Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
还是水灵灵地通过了博资答辩
Published:
前些日子主包科研受挫，道心破碎，写了一篇随感录，大意是想退出科研圈，归隐山林。
一些写在参加博士资格答辩前的话
Published:
现在是凌晨三点，我躺在公寓的床上，思绪翻滚，难以入睡，索性起身来到桌前，想写些什么。
春季学期即将结束，最近忙着收尾两个项目、准备明天理论课的final，以及，准备一周之后的博士资格答辩，也即QE。
是的，我们系第一年结束就要QE，形式是向三位系里的教授做二十分钟的研究展示，然后接受一个小时的提问拷打。最后由教授打分决定去留。自己的导师不能参与，也无权干涉。往届确实有人在这个环节栽过跟头，然后退出了项目，所以这并不是走个过场。
我本科学的是芯片设计，但读博的研究方向却大相径庭：人工智能与计算机视觉。回头看，我的第一年很多时间都花在了补足基础知识和摸索实验上，有些挣扎，但也在持续进步。
诚然，进步的感觉让我开心，紧跟科技最前沿也让我兴奋。但我越来越意识到，只有极少数人是真的在享受读博，而我很少感到那种发自内心的热情。这几天我开始反复想一个问题：如果不读这个博，我会去做什么？或者说，如果我有更多选择，我还会选择读这个博吗？
也许不会。
如果只是顺从内心，我可能会去做一些自己喜欢的事情：当篮球教练，做比赛录像分析师，或者认真经营自媒体。此刻写下这些文字时，我感受到的状态，和站在球场上时很像——兴奋又充满动力。做科研偶尔会给我这样的感受，但不持久。
回顾人生的前二十二年，我发现自己好像一直在沿着一条世俗意义上的“正确路径”赶路：初中备战中考，高中备战高考，大学卷绩点卷科研准备出国申请，读了博以后继续卷论文。我似乎也能预见未来的样子：这几年继续卷论文卷实习，临近毕业卷找工，找到工作后卷薪资，然后一直卷到卷不动为止。
周围人好像总是在意你走得快不快、远不远，却鲜有人关心：你走得累不累？开不开心？
而且，当下AI工具的产出和实操能力，常常让我惊叹。它们既给我即将被取代的危机，又让我陷入一种虚无感：寒窗苦读一二十年，所掌握的知识广度，甚至深度，似乎都未必比得上大模型在海量数据上训练几个月后的产出。AI 带来的知识平权，让我重新思考继续待在象牙塔里的必要性；作为一个普通人，我也对白领工作的未来感到不安。
我不确定自己能否完成这次从student到candidate的跨越。如果通过QE，那就先沿着既有道路走下去，走一步看一步。如果没有通过，我也许会gap一段时间，好好想想自己未来到底想做些什么。慢下来，这终究是我的人生。
就算没有达到别人的期待，如何呢，又能怎？
计算机视觉领域正在走进历史的垃圾堆？
Published:
——读 Vincent Sitzmann 的 “The flavor of the bitter lesson for computer vision” 有感。
Is Computer Vision Heading for the Dustbin of History?
Published:
Reflections on Vincent Sitzmann’s “The flavor of the bitter lesson for computer vision”.
从迷茫少年到赴美读博，我在华科大的这四年
Published:
有人说，大学是人生的预演。而对我来说，在华科大的四年，像是一部早已埋下伏笔的成长电影。主角，是一个从迷茫走向坚定的少年。
高校造神之风何时能休
Published:
“这个寝室，全员保研！”“本科期间发表14篇 SCI 论文！”“GPA 全院第一，三年国奖，TA 是这样做到的！”不知从什么时候起，许多高校公众号越来越偏爱此类叙事：把某位优秀学生的深造去向、绩点排名、论文专利、竞赛奖项、学生工作、志愿服务、文体特长一项项摆出来，最后汇成一个几乎无懈可击的样本，以供后生“瞻仰”。也不知道从何时开始，每当我看到这种推文，都会不自觉地产生反感。
portfolio
publications
A Low-Latency and High-Accuracy Dual-Mode Neuron Design for Accelerating Neurological Diseases Simulation and Analysis
Published in IEEE Region 10 Conference (TENCON), Singapore, 2024
Biological realism and computational efficiency are crucial for modeling neurological diseases with spiking neural networks (SNNs), as biological realism is necessary for observing neuron ion channel behaviors and computational efficiency is essential for simulating the action potentials of large-scale networks. However, existing spiking neuron models cannot achieve both high biological realism and computational efficiency, resulting in SNN constructed from a single type of neuron to make a compromise between these two attributes, thus reducing the SNN effectiveness in disease simulation and analysis. In this paper, we propose a dual-mode spiking neuron hardware design with an efficient reconfigurable architecture to achieve both biological realism and computational efficiency for diseases modeling. By exploiting the common arithmetic operators in Hodgkin-Huxley neuron and Adaptive Exponential (AdEx) neuron, our design can reuse the computational units including adder, multiplier, and CORDIC to efficiently realize these two neurons. An optimized pipeline design based on data flow dependency and Reconfigurable Fast-Convergence CORDIC is proposed to reduce overall computation latency, while a dynamic bit-width allocation strategy is employed to improve the implementation accuracy. FPGA implementation result shows that our design significantly improves computation latency and accuracy compared to previous neuron designs.
Recommended citation: Guo, Jiatong, Jinxiang Gao, et al. "A Low-Latency and High-Accuracy Dual-Mode Neuron Design for Accelerating Neurological Diseases Simulation and Analysis." TENCON 2024-2024 IEEE Region 10 Conference (TENCON). IEEE, 2024.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.