frac1t2) Method
- Human Emotion Recognition Based On Galvanic Skin Response signal Feature Selection and SVM
- Multi-Task Learning to Enhance Generalizability of Neural Network Equalizers in Coherent Optical Systems
- SleepEGAN: A GAN-enhanced Ensemble Deep Learning Model for Imbalanced Classification of Sleep Stages
- Decoding the Popularity of TV Series: A Network Analysis Perspective
- A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation
- Transcribing Educational Videos Using Whisper: A preliminary study on using AI for transcribing educational videos
- A multilevel framework for AI governance
- Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review
- Generalization Guarantees via Algorithm-dependent Rademacher Complexity
- Interpretable Computer Vision Models through Adversarial Training: Unveiling the Robustness-Interpretability Connection
- Multi-gauge Hydrological Variational Data Assimilation: Regionalization Learning with Spatial Gradients using Multilayer Perceptron and Bayesian-Guided Multivariate Regression
- Learning to reconstruct the bubble distribution with conductivity maps using Invertible Neural Networks and Error Diffusion
- Anomaly detection in image or latent space of patch-based auto-encoders for industrial image analysis
- FREEDOM: Target Label & Source Data & Domain Information-Free Multi-Source Domain Adaptation for Unsupervised Personalization
- TablEye: Seeing small Tables through the Lens of Images
- Hybrid Neural Diffeomorphic Flow for Shape Representation and Generation via Triplane
- Algorithme EM r'egularis'e
- FEMDA: Une m'ethode de classification robuste et flexible
- Toward more frugal models for functional cerebral networks automatic recognition with resting-state fMRI
- A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks
- Causal Video Summarizer for Video Exploration
- ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization
- Query-based Video Summarization with Pseudo Label Supervision
- Text + Sketch: Image Compression at Ultra Low Rates
- Physics-based Motion Retargeting from Sparse Inputs
- A Neural Network-Based Enrichment of Reproducing Kernel Approximation for Modeling Brittle Fracture
- Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs
- Integrating Random Forests and Generalized Linear Models for Improved Accuracy and Interpretability
- Learning ECG Signal Features Without Backpropagation Using Linear Laws
- Stranding Risk for Underactuated Vessels in Complex Ocean Currents: Analysis and Controllers
- Maximizing Seaweed Growth on Autonomous Farms: A Dynamic Programming Approach for Underactuated Systems Navigating on Uncertain Ocean Currents
- ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling
- Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers
- Transformed Protoform Reconstruction
- EANet: Enhanced Attribute-based RGBT Tracker Network
- ProPILE: Probing Privacy Leakage in Large Language Models
- Stability Analysis Framework for Particle-based Distance GANs with Wasserstein Gradient Flow
- Fast Private Kernel Density Estimation via Locality Sensitive Quantization
- Approximate, Adapt, Anonymize (3A): a Framework for Privacy Preserving Training Data Release for Machine Learning
- A hybrid machine learning framework for clad characteristics prediction in metal additive manufacturing
- Exploring Non-Verbal Predicates in Semantic Role Labeling: Challenges and Opportunities
- MaskBEV: Joint Object Detection and Footprint Completion for Bird's-eye View 3D Point Clouds
- Self-Consuming Generative Models Go MAD
- Embodied Task Planning with Large Language Models
- Grad-FEC: Unequal Loss Protection of Deep Features in Collaborative Intelligence
- Deep Features for Contactless Fingerprint Presentation Attack Detection: Can They Be Generalized?
- Advancing Wound Filling Extraction on 3D Faces: Auto-Segmentation and Wound Face Regeneration Approach
- Empirical Sample Complexity of Neural Network Mixed State Reconstruction
- EdgeFace: Efficient Face Recognition Model for Edge Devices
- On the Matrix Form of the Quaternion Fourier Transform and Quaternion Convolution
- Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses
- Human Trajectory Forecasting with Explainable Behavioral Uncertainty
- Structural Balance and Random Walks on Complex Networks with Complex Weights
- SUIT: Learning Significance-guided Information for 3D Temporal Detection
- DeepFlorist: Rethinking Deep Neural Networks and Ensemble Learning as A Meta-Classifier For Object Classification
- Capturing Local Temperature Evolution during Additive Manufacturing through Fourier Neural Operators
- Edge-aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRI
- GHOST: A Graph Neural Network Accelerator using Silicon Photonics
- FedHIL: Heterogeneity Resilient Federated Learning for Robust Indoor Localization with Mobile Devices
- Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling
- Shapley Sets: Feature Attribution via Recursive Function Decomposition
- Fast Optimal Transport through Sliced Wasserstein Generalized Geodesics
- Localized Data Work as a Precondition for Data-Centric ML: A Case Study of Full Lifecycle Crop Disease Identification in Ghana
- Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data
- Pretraining is All You Need: A Multi-Atlas Enhanced Transformer Framework for Autism Spectrum Disorder Classification
- K-complex Detection Using Fourier Spectrum Analysis In EEG
- Local primordial non-Gaussianity from the large-scale clustering of photometric DESI luminous red galaxies
- SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detection
- Ben-ge: Extending BigEarthNet with Geographical and Environmental Data
- Synchronous Image-Label Diffusion Probability Model with Application to Stroke Lesion Segmentation on Non-contrast CT
- Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis
- RRCNN: A novel signal decomposition approach based on recurrent residue convolutional neural network
- MOPO-LSI: A User Guide
- On the Constrained Time-Series Generation Problem
- Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
- Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting
- Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning
All 183
