BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.coscup.org//coscup-2026//speaker//UDMCG7
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:CST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-coscup-2026-7Q8NTC@pretalx.coscup.org
DTSTART;TZID=CST:20260808T123000
DTEND;TZID=CST:20260808T130000
DESCRIPTION:LLM 與相關技術為科技與人類帶來了巨大的轉變
 。但我們依然不知道 LLM 內部的原理與如何確保 LLM 不會
 有惡意行為。可解釋性技術提供了少數的切入點。與其
 存外部在訓練過程中控制語言模型的行為，不如直接打
 開模型，去直接探索甚至控制LLM的行為。\n\n但這麼重要
 的技術卻鮮少被討論跟應用。這裡我們打開他的面紗，
 為未來控制更強大的 AI 爭取希望\n\nCode: https://github.com/ma
 rty1885/llama.cpp/tree/rwkv-edit
DTSTAMP:20260713T132518Z
LOCATION:TR212
SUMMARY:可解釋性與應用：人類的最終防線 - Martin Chang
URL:https://pretalx.coscup.org/coscup-2026/talk/7Q8NTC/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-coscup-2026-YTHB9R@pretalx.coscup.org
DTSTART;TZID=CST:20260809T093000
DTEND;TZID=CST:20260809T100000
DESCRIPTION:Nekko open sourced the CORE-ET AI inference accelerator design 
 based on Esperanto Technologies' ET-SOC-1 processor. This talk goes into h
 ow open sourcing RTL enables downstream  development\, any what's now poss
 ible only on open source hardware and the RISC-V open ISA \n\nSource: http
 s://github.com/openhwgroup/core-et
DTSTAMP:20260713T132518Z
LOCATION:TR515
SUMMARY:Open Source accelerator chip and how RISC-V plays a role - Martin C
 hang
URL:https://pretalx.coscup.org/coscup-2026/talk/YTHB9R/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-coscup-2026-CKHDBZ@pretalx.coscup.org
DTSTART;TZID=CST:20260809T151000
DTEND;TZID=CST:20260809T154000
DESCRIPTION:As AI workloads continue to expand beyond the cloud\, developer
 s are increasingly looking for open\, efficient\, and flexible platforms t
 o run models at the edge and on personal devices. RISC-V\, as an open inst
 ruction set architecture\, is emerging as a promising foundation for this 
 shift.\nIn this session\, Martin will share practical engineering experien
 ces from building AI-capable RISC-V systems — covering key areas such as
  CPU–accelerator integration\, software stack enablement\, and optimizat
 ion for real-world workloads.\nThe talk will explore how Linux-based envir
 onments can support AI development on RISC-V today\, what challenges remai
 n across toolchains and runtimes\, and how upstream collaboration is helpi
 ng accelerate ecosystem maturity.\n\nMore info: https://events.canonical.c
 om/event/146/contributions/952/
DTSTAMP:20260713T132518Z
LOCATION:TR211
SUMMARY:Bringing AI to RISC-V: From Edge Devices to Developer-Ready Systems
  - Martin Chang\, Yuning Liang
URL:https://pretalx.coscup.org/coscup-2026/talk/CKHDBZ/
END:VEVENT
END:VCALENDAR