BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Huntsville AI - ECPv6.8.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Huntsville AI
X-ORIGINAL-URL:https://hsv.ai
X-WR-CALDESC:Events for Huntsville AI
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20250309T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20251102T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250212T180000
DTEND;TZID=America/Chicago:20250212T193000
DTSTAMP:20260425T033705
CREATED:20250209T145141Z
LAST-MODIFIED:20250209T145141Z
UID:1851-1739383200-1739388600@hsv.ai
SUMMARY:Virtual Paper Review - Reasoning
DESCRIPTION:Join us virtually this Wednesday at 6pm to kick off our monthly Paper Review series! We will be holding these sessions every 4 weeks on Zoom. The first one will be led by Josh Phillips: \nThis month we will be exploring the current evolution in AI reasoning models. We will start with a short review of the history of combining reinforcement learning with tree search for reasoning (AlphaGo/MuZero). Then we will cover the real start of the reasoning race with the chain-of-thought innovations highlighted by “Let’s Verify Step by Step.” And finally of course\, we’ll cover the most important insights from DeepSeek’s three recent papers that build on all of this prior foundation: \n\nDeepSeek-V3 – a highly efficient MoE-based approach (671B parameters\, only 37B active per token) powered by advanced CUDA/NCCL optimizations and low-precision (FP8) training\, making huge models tractable on constrained hardware.\nDeepSeek-R1 – the first open demonstration that an LLM can learn complex reasoning purely through RL rewards\, without any annotated examples (r1-zero)\nDeepSeekMath– which introduces GRPO (an alternative to PPO that simplifies training and removes the need for a separate value network).\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks: \n\nMastering Atari\, Go\, Chess and Shogi by Planning with a Learned Model (2019) :  https://arxiv.org/pdf/1911.08265\nLets Verify Step by Step (2023) : https://arxiv.org/abs/2305.20050\nDeepseek V3 Technical Report (2024): https://github.com/deepseek-ai/DeepSeek-V3/blob/main/DeepSeek_V3.pdf\nDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning  (2025) https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf\nDeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models (2025): https://arxiv.org/pdf/2402.03300\n(Bonus) “We’ve got R1 at home” : https://unsloth.ai/blog/r1-reasoning\n\nDetails: \n\nDate – 2/12/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/86964741971?pwd=SXmv4xfY8M6TZbEOIXyYfLu5Y3FAil.1
URL:https://hsv.ai/event/virtual-paper-review-reasoning/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/02/Paper-Series-Reasoning.png
END:VEVENT
END:VCALENDAR