Hugging Face Daily Papers · · 7 min read

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

From paper to poster, video, blog, and reel — Automating the Last Mile of Research Dissemination.\n\n**ResearchStudio** streamlines the final steps of a research project — the materials a paper needs *after* the writing is done. Drop in one PDF and get back the artifacts that turn a paper into a conference submission and a public release: a structured asset bundle, a print-ready poster, a narrated walkthrough video, a bilingual blog post ready for an editor, and an interactive reel viewer.\n\n<!-- Hero strip: two demos side by side. Left: the Paper2Reel interactive reel walkthrough. Right: a real Paper2Poster build. -->\n<table align=\"center\">\n<tr>\n<td align=\"center\" valign=\"top\" width=\"49%\">\n<img src=\"https://raw.githubusercontent.com/ai-nuts/Storage/main/ResearchStudio/ResearchStudio-Reel/docs/figures/reel_demo.gif\" alt=\"Paper2Reel — interactive reel feature demo\" width=\"100%\">\n</td>\n<td align=\"center\" valign=\"top\" width=\"50%\">\n<a href=\"https://raw.githubusercontent.com/ai-nuts/Storage/main/ResearchStudio/ResearchStudio-Reel/docs/examples/latent_diffusion_landscape/poster.png\" target=\"_blank\" rel=\"noopener\"><img src=\"https://raw.githubusercontent.com/ai-nuts/Storage/main/ResearchStudio/ResearchStudio-Reel/docs/figures/poster_demo.gif\" alt=\"Paper2Poster — building a conference poster from one PDF\" width=\"100%\"></a>\n</td>\n</tr>\n\n<tr>\n<td align=\"center\" valign=\"top\"><sub><b>Paper2Reel</b> — presenting an interactive reel.</sub></td>\n<td align=\"center\" valign=\"top\"><sub><b>Paper2Poster</b> — building a poster from one PDF.</sub></td>\n</tr>\n\n</table>","html":"<h1 class=\"relative group flex items-baseline\">\n\t<a id=\"researchstudio---reel\" class=\"block pr-1.5 text-lg md:absolute md:p-1.5 md:opacity-0 md:group-hover:opacity-100 md:right-full\" href=\"#researchstudio---reel\" rel=\"nofollow\">\n\t\t<span class=\"header-link\"><svg class=\"text-gray-500 hover:text-black dark:hover:text-gray-200 w-4\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" aria-hidden=\"true\" role=\"img\" width=\"1em\" height=\"1em\" preserveAspectRatio=\"xMidYMid meet\" viewBox=\"0 0 256 256\"><path d=\"M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z\" fill=\"currentColor\"></path></svg></span>\n\t</a>\n\t<span>\n\t\tResearchStudio - Reel\n\t</span>\n</h1>\n<blockquote>\n<p>From paper to poster, video, blog, and reel — Automating the Last Mile of Research Dissemination.</p>\n</blockquote>\n<p><strong>ResearchStudio</strong> streamlines the final steps of a research project — the materials a paper needs <em>after</em> the writing is done. Drop in one PDF and get back the artifacts that turn a paper into a conference submission and a public release: a structured asset bundle, a print-ready poster, a narrated walkthrough video, a bilingual blog post ready for an editor, and an interactive reel viewer.</p>\n\n<table align=\"center\">\n<tbody><tr>\n<td align=\"center\" valign=\"top\" width=\"49%\">\n<img src=\"https://raw.githubusercontent.com/ai-nuts/Storage/main/ResearchStudio/ResearchStudio-Reel/docs/figures/reel_demo.gif\" alt=\"Paper2Reel — interactive reel feature demo\" width=\"100%\">\n</td>\n<td align=\"center\" valign=\"top\" width=\"50%\">\n<a href=\"https://raw.githubusercontent.com/ai-nuts/Storage/main/ResearchStudio/ResearchStudio-Reel/docs/examples/latent_diffusion_landscape/poster.png\" rel=\"nofollow\"><img src=\"https://raw.githubusercontent.com/ai-nuts/Storage/main/ResearchStudio/ResearchStudio-Reel/docs/figures/poster_demo.gif\" alt=\"Paper2Poster — building a conference poster from one PDF\" width=\"100%\"></a>\n</td>\n</tr>\n\n<tr>\n<td align=\"center\" valign=\"top\"><sub><b>Paper2Reel</b> — presenting an interactive reel.</sub></td>\n<td align=\"center\" valign=\"top\"><sub><b>Paper2Poster</b> — building a poster from one PDF.</sub></td>\n</tr>\n\n</tbody></table>","updatedAt":"2026-07-07T02:27:49.978Z","author":{"_id":"64c66647725ffa04b2fd6c94","avatarUrl":"/avatars/620f63f27fa1e90423b0dc22aa8e5809.svg","fullname":"yangyu huang","name":"yangyu90","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6036145091056824},"editors":["yangyu90"],"editorAvatarUrls":["/avatars/620f63f27fa1e90423b0dc22aa8e5809.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.04438","authors":[{"_id":"6a4c62a325849b193a834020","name":"Lingao Xiao","hidden":false},{"_id":"6a4c62a325849b193a834021","name":"Yalun Dai","hidden":false},{"_id":"6a4c62a325849b193a834022","name":"Yangyu Huang","hidden":false},{"_id":"6a4c62a325849b193a834023","name":"Qihao Zhao","hidden":false},{"_id":"6a4c62a325849b193a834024","name":"Wenshan Wu","hidden":false},{"_id":"6a4c62a325849b193a834025","name":"Hugo He","hidden":false},{"_id":"6a4c62a325849b193a834026","name":"Ruishuo Chen","hidden":false},{"_id":"6a4c62a325849b193a834027","name":"Jin Jiang","hidden":false},{"_id":"6a4c62a325849b193a834028","name":"Qianli Ma","hidden":false},{"_id":"6a4c62a325849b193a834029","name":"Jiahuan Zhang","hidden":false},{"_id":"6a4c62a325849b193a83402a","name":"Xin Zhang","hidden":false},{"_id":"6a4c62a325849b193a83402b","name":"Ying Xin","hidden":false},{"_id":"6a4c62a325849b193a83402c","name":"Yang Ou","hidden":false},{"_id":"6a4c62a325849b193a83402d","name":"Yan Xia","hidden":false},{"_id":"6a4c62a325849b193a83402e","name":"Scarlett Li","hidden":false},{"_id":"6a4c62a325849b193a83402f","name":"Longbo Huang","hidden":false},{"_id":"6a4c62a325849b193a834030","name":"Zhipeng Zhang","hidden":false},{"_id":"6a4c62a325849b193a834031","name":"Yang He","hidden":false},{"_id":"6a4c62a325849b193a834032","name":"Yap Kim