Papers
Tue 27 Jun 2023
216 papers
- Easing Color Shifts in Score-Based Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Structured State Space Models for Multiple Instance Learning in Digital PathologyState-space sequence models (S4, Mamba) → Mamba for medical image analysis
- Ticketed Learning-Unlearning SchemesLLM safety and security → Machine unlearning
- Face Morphing Attack Detection with Denoising Diffusion Probabilistic ModelsDiffusion models → Robustness, privacy and adversarial aspects
- Rethinking Closed-loop Training for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- Approximated Prompt Tuning for Vision-Language Pre-trained ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- LeanDojo: Theorem Proving with Retrieval-Augmented Language ModelsRetrieval-augmented generation → Agentic RAG, agents and memory
- Trajectory Generation, Control, and Safety with Denoising Diffusion Probabilistic ModelsDiffusion models → Diffusion and flow policies for robotics
- Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- IDOL: Indicator-oriented Logic Pre-training for Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human SupervisorsOffline RL and imitation learning from data → Imitation learning methods
- Shikra: Unleashing Multimodal LLM's Referential Dialogue MagicMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillationKnowledge distillation → Speech and audio distillation
- Learning non-Markovian Decision-Making from State-only SequencesOffline RL and imitation learning from data → Imitation learning methods
- Dual Radar SAR Controller
- Artificial intelligence is algorithmic mimicry: why artificial "agents" are not (and won't be) proper agents
- Explainability is NOT a Game
- Tensor Completion via Leverage Sampling and Tensor QR Decomposition for Network Latency Estimation
- On Detecting Some Defective Items in Group Testing
- SAHAAYAK 2023 -- the Multi Domain Bilingual Parallel Corpus of Sanskrit to Hindi for Machine Translation
- CASEIN: Cascading Explicit and Implicit Control for Fine-grained Emotion Intensity Regulation
- Classification and Explanation of Distributed Denial-of-Service (DDoS) Attack Detection using Machine Learning and Shapley Additive Explanation (SHAP) Methods
- Shilling Black-box Review-based Recommender Systems through Fake Review Generation
- Long-Term Hourly Scenario Generation for Correlated Wind and Solar Power combining Variational Autoencoders with Radial Basis Function Kernels
- Symbol emergence as interpersonal cross-situational learning: the emergence of lexical knowledge with combinatoriality
- A generic self-supervised learning (SSL) framework for representation learning from spectra-spatial feature of unlabeled remote sensing imagery
- Non-parametric online market regime detection and regime clustering for multidimensional and path-dependent data structures
- MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning
- Confidence-based Ensembles of End-to-End Speech Recognition Models
- Learning normal asymmetry representations for homologous brain structures
- G"odel-Dummett linear temporal logic
- On Logic-Based Explainability with Partially Specified Inputs
- FLuRKA: Fast and accurate unified Low-Rank & Kernel Attention
- ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis
- HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
- A Population-Level Analysis of Neural Dynamics in Robust Legged Robots
- Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile
- Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese
- An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning
- NCIS: Deep Color Gradient Maps Regression and Three-Class Pixel Classification for Enhanced Neuronal Cell Instance Segmentation in Nissl-Stained Histological Images
- UTRNet: High-Resolution Urdu Text Recognition In Printed Documents
- "Is a picture of a bird a bird": Policy recommendations for dealing with ambiguity in machine vision models
- Next Steps for Human-Centered Generative AI: A Technical Perspective
- What Makes ImageNet Look Unlike LAION
- An Efficient Deep Convolutional Neural Network Model For Yoga Pose Recognition Using Single Images
- Evidential Detection and Tracking Collaboration: New Problem, Benchmark and Algorithm for Robust Anti-UAV System
- Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost
- A Novel Two Stream Decision Level Fusion of Vision and Inertial Sensors Data for Automatic Multimodal Human Activity Recognition System
- High Fidelity Image Counterfactuals with Probabilistic Causal Models
- Predicting the Impact of Batch Refactoring Code Smells on Application Resource Consumption
- Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures
- xAI-CycleGAN, a Cycle-Consistent Generative Assistive Network
- Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving
- To Spike or Not To Spike: A Digital Hardware Perspective on Deep Learning Acceleration
- CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor Fusion
- Identity Construction in a Misogynist Incels Forum
- Differentially Private Video Activity Recognition
- DMNER: Biomedical Entity Recognition by Detection and Matching
- A Weakly Supervised Classifier and Dataset of White Supremacist Language
- Stochastic Gradient Bayesian Optimal Experimental Designs for Simulation-based Inference
- Physics-inspired spatiotemporal-graph AI ensemble for the detection of higher order wave mode signals of spinning binary black hole mergers
- REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction
- Semi-supervised Multimodal Representation Learning through a Global Workspace
- Privacy-Preserving Community Detection for Locally Distributed Multiple Networks
- Quantum Federated Learning: Analysis, Design and Implementation Challenges
- On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection
- MAE-GEBD:Winning the CVPR'2023 LOVEU-GEBD Challenge
- Symphonize 3D Semantic Scene Completion with Contextual Instance Queries
- Detector-Free Structure from Motion
- Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties
- PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment
- Benchmarking Stroke Forecasting with Stroke-Level Badminton Dataset
- Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation
