A survey on causal inference
Causal inference is a critical research topic across many domains, such as statistics,
computer science, education, public policy, and economics, for decades. Nowadays …
computer science, education, public policy, and economics, for decades. Nowadays …
Teaching structured vision & language concepts to vision & language models
Vision and Language (VL) models have demonstrated remarkable zero-shot performance in
a variety of tasks. However, some aspects of complex language understanding still remain a …
a variety of tasks. However, some aspects of complex language understanding still remain a …
Learning de-biased representations with biased representations
Many machine learning algorithms are trained and evaluated by splitting data from a single
source into training and test sets. While such focus on in-distribution learning scenarios has …
source into training and test sets. While such focus on in-distribution learning scenarios has …
Visual language integration: A survey and open challenges
SM Park, YG Kim - Computer Science Review, 2023 - Elsevier
With the recent development of deep learning technology comes the wide use of artificial
intelligence (AI) models in various domains. AI shows good performance for definite …
intelligence (AI) models in various domains. AI shows good performance for definite …
Benchmarking spatial relationships in text-to-image generation
Spatial understanding is a fundamental aspect of computer vision and integral for human-
level reasoning about images, making it an important component for grounded language …
level reasoning about images, making it an important component for grounded language …
Biaswap: Removing dataset bias with bias-tailored swapping augmentation
Deep neural networks often make decisions based on the spurious correlations inherent in
the dataset, failing to generalize in an unbiased data distribution. Although previous …
the dataset, failing to generalize in an unbiased data distribution. Although previous …
Mutant: A training paradigm for out-of-distribution generalization in visual question answering
While progress has been made on the visual question answering leaderboards, models
often utilize spurious correlations and priors in datasets under the iid setting. As such …
often utilize spurious correlations and priors in datasets under the iid setting. As such …
Enhancing self-consistency and performance of pre-trained language models through natural language inference
While large pre-trained language models are powerful, their predictions often lack logical
consistency across test inputs. For example, a state-of-the-art Macaw question-answering …
consistency across test inputs. For example, a state-of-the-art Macaw question-answering …
Negative object presence evaluation (nope) to measure object hallucination in vision-language models
Object hallucination poses a significant challenge in vision-language (VL) models, often
leading to the generation of nonsensical or unfaithful responses with non-existent objects …
leading to the generation of nonsensical or unfaithful responses with non-existent objects …
Vqamix: Conditional triplet mixup for medical visual question answering
Medical visual question answering (VQA) aims to correctly answer a clinical question related
to a given medical image. Nevertheless, owing to the expensive manual annotations of …
to a given medical image. Nevertheless, owing to the expensive manual annotations of …