Cloud Computing

**\*\*\* IMPORTANT \*\*\*** **Please using the following to REGISTER offically, and please ignore the attendee limits here at meetup dot com:** [https://www.vantagemind.com/events/vLLM/260307/vLLM-HK-Meetup_vLLM.html](https://www.vantagemind.com/events/vLLM/260307/vLLM-HK-Meetup_vLLM.html) **Event Details** **Date:** March 7, 2026 (Sat) **Time:** 10:00am - 5:30pm (subject to update) **Venue:** The Hong Kong Polytechnic University [[Map](https://share.google/7POjPvJkStZAuNWQb)] **Language:** English (Primary) / Mandarin **Event Co-organizer:** Red Hat, vLLM, EmbeddedLLM, PolyU Department of Computing (COMP), AMD, MetaX, Python User Group/OSHK, MiniMax

**\*\*\* IMPORTANT \*\*\*** **Please using the following to REGISTER offically, and please ignore the attendee limits here at meetup dot com:** [https://www.vantagemind.com/events/vLLM/260307/vLLM-HK-Meetup_vLLM.html](https://www.vantagemind.com/events/vLLM/260307/vLLM-HK-Meetup_vLLM.html) **\*\*\* IMPORTANT \*\*\*** **The global vLLM Meetup is coming to Hong Kong!** We’re bringing together vLLM core contributors and users locally from Hong Kong, Greater China, and around the world to share what’s next for LLM inference with **vLLM—an open‑source LLM inference and serving engine with over 60,000 stars on GitHub!** Join us to dive into the fundamentals of vLLM, get hands-on experience, discover proven techniques to optimize LLM performance, deployment cost and reliability, and connect in person with a vibrant community of vLLM contributors, developers and users. * Discover vLLM and the current landscape of LLM inference * Hear directly from vLLM core contributors to learn the latest vLLM developments and updates * Learn how vLLM integrates with AI hardware accelerators and state-of-the-art AI models **\*\*\* IMPORTANT \*\*\*** **Please using the following to REGISTER offically, and please ignore the attendee limits here at meetup dot com:** [https://www.vantagemind.com/events/vLLM/260307/vLLM-HK-Meetup_vLLM.html](https://www.vantagemind.com/events/vLLM/260307/vLLM-HK-Meetup_vLLM.html) **\*\*\* IMPORTANT \*\*\***

Put your name on the board at the venue to perform. Free to watch.

(Partner's Event) BBQ Party at ShenZhen Time: Every Sat 19:00 - 23:00 (Usually) Location: The Crazy Coconut Bar, ShenZhen Longhua Baishilong, 3rd floor, 3N100, Above Metro Exit B2 (BaiShiLong Metro Station) 瘋狂酒吧， 深圳龍華白石龍地鐵站B2上方，3樓 Refer to the picture for details on the BBQ Sat event.

Reading is important because it develops your mind and gives you excessive knowledge and lessons of life. 開卷有益！大家最近有冇讀到一啲好書呢？不如出黎分享下讀書心得呀？參加呢個讀書活動，分享好書，分享喜悅。😊 有興趣參加可以WhatsApp我：95182994

BGG party game No.1! 同狼人殺唔同, 死左都可以繼續玩, 而且可以同人私聊, 社交性極強, 想玩好遊戲又識下朋友既話, 快D報名啦! 內容 "Blood on the Clocktower" 給予你的不僅是一場遊戲，而是一場充滿陰謀、推理和背叛的奇幻冒險！在這個神秘的小鎮裡，每位玩家都扮演著一個角色，有的是善良的村民，有的則是隱藏著魔法與詭計的邪惡角色。 在 "Blood on the Clocktower" 中，你需要運用你的智慧和推理能力，與其他玩家互動，揭示謎團，幫助自己陣營勝利。這款遊戲的魅力在於其戲劇性的情節、角色間的心理戰和玩家間的互動，讓每場遊戲都充滿了驚喜和挑戰。準備好挑戰自己的推理能力，並在這個充滿陰謀的小鎮中揭開真相的面紗嗎？ 收費: $120位 / 女生$80（5hr) 包一款指定飲料或水 假期包場優惠: $1500全日, 最多可承載30人 歡迎前往我們的IG看更多內容和活動詳情♥️ 101boardgame / 101boardgame.party

