# rhfeiyang/HC-DLM

> Official implementation of HC-DLM, a diffusion language model that combines a continuous latent plan with discrete token guidance at every generation step. Code and artifacts are not yet released.

- Magnitude: 0.6 out of 10 — Steady
- Stars: 54 total · +0 stars today, ≈ 2 by evening
- Star trust: star growth looks organic
- Category: Language models · Created: 2026-09-29 · Last push: 2026-10-02
- GitHub: https://github.com/rhfeiyang/HC-DLM · Homepage: https://hc-dlm.github.io/ · Page: https://gitnova.dev/en/r/rhfeiyang/HC-DLM

## Useful for

- Train a diffusion-based text generation model with discrete token guidance
- Compare HC-DLM quality against other diffusion language models on Sudoku and Countdown tasks
- Study the hybrid discrete-continuous diffusion architecture for research

## Why it’s here

- 0 stars so far today, about 2 expected by the end of the day.
- The repository is 5 days old and already has 54 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 9 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 8 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-04: 0, 0, 0, 0, 42, 10, 2, 0

## More in this category

1. **Niko1221/Strata** — 7.1 · Breakout · Language models · C++ · +0 stars today, ≈ 1,297 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md
2. **StayLameBro/backburner** — 5.3 · Early signal · Language models · Python · +0 stars today, ≈ 87 by evening
   A llama.cpp fork that plugs an iPhone into a Mac over USB-C and splits the work: the Mac runs layers 1-40, the iPhone runs 41-64 on its GPU, speeding up prefill and allowing context up to 196k-229k tokens. Aimed at people running…
   Full card: https://gitnova.dev/en/r/StayLameBro/backburner.md
3. **heise3/academic-deai** — 4.5 · Early signal · Language models · Python · +0 stars today, ≈ 70 by evening
   A skill for editing Chinese and English academic prose: removes formulaic AI phrasing while preserving facts, citations, terminology, and author voice.
   Full card: https://gitnova.dev/en/r/heise3/academic-deai.md
4. **zzzz7788990213-ops/EvoVLM** — 4.5 · Early signal · Language models · Python · +0 stars today, ≈ 63 by evening
   Research project on evolutionary search over vision-language inference programs: without fine-tuning weights, it tunes prompts, image preprocessing, and generation budgets to improve the accuracy–latency trade-off on scientific chart…
   Full card: https://gitnova.dev/en/r/zzzz7788990213-ops/EvoVLM.md
5. **jamwithai/production-agentic-rag-course** — 4.4 · Breakout · Language models · Python · +0 stars today, ≈ 135 by evening
   A hands-on course for building a production-grade RAG system: from infrastructure and an arXiv ingestion pipeline to hybrid search, agentic RAG with LangGraph, and a Telegram bot.
   Full card: https://gitnova.dev/en/r/jamwithai/production-agentic-rag-course.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-04 03:12 UTC, updated every 30 minutes.