3 papers
cs.CV2026
Learning to Rank Caption Chains for Video-Text Alignment
Ansel Blume, Burak Uzkent, Shalini Chaudhuri +1
Direct preference optimization (DPO) is an effective technique to train language models to generate preferred over dispreferred responses. However, this binary "winner-takes-all" a…
cs.CV2025
SYNTHIA: Novel Concept Design with Affordance Composition
Hyeonjeong Ha, Xiaomeng Jin, Jeonghwan Kim +7
Text-to-image (T2I) models enable rapid concept design, making them widely used in AI-driven design. While recent studies focus on generating semantic and stylistic variations of g…
cs.CV2025
PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding
Ansel Blume, Jeonghwan Kim, Hyeonjeong Ha +7
Real-world objects are composed of distinctive, object-specific parts. Identifying these parts is key to performing fine-grained, compositional reasoning-yet, large multimodal mode…