- Graph-Ensemble Learning Model for Multi-label Skin Lesion Classification using Dermoscopy and Clinical Images
- Learning to Augment: Hallucinating Data for Domain Generalized Segmentation
- Spike-driven Transformer
- Racial Bias Trends in the Text of US Legal Opinions
- Online Learning and Solving Infinite Games with an ERM Oracle
- Serving Graph Neural Networks With Distributed Fog Servers For Smart IoT Services
- Learning Discrete Weights and Activations Using the Local Reparameterization Trick
- Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation
- RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Games
- Disentanglement in a GAN for Unconditional Speech Synthesis
- Boosting Norwegian Automatic Speech Recognition
- Training Energy-Based Models with Diffusion Contrastive Divergences
- Sensors and Systems for Monitoring Mental Fatigue: A systematic review
- Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues
- Exploring Transformers for On-Line Handwritten Signature Verification
- Task Planning Support for Arborists and Foresters: Comparing Deep Learning Approaches for Tree Inventory and Tree Vitality Assessment Based on UAV-Data
- Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
- In-Domain Self-Supervised Learning Improves Remote Sensing Image Scene Classification
- Heuristic Algorithms for the Approximation of Mutual Coherence
- Random Walk on Multiple Networks
- HAGNN: Hybrid Aggregation for Heterogeneous Graph Neural Networks
- ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour
- Renewable energy management in smart home environment via forecast embedded scheduling based on Recurrent Trend Predictive Neural Network
- SageFormer: Series-Aware Framework for Long-term Multivariate Time Series Forecasting
- A Language Model for Grammatical Error Correction in L2 Russian
- Prototypes as Explanation for Time Series Anomaly Detection
- A Scalable Reinforcement Learning-based System Using On-Chain Data for Cryptocurrency Portfolio Management
- Unlocking the Potential of Deep Learning in Peak-Hour Series Forecasting
- Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases
- Cross-Element Combinatorial Selection for Multi-Element Creative in Display Advertising
- Learning Lie Group Symmetry Transformations with Neural Networks
- IAdet: Simplest human-in-the-loop object detection
- Optimal and Efficient Binary Questioning for Human-in-the-Loop Annotation
- Conceptual Cognitive Maps Formation with Neural Successor Networks and Word Embeddings
- Machine Learning-Based Intrusion Detection: Feature Selection versus Feature Extraction
- Last layer state space model for representation learning and uncertainty quantification
- Approximate information for efficient exploration-exploitation strategies
- Secure Deep Learning-based Distributed Intelligence on Pocket-sized Drones
- Scalable variable selection for two-view learning tasks with projection operators
- Separated RoadTopoFormer
- Knowledge Graph for NLG in the context of conversational agents
- EffSeg: Efficient Fine-Grained Instance Segmentation using Structure-Preserving Sparsity
- Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation
- Learning to Prompt in the Classroom to Understand AI Limits: A pilot study
- Analyzing Intentional Behavior in Autonomous Agents under Uncertainty
- Tomato Maturity Recognition with Convolutional Transformers
- Exploiting Richness of Learned Compressed Representation of Images for Semantic Segmentation
- LEAT: Towards Robust Deepfake Disruption in Real-World Scenarios via Latent Ensemble Attack
- Deep Attention Q-Network for Personalized Treatment Recommendation
- LPN: Language-guided Prototypical Network for few-shot classification
- SelfFed: Self-Supervised Federated Learning for Data Heterogeneity and Label Scarcity in Medical Images
- Relation-aware graph structure embedding with co-contrastive learning for drug-drug interaction prediction
- All in One: Multi-task Prompting for Graph Neural Networks
- On Evaluating and Mitigating Gender Biases in Multilingual Settings
- Clinical application of HEDI for biomechanical evaluation and visualisation in incisional hernia repair
- Accelerated stochastic approximation with state-dependent noise
- Review of Deep Learning-based Malware Detection for Android and Windows System
- Semantic Segmentation on 3D Point Clouds with High Density Variations
- SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classification
- H-DenseFormer: An Efficient Hybrid Densely Connected Transformer for Multimodal Tumor Segmentation
- Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale
- Mitigating Bias: Enhancing Image Classification by Improving Model Explanations
- A Review of Driver Gaze Estimation and Application in Gaze Behavior Understanding
- Generating Animatable 3D Cartoon Faces from Single Portraits
- Technical Report for Ego4D Long Term Action Anticipation Challenge 2023
- AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation
- Unsupervised Quality Prediction for Improved Single-Frame and Weighted Sequential Visual Place Recognition
- Practical Collaborative Perception: A Framework for Asynchronous and Multi-Agent 3D Object Detection
- CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care
- Causal Reinforcement Learning: A Survey
- A Double Machine Learning Approach to Combining Experimental and Observational Data
- ReactIE: Enhancing Chemical Reaction Extraction with Weak Supervision
- Learning Feature Matching via Matchable Keypoint-Assisted Graph Neural Network
- On Conditional and Compositional Language Model Differentiable Prompting
- Learning to Branch in Combinatorial Optimization with Graph Pointer Networks
- Continual Learning in Open-vocabulary Classification with Complementary Memory Systems
- Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios
- DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
- Consistent Multimodal Generation via A Unified GAN Framework
- Generative Flow Networks: a Markov Chain Perspective
- Unsupervised Feature Learning with Emergent Data-Driven Prototypicality
- Modeling Tag Prediction based on Question Tagging Behavior Analysis of CommunityQA Platform Users
- Free energy of Bayesian Convolutional Neural Network with Skip Connection