Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
Paper ā¢ 2605.14386 ā¢ Published ā¢ 43
TenAI PRO
honey90
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning reacted to SeaWolf-AI's post with š„ about 21 hours ago
š§¬ 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 ā sharing the core ideas below.
š Paper: https://huggingface.co/papers/2605.14386
š arXiv: https://arxiv.org/abs/2605.14386
š 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 ā with zero
gradient-based training ā it reaches frontier-level reasoning.
- š Darwin-28B-Opus: GPQA Diamond 88.89%
- šø Zero gradient steps ā not a single B200 or H200 hour needed
- š§¬ Consistent gains across 4B ā 35B scale
- š Cross-architecture breeding between Transformer and Mamba families
- š Stable recursive multi-generation evolution
#Three Core Mechanisms
ā 14-dim Adaptive Merge Genome ā fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
ā” MRI-Trust Fusion ā 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 ā Darwin learns the balance from data.
ā¢ Architecture Mapper ā weight-space breeding across heterogeneous
families. Attention Ć SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them ā no gradients required.
Replies and critiques welcome šOrganizations
None yet
upvoted a paper about 18 hours ago
upvoted an article about 21 hours ago
Article
Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step
FINAL-Bench
ā¢ ā¢ 12 reacted to SeaWolf-AI's post with š„ about 21 hours ago
Post
2069
š§¬ 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 ā sharing the core ideas below.
š Paper: Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning (2605.14386)
š arXiv: https://arxiv.org/abs/2605.14386
š Model: 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 ā with zero
gradient-based training ā it reaches frontier-level reasoning.
- š Darwin-28B-Opus: GPQA Diamond 88.89%
- šø Zero gradient steps ā not a single B200 or H200 hour needed
- š§¬ Consistent gains across 4B ā 35B scale
- š Cross-architecture breeding between Transformer and Mamba families
- š Stable recursive multi-generation evolution
#Three Core Mechanisms
ā 14-dim Adaptive Merge Genome ā fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
ā” MRI-Trust Fusion ā 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 ā Darwin learns the balance from data.
ā¢ Architecture Mapper ā weight-space breeding across heterogeneous
families. Attention Ć SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them ā no gradients required.
Replies and critiques welcome š
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 ā sharing the core ideas below.
š Paper: Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning (2605.14386)
š arXiv: https://arxiv.org/abs/2605.14386
š Model: 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 ā with zero
gradient-based training ā it reaches frontier-level reasoning.
- š Darwin-28B-Opus: GPQA Diamond 88.89%
- šø Zero gradient steps ā not a single B200 or H200 hour needed
- š§¬ Consistent gains across 4B ā 35B scale
- š Cross-architecture breeding between Transformer and Mamba families
- š Stable recursive multi-generation evolution
#Three Core Mechanisms
ā 14-dim Adaptive Merge Genome ā fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
ā” MRI-Trust Fusion ā 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 ā Darwin learns the balance from data.
ā¢ Architecture Mapper ā weight-space breeding across heterogeneous
families. Attention Ć SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them ā no gradients required.
Replies and critiques welcome š
- 1 reply
liked a
model 1 day ago
liked a
Space 7 days ago
liked a
model 13 days ago
liked a
Space 16 days ago
reacted to SeaWolf-AI's post with š¤ 16 days ago
Post
5071
š Introducing Model Galaxy ā