PhysiQuanty/Binary-LLM-POC
Text Generation • Updated • 369 • 9
PhysiQuanty PRO
PhysiQuanty
AI & ML interests
Theoretical Physics, Invariant Tokenization, Standard Model of Particle Physics Applied ML (coming soon)
Recent Activity
reacted to SeaWolf-AI's post with 🔥 about 5 hours ago
🧬 Darwin Family: Zero Gradient Steps, GPQA Diamond 88.89%
How far can we push LLM reasoning *without* training?
Our team at VIDRAFT submitted this paper to Daily Papers yesterday, and it's
currently #3. Huge thanks to everyone who upvoted — sharing the core ideas below.
🔗 Paper: https://huggingface.co/papers/2605.14386
🔗 arXiv: https://arxiv.org/abs/2605.14386
🔗 Model: https://huggingface.co/FINAL-Bench/Darwin-28B-Opus
---
TL;DR
Darwin Family is a training-free evolutionary merging framework.
By recombining the weight spaces of existing LLM checkpoints — with zero
gradient-based training — it reaches frontier-level reasoning.
- 🏆 Darwin-28B-Opus: GPQA Diamond 88.89%
- 💸 Zero gradient steps — not a single B200 or H200 hour needed
- 🧬 Consistent gains across 4B → 35B scale
- 🔀 Cross-architecture breeding between Transformer and Mamba families
- 🔁 Stable recursive multi-generation evolution
#Three Core Mechanisms
① 14-dim Adaptive Merge Genome — fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
② MRI-Trust Fusion — we diagnose each layer's reasoning contribution
via an **MRI (Model Reasoning Importance)** signal and fuse it with
evolutionary search through a **learnable trust parameter**. Trust the
diagnostic too much and search collapses; ignore it and search becomes
inefficient — Darwin learns the balance from data.
③ Architecture Mapper — weight-space breeding across heterogeneous
families. Attention × SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them — no gradients required.
Replies and critiques welcome 🙌 reacted to theirpost with 🔥 about 20 hours ago
❗ Dating apps do not allow us to control the profiles suggested to us based on our mutual search criteria ❗
🧬 If you want to see if your soulmate has already existed, I have published a dataset of 59k anonymized public profiles
https://huggingface.co/datasets/SpiceeChat/OkCupid-59k-Anonymized-Profiles
Are you looking for a female ML engineer who is looking for a male ML engineer and you can't find it on the apps ?
You need to look for her, but more importantly, she needs to look for you.
Personally, I'm looking for a physicist I'm encountering the same problem. I can't find it
My answer : Paradox of choice of dating apps solved by patent ⚡ WO2026082672 ⚡
https://patentscope.wipo.int/search/en/detail.jsf?docId=WO2026082672
J'ai du breveté pour te trouver et on se trouvera bientôt !
reacted to theirpost with 🚀 about 20 hours ago
❗ Dating apps do not allow us to control the profiles suggested to us based on our mutual search criteria ❗
🧬 If you want to see if your soulmate has already existed, I have published a dataset of 59k anonymized public profiles
https://huggingface.co/datasets/SpiceeChat/OkCupid-59k-Anonymized-Profiles
Are you looking for a female ML engineer who is looking for a male ML engineer and you can't find it on the apps ?
You need to look for her, but more importantly, she needs to look for you.
Personally, I'm looking for a physicist I'm encountering the same problem. I can't find it
My answer : Paradox of choice of dating apps solved by patent ⚡ WO2026082672 ⚡
https://patentscope.wipo.int/search/en/detail.jsf?docId=WO2026082672
J'ai du breveté pour te trouver et on se trouvera bientôt !
Organizations
PhysiQuanty/Wiki-Test2
Updated • 61
PhysiQuanty/Wiki-Test
Updated • 59 • 1
PhysiQuanty/Patenty-Test2-Radix-65536
Updated • 2
PhysiQuanty/VOCAB-4294967296-FOUR-SOFTMAX-256
Updated • 20 • 2
PhysiQuanty/Patent-Dual-Cross-Entropie
Updated • 8
PhysiQuanty/Patent-Test-Radix-65536-AutoTokenizer_FineTune
79.7M • Updated • 8
PhysiQuanty/Patenty-0.1
Updated • 2
PhysiQuanty/Patenty1-0.1B
Updated • 4
PhysiQuanty/Patent-Test-Radix-65536-AutoTokenizer
Updated • 6
PhysiQuanty/Patent-Test-Radix-65536
Updated • 1
PhysiQuanty/Binary-Addition-LLM-POC
Text Generation • Updated • 10 • 3