Papers
Thu 10 Aug 2023
170 papers
- AudioLDM 2: Learning Holistic Audio Generation with Self-supervised PretrainingDiffusion models → Audio, speech and music
- PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE SolversDiffusion models → Flow matching, time series and science
- Exploring the Potential of World Models for Anomaly Detection in Autonomous DrivingWorld models → World models for autonomous driving +1
- A Preliminary Study of the Intrinsic Relationship between Complexity and AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Masked Diffusion as Self-supervised Representation LearnerDiffusion models → Medical imaging and segmentation
- Proximal Policy Optimization Actual Combat: Manipulating Output Tokenizer LengthLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Generative Diffusion Models for Radio Wireless Channel Modelling and SamplingDiffusion models → Diffusion for compression and wireless
- Enhancing Trust in LLM-Based AI Automation Agents: New Considerations and Future ChallengesLLM agents and tool use → General LLM agent frameworks and benchmarks
- Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network OptimizationDiffusion models → Diffusion for compression and wireless
- Towards General and Fast Video Derain via Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Aviation Safety Risk Analysis and Flight Technology Assessment Issues
- Commodities Trading through Deep Policy Gradient Methods
- Addressing Data Scarcity in Optical Matrix Multiplier Modeling Using Transfer Learning
- CSPM: A Contrastive Spatiotemporal Preference Model for CTR Prediction in On-Demand Food Delivery Services
- Comprehensive Analysis of Network Robustness Evaluation Based on Convolutional Neural Networks with Spatial Pyramid Pooling
- Existential Notation3 Logic
- Are We Closing the Loop Yet? Gaps in the Generalizability of VIS4ML Research
- Spatial Pathomics Toolkit for Quantitative Analysis of Podocyte Nuclei with Histology and Spatial Transcriptomics Data in Renal Pathology
- GPLaSDI: Gaussian Process-based Interpretable Latent Space Dynamics Identification through Deep Autoencoder
- Aphid Cluster Recognition and Detection in the Wild Using Deep Learning Models
- Composable Core-sets for Diversity Approximation on Multi-Dataset Streams
- Revisiting N-CNN for Clinical Practice
- Vision Backbone Enhancement via Multi-Stage Cross-Scale Attention
- UFed-GAN: A Secure Federated Learning Framework with Constrained Computation and Unlabeled Data
- Shared Memory-contention-aware Concurrent DNN Execution for Diversely Heterogeneous System-on-Chips
- Using Twitter Data to Determine Hurricane Category: An Experiment
- The Multi-modality Cell Segmentation Challenge: Towards Universal Solutions
- Unleashing the Strengths of Unlabeled Data in Pan-cancer Abdominal Organ Quantification: the FLARE22 Challenge
- Knowledge Propagation over Conditional Independence Graphs
- SegDA: Maximum Separable Segment Mask with Pseudo Labels for Domain Adaptive Semantic Segmentation
- Seed Kernel Counting using Domain Randomization and Object Tracking Neural Networks
- GaborPINN: Efficient physics informed neural networks using multiplicative filtered networks
- FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attacks
- DiLogics: Creating Web Automation Programs With Diverse Logics
- Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception
- Recognizing Handwritten Mathematical Expressions of Vertical Addition and Subtraction
- Absorption-Based, Passive Range Imaging from Hyperspectral Thermal Measurements
- Spintronics for image recognition: performance benchmarking via data-driven simulations
- Temporally-Adaptive Models for Efficient Video Understanding
- Leverage Weakly Annotation to Pixel-wise Annotation via Zero-shot Segment Anything Model for Molecular-empowered Learning
- High-performance Data Management for Whole Slide Image Analysis in Digital Pathology
