BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Huntsville AI - ECPv6.8.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.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:20250716T180000
DTEND;TZID=America/Chicago:20250716T193000
DTSTAMP:20260424T102044
CREATED:20250515T000330Z
LAST-MODIFIED:20250714T164604Z
UID:1954-1752688800-1752694200@www.hsv.ai
SUMMARY:Virtual Paper Review – Unifying Embeddings: From Words to Pixels
DESCRIPTION:Join us virtually this Wednesday as we crack open the magic behind modern multimodal embeddings and why they’re not just “text embeddings with pictures pasted on.” \nPart I – Foundations\n\n\nModality alignment 101 – How contrastive pre-training pulls text\, images\, and video frames into one joint space. \n\n\nVector anatomy – Why pixel patches\, temporal frame sequences\, and word tokens all reduce to the same dot-product math. \n\n\nEvaluation metrics – What “recall\,” “precision\,” and “rankability” really mean once your queries aren’t just strings. \n\n\nPart II – Deep Dive\nWe’ll explore two recent papers as our testbed for these concepts: \n\nJinaEmbed V4 – A single-path backbone unifying images\, video\, text\, and code.\nOn the Rankability of Visual Embeddings – Recovering numeric “more vs. less” axes with only two labeled examples.\n\nWe’ll finish by surveying how to turn these insights into a two-stage reranking pipeline from dense k-NN recall to lightweight LoRA heads or simple linear probes for precision uplift. \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\nJinaEmbed V4 (PDF): https://arxiv.org/abs/2506.18902\nRankability: https://arxiv.org/abs/2507.03683\n\nDetails: \n\nDate – 7/16/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/85067618698?pwd=lnLbLGFfcKMzjnSplzF9GdkyG9FOJU.1
URL:https://www.hsv.ai/event/unifying-embeddings/
ATTACH;FMTTYPE=image/png:https://www.hsv.ai/wp-content/uploads/2025/05/Unifying-Embeddings-From-Words-to-Pixels.png
END:VEVENT
END:VCALENDAR