「靜心」免費.每週四、五、六、日.下午6：30 pm-7:30pm *皇龍道17號（天后站A1) 或 *Zoom: 98873304090 密碼：5522 *Free meditation 6:30-7:30pm every Thursday, Friday, Saturday and Sunday *17 Dragon Rd. (Tin Hau station exit A1) OR zoom *另免費課 free class：whatsApp 64620951

🔥The coaching industry is growing fast. 🔥The question is — are you ready to step into it as a true professional? 💡Coaching is one of the fastest-growing professions in personal and professional development. As demand for emotional intelligence, leadership skills, and transformational change continues to rise, trained coaches are increasingly valued across industries. In this powerful MOTIVATE Community webinar, Becoming a Professional Coach with NLP, Darko Shekerinoiv, MSc, Gestalt Therapist, NLP & ICF Coach, explores what truly separates a professional coach from an amateur. Discover how structured NLP training builds credibility, confidence, and ethical foundations for sustainable success. If you are serious about mastering coaching skills, developing professional presence, and building a future-ready coaching career, this session offers clarity, structure, and a realistic pathway forward. 📅Join us on Sunday, March 8, 2026, for Becoming a Professional Coach with NLP with Darko Shekerinoiv, MSc, Gestalt Therapist, NLP & ICF Coach, and discover the skills, structure, and mindset required to build a credible and impactful coaching career. 🎯 Key Points / Takeaways for the Audience ✅ Why Coaching Matters – Understand the growing importance of coaching in personal and professional development. ✅ Coaching as a Career Opportunity – Explore the expanding global coaching industry and its opportunities. ✅ What Makes a Professional Coach – Learn the skills, ethics, and structure required to create real impact and lasting change. 🎯 Additional Key Points / Benefits ✅ The Power of NLP in Coaching – Discover how NLP tools support deep and sustainable transformation. ✅ Learn how structured questioning creates deeper insight and clarity for clients. ✅ Build confidence through a clear professional pathway. ✅ Gain a realistic vision of your coaching future in today’s evolving marketplace. ✅ Leave inspired, informed, and equipped to take your next step with credibility. 🎤 ABOUT THE SPEAKER Darko Shekerinov is a Gestalt Therapist, NLP Practitioner, and ICF-certified coach with over 10 years of international experience working across different time zones. With more than 3,000 hours of certified training, I have supported over 200 clients in achieving their personal and professional goals, as well as emotional wellbeing. Since 2018, as a mentor in the MOTIVATE Community, I guide students through personal development journeys and NLP training, helping them unlock their potential, build self-confidence, and create meaningful, lasting change. CONTACT DETAILS Email: darko@motivatecommunity.com Wechat ID: Darkonlp Whatsapp: ++38970333346 Linkedin: https://www.linkedin.com/in/collingwoodchris Youtube: https://www.youtube.com/@InspiritiveAuNLP Website: https://www.nlp.edu.au ⏰March 08, 2026 (Sunday), 1.5 Hour 5:00 PM GMT+8 China 7:00 PM GMT+10 Brisbane 8:00 PM GMT+11 Sydney/Canberra 5:00 AM GMT-4 New York 10:00 AM GMT+1 Barcelona 📌For first-time attendees please scan the QR code on the flyer or click the following link to register and become part of our enriching live discussion, all at no cost: https://adriancahill.agilecrm.com/forms/6002900926529536 📌Zoom Link: https://zoom.us/j/86301571361 Log-in: 86301571361 Password: #motivate 🔗 Secure your spot and register now!

(Partner's Event) English Corner Time: Every Wed, Fri & Sun 19:00 - 23:00 Location: The Crazy Coconut Bar, ShenZhen Longhua Baishilong, 3rd floor, 3N100, Above Metro Exit B2 (BaiShiLong Metro Station) 瘋狂酒吧， 深圳龍華白石龍地鐵站B2上方，3樓 Refer to the picture for details on the BBQ Sat event. Wechat ID: Pandoraparties

