https://aikm.ai/assets/research-focus-BHbpFbOX.js

1import{r as e}from"./useRouter-Bbx_8wWX.js";import{dt as t,ot as n}from"./index-DOrqagtV.js";var r=e(),i=[{id:`rag`,field:`Retrieval`,h:`Retrieval-augmented generation (RAG)`,p1:`Large language models are fluent but forgetful: they know the public internet, not your organisation. RAG grounds model answers in an enterprise's own documents so responses are accurate, current and citable, the foundation of trustworthy enterprise Q&A, search and assistant systems.`,p2:`Our research examines the full pipeline: document chunking and embedding strategies for mixed English–Chinese corpora, hybrid dense-plus-keyword retrieval, re-ranking, and citation fidelity. We place particular weight on evaluation: frameworks that measure faithfulness and answer completeness, not just fluency.`,themes:`bilingual retrieval quality · long-document strategies · retrieval evaluation benchmarks · hallucination reduction`},{id:`knowledge-graphs`,field:`Structure`,h:`Enterprise knowledge graphs`,p1:`Most institutional knowledge is trapped in unstructured content: contracts, reports, emails, wikis. Knowledge graphs extract the entities and relationships inside that content and connect them into a navigable structure: who worked on what, which product depends on which supplier, how decisions trace to evidence.`,p2:`We study automated graph construction with LLMs, graph-augmented retrieval (GraphRAG) that combines structural and semantic search, and the harder operational problem: keeping a graph current as the organisation, its people and its products change.`,themes:`LLM-based entity and relation extraction · GraphRAG architectures · graph maintenance and versioning · ontology design for business domains`},{id:`agentic-ai`,field:`Autonomy`,h:`Agentic AI systems`,p1:`The next layer above retrieval is action: AI agents that plan multi-step work, call tools, query systems and produce finished outputs such as research memos, reports and process runs. The engineering challenge is reliability; the organisational challenge is control.`,p2:`Our work covers task decomposition, tool-use robustness, multi-agent coordination, and human-in-the-loop checkpoints that let enterprises delegate real workflows without surrendering oversight. We benchmark agent behaviour on realistic enterprise tasks rather than synthetic puzzles.`,themes:`agent reliability measurement · tool and MCP integration patterns · approval and escalation design · agentic workflow economics`},{id:`generative-ai`,field:`Generation`,h:`Multimodal & generative AI`,p1:`Enterprise knowledge is not only text. We research generative models across text, image and video for business use, from technical documentation and marketing assets to full AIGC production pipelines for product design and communication.`,p2:`The questions we pursue are practical: how to keep generated output consistent with brand and factual source material, how to track provenance and comply with emerging disclosure rules, and how the economics of generation at scale change content operations.`,themes:`video generation pipelines · brand-consistent generation · content provenance and watermarking · AIGC workflow design`},{id:`governance`,field:`Governance`,h:`Responsible AI & governance`,p1:`None of the above reaches production in a serious enterprise without governance. We develop frameworks for deploying AI in regulated, bilingual business environments: data privacy under Hong Kong's PDPO and cross-border rules, model risk assessment, auditability of AI-assisted decisions, and readiness for international AI regulation affecting companies that operate globally.