Hui","hidden":false},{"_id":"6a4c62a325849b193a834033","name":"Yan Lu","hidden":false}],"publishedAt":"2026-07-05T00:00:00.000Z","submittedOnDailyAt":"2026-07-07T00:00:00.000Z","title":"ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog","submittedOnDailyBy":{"_id":"64c66647725ffa04b2fd6c94","avatarUrl":"/avatars/620f63f27fa1e90423b0dc22aa8e5809.svg","isPro":false,"fullname":"yangyu huang","user":"yangyu90","type":"user","name":"yangyu90"},"summary":"Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile. Prior automation treats each artifact in isolation that each re-extract the paper from scratch, usually ship one-way renders the author cannot reopen in PowerPoint or Word, and gates quality on soft VLM-preference scores that plateau while load-bearing sections still read as empty. We argue this last mile is best built as a composition of skills: thin agent-readable contracts that share one upstream extractor and wrap deterministic primitives in a measured-fill loop whose exits are hard pass/fail render gates. We instantiate this as ResearchStudio-Reel, five Claude Code and Codex skills organized into one shared extractor (Paper2Assets), three editable generators (Paper2Poster, Paper2Video, Paper2Blog), and one interactive convergence layer (Paper2Reel). Paper2Assets extracts each paper once into a shared bundle that can be reused by every downstream skill; The three generators produce a print-ready poster, a synchronized talk video, and a bilingual blog that stay factually consistent and round-trip through PowerPoint or Word; Paper2Reel then binds all three into a self-contained HTML viewer whose section-level clicks jump the video, slides, captions, and blog to matching content. On the Paper2Poster benchmark, our posters lead every aesthetic and information sub-criterion against both prior automated systems and single-shot frontier LLMs, surpassing the authors' own on aesthetics under two held-out VLM judges and winning overall on 84% to 93% of papers; capability audits further show that, by uniquely pairing narration-aligned on-slide highlights with a bilingual blog gated by layout-aware DOCX repair, ResearchStudio-Reel is the only pipeline to ship all three editable artifacts. Project is available at https://aka.ms/ResearchStudio","upvotes":47,"discussionId":"6a4c62a325849b193a834034","projectPage":"https://aka.ms/ResearchStudio","ai_summary":"ResearchStudio-Reel automates research dissemination by composing specialized skills around a shared paper extractor, generating consistent and editable artifacts including posters, videos, and blogs with hard pass/fail quality gates.","ai_keywords":["research dissemination","automated artifact generation","paper extraction","poster generation","talk video creation","blog post writing","VLM preference scores","deterministic primitives","measured-fill loop","render gates","paper-to-assets extractor","editable generators","interactive convergence layer","HTML viewer","section-level navigation","layout-aware DOCX repair","capability audit"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"5e6485f787403103f9f1055e","name":"microsoft","fullname":"Microsoft","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1583646260758-5e64858c87403103f9f1055d.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64c66647725ffa04b2fd6c94","avatarUrl":"/avatars/620f63f27fa1e90423b0dc22aa8e5809.svg","isPro":false,"fullname":"yangyu huang","user":"yangyu90","type":"user"},{"_id":"65162ceca546159af98d6721","avatarUrl":"/avatars/8d0f58bcb83cd2e95512885c1b6e4a26.svg","isPro":false,"fullname":"LINGAO XIAO","user":"xiaolingao","type":"user"},{"_id":"6463554dd2044cd1d7c6e0bf","avatarUrl":"/avatars/d7653623117268c545a7063fec69664b.svg","isPro":false,"fullname":"Bingzheng Wei","user":"Bingzheng","type":"user"},{"_id":"6448b2f53e7b3c11be684348","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg","isPro":true,"fullname":"Qianli Ma","user":"Mqleet","type":"user"},{"_id":"661aaed0eee5f3104f993c31","avatarUrl":"/avatars/48e3a606a903ba660442f41dd8b40863.svg","isPro":false,"fullname":"Huanhuan","user":"Chrishuanhuan","type":"user"},{"_id":"67694a8afafd99c6a775ac48","avatarUrl":"/avatars/1d3c7dcb60fefd5fc20b3bfa47d0cf18.svg","isPro":false,"fullname":"Yan Xia","user":"sd983527","type":"user"},{"_id":"60657370abd8d3692e3e2edd","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60657370abd8d3692e3e2edd/fPhOarSFs8G-OqnzsgDe5.jpeg","isPro":false,"fullname":"jiangjin","user":"jiangjin","type":"user"},{"_id":"661230e7941ed67394a873e7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/661230e7941ed67394a873e7/MoQ-FHlTu1In-UpG6E9j2.jpeg","isPro":false,"fullname":"Li Yu","user":"phxember","type":"user"},{"_id":"646217dab7fb9d680861368b","avatarUrl":"/avatars/94f3c860294a5b25bd62a674797d4c42.svg","isPro":false,"fullname":"Chen","user":"v-xchen-v","type":"user"},{"_id":"65373f89912eef2590908272","avatarUrl":"/avatars/8c21b9b3a7818e5eaf7d2bdfeab242ad.svg","isPro":false,"fullname":"somebody","user":"neverstop","type":"user"},{"_id":"64b749f58c632fbca93fdd74","avatarUrl":"/avatars/613f2412c7163376a88704ef4d139e65.svg","isPro":false,"fullname":"Lin Luo","user":"Lidaluobei","type":"user"},{"_id":"622eb138165ba2c1bcbc76ed","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/622eb138165ba2c1bcbc76ed/zWbMA3TWI-MUcqwFK9wRx.png","isPro":false,"fullname":"Scarlett Li","user":"dongbing","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":3,"organization":{"_id":"5e6485f787403103f9f1055e","name":"microsoft","fullname":"Microsoft","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1583646260758-5e64858c87403103f9f1055d.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.04438.md","query":{}}">
Papers
arxiv:2607.04438

