No article text was recorded for this version.
bag-of-words bias
Version 1 of 140 papers41 conceptsfrozen 2026-10-04
Papers in this version
- Blog: RoCOCO: Robustness Benchmark of MS-COCO to Stress-Test Image-Text Matching Models
- Blog: Investigating Compositional Challenges in Vision-Language Models for Visual Grounding
- Blog: CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions
- Blog: ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation
- Blog: FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension
- Blog: Text encoders bottleneck compositionality in contrastive vision-language models
- Blog: Compositional Image-Text Matching and Retrieval by Grounding Entities
- Blog: Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding
- Blog: Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining
- Blog: Weak-to-Strong Compositional Learning from Generative Models for Language-Based Object Detection
- Blog: Enhancing Semantic Understanding in Vision Language Models Using Meaning Representation Negative Generation
- Blog: Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality
- Blog: Natural Language Inference Improves Compositionality in Vision-Language Models
- Blog: Grounded Image Text Matching with Mismatched Relation Reasoning
- Blog: LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent
- Blog: In-Context Learning Improves Compositional Understanding of Vision-Language Models
- Blog: CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding
- Blog: Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training
- Blog: DesCo: Learning Object Recognition with Rich Language Descriptions
- Blog: When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It?
- Blog: Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
- Blog: VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models
- Blog: Scalable Performance Analysis for Vision-Language Models
- Blog: Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
- Blog: Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?
- Blog: Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions
- Blog: Do Vision-Language Models Understand Compound Nouns?
- Blog: Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
- Blog: CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally
- Blog: Weakly Supervised Referring Image Segmentation with Intra-Chunk and Inter-Chunk Consistency
- Blog: Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-Modal Structured Representations
- Blog: Decoupled Global-Local Alignment for Improving Compositional Understanding
- Blog: Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?
- Blog: Causal Graphical Models for Vision-Language Compositional Understanding
- Blog: Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View
- Blog: TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
- Blog: Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
- Blog: Bridge To Answer: Structure-Aware Graph Interaction Network for Video Question Answering
- Blog: Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
- Blog: Towards an Exhaustive Evaluation of Vision-Language Foundation Models
History & citation
Current · Permanent link
- This direction split from Overcoming the Bag-of-Words Bias in Vision-Language Models (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_bag_of_words_bias_fd2fbfd9,
title = {bag-of-words bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/bag-of-words-bias/rdr_fd2fbfd931e441a788231c8976dd4fc5},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_bag_of_words_bias_fd2fbfd9_v1,
title = {bag-of-words bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/bag-of-words-bias/rdr_fd2fbfd931e441a788231c8976dd4fc5/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}