$ show yunlong10/Awesome-Video-LMM-Post-Training
This repository is an awesome list curating research papers on Video-LMM Post-Training for video reasoning. It maintains a JSON dataset of paper metadata (title, release date, links, tags, etc.) and uses a Python script to generate a categorized README.md with markdown tables organized by research paradigm (Reinforced Video-LMMs, SFT for Reasoning, Test-Time Scaling, Benchmarks, Surveys). The repository serves as a reference tracker for the latest advancements in enhancing reasoning capabilities of video-focused multimodal models through post-training techniques. The hybrid nature lies in its dual role as both a data collection (the JSON paper metadata) and a lightweight data presentation system (the generation script).
The LLM identified 1 files worth highlighting for reuse:
Converts JSON paper metadata into a categorized markdown awesome list. Reads paper entries, groups by tags (RL, SFT, TTS, Benchmark, Survey), sorts each group by release date descending, and generates markdown tables for each category. Handles papers with multiple tags (appearing in multiple categories) and missing fields gracefully. Demonstrates reusable ETL pattern for academic paper lists with minimal adaptation needed for different datasets or categorization schemes.