ULTra: Unveiling Latent Token Interpretability in Transformer Based Understanding

2024-11-15 · Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr

Transformers have revolutionized Computer Vision (CV) and Natural Language Processing (NLP) through self-attention mechanisms. However, due to their complexity, their latent token representations are often difficult to interpret. We introduce a novel framework that interprets Transformer embeddings, uncovering meaningful semantic patterns within them. Based on this framework, we demonstrate that zero-shot unsupervised semantic segmentation can be performed effectively without any fine-tuning using a model pre-trained for tasks other than segmentation. Our method reveals the inherent capacity of Transformer models for understanding input semantics and achieves state-of-the-art performance in semantic segmentation, outperforming traditional segmentation models. Specifically, our approach achieves an accuracy of 67.2 % and an mIoU of 32.9 % on the COCO-Stuff dataset, as well as an mIoU of 51.9 % on the PASCAL VOC dataset. Additionally, we validate our interpretability framework on LLMs for text summarization, demonstrating its broad applicability and robustness.

📄 PDF Abstract BibTeX arXiv:2411.12589

Code (0)

등록된 구현이 없습니다.

Tasks

Segmentation Semantic Segmentation Text Summarization Unsupervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Adam 설명 없음

Residual Connection 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

2026-06-12 · NVIDIA, :, Aaron Blakeman, Aaron Thomas 외 arxiv

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the c…

Reinforcement Learning

E-BayesSAM: Efficient Bayesian Adaptation of SAM with Self-Optimizing KAN-Based Interpretation for Uncertainty-Aware Ultrasonic Segmentation

2025-08-24 · Bin Huang, Zhong Liu, Huiying Wen, Bingsheng Huang 외 arxiv

Although the Segment Anything Model (SAM) has advanced medical image segmentation, its Bayesian adaptation for uncertainty-aware segmentation remains hindered by three key issues: (1) instability in Bayesian fine-tuning …

Medical Image Segmentation Self-Supervised Learning Bayesian Inference

Autonomous Vehicles Common Sense Reasoning Zero-shot Generalization

ULTra: Unveiling Latent Token Interpretability in Transformer Based Understanding

Code (0)

Tasks

Methods 이 논문이 사용한 방법론

Similar Papers 제목 키워드 기반

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

E-BayesSAM: Efficient Bayesian Adaptation of SAM with Self-Optimizing KAN-Based Interpretation for Uncertainty-Aware Ultrasonic Segmentation

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

FOCUS: Fused Observation of Channels for Unveiling Spectra

Categorical Traffic Transformer: Interpretable and Diverse Behavior Prediction with Tokenized Latent