Learn from Foundation Model: Fruit Detection Model without Manual Annotationby Yanan Wang, Zhenghao Fei, Ruichen…
BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligenceby Xuewu Lin, Tianwei Lin, Lichao…
Multimodal Autoregressive Pre-training of Large Vision Encodersby Enrico Fini, Mustafa Shukor, Xiujun Li, Philipp Dufter,…
LLaSA: Large Language and Structured Data Assistantby Yao Xu, Shizhu He, Jiabei Chen, Zeng Xiangrong,…
NewsInterview: a Dataset and a Playground to Evaluate LLMs’ Ground Gap via Informational Interviewsby Michael…
MEGL: Multimodal Explanation-Guided Learningby Yifei Zhang, Tianxu Jiang, Bo Pan, Jingyu Wang, Guangji Bai, Liang…
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videosby Yunong Liu, Cristobal…
Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoderby Siting Li,…
Interpretable Language Modeling via Induction-head Ngram Modelsby Eunji Kim, Sriya Mantena, Weiwei Yang, Chandan Singh,…
Neuro-symbolic Learning Yielding Logical Constraintsby Zenan Li, Yunpeng Huang, Zhaoyu Li, Yuan Yao, Jingwei Xu,…