3 papers
cs.CL2025
Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
Jaewoo Ahn, Heeseung Yun, Dayoon Ko +1
While pre-trained multimodal representations (e.g., CLIP) have shown impressive capabilities, they exhibit significant compositional vulnerabilities leading to counterintuitive jud…
cs.CV2025
ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams
Chris Dongjoo Kim, Jihwan Moon, Sangwoo Moon +7
The rapid growth of video-text data presents challenges in storage and computation during training. Online learning, which processes streaming data in real-time, offers a promising…
cs.LG2025
Sample Selection via Contrastive Fragmentation for Noisy Label Regression
Chris Dongjoo Kim, Sangwoo Moon, Jihwan Moon +2
As with many other problems, real-world regression is plagued by the presence of noisy labels, an inevitable issue that demands our attention. Fortunately, much real-world data oft…