- Enhancing Representation Learning on High-Dimensional, Small-Size Tabular Data: A Divide and Conquer Method with Ensembled VAEs
- CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a 10,000 Budget; An Extra 4,000 Unlocks 81.8% Accuracy
- The Distortion of Binomial Voting Defies Expectation
- SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design
- Dental CLAIRES: Contrastive LAnguage Image REtrieval Search for Dental Research
- Effective resistance in metric spaces
- Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos
- Neural Bayes estimators for censored inference with peaks-over-threshold models
- On the Usefulness of Synthetic Tabular Data Generation
- Automatic Annotation of Direct Speech in Written French Narratives
- Asynchronous Algorithmic Alignment with Cocycles
- Coupling parameter and particle dynamics for adaptive sampling in Neural Galerkin schemes
- Machine-learning based noise characterization and correction on neutral atoms NISQ devices
- Value-aware Importance Weighting for Off-policy Reinforcement Learning
- SCENEREPLICA: Benchmarking Real-World Robot Manipulation by Creating Replicable Scenes
- DCID: Deep Canonical Information Decomposition
- Learning Nonautonomous Systems via Dynamic Mode Decomposition
- Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching
- Constructing Multilingual Code Search Dataset Using Neural Machine Translation
- Coupling a Recurrent Neural Network to SPAD TCSPC Systems for Real-time Fluorescence Lifetime Imaging
- Extending Context Window of Large Language Models via Positional Interpolation
- Cardiac CT perfusion imaging of pericoronary adipose tissue (PCAT) highlights potential confounds in coronary CTA
- Learning to Sail Dynamic Networks: The MARLIN Reinforcement Learning Framework for Congestion Control in Tactical Environments
- Optimizing Credit Limit Adjustments Under Adversarial Goals Using Reinforcement Learning
- Approximate Message Passing for the Matrix Tensor Product Model
- PyBADS: Fast and robust black-box optimization in Python
- See Through the Fog: Curriculum Learning with Progressive Occlusion in Medical Imaging
All 216
- Generating Elementary Integrable Expressions
- A Three-Way Knot: Privacy, Fairness, and Predictive Performance Dynamics
- You Can Mask More For Extremely Low-Bitrate Image Compression
- RansomAI: AI-powered Ransomware for Stealthy Encryption
- Simple Steps to Success: A Method for Step-Based Counterfactual Explanations
- A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms
- MyCrunchGPT: A chatGPT assisted framework for scientific machine learning
- CamemBERT-bio: Leveraging Continual Pre-training for Cost-Effective Models on French Biomedical Data
- Geometric Ultrasound Localization Microscopy
- When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions
- Unleashing the Power of User Reviews: Exploring Airline Choices at Catania Airport, Italy
- DataCI: A Platform for Data-Centric AI on Streaming Data
- Higher-order Graph Attention Network for Stock Selection with Joint Analysis
- What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation
- Paradigm Shift in Sustainability Disclosure Analysis: Empowering Stakeholders with CHATREPORT, a Language Model-Based Tool
- Enhancing Navigation Benchmarking and Perception Data Generation for Row-based Crops in Simulation
- Abdominal organ segmentation via deep diffeomorphic mesh deformations
- Self-supervised Learning of Event-guided Video Frame Interpolation for Rolling Shutter Frames
- A novel structured argumentation framework for improved explainability of classification tasks
- Using Large Language Models to Provide Explanatory Feedback to Human Tutors
- EVD Surgical Guidance with Retro-Reflective Tool Tracking and Spatial Reconstruction using Head-Mounted Augmented Reality Device
- Precursor-of-Anomaly Detection for Irregular Time Series
- Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets
- Predictive Coding beyond Correlations
- Taming Detection Transformers for Medical Object Detection
- Large-scale unsupervised audio pre-training for video-to-speech synthesis
- Robust Proxy: Improving Adversarial Robustness by Robust Proxy Learning
- Advancing Adversarial Training by Injecting Booster Signal
- UniUD Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023
- Limited-Memory Greedy Quasi-Newton Method with Non-asymptotic Superlinear Convergence Rate
- No-Service Rail Surface Defect Segmentation via Normalized Attention and Dual-scale Interaction
- COMPASS: Unsupervised and Online Clustering of Complex Human Activities from Smartphone Sensors
- KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation
- Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
- Phase Space Analysis of Cardiac Spectra
- Freestyle 3D-Aware Portrait Synthesis Based on Compositional Generative Priors
- Irregular Change Detection in Sparse Bi-Temporal Point Clouds using Learned Place Recognition Descriptors and Point-to-Voxel Comparison
- AutoGraph: Predicting Lane Graphs from Traffic Observations
- Verifying Safety of Neural Networks from Topological Perspectives
- Length Generalization in Arithmetic Transformers
- Quality Estimation of Machine Translated Texts based on Direct Evidence from Training Data
- Requirements for Explainability and Acceptance of Artificial Intelligence in Collaborative Work
- Assessing Dataset Quality Through Decision Tree Characteristics in Autoencoder-Processed Spaces
- DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs
- Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection
- TrickVOS: A Bag of Tricks for Video Object Segmentation
- Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations
- LeCo: Lightweight Compression via Learning Serial Correlations
- A Meta-analytical Comparison of Naive Bayes and Random Forest for Software Defect Prediction
- Mean Field Theory in Deep Metric Learning
- Herb-Drug Interactions: A Holistic Decision Support System in Healthcare
- The Architecture of a Biologically Plausible Language Organ
- Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferability
- Planning Landmark Based Goal Recognition Revisited: Does Using Initial State Landmarks Make Sense?