`,p2:`This area cuts across every project we run: governance designed in at the start, not retrofitted after an incident.`,themes:`AI risk assessment for SMEs and enterprises · audit trails for agentic systems · regulatory horizon scanning · bilingual policy documentation`}];function a(){return(0,r.jsxs)(r.Fragment,{children:[(0,r.jsx)(`div`,{className:`page-head`,children:(0,r.jsxs)(`div`,{className:`wrap`,children:[(0,r.jsxs)(`nav`,{className:`crumbs`,"aria-label":`Breadcrumb`,children:[(0,r.jsx)(t,{to:`/`,children:`Home`}),` / `,(0,r.jsx)(`span`,{"aria-current":`page`,children:`Research Focus`})]}),(0,r.jsx)(`p`,{className:`eyebrow`,children:`Research focus`}),(0,r.jsx)(`h1`,{children:`Five connected areas, one programme`}),(0,r.jsx)(`p`,{className:`intro`,children:`As one of Hong Kong's pioneering institutes in enterprise knowledge management, our research runs from how machines find knowledge, to how they structure it, act on it, generate with it, and govern it. Eac

1h area feeds the next, all validated against real enterprise data, and all shaped by a farsighted team attentive to the societal impact of deep learning and AI.`})]})}),(0,r.jsx)(`section`,{children:(0,r.jsxs)(`div`,{className:`wrap`,children:[(0,r.jsx)(`div`,{className:`research-list`,children:i.map(e=>(0,r.jsxs)(`div`,{id:e.id,className:`r-row reveal`,children:[(0,r.jsx)(`div`,{className:`field`,children:e.field}),(0,r.jsxs)(`div`,{children:[(0,r.jsx)(`h2`,{children:e.h}),(0,r.jsx)(`p`,{children:e.p1}),(0,r.jsx)(`p`,{children:e.p2}),(0,r.jsxs)(`p`,{className:`themes`,children:[(0,r.jsx)(`strong`,{children:`Current themes:`}),` `,e.themes]})]})]},e.id))}),(0,r.jsxs)(`p`,{style:{marginTop:40,display:`flex`,gap:14,flexWrap:`wrap`},children:[(0,r.jsx)(t,{to:`/contact`,className:`cta-btn blue`,children:`Collaborate with us`}),(0,r.jsx)(t,{to:`/research/ai-km-roi`,className:`cta-btn ghost`,children:`Guide: measuring AI KM ROI`}),(0,r.jsx)(t,{to:`/about`,className:`cta-btn ghost`,children:`About the institute`})]})]})}),(0,r.jsx)(`section`,{className:`tint`,children:(0,r.jsxs)(`div`,{className:`wrap`,children:[(0,r.jsxs)(`div`,{className:`sec-head reveal`,children:[(0,r.jsx)(`p`,{className:`eyebrow`,children:`Research briefs`}),(0,r.jsx)(`h2`,{children:`In-depth notes from our engagements`})]}),(0,r.jsxs)(`ul`,{style:{listStyle:`none`,padding:0,display:`grid`,gap:12},children:[(0,r.jsx)(`li`,{children:(0,r.jsx)(t,{to:`/research/rag-enterprise-patterns`,children:`RAG patterns for enterprise knowledge →`})}),(0,r.jsx)(`li`,{children:(0,r.jsx)(t,{to:`/research/enterprise-knowledge-graphs`,children:`Enterprise knowledge graphs: construction and use →`})}),(0,r.jsx)(`li`,{children:(0,r.jsx)(t,{to:`/research/agentic-ai-governance`,children:`Agentic AI governance checklist →`})}),(0,r.jsx)(`li`,{children:(0,r.jsx)(t,{to:`/research/multimodal-enterprise-ai`,children:`Multimodal AI for enterprise content →`})}),(0,r.jsx)(`li`,{children:(0,r.jsx)(t,{to:`/research/evaluating-enterprise-ai`,children:`Evaluating enterprise AI: groundedness and drift →`})}),(0,r.jsx)(`li`,{children:(0,r.jsx)(t,{to:`/research/llm-cost-optimization`,children:`Cost optimisation for enterprise LLM deployments →`})}),(0,r.jsx)(`li`,{children:(0,r.jsx)(t,{to:`/research/ai-km-roi`,children:`Measuring AI KM ROI →`})})]})]})}),(0,r.jsx)(`section`,{id:`faq`,className:`faq`,children:(0,r.jsxs)(`div`,{className:`wrap`,children:[(0,r.jsxs)(`div`,{className:`sec-head reveal`,children:[(0,r.jsx)(`p`,{className:`eyebrow`,children:`Frequently asked questions`}),(0,r.jsx)(`h2`,{children:`AIKm research focus: FAQ`})]}),n.map(e=>(0,r.jsxs)(`details`,{children:[(0,r.jsx)(`summary`,{children:e.q}),(0,r.jsx)(`p`,{children:e.a})]},e.q))]})})]})}export{a as component};