10 papers
Thinking With Bounding Boxes: Enhancing Spatio-Temporal Video Grounding via Reinforcement Fine-Tuning
Xin Gu, Haoji Zhang, Qihang Fan +7
Spatio-temporal video grounding (STVG) requires localizing a target object in untrimmed videos both temporally and spatially from natural language descriptions. Despite their stron…
Vidi2.5: Large Multimodal Models for Video Understanding and Creation
Vidi Team, Chia-Wen Kuo, Chuang Huang +31
Video has emerged as the primary medium for communication and creativity on the Internet, driving strong demand for scalable, high-quality video production. Vidi models continue to…
The Coverage Principle: How Pre-Training Enables Post-Training
Fan Chen, Audrey Huang, Noah Golowich +5
Language models demonstrate remarkable abilities when pre-trained on large text corpora and fine-tuned for specific tasks, but how and why pre-training shapes the success of the fi…
SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing
Ming Li, Xin Gu, Fan Chen +4
Due to the challenges of manually collecting accurate editing data, existing datasets are typically constructed using various automated methods, leading to noisy supervision signal…
Vidi: Large Multimodal Models for Video Understanding and Editing
Vidi Team, Celong Liu, Chia-Wen Kuo +20
Humans naturally share information with those they are connected to, and video has become one of the dominant mediums for communication and expression on the Internet. To support t…
Where do Large Vision-Language Models Look at when Answering Questions?
Xiaoying Xing, Chia-Wen Kuo, Li Fuxin +6
Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks. However, their visual understanding behaviors remain und…