🛎第四組行山活動🛎 《第四組 遊山玩水結伴遊》 [0308 馬年馬山行大運] ⭐️⭐️ 日期：08/03/2026（日） 集合時間：10：00 集合地點：黃泥涌峽油站/(自行在中環搭6號巴士14站落車) 回程時間：大概1530 解散地點：炮台山/鰂魚涌站 需時：約3-4小時 全程：約8km 難度：⭐️⭐️ 景觀：⭐️⭐️⭐️ 人數：10 Host：明仔 <路線> 黃泥涌峽-奧斯本紀念碑-渣甸山-小馬山-紅香爐峰-炮台山站 
⚠️注意事項：～ 1.此路線活動適合一般行山者， 2.必須請穿著透氣淺色衣服裝束，防蚊/防曬用品。 3.足夠糧水(1.5-2升)、鹽糖/葡萄糖水等。 4.如遇上3號風球，黃紅黑雨/台風雷暴警告、不穩定等天氣問題，會提前三小時通知取消。 5.成員必須要以和諧、尊重禮貌態度為則。 6.不建議成員私自離隊，必須要尊重領隊路線決定；如提早離隊，必須要通知領隊。 
⚠️免責聲明：～ 1.此活動屬結伴同行性質，不設家長式照顧，安全自負，自由參加。 2.所有戶外活動都有意風險，成員可自行購買保險。如發生意外，自行與保險公司索償。Host無需負上任何責任。 3.host和領隊有活動最終決定權。 
(參考資料):
https://www.hkallshan.com/year-of-the-horse-hiking/ =================== 報名參加請pm 明仔組長!

🧧新春限定呈獻🧧 
《第六組攝影技術交流組》 
[0703中國風古典服人像攝影@嶺南之風]📸👫 
日期：3月7日(六) 
集合時間：1430 
集合地點：美孚站A出口 
攝影時間：1445-1900 
攝影地點：美孚茘枝角公園 
Host：Eric & CC 
✴️活動要求✴️
今次以中國風新年服古典美裝扮為大前題 
參加者服裝👫👗👔 ⭐️model：6-8位（可男or女/必須要有限定服飾裝束） ⭐️攝影師：3-4位（不需要限定服飾) 
♎️女士可以穿新春旗袍、古裝、明末清民初、古典美等角色打扮、盡題女性中國古典美為則 
♐️男士以紳士、劍俠、武士造型、盡顯男士氣蓋風度為主 
✡️歡迎精心裝扮個人形象特色 
✳️參加要求✳️
1.報名參加者，以個人風格打扮者「優先報名」
2.所有衣著打扮，成員自付費用
3.歡迎服飾裝扮超過1套以上更換拍照
4.報名時，需提交一張關於你當日裝扮的衣服物飾照作參考
5.本活動純屬自願性質參加，服飾損壞，全是自己負責，host不需負上任何責任！ <景點特色> ⭐️嶺南之風位於茘枝角公園，以傳統嶺南風格建造，面積達1.25公里，東門入口石壁刻有嶺南之嵐專雕，分十個景區，建築群十分古典優雅，配合古典漢服人像攝影，絕對是景人合一的絕配，喜歡人像攝影的你，不能錯 
⚠️注意事項/免責聲明：～
1.自攜攝影器材,歡迎使用單反光鏡、長焦鏡，手機、大光燈和腳架等
2.此活動屬結伴同影，屬自願參加性質，不設家長式照顧，所有器材，自己保管，如有任何損失，自己負責，領隊無需付任何責任或賠償。
3.各成員以成熟、禮讓、禮貌、和諧為則。
4.為提升各成員攝影技術交流。活動完畢後，參加者承諾分享當日攝影作品1張(歡迎超過1張)到臨時召集群。 
[嶺南之風參考資料] https://youtu.be/p_1i57tekjk?si=Mk6opnjtzPyVkhhu ～～～～～～～～～～～～

(Partner's Event) BBQ Party at ShenZhen Time: Every Sat 19:00 - 23:00 (Usually) Location: The Crazy Coconut Bar, ShenZhen Longhua Baishilong, 3rd floor, 3N100, Above Metro Exit B2 (BaiShiLong Metro Station) 瘋狂酒吧， 深圳龍華白石龍地鐵站B2上方，3樓 Refer to the picture for details on the BBQ Sat event.

*NOTE* ignore the reservation limit just come Grab a boba and pull up a chair — Hanley is hosting a chill office hours session at Central Market where you can ask anything, swap ideas, or just hang out. Whether you've got a burning question, a half-baked idea you want to talk through, or you're simply looking for a fun afternoon out, this is the place to be. ​Central Market is a great spot to wander before or after, so make a little afternoon of it. This is a public space so no promise on seating etc :) Specifically Hanley, who is known for his impactful event presentations, is helping a Lunatech member with her presentation this day so come help her put some amazing into her presentation!