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

Published on Jul 5
· Submitted by
yangyu huang
on Jul 7
#3 Paper of the day
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

ResearchStudio-Reel automates research dissemination by composing specialized skills around a shared paper extractor, generating consistent and editable artifacts including posters, videos, and blogs with hard pass/fail quality gates.

Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile. Prior automation treats each artifact in isolation that each re-extract the paper from scratch, usually ship one-way renders the author cannot reopen in PowerPoint or Word, and gates quality on soft VLM-preference scores that plateau while load-bearing sections still read as empty. We argue this last mile is best built as a composition of skills: thin agent-readable contracts that share one upstream extractor and wrap deterministic primitives in a measured-fill loop whose exits are hard pass/fail render gates. We instantiate this as ResearchStudio-Reel, five Claude Code and Codex skills organized into one shared extractor (Paper2Assets), three editable generators (Paper2Poster, Paper2Video, Paper2Blog), and one interactive convergence layer (Paper2Reel). Paper2Assets extracts each paper once into a shared bundle that can be reused by every downstream skill; The three generators produce a print-ready poster, a synchronized talk video, and a bilingual blog that stay factually consistent and round-trip through PowerPoint or Word; Paper2Reel then binds all three into a self-contained HTML viewer whose section-level clicks jump the video, slides, captions, and blog to matching content. On the Paper2Poster benchmark, our posters lead every aesthetic and information sub-criterion against both prior automated systems and single-shot frontier LLMs, surpassing the authors' own on aesthetics under two held-out VLM judges and winning overall on 84% to 93% of papers; capability audits further show that, by uniquely pairing narration-aligned on-slide highlights with a bilingual blog gated by layout-aware DOCX repair, ResearchStudio-Reel is the only pipeline to ship all three editable artifacts. Project is available at https://aka.ms/ResearchStudio

Community

Paper submitter about 20 hours ago

ResearchStudio - Reel

From paper to poster, video, blog, and reel — Automating the Last Mile of Research Dissemination.

ResearchStudio streamlines the final steps of a research project — the materials a paper needs after the writing is done. Drop in one PDF and get back the artifacts that turn a paper into a conference submission and a public release: a structured asset bundle, a print-ready poster, a narrated walkthrough video, a bilingual blog post ready for an editor, and an interactive reel viewer.

Paper2Reel — interactive reel feature demo Paper2Poster — building a conference poster from one PDF
Paper2Reel — presenting an interactive reel. Paper2Poster — building a poster from one PDF.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Get this paper in your agent:

hf papers read 2607.04438
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2607.04438 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2607.04438 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2607.04438 in a Space README.md to link it from this page.

Collections including this paper 2

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers