Papers
Thu 6 Jul 2023
192 papers
- Vision Language Transformers: A SurveyMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- TGRL: An Algorithm for Teacher Guided Reinforcement LearningKnowledge distillation → On-policy and self-distillation for LLMs
- PanoDiffusion: 360-degree Panorama Outpainting via DiffusionDiffusion models → 3D, point cloud and scene generation
- Distilling Large Vision-Language Model with Out-of-Distribution GeneralizabilityMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
- Proto-CLIP: Vision-Language Prototypical Network for Few-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Improving Retrieval-Augmented Large Language Models via Data Importance LearningRetrieval-augmented generation → Generation and context integration
- Probabilistic and Semantic Descriptions of Image Manifolds and Their ApplicationsDiffusion models → Diffusion foundations and sampling
- A Critical Look at the Current Usage of Foundation Model for Dense Recognition TaskDiffusion models → Medical imaging and segmentation
- Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Policy Contrastive Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Single Image LDR to HDR Conversion using Conditional DiffusionDiffusion models → Inverse problems and image restoration
- Censored Sampling of Diffusion Models Using 3 Minutes of Human FeedbackDiffusion models → Robustness, privacy and adversarial aspects +1
- Training Models to Generate, Recognize, and Reframe Unhelpful ThoughtsLLM reasoning → Clinical and biomedical applications
- Wireless Multi-Agent Generative AI: From Connected Intelligence to Collective IntelligenceLLM agents and tool use → Agentic AI for wireless networks
- Offline Reinforcement Learning with Imbalanced DatasetsOffline RL and imitation learning from data → Offline RL algorithms
- On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge DistillationKnowledge distillation → Speech and audio distillation
- Dequantization and Color Transfer with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schr"odinger Equation
- A Novel Site-Agnostic Multimodal Deep Learning Model to Identify Pro-Eating Disorder Content on Social Media
- A Machine-Learned Ranking Algorithm for Dynamic and Personalised Car Pooling Services
- Sparse learned kernels for interpretable and efficient medical time series processing
- UniCoRN: Unified Cognitive Signal ReconstructioN bridging cognitive signals and human language
- Amplifying Limitations, Harms and Risks of Large Language Models
- S2vNTM: Semi-supervised vMF Neural Topic Modeling
- Performance Comparison of Pre-trained Models for Speech-to-Text in Turkish: Whisper-Small and Wav2Vec2-XLS-R-300M
- How word semantics and phonology affect handwriting of Alzheimer's patients: a machine learning based analysis
- CORE-GPT: Combining Open Access research and large language models for credible, trustworthy question answering
- Can ChatGPT's Responses Boost Traditional Natural Language Processing?
- Read, Look or Listen? What's Needed for Solving a Multimodal Dataset
- A Fully Automated and Explainable Algorithm for the Prediction of Malignant Transformation in Oral Epithelial Dysplasia
- FITS: Modeling Time Series with 10k Parameters
- Steel Surface Roughness Parameter Calculations Using Lasers and Machine Learning Models
- Frontier AI Regulation: Managing Emerging Risks to Public Safety
- Undecimated Wavelet Transform for Word Embedded Semantic Marginal Autoencoder in Security improvement and Denoising different Languages
- Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning
- ACDNet: Attention-guided Collaborative Decision Network for Effective Medication Recommendation
- Facial Landmark Detection Evaluation on MOBIO Database
- Encoder-Decoder Networks for Self-Supervised Pretraining and Downstream Signal Bandwidth Regression on Digital Antenna Arrays
- Machine Learning to detect cyber-attacks and discriminating the types of power system disturbances
- BiPhone: Modeling Inter Language Phonetic Influences in Text
- Covering Uncommon Ground: Gap-Focused Question Generation for Answer Assessment
- Assisting Clinical Decisions for Scarcely Available Treatment via Disentangled Latent Representation
- InfoSync: Information Synchronization across Multilingual Semi-structured Tables
- On Invariance, Equivariance, Correlation and Convolution of Spherical Harmonic Representations for Scalar and Vectorial Data
- When Fair Classification Meets Noisy Protected Attributes
- A Vulnerability of Attribution Methods Using Pre-Softmax Scores
- Application of Spherical Convolutional Neural Networks to Image Reconstruction and Denoising in Nuclear Medicine
- Gammatonegram Representation for End-to-End Dysarthric Speech Processing Tasks: Speech Recognition, Speaker Identification, and Intelligibility Assessment
- CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images
- OmniBoost: Boosting Throughput of Heterogeneous Embedded Devices under Multi-DNN Workload