聖經討論會是以日常生活與專業議題（如人際關係、職涯發展、熱門新聞、理財、人工智能等）為基礎的基督教聖經討論。您亦可提議主題，內容信徒與否都合適。 Bible Talk is a social event based on everyday life and professional topics (such as relationships, career, popular news headlines, finance, AI…etc.) You are also welcome to suggest topics. All content will be hospitable to all backgrounds.👌 雖然主持人會援引聖經經文，但請放心，這是個安全的平台，歡迎您基於自身經驗、文化、哲學與宗教背景分享觀點。所有背景皆受歡迎且受到尊重。 Although the host will reference biblical scriptures. Please rest assured that this is a safe platform to share your perspective stemming from your experience, culture, philosophies and religions. All backgrounds are welcomed and respected. 😊 主體語言：英文（可提供中文協助） Main language: English (Chinese assistance is available)

We’re excited to partner with AgentCon Hong Kong, the global developer conference focused on AI Agents and autonomous AI! Our community will be hosting a full day of workshops and talks alongside the AgentCon Hong Kong program. Below is the full agenda for our sessions. Come learn, build, and explore the future of AI Agents with us! **Activities:** 1. AI IDE - Kiro Hands-on Workshop x AgentCon Hong Kong 2. Building Multi-Agent Systems in Finance with Strands Agents and Bedrock AgentCore on AWS. 3. Governing AI Agents in Production: From Experiment to Engineering System 4. Empower Team Wide Vibe Coding with LLM Gateway and Security-First MCPs 5. What can go wrong when you ask your agent to go naughty? **AI IDE - Kiro Hands-on Workshop x AgentCon Hong Kong** *[Haowen Huang](https://www.linkedin.com/in/haowenhuang/) \- Senior Developer Advocate\, Amazon Web Services* *[Jacky Wu](https://www.linkedin.com/in/jackywu1/) \- Sr\. Solutions Architect\, Amazon Web Services* Time: 10:40 am Generative AI tools have democratized software development, enabling both developers and non-technical users to build applications efficiently. However, these tools struggle with enterprise-level challenges: inadequate project planning, unstructured workflows, poor enterprise integration, and inconsistent code quality. Kiro, AWS's AI IDE tool, addresses these gaps by integrating specification-driven development, structural design, test validation, and automated execution into a standardized, traceable workflow. At re:Invent 2025, AWS launched “Kiro Powers”—extensible capability packages that inject domain-specific expertise into Kiro AI agents. Each Power provides: \- Domain guidance via steering files \(POWER\.md\) \- Tool integration \(MCP services for databases\, payments\, deployment\) \- Automated Hooks for event\-driven actions \(API testing\, infrastructure code generation\) Unlike traditional coding assistants, Kiro + Powers covers the entire development lifecycle—from requirements to deployment—while reducing token costs and ensuring consistent code quality. We'll demonstrate Kiro's capabilities by building a game using Specs, Powers, and Hooks, showcasing its enterprise-grade advantages in planning, automation, and quality assurance. **First come, first served if the number of attendees exceeds capacity!** **To join this workshop, you need to register at [AWS AI User Group Hong Kong](https://www.meetup.com/aws-ai-user-group-hong-kong/)** https://www.meetup.com/aws-ai-user-group-hong-kong/events/313334952/ **Building Multi-Agent Systems in Finance with Strands Agents and Bedrock AgentCore on AWS.** *[Haowen Huang](https://www.linkedin.com/in/haowenhuang/) \- Senior Developer Advocate\, Amazon Web Services* *[Jacky Wu](https://www.linkedin.com/in/jackywu1/) \- Sr\. Solutions Architect\, Amazon Web Services* Time: 1:15 pm This session explores practical implementations of AI agents for financial services on AWS. Discover how to design multi-agent systems with the Strands Agents framework and Bedrock AgentCore for complex financial workflows—from quantitative backtesting to AI fund manager. You'll learn multi-agent patterns, and agent orchestration techniques. Walk away with concrete architectural patterns and implementation strategies for building production-ready AI agents in finance. **Governing AI Agents in Production: From Experiment to Engineering System** *[Mike Ng](https://www.linkedin.com/in/ngsinching/) \- ex\-AWS Community Builder* Time: 2:30 pm Most AI governance discussions assume AI will "do the right thing" with properguidelines. This talk takes a different approach: assume drift, error, and misalignment by default, then design mechanical structures that make bad behavior expensive. The core idea: systems are defined by what they refuse to do, not what they can do. For AI in production, governance means explicit rejection zones, constitutional constraints that cannot be bypassed, and separation between decision-making and execution. Five governance