Imagen de Portada

ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hosseini, Hesam, Mighan, Ghazal Hosseini, Afzali, Amirabbas, Amini, Sajjad, Houmansadr, Amir
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Clustering Time Series Data with Gaussian Mixture Embeddings in a Graph Autoencoder Framework
por: Afzali, Amirabbas, et al.
Publicado: (2024)

LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
por: Khodabandeh, Borna, et al.
Publicado: (2025)

Real-Time Semantic Segmentation on FPGA for Autonomous Vehicles Using LMIINet with the CGRA4ML Framework
por: Hosseini, Amir Mohammad Khadem, et al.
Publicado: (2025)

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
por: Amini, Sajjad, et al.
Publicado: (2024)

GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
por: Parast, Aryan Yazdan, et al.
Publicado: (2025)

FairNVT: Improving Fairness via Noise Injection in Vision Transformers
por: Tang, Qiaoyue, et al.
Publicado: (2026)

SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
por: Nasiri-Sarvi, Ali, et al.
Publicado: (2025)

Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation
por: Ghaznavi, Mahdi, et al.
Publicado: (2024)

Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformer
por: Noghre, Ghazal Alinezhad, et al.
Publicado: (2024)

Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data
por: Hosseini, Mohammad, et al.
Publicado: (2025)

Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation
por: Yang, Zhiyuan, et al.
Publicado: (2026)

CAT-SG: A Large Dynamic Scene Graph Dataset for Fine-Grained Understanding of Cataract Surgery
por: Holm, Felix, et al.
Publicado: (2025)

LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
por: Krojer, Benno, et al.
Publicado: (2026)

Enhancing Interpretability of Sparse Latent Representations with Class Information
por: Abiz, Farshad Sangari, et al.
Publicado: (2025)

GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction
por: Ghasemi, Narges, et al.
Publicado: (2025)

AI-Powered Intracranial Hemorrhage Detection: A Co-Scale Convolutional Attention Model with Uncertainty-Based Fuzzy Integral Operator and Feature Screening
por: Chagahi, Mehdi Hosseini, et al.
Publicado: (2024)

WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion
por: Pakdamansavoji, Sajjad, et al.
Publicado: (2025)

Box6D : Zero-shot Category-level 6D Pose Estimation of Warehouse Boxes
por: Ma, Yintao, et al.
Publicado: (2025)

Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
por: Jeong, Wooseong, et al.
Publicado: (2025)

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
por: Li, Wenhao, et al.
Publicado: (2023)

Taming Outlier Tokens in Diffusion Transformers
por: Wu, Xiaoyu, et al.
Publicado: (2026)

GeoPos: A Minimal Positional Encoding for Enhanced Fine-Grained Details in Image Synthesis Using Convolutional Neural Networks
por: Hosseini, Mehran, et al.
Publicado: (2024)

A Multimodal Intermediate Fusion Network with Manifold Learning for Stress Detection
por: Bodaghi, Morteza, et al.
Publicado: (2024)

End-to-End Training for Unified Tokenization and Latent Denoising
por: Duggal, Shivam, et al.
Publicado: (2026)

The Missing Point in Vision Transformers for Universal Image Segmentation
por: Shahabodini, Sajjad, et al.
Publicado: (2025)

Robustness Tokens: Towards Adversarial Robustness of Transformers
por: Pulfer, Brian, et al.
Publicado: (2025)

From Video to EEG: Adapting Joint Embedding Predictive Architecture to Uncover Saptiotemporal Dynamics in Brain Signal Analysis
por: Hojjati, Amirabbas, et al.
Publicado: (2025)

Improving Interpretation Faithfulness for Vision Transformers
por: Hu, Lijie, et al.
Publicado: (2023)

Accelerating Diffusion Transformers with Token-wise Feature Caching
por: Zou, Chang, et al.
Publicado: (2024)

Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation
por: Kienzle, Daniel, et al.
Publicado: (2024)

Accurate and Efficient World Modeling with Masked Latent Transformers
por: Burchi, Maxime, et al.
Publicado: (2025)

Understanding Multi-View Transformers
por: Stary, Michal, et al.
Publicado: (2025)

TRACER: Persistent Regularization for Robust Multimodal Finetuning
por: Asadollahzadeh, Hesam, et al.
Publicado: (2026)

Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization
por: Vali, Mohammad Hassan, et al.
Publicado: (2024)

I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
por: Sassoon, Jordan, et al.
Publicado: (2025)

TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration
por: Olszewski, Jan, et al.
Publicado: (2023)

Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds
por: Stone, Gunner, et al.
Publicado: (2025)

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
por: You, Haoran, et al.
Publicado: (2024)

H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers
por: Li, Wenhao, et al.
Publicado: (2025)

B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
por: Arya, Shreyash, et al.
Publicado: (2024)