Skip to content

Enhance "Tiny Recursive Model" project page with a new embedded YouTu… #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vukrosic merged 1 commit into from
Oct 15, 2025
Merged

Enhance "Tiny Recursive Model" project page with a new embedded YouTu… #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 14 additions & 2 deletions app/blog/tiny-recursive-model/page.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,7 +186,7 @@ export default function TinyRecursiveModelProject() {
)}

{/* Links to Paper and GitHub */}
<div className="flex flex-wrap items-center justify-center gap-4 mb-8">
<div className="relative z-10 flex flex-wrap items-center justify-center gap-4 mb-8">
<a
href="https://arxiv.org/pdf/2510.04871v1"
target="_blank"
Expand Down Expand Up @@ -218,7 +218,7 @@ export default function TinyRecursiveModelProject() {
</div>

{/* Glow effect for the title */}
<div className="absolute inset-0 text-4xl md:text-5xl lg:text-6xl font-medium leading-tight blur-sm">
<div className="absolute inset-0 text-4xl md:text-5xl lg:text-6xl font-medium leading-tight blur-sm pointer-events-none">
<span className="bg-gradient-to-r from-blue-400/20 via-purple-400/20 to-cyan-400/20 bg-clip-text text-transparent">
{heroData?.title || 'Tiny Recursive Model'}
</span>
Expand Down Expand Up @@ -280,6 +280,18 @@ export default function TinyRecursiveModelProject() {

{/* Article Body */}
<div className="px-8 sm:px-12 pb-20">
<div className="mb-8">
<div className="relative" style={{ paddingTop: '56.25%' }}>
<iframe
className="absolute top-0 left-0 w-full h-full rounded-lg shadow-2xl"
src="https://www.youtube.com/embed/51uVH-sEvk0"
title="YouTube video player"
frameBorder="0"
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
allowFullScreen
></iframe>
</div>
</div>
<div className="prose prose-lg prose-invert max-w-none">
<MarkdownRenderer content={markdownContent} />
</div>
Expand Down
8 changes: 6 additions & 2 deletions components/markdown-renderer.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,6 +106,10 @@ export function MarkdownRenderer({ content }: MarkdownRendererProps) {
img: ({ src, alt }) => {
if (!src) return null;

// Check if this is the architecture diagram that should be smaller
const isArchitectureDiagram = alt?.includes('Architecture') || src?.includes('architecture');
const imageClassName = isArchitectureDiagram ? "w-1/2 h-auto mx-auto" : "w-full h-auto";

// Handle external images
if (typeof src === 'string' && src.startsWith('http')) {
return (
Expand All @@ -115,7 +119,7 @@ export function MarkdownRenderer({ content }: MarkdownRendererProps) {
alt={alt || ''}
width={800}
height={400}
className="w-full h-auto"
className={imageClassName}
loading="lazy"
/>
{alt && (
Expand All @@ -135,7 +139,7 @@ export function MarkdownRenderer({ content }: MarkdownRendererProps) {
alt={alt || ''}
width={800}
height={400}
className="w-full h-auto"
className={imageClassName}
priority={false}
/>
{alt && (
Expand Down
2 changes: 1 addition & 1 deletion public/content/tiny-recursive-model/tiny-recursive-model-content.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ hero:

## The New AI Reasoning Architecture

#### How a 7M Model Beats 1T Models at Sudoku, Mazes, ARC-AGI
How a 7M Model Beats 1T Models at Sudoku, Mazes, ARC-AGI

**The Tiny Reasoning Model (TRM)** uses a 2-layer transformer (7M parameters) that reuses the same layers hundreds of times to reason about problems recursively.

Expand Down
Loading