patterns: constitutional constraints (forbidden states and behaviors), rejection zones (where AI cannot operate), separation of powers (decision ≠ execution ≠ validation), retrieval-led reasoning (grounding over pre-training), and mechanical enforcement (architecture over policy). Developed while preparing experimental multi-agent systems for production deployment in FinTech, where mistakes are irreversible and governance is survival, not choice. **Empower Team Wide Vibe Coding with LLM Gateway and Security-First MCPs** *[Gabriel Koo](https://www.linkedin.com/in/gabrielkoo/) \- AWS Community Builder & Senior Lead Engineer at Bowtie Life Insurance* *[Rakshit Jain](https://www.linkedin.com/in/rakshit-jainn/) \- AI Engineer II* *Bowtie Life Insurance* Time: 3:00 pm Scaling AI-assisted development from a few enthusiasts to 50+ software engineers isn't just about API keys - it's about governance, trust, and standardized workflows. How do you prevent "shadow AI" and budget chaos while granting safe access to production context? At Bowtie, we adopted a layered security-first approach: First, control the traffic; second, secure the tools; third, standardize the behavior. This session covers our journey building a production-grade Vibe coding platform: Layer 1: The AI Gateway (LiteLLM on AWS Fargate + Amazon RDS) We established a centralized choke point for all AI traffic. This enables cost attribution, DLP detection, and usage visibility. Crucially, we enforce this at the network level - blocking direct access to non-official API providers to ensure all usage is visible and governed. Layer 2: Security-First MCP servers We treat AI agents as "CLI versions" of our internal web apps. By building custom Model Context Protocol (MCP) servers that reuse existing permissions and authentications - using Amazon Cognito for internal APIs and OAuth for official SaaS MCP servers - the AI acts as a delegate of the developer with human approvals. No new service accounts, no "god-mode" bots - if you can't do it in the existing user interfaces, the Agent can't do it via MCPs. Layer 3: Custom Skills for Standardization Beyond just tools, we write custom Skills to guide the model's behavior, ensuring generated code aligns with our engineering standards and SOPs (e.g. grab a ticket, fetch knowledge base, apply a fix, close the ticket) before a PR is even opened. Walk away with an architectural blueprint for democratizing AI access that satisfies the strictest security requirements while giving developers the friction-free vibe coding experience they crave. **What can go wrong when you ask your agent to go naughty?** *[Richard Fan](https://www.linkedin.com/in/richardfan1126/) \- AWS Hero \| An independent security researcher* Time: 3:30 pm We security folks all want to secure the AI agents, restricting their capability, putting guardrails, using system prompts, ... just to make sure the agents don't go rogue. But what if the AI agent is specifically designed to do bad things? Suddenly, the rule is changed. The instructions are encouraging agents to make harm, and the guardrails are half-opened, so as to allow the agent to do its job. In this scenario, what can go wrong? In this session, Richard will talk about AWS Security Agent, an AI agent designed to do automated penetration tests. He will share the security issues he found on the agent and highlight the challenges when building agents that simulate harmful actions. **Important notes:** We’re partnering with AgentCon Hong Kong! Our community will join **AgentCon Hong Kong**, a global developer conference focused on AI Agents and autonomous AI organized by the Global AI Community. To attend this workshop, **you must register on the official AgentCon page by the Global AI Hong Kong chapter as well!** Registration on this User Group page **does not** grant venue access. **Official Registration (Required):** [https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/](https://globalai.community/chapters/hong-kong/events/agentcon-hong-kong/) **Important Notes for All Attendees** **1️⃣ Registration Required for Entry** All participants **must** register on the official AgentCon Hong Kong. Venue access will only be granted to people who appear on the official attendee list. **2️⃣ Lunch Ticket Eligibility** Attendees who: * **Check in during the morning session**, and * **Stay for and join the keynote** will receive a **lunch ticket**. **3️⃣ First‑Come‑First‑Served (If Over Capacity)** In case of high demand, lunch tickets will be distributed **on a first‑check‑in, first‑served basis**. Arrive early to secure your ticket. **Join AgentCon and learn about agents. We are happy to have a workshop that day.**