- Multi-scale Multi-site Renal Microvascular Structures Segmentation for Whole Slide Imaging in Renal Pathology
- Optical Script Identification for multi-lingual Indic-script
- Fine-Grained Self-Supervised Learning with Jigsaw Puzzles for Medical Image Classification
- Iterative Reweighted Least Squares Networks With Convergence Guarantees for Solving Inverse Imaging Problems
- PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs
- Neural Progressive Meshes
- Zero Grads: Learning Local Surrogate Losses for Non-Differentiable Graphics
- Follow Anything: Open-set detection, tracking, and following in real-time
- MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
- FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models
- The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Review
- EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
- Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions
- DeGMix: Efficient Multi-Task Dense Prediction with Deformable and Gating Mixer
- Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems
- A Comparison of Classical and Deep Reinforcement Learning Methods for HVAC Control
- Shadow Datasets, New challenging datasets for Causal Representation Learning
- SSLRec: A Self-Supervised Learning Framework for Recommendation
- Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient
- Breaking Language Barriers with MMTweets: Advancing Cross-Lingual Debunked Narrative Retrieval for Fact-Checking
- 2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds
- Exploring Deep Learning Approaches to Predict Person and Vehicle Trips: An Analysis of NHTS Data
- AD-CLIP: Adapting Domains in Prompt Space Using CLIP
- Automatic Extraction of Relevant Road Infrastructure using Connected vehicle data and Deep Learning Model
- Attention-based 3D CNN with Multi-layer Features for Alzheimer's Disease Diagnosis using Brain Images
- Counterfactual Cross-modality Reasoning for Weakly Supervised Video Moment Localization
- AST-MHSA : Code Summarization using Multi-Head Self-Attention
- A Comparative Visual Analytics Framework for Evaluating Evolutionary Processes in Multi-objective Optimization
- IIHT: Medical Report Generation with Image-to-Indicator Hierarchical Transformer
- Inhibitor Transformers and Gated RNNs for Torus Efficient Fully Homomorphic Encryption
- Normalized Gradients for All
- Updating Clinical Risk Stratification Models Using Rank-Based Compatibility: Approaches for Evaluating and Optimizing Clinician-Model Team Performance
- A Neural Network Based Choice Model for Assortment Optimization
- A Smart Robotic System for Industrial Plant Supervision
- LASIGE and UNICAGE solution to the NASA LitCoin NLP Competition
- Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network
- Object Goal Navigation with Recursive Implicit Maps
- Multi-graph Spatio-temporal Graph Convolutional Network for Traffic Flow Prediction
- NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search
- You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
- Test-Time Selection for Robust Skin Lesion Analysis
- Category Feature Transformer for Semantic Segmentation
- Do Language Models' Words Refer?
- Symmetry Defense Against XGBoost Adversarial Perturbation Attacks
- Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages
- C5: Towards Better Conversation Comprehension and Contextual Continuity for ChatGPT
- AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecasting
- Large Skew-t Copula Models and Asymmetric Dependence in Intraday Equity Returns
- Recent Advancements In The Field Of Deepfake Detection
- Cross-Domain Product Representation Learning for Rich-Content E-Commerce
- Learning (With) Distributed Optimization
- Enhancing AUV Autonomy With Model Predictive Path Integral Control
- Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurring
- Robust Asymmetric Loss for Multi-Label Long-Tailed Learning
- Is there progress in activity progress prediction?
