2

Accelerating Inference of Discrete Autoregressive Normalizing Flows by Selective Jacobi Decoding
Jiaru Zhang, Juanwu Lu, Xiaoyu Wu, Ziran Wang, Ruqi Zhang
PDF Code OpenReview Full Text 中文全文
LLM4AD: Large Language Models for Autonomous Driving—Concept, Review, Benchmark, Experiments, and Future Trends
LLM4AD reviews large language models for autonomous driving and evaluates their instruction-following, reasoning, deployment, personalized decision-making, and motion-control capabilities through benchmarks and real-world experiments.
Can Cui, Yunsheng Ma, Sung-Yeon Park, Zichong Yang, Yupeng Zhou, Peiran Liu, Juanwu Lu, Juntong Peng, Jiaru Zhang, Ruqi Zhang, Lingxi Li, Yaobin Chen, Jitesh H. Panchal, Amr Abdelraouf, Rohit Gupta, Kyungtae Han, Ziran Wang
PDF Cite DOI IEEE Xplore arXiv Project
AMPERE: A Generic Energy Estimation Approach for On-Device Training
AMPERE provides a generic, layer-wise Gaussian Process approach for estimating the energy consumption of on-device DNN training across heterogeneous models and devices.
Jiaru Zhang, Zesong Wang, Hao Wang, Tao Song, Huai-an Su, Rui Chen, Yang Hua, Xiangwei Zhou, Ruhui Ma, Miao Pan, Haibing Guan
PDF Cite DOI ACM Digital Library arXiv (THOR preprint)
Hierarchical Satellite System Graph for Approximate Nearest Neighbor Search on Big Data
We propose Hierarchical Satellite System Graph (HSSG) and present its index algorithm and search algorithm. The index process can be distributed deployed due to the good parallelism of our designed hierarchical structure. The theoretical analysis reveals that HSSG decreases the search steps and reduces the computational cost and reduces the search time by searching on the hierarchical structure.
Jiaru Zhang, Ruhui Ma, Tao Song, Yang Hua, Zhengui Xue, Chenyang Guan, Haibing Guan
PDF Cite Code
Hierarchical Satellite System Graph for Approximate Nearest Neighbor Search on Big Data