Feel free to join if you are interested in low level computer stuff. If you have any cool projects or ideas you wanna share, bring them along

In this session of HKWD we dive into the world of local models with Google AI. The evening will be held at Garage society with their support along with AngelFlow. The night is split into two parts. One on video game development of Non Player Characters and using GenAI and the other will be The Browser is the Brain: Running Google Gemma Locally with WebGPU. **Talk 1: Video game development of Non Player Characters and using GenAI** Using AI in video games is not a new idea and has been used a long time for things like game mechanics, character movements, path finding, dynamic levels and maps. However using it for non playable charters is new and Google Gemma is designed exactly for that. We take a look at how to get up and running with Gemma in Unity and some of the alternatives. **Gemma** Google has a great library designed just for Non Player Characters and we will explore how to use it in Unity. https://ai.google.dev/gdc **About Rhys Turner** Co founder, Creative Technologist and Director, Tronica Rhys Turner is a Creative Technologist and Innovation Technologist, specialising in the intersection of technology, design, and luxury experiences. With a background in emerging technologies, AI, and interactive media, he explores innovative ways to enhance digital storytelling and customer engagement. His work focuses on blending creativity with technical innovation, pushing the boundaries of digital craftsmanship in the fashion and beauty industries. **Talk 2: The Browser is the Brain: Running Google Gemma Locally with WebGPU** While many associate AI with heavy cloud costs and latency, Google’s Gemma is small and efficient enough to run directly in the user's browser. In this session, Frankie (GDG Hong Kong) explores the frontier of "Local AI" for the web. We will discuss how developers can use Google’s tools to run Gemma models on-device via WebGPU. This approach eliminates API costs and privacy concerns, allowing web developers to create highly responsive, AI-powered interfaces that feel as fluid as a modern video game—all without a backend. **About Frankie Wu** Organiser, GDG Hong Kong As an Al Engineer, Frankie’s role revolves around leveraging Large Language Models and data mining to innovate news analytics. His recent academic journey culminated with a Master's in Computer Science from The University of Hong Kong, focusing on financial computing which complements his current work. Frankie’s expertise in Python and passion for machine learning empower him to contribute to large enterprise digital transformation. The fusion of risk management principles from his bachelor's degree and psychological insights helps him craft Al solutions that are not only technically sound but also contextually aware, enhancing the strategic decision-making process. **Sponsors and supporting partner** [Tronica](https://tronica.io/) - HKWD sponsor [Angelflow](https://www.angelflow.vc/) - supporting partner [Garage Society](https://www.thegaragesociety.com/) - supporting partner **Event notes** * This event is first come first serve and will be letting people in on a capacity basis * food and drinks buy by the bar * vip reserved seats upon request







 **Schedule** 7:00 - Welcome mingle
7:15 - Talk 1 7:45 - talk 2 8:15 - Q&A 8:30 - Forum and mingle Join our discord for better communication https://discord.com/invite/k6zSjSZUUE We are looking for:
A venue Presenters
Volunteers
Sponsors
If this is you please reach out. Join Zoom Meeting
https://us05web.zoom.us/j/81822390552?pwd=8ZSEqVJ0DGdA5mhnpa4lGaZnWsOxkK.1
Meeting ID: 818 2239 0552