- Robustifying Point Cloud Networks by Refocusing
- Models Matter: The Impact of Single-Step Retrosynthesis on Synthesis Planning
- Mono-hydra: Real-time 3D scene graph construction from monocular camera input with IMU
- On the Optimal Expressive Power of ReLU DNNs and Its Application in Approximation with Kolmogorov Superposition Theorem
All 170
- Multi-domain Recommendation with Embedding Disentangling and Domain Alignment
- EFX Allocations Exist for Binary Valuations
- Bringing order into the realm of Transformer-based language models for artificial intelligence and law
- More Than Meets the Eye: Analyzing Anesthesiologists' Visual Attention in the Operating Room Using Deep Learning Models
- Exploring XAI for the Arts: Explaining Latent Space in Generative Music
- Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation
- Quality Diversity under Sparse Reward and Sparse Interaction: Application to Grasping in Robotics
- LLM As DBA
- YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection
- Reviewing 3D Object Detectors in the Context of High-Resolution 3+1D Radar
- Exploring Machine Learning and Transformer-based Approaches for Deceptive Text Classification: A Comparative Analysis
- Spatio-Temporal Encoding of Brain Dynamics with Surface Masked Autoencoders
- Provably Efficient Algorithm for Nonstationary Low-Rank MDPs
- G2Pxy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns
- KS-APR: Keyframe Selection for Robust Absolute Pose Regression
- A Forecaster's Review of Judea Pearl's Causality: Models, Reasoning and Inference, Second Edition, 2009
- Transforming Breast Cancer Diagnosis: Towards Real-Time Ultrasound to Mammogram Conversion for Cost-Effective Diagnosis
- A Generalized Physical-knowledge-guided Dynamic Model for Underwater Image Enhancement
- Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation
- Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimation
- Ensemble Modeling for Multimodal Visual Action Recognition
- Speech-Driven 3D Face Animation with Composite and Regional Facial Movements
- Adaptive Low Rank Adaptation of Segment Anything to Salient Object Detection
- TSLiNGAM: DirectLiNGAM under heavy tails
- Progressive Spatio-temporal Perception for Audio-Visual Question Answering
- Unifying Distributionally Robust Optimization via Optimal Transport Theory
- Explainable AI applications in the Medical Domain: a systematic review
- SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data
- A Comparative Assessment of Multi-view fusion learning for Crop Classification
- Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network
- Learning Gabor Texture Features for Fine-Grained Recognition
- Robust Localization with Visual-Inertial Odometry Constraints for Markerless Mobile AR
- Product Review Image Ranking for Fashion E-commerce
- HGDNet: A Height-Hierarchy Guided Dual-Decoder Network for Single View Building Extraction and Height Estimation
- Adaptive Taxonomy Learning and Historical Patterns Modelling for Patent Classification
- Interaction-aware Joint Attention Estimation Using People Attributes
- Beyond Semantics: Learning a Behavior Augmented Relevance Model with Self-supervised Learning
- Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
- Flexible Isosurface Extraction for Gradient-Based Mesh Optimization
- TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms
- Machine Learning aided Computer Architecture Design for CNN Inferencing Systems
- FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis
- WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine
- Pseudo-label Alignment for Semi-supervised Instance Segmentation
- Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbone
- TCSloT: Text Guided 3D Context and Slope Aware Triple Network for Dental Implant Position Prediction
- Preemptive Detection of Fake Accounts on Social Networks via Multi-Class Preferential Attachment Classifiers
- RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model
- Prostate Age Gap (PAG): An MRI surrogate marker of aging for prostate cancer detection
- Metacognitive Prompting Improves Understanding in Large Language Models
- Classification of Human- and AI-Generated Texts: Investigating Features for ChatGPT
- Developing an Informal-Formal Persian Corpus
- OpenProteinSet: Training data for structural biology at scale
- Generating Transferable and Stealthy Adversarial Patch via Attention-guided Adversarial Inpainting
- RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimation
- Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
- Deep Semantic Graph Matching for Large-scale Outdoor Point Clouds Registration
- DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting
- Homophily-enhanced Structure Learning for Graph Clustering
- From CNN to Transformer: A Review of Medical Image Segmentation Models
- Multi-Visual-Inertial System: Analysis, Calibration and Estimation
- Double-chain Constraints for 3D Human Pose Estimation in Images and Videos
- Multimodal Pretrained Models for Verifiable Sequential Decision-Making: Planning, Grounding, and Perception
- Byzantine-Robust Decentralized Stochastic Optimization with Stochastic Gradient Noise-Independent Learning Error
- Informative Scene Graph Generation via Debiasing
- Investigating disaster response through social media data and the Susceptible-Infected-Recovered (SIR) model: A case study of 2020 Western U.S. wildfire season
- Cross-heterogeneity Graph Few-shot Learning
- Local-Global Information Interaction Debiasing for Dynamic Scene Graph Generation
- A Novel Self-training Approach for Low-resource Speech Recognition
- TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization