Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languagesby Ashutosh Bajpai, Tanmoy ChakrabortyFirst…
Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentationby Kexin Li, Zongxin Yang, Yi Yang,…
AmCLR: Unified Augmented Learning for Cross-Modal Representationsby Ajay Jagannath, Aayush Upadhyay, Anant MehtaFirst submitted to…
Boosting Alignment for Post-Unlearning Text-to-Image Generative Modelsby Myeongseob Ko, Henry Li, Zhun Wang, Jonathan Patsenker,…
EGEAN: An Exposure-Guided Embedding Alignment Network for Post-Click Conversion Estimationby Huajian Feng, Guoxiao Zhang, Yadong…
Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertaintyby Meera Hahn, Wenjun Zeng, Nithish Kannen, Rich…
Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformersby Johanna Vielhaben, Dilyara Bareeva, Jim Berend, Wojciech…
MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimizationby Kangyu Zhu, Peng Xia, Yun…
SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generationby Leigang Qu, Haochuan Li, Wenjie Wang,…
Multi-Objective Alignment of Large Language Models Through Hypervolume Maximizationby Subhojyoti Mukherjee, Anusha Lalitha, Sailik Sengupta,…