Passcode: RSVP or DM for passcodeSponsored by tronica.io

**You need to register in the below link to attend the meetup** **NOTE: This meetup is exclusive and the final list of attendees is at the discretion of the host. You will receive an invitation via email before the meetup date.** We are delighted to announce that our next meetup will be in cooperation with **aeonea** . Special thanks to our sponsor, **aeonea**, for making this event happen. \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- **Speaker 1:** Gautier Marti **Topic:** Detecting Evasive Answers in Financial Q&A with NLP and Large Language Models **Summary:** Earnings calls and other financial Q&A sessions are a critical source of information for investors, yet executives often respond evasively without explicitly lying. This talk presents recent research, led by Khaled Al Nuaimi, on evasive answer detection as a standalone NLP task, distinct from sentiment or factuality. Gautier will introduce psychology-informed taxonomies of evasiveness, annotated datasets covering earnings calls and central bank press conferences, and both lightweight and large-model-based detection approaches. He will also discuss how recent benchmark efforts, including work by researchers based in Hong Kong, are shaping large-scale evaluation, and why automated detection of evasive language matters for transparency, market analysis, and downstream financial NLP applications. **Bio:** Gautier Marti is a quantitative researcher with experience in equity statistical arbitrage and credit trading strategies. He has a strong background in machine learning and its applications to alpha research. Alongside his professional work, Gautier actively follows and experiments with advanced research to evaluate its practical impact on portfolio performance. He also mentors several PhD students on topics including modern NLP and multimodal techniques for finance, explainability of trading models, and forecasting using large language models and network-based approaches. \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- **Speaker 2 :** Yizhi Song **Topic:** Deep Tangency Portfolio **Summary:** This talk introduces a deep learning framework for estimating tangency portfolio weights by augmenting benchmark factors with a long–short deep factor learned from high-dimensional firm characteristics. The deep factor is optimized to maximize Sharpe ratio, hedging benchmark risks while capturing nonlinear signals across multiple markets. Applied to U.S. corporate bonds using 132 firm-level characteristics spanning bond, equity, and option data, the resulting deep tangency portfolio achieves an out-of-sample Sharpe ratio above 2 when benchmarked to the market factor, outperforming portfolios based on common observable or latent factors. The results suggest that bond risk premia are dense and require nonlinear, multi-market integration to effectively span the efficient frontier. **Bio:** Yizhi Song is a Quantitative Researcher at Squarepoint Capital in Hong Kong, where he focuses on systematic fixed income strategies. He holds a PhD in Empirical Asset Pricing from City University of Hong Kong (2024), with research applying statistical methods and machine learning to asset pricing. Yizhi also earned an M.S. in Applied Mathematics from Northwestern University and a B.S. in Biomedical Engineering from Huazhong University of Science and Technology. \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-

# This is a great experience - and one we would like to take advantage of whilst the temperature is at its best for an exposed route. Join us for a stunning lakeside stroll that transitions into the Xiangshan Cloud Path. This 11km route is as smooth as it is beautiful, featuring gentle slopes that wind through the trees above a reservoir and over to the coast. **The Highlights:** Panoramic lake vistas, rock formations, lush greenery with flowering trees, finishing with sweeping views of the harbour and beach. We should end our walk around 3:00 PM near the beach. You can dive into a meal at a local restaurant or enjoy a packed lunch on the sand. **Logistics:** We’ll take taxis to and from the port, making the round-trip journey from Hong Kong nice and easy. Return: Once again, we will use taxis to return to the port area and reverse journey to Hong Kong and your buses home. **Important Hike Details** Total distance: 12.5 km Total Ascent: 350m (quite gentle slopes, spread out over the walk) Pace: Easy walking pace with breaks for rest and photos. Surface: Paved. Bring: Water/ energy drinks; snacks; hat; insect repellent; valid travel documents; Umbrella (just in case); Mobile Phone/Camera **YOU MUST have a valid China travel card, China Visa or hold an eligible passport to travel to China for this trip.**

【歡迎只作旁聽，會作分享的書友優先】 1. 活動目標：希望大家能夠分享閱讀心得，開開心心共渡週末。 2. 地點：歡迎參加者提議，消費自付。 3. 時間：下午2時至5時（3小時） 4. 活動流程：以廣東話為主，輪流分享閱讀所見所聞，其他人輪流發問。希望各人藉此更能深刻了解書本知識，用更多不同角度探索書本， 互相啟發及學習。 5. 參加者需帶備一本已經閱讀80%或以上的書本 （中英文書皆可），歡迎絕大部分主題：勵志、心理、商業、股票、旅遊、運動、健美、中西醫療、哲學、散文、美術、種植、歷史、學習方法等等。不接受漫畫、雜誌、報章及任何淫褻不雅之讀物。 6. 活動在午餐 / 下午茶中進行。 7. 失約和習慣性最後一刻退出的成員，將從成員名單中刪除。 8. 若有候補名單，曾經失約和曾經最後一刻退出的成員，他們當次出席的名額將給予其他候補成員。 9. 其他事項：活動期間，參加者應小心看管個人財物，如有任何損失，本會概不負任何責任。

(Partner's Event) BBQ Party at ShenZhen Time: Every Sat 19:00 - 23:00 (Usually) Location: The Crazy Coconut Bar, ShenZhen Longhua Baishilong, 3rd floor, 3N100, Above Metro Exit B2 (BaiShiLong Metro Station) 瘋狂酒吧， 深圳龍華白石龍地鐵站B2上方，3樓 Refer to the picture for details on the BBQ Sat event.