mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-03-11 22:03:34 -05:00
2a9b692621
Major cuts to eliminate redundant content: 1. Introduction: - Cut redundant paragraph before contributions (lines 388-389) - Removed repeated examples (Adam, Conv2d, KV caching) from contribution 1 - Simplified contribution 2 (save PyTorch history for Section 4) 2. Related Work: - Condensed bullet comparison list to single paragraph - Cut ~200 words of repeated distinctions 3. Section 3 (TinyTorch Architecture): - Cut redundant problem statement that repeated intro - Streamlined opening 4. Section 4 (Progressive Disclosure): - Cut re-explanation of pedagogical dilemma - Start directly with implementation details 5. Discussion: - Removed entire "Pedagogical Flexibility" subsection (7.2) - Content was duplicate of Section 6.2 configurations - Key rationale points merged into 6.2 Estimated savings: ~1,000 words Paper now builds progressively without restating same concepts. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
TinyTorch Research Paper
Complete LaTeX source for the TinyTorch research paper.
Files
- paper.tex - Main paper (~12-15 pages, two-column format)
- references.bib - Bibliography (22 references)
- compile_paper.sh - Build script (requires LaTeX installation)
Quick Start: Get PDF
Option 1: Overleaf (Recommended)
- Go to Overleaf.com
- Create free account
- Upload
paper.texandreferences.bib - Click "Recompile"
- Download PDF
Option 2: Local Compilation
./compile_paper.sh
Requires LaTeX installation (MacTeX or BasicTeX).
Paper Details
- Format: Two-column LaTeX (conference-standard)
- Length: ~12-15 pages
- Sections: 7 complete sections
- Tables: 3 (framework comparison, learning objectives, performance benchmarks)
- Code listings: 5 (syntax-highlighted Python examples)
- References: 22 citations
Key Contributions
- Progressive disclosure via monkey-patching - Novel pedagogical pattern
- Systems-first curriculum design - Memory/FLOPs from Module 01
- Historical milestone validation - 70 years of ML as learning modules
- Constructionist framework building - Students build complete ML system
Framed as design contribution with empirical validation planned for Fall 2025.
Submission Venues
- ArXiv - Immediate (establish priority)
- SIGCSE 2026 - August deadline (may need 6-page condensed version)
- ICER 2026 - After classroom data (full empirical study)
Ready for submission! Upload to Overleaf to get your PDF.