5 papers
OPSDL: On-Policy Self-Distillation for Long-Context Language Models
Xinsen Zhang, Zhenkai Ding, Tianjun Pan +4
Extending the effective context length of large language models (LLMs) remains a central challenge for real-world applications. While recent post-training methods have made progres…
Revisiting Radar Perception With Spectral Point Clouds
Hamza Alsharif, Jing Gu, Pavol Jancura +2
Radar perception models are trained with different inputs, from range-Doppler spectra to sparse point clouds. Dense spectra are assumed to outperform sparse point clouds, yet they…
Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models
Jing Gu, Niccolò Cavagnero, Gijs Dubbelman
Leveraging the general world knowledge of Large Language Models (LLMs) holds significant promise for improving the ability of autonomous driving systems to handle rare and complex…
Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
Daxiang Dong, Mingming Zheng, Dong Xu +17
We present Qianfan-OCR, a 4B-parameter end-to-end vision-language model that unifies document parsing, layout analysis, and document understanding within a single architecture. It…
Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs
Fangrui Zhu, Hanhui Wang, Yiming Xie +4
Unlocking spatial reasoning in Multimodal Large Language Models (MLLMs) is crucial for enabling intelligent interaction with 3D environments. While prior efforts often rely on expl…