- 3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement
- CellViT: Vision Transformers for Precise Cell Segmentation and Classification
- SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion
- PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation
- FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformer
- Novel Hybrid-Learning Algorithms for Improved Millimeter-Wave Imaging Systems
- A Toolbox for Fast Interval Arithmetic in numpy with an Application to Formal Verification of Neural Network Controlled Systems
- Homological Neural Networks: A Sparse Architecture for Multivariate Complexity
- Understanding Client Reactions in Online Mental Health Counseling
- Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning
- Simulating counterfactuals
- Anomaly Detection in Networks via Score-Based Generative Models
- Multi-Dimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition
- Nano1D: An accurate Computer Vision software for analysis and segmentation of low-dimensional nanostructures
- Towards predicting Pedestrian Evacuation Time and Density from Floorplans using a Vision Transformer
- Machine learning in solar physics
- Transferability Metrics for Object Detection
- FAIRER: Fairness as Decision Rationale Alignment
- Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task
- Adaptive Annealed Importance Sampling with Constant Rate Progress
- Variational latent discrete representation for time series modelling
- Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract
- Delivering Inflated Explanations
- Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?
- Generalized Out-of-distribution Fault Diagnosis (GOOFD) via Internal Contrastive Learning
- Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition
- A Survey on Out-of-Distribution Evaluation of Neural NLP Models
- GroundNLQ @ Ego4D Natural Language Queries Challenge 2023
- MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation
- C-PMI: Conditional Pointwise Mutual Information for Turn-level Dialogue Evaluation
- Cutting-Edge Techniques for Depth Map Super-Resolution
- Positional Embedding-Aware Activations
- Emulating Reader Behaviors for Fake News Detection
- Learning to Rank in Generative Retrieval
- [Re] Double Sampling Randomized Smoothing
- S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networks
- Semantic Segmentation Using Super Resolution Technique as Pre-Processing
- Unsupervised Episode Generation for Graph Meta-learning
- TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection
- Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction
- Modified Feature Selection for Improved Classification of Resting-State Raw EEG Signals in Chronic Knee Pain
- FBA-Net: Foreground and Background Aware Contrastive Learning for Semi-Supervised Atrium Segmentation
- One-class systems seamlessly fit in the forward-forward algorithm
- Automatic Truss Design with Reinforcement Learning
- Delving into Crispness: Guided Label Refinement for Crisp Edge Detection
- Exploiting Inferential Structure in Neural Processes
- Constraining Generative Models for Engineering Design with Negative Data
- DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization
- Wasserstein Generative Regression
- YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus
- Evaluation of machine learning architectures on the quantification of epistemic and aleatoric uncertainties in complex dynamical systems
- Revisiting Tropical Polynomial Division: Theory, Algorithms and Application to Neural Networks
- SENSEi: Input-Sensitive Compilation for Accelerating GNNs
- Contrastive Meta-Learning for Few-shot Node Classification
- LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network
- A Restarted Large-Scale Spectral Clustering with Self-Guiding and Block Diagonal Representation
- What Truly Matters in Trajectory Prediction for Autonomous Driving?
- The Perspective of Software Professionals on Algorithmic Racism
- MIMIC: Masked Image Modeling with Image Correspondences
- Identifying and Consolidating Knowledge Engineering Requirements
- Investigating Cross-Domain Behaviors of BERT in Review Understanding
- Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation