Cover Image

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Eunji, Shim, Kyuhong, Chang, Simyung, Yoon, Sungroh
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models
by: Kim, Donghoon, et al.
Published: (2024)

InfiniPot: Infinite Context Processing on Memory-Constrained LLMs
by: Kim, Minsoo, et al.
Published: (2024)

Unlocking Transfer Learning for Open-World Few-Shot Recognition
by: Kim, Byeonggeun, et al.
Published: (2024)

Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models
by: Kim, Donghoon, et al.
Published: (2025)

Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens
by: Lew, Jaihyun, et al.
Published: (2024)

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
by: Vasu, Pavan Kumar Anasosalu, et al.
Published: (2023)

TiC-CLIP: Continual Training of CLIP Models
by: Garg, Saurabh, et al.
Published: (2023)

Enhancing CLIP Conceptual Embedding through Knowledge Distillation
by: Kao, Kuei-Chun
Published: (2024)

Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP
by: Park, Junsung, et al.
Published: (2025)

DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection
by: Song, Jaewoo, et al.
Published: (2025)

Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps
by: Kim, Jeeyung, et al.
Published: (2024)

Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
by: Bhalla, Usha, et al.
Published: (2024)

Improving Diffusion-Based Generative Models via Approximated Optimal Transport
by: Kim, Daegyu, et al.
Published: (2024)

What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights
by: Wen, Xin, et al.
Published: (2024)

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers
by: Tas, Omer Sahin, et al.
Published: (2024)

D$^{3}$ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs
by: Chang, Shuochen, et al.
Published: (2025)

Teach CLIP to Develop a Number Sense for Ordinal Regression
by: Du, Yao, et al.
Published: (2024)

BioCLIP: A Vision Foundation Model for the Tree of Life
by: Stevens, Samuel, et al.
Published: (2023)

Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation
by: Yang, Zhiwei, et al.
Published: (2025)

Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment
by: Park, Sangha, et al.
Published: (2025)

CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
by: Zhou, Chenliang, et al.
Published: (2022)

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
by: Ahn, Jaewoo, et al.
Published: (2025)

Dynamic Token Reweighting for Robust Vision-Language Models
by: Jiang, Tanqiu, et al.
Published: (2025)

Verbalized Representation Learning for Interpretable Few-Shot Generalization
by: Yang, Cheng-Fu, et al.
Published: (2024)

C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
by: Yoon, Hee Suk, et al.
Published: (2024)

Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models
by: Park, NaHyeon, et al.
Published: (2025)

Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
by: Abbasi, Reza, et al.
Published: (2024)

AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning
by: Tang, Yuwei, et al.
Published: (2024)

BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
by: Gu, Jianyang, et al.
Published: (2025)

Gloss2Text: Sign Language Gloss translation using LLMs and Semantically Aware Label Smoothing
by: Fayyazsanavi, Pooya, et al.
Published: (2024)

RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction
by: Park, Jonggwon, et al.
Published: (2025)

RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability
by: Park, Jonggwon, et al.
Published: (2025)

Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models
by: Hossain, Md Zarif, et al.
Published: (2024)

CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections
by: Imam, Mohamed Fazli, et al.
Published: (2024)

Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder
by: Li, Siting, et al.
Published: (2024)

MoDE: CLIP Data Experts via Clustering
by: Ma, Jiawei, et al.
Published: (2024)

Text Role Classification in Scientific Charts Using Multimodal Transformers
by: Kim, Hye Jin, et al.
Published: (2024)

Set-CLIP: Exploring Aligned Semantic From Low-Alignment Multimodal Data Through A Distribution View
by: Song, Zijia, et al.
Published: (2024)

If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
by: Esfandiarpoor, Reza, et al.
Published: (2024)

Feature Diversification and Adaptation for Federated Domain Generalization
by: Yang, Seunghan, et al.
Published: (2024)