Search Results for author: Yiran Ding

Found 2 papers, 0 papers with code

OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction

no code implementations8 Mar 2024 Ji Zhang, Yiran Ding

We introduce OccFusion, a multi-modal fusion method free from depth estimation, and a corresponding point cloud sampling algorithm for dense integration of image features.

Autonomous Driving Depth Estimation +1

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

no code implementations21 Feb 2024 Yiran Ding, Li Lyna Zhang, Chengruidong Zhang, Yuanyuan Xu, Ning Shang, Jiahang Xu, Fan Yang, Mao Yang

This is achieved by three key innovations: (i) we identify and exploit two forms of non-uniformities in positional interpolation through an efficient search, providing a better initialization for fine-tuning and enabling an 8x extension in non-fine-tuning scenarios; (ii) we introduce a progressive extension strategy that first fine-tunes a 256k length LLM and then conducts a second positional interpolation on the fine-tuned extended LLM to achieve a 2048k context window; (iii) we readjust LongRoPE on 8k length to recover the short context window performance.

8k

Cannot find the paper you are looking for? You can Submit a new open access paper.