- Optimal Scalarizations for Sublinear Hypervolume Regret
- To pretrain or not to pretrain? A case study of domain-specific pretraining for semantic segmentation in histopathology
- It is not Sexually Suggestive, It is Educative. Separating Sex Education from Suggestive Content on TikTok Videos
- ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Images
- Empirical Analysis of a Segmentation Foundation Model in Prostate Imaging
- PSDR-Room: Single Photo to Scene using Differentiable Rendering
- That's BAD: Blind Anomaly Detection by Implicit Local Feature Clustering
- Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification
- Neural Network Field Theories: Non-Gaussianity, Actions, and Locality
- Quantification of Uncertainty with Adversarial Models
- PREADD: Prefix-Adaptive Decoding for Controlled Text Generation
- Attentive Graph Enhanced Region Representation Learning
- PseudoCell: Hard Negative Mining as Pseudo Labeling for Deep Learning-Based Centroblast Cell Detection
- Sparse Graphical Linear Dynamical Systems
- Optimal Bandwidth Selection for DENCLUE Algorithm
- Text-Guided Synthesis of Eulerian Cinemagraphs
- Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles
- Push Past Green: Learning to Look Behind Plant Foliage by Moving It
- Lost in the Middle: How Language Models Use Long Contexts
- LEO: Learning Efficient Orderings for Multiobjective Binary Decision Diagrams
- Focused Transformer: Contrastive Training for Context Scaling
- VideoGLUE: Video General Understanding Evaluation of Foundation Models
- BrickPal: Augmented Reality-based Assembly Instructions for Brick Models
- Achieving Reliable and Fair Skin Lesion Diagnosis via Unsupervised Domain Adaptation
- MultiVENT: Multilingual Videos of Events with Aligned Natural Text
- Topology-Aware Loss for Aorta and Great Vessel Segmentation in Computed Tomography Images
- Multiplicative Updates for Online Convex Optimization over Symmetric Cones
- Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification
- T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
- BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training
- VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering
- Principal subbundles for dimension reduction
- Context-Aware Configuration and Management of WiFi Direct Groups for Real Opportunistic Networks
- Extracting Multi-valued Relations from Language Models
- Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance
- Quantum Solutions to the Privacy vs. Utility Tradeoff
- KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding
- LISSNAS: Locality-based Iterative Search Space Shrinkage for Neural Architecture Search
- A Survey on Evaluation of Large Language Models
- Efficient Domain Adaptation of Sentence Embeddings Using Adapters
- Contextual Affinity Distillation for Image Anomaly Detection
- Beyond Intuition, a Framework for Applying GPs to Real-World Data
- Learning Disentangled Representations in Signed Directed Graphs without Social Assumptions
- Hybrid Knowledge-Data Driven Channel Semantic Acquisition and Beamforming for Cell-Free Massive MIMO
- A Hybrid End-to-End Spatio-Temporal Attention Neural Network with Graph-Smooth Signals for EEG Emotion Recognition
- DeepOnto: A Python Package for Ontology Engineering with Deep Learning
- Generalizing Backpropagation for Gradient-Based Interpretability
- Origin-Destination Travel Time Oracle for Map-based Services
- Track Mix Generation on Music Streaming Services using Transformers
All 192
- A Near-Linear Time Algorithm for the Chamfer Distance
- Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain
- Art Authentication with Vision Transformers
- General Formulation and PCL-Analysis for Restless Bandits with Limited Observability
- Style Over Substance: Evaluation Biases for Large Language Models
- RealLiFe: Real-Time Light Field Reconstruction via Hierarchical Sparse Gradient Descent
- Sequential Neural Barriers for Scalable Dynamic Obstacle Avoidance
- Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentation
- Self-supervised Optimization of Hand Pose Estimation using Anatomical Features and Iterative Learning
- Improving the Efficiency of Human-in-the-Loop Systems: Adding Artificial to Human Experts
- Fourier-Net+: Leveraging Band-Limited Representation for Efficient 3D Medical Image Registration
- ContainerGym: A Real-World Reinforcement Learning Benchmark for Resource Allocation
- A Privacy-Preserving Walk in the Latent Space of Generative Models for Medical Applications
- Efficient Semiring-Weighted Earley Parsing
- Multi-modal multi-class Parkinson disease classification using CNN and decision level fusion
- Transfer Learning for the Efficient Detection of COVID-19 from Smartphone Audio Data
- Cross-Spatial Pixel Integration and Cross-Stage Feature Fusion Based Transformer Network for Remote Sensing Image Super-Resolution
- Pruning vs Quantization: Which is Better?
