5 papers
Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction
Shannan Yan, Leqi Zheng, Keyu Lv +7
We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-e…
SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation
Jingzhuo Wu, Jiajun Zhang, Keyan Jin +2
Modern large language models (LLMs) excel at generating fluent and faithful translations. However, they struggle to preserve an author's unique literary style, often producing sema…
TAG: Thinking with Action Unit Grounding for Facial Expression Recognition
Haobo Lin, Tianyi Bai, Jiajun Zhang +5
Facial Expression Recognition (FER) is a fine-grained visual understanding task where reliable predictions require reasoning over localized and meaningful facial cues. Recent visio…
Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code
Haobo Lin, Tianyi Bai, Chen Chen +4
Multimodal geometry reasoning requires models to jointly understand visual diagrams and perform structured symbolic inference, yet current vision--language models struggle with com…
Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT
Yesheng Liu, Hao Li, Haiyu Xu +9
Multiple-choice question answering (MCQA) has been a popular format for evaluating and reinforcement fine-tuning (RFT) of modern multimodal language models. Its constrained output…