- On the Cultural Gap in Text-to-Image Generation
- DPM: Clustering Sensitive Data through Separation
- SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks
- A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observations
- DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning
- In Time and Space: Towards Usable Adaptive Control for Assistive Robotic Arms
- When No-Rejection Learning is Consistent for Regression with Rejection
- LEA: Improving Sentence Similarity Robustness to Typos Using Lexical Attention Bias
- Agentivit`a e telicit`a in GilBERTo: implicazioni cognitive
- Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition
- A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition
- Stability for Inference with Persistent Homology Rank Functions
- PUFFIN: A Path-Unifying Feed-Forward Interfaced Network for Vapor Pressure Prediction
- RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution
- Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge
- The Relationship Between Speech Features Changes When You Get Depressed: Feature Correlations for Improving Speed and Performance of Depression Detection
- BaBE: Enhancing Fairness via Estimation of Latent Explaining Variables
- Learning to Solve Tasks with Exploring Prior Behaviours
- Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
- Contrast Is All You Need
- Towards accurate instance segmentation in large-scale LiDAR point clouds
- Reference-based Motion Blur Removal: Learning to Utilize Sharpness in the Reference Image
- MomentDiff: Generative Video Moment Retrieval from Random to Real
- Towards a safe MLOps Process for the Continuous Development and Safety Assurance of ML-based Systems in the Railway Domain
- PLIERS: a Popularity-Based Recommender System for Content Dissemination in Online Social Networks
- ValiText -- a unified validation framework for computational text-based measures of social constructs
- Deep Ensemble Learning with Frame Skipping for Face Anti-Spoofing
- NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic
- Revisiting Computer-Aided Tuberculosis Diagnosis
- Enhancing LLM with Evolutionary Fine Tuning for News Summary Generation
- Noise-to-Norm Reconstruction for Industrial Anomaly Detection and Localization
- Generative Zero-Shot Prompt Learning for Cross-Domain Slot Filling with Inverse Prompting
- Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks
- Bundle-specific Tractogram Distribution Estimation Using Higher-order Streamline Differential Equation
- Evaluating raw waveforms with deep learning frameworks for speech emotion recognition
- Trends in Machine Learning and Electroencephalogram (EEG): A Review for Undergraduate Researchers
- Degree Heterogeneity in Higher-Order Networks: Inference in the Hypergraph boldsymbolβ-Model
- CPDG: A Contrastive Pre-Training Method for Dynamic Graph Neural Networks
- Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation
- OLR-WA Online Regression with Weighted Average
- Few-shot Personalized Saliency Prediction Based on Interpersonal Gaze Patterns
- Semi-supervised Domain Adaptive Medical Image Segmentation through Consistency Regularized Disentangled Contrastive Learning
- BHEISR: Nudging from Bias to Balance -- Promoting Belief Harmony by Eliminating Ideological Segregation in Knowledge-based Recommendations
- VerifAI: Verified Generative AI
- What Should Data Science Education Do with Large Language Models?
- The Role of Subgroup Separability in Group-Fair Medical Image Classification
- UIT-Saviors at MEDVQA-GI 2023: Improving Multimodal Learning with Image Enhancement for Gastrointestinal Visual Question Answering
- Large Language Models Empowered Autonomous Edge AI for Connected Intelligence
- SeLiNet: Sentiment enriched Lightweight Network for Emotion Recognition in Images
- Temporal Difference Learning for High-Dimensional PIDEs with Jumps
- When Does Confidence-Based Cascade Deferral Suffice?
- Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social Relationships
- PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations
- Knowledge Graph Self-Supervised Rationalization for Recommendation
- Exploring Linguistic Style Matching in Online Communities: The Role of Social Context and Conversation Dynamics
- CityTrack: Improving City-Scale Multi-Camera Multi-Target Tracking by Location-Aware Tracking and Box-Grained Matching
- ALPCAH: Sample-wise Heteroscedastic PCA with Tail Singular Value Regularization
- Active Learning with Contrastive Pre-training for Facial Expression Recognition
- Dense Retrieval Adaptation using Target Domain Description
- RecallM: An Adaptable Memory Mechanism with Temporal Understanding for Large Language Models
- An Uncertainty Aided Framework for Learning based Liver T1ρ Mapping and Analysis
- MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection
- Evaluating the Evaluators: Are Current Few-Shot Learning Benchmarks Fit for Purpose?
- Fine-grained Action Analysis: A Multi-modality and Multi-task Dataset of Figure Skating
- Text Alignment Is An Efficient Unified Model for Massive NLP Tasks
- Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learning
- Through the Fairness Lens: Experimental Analysis and Evaluation of Entity Matching
- Understanding Uncertainty Sampling via Equivalent Loss
- TL-nvSRAM-CIM: Ultra-High-Density Three-Level ReRAM-Assisted Computing-in-nvSRAM with DC-Power Free Restore and Ternary MAC Operations
- CFSum: A Coarse-to-Fine Contribution Network for Multimodal Summarization
- Multi-Similarity Contrastive Learning
- Validation of the Practicability of Logical Assessment Formula for Evaluations with Inaccurate Ground-Truth Labels: An Application Study on Tumour Segmentation for Breast Cancer
- Towards Symmetry-Aware Generation of Periodic Materials
- Strahler Number of Natural Language Sentences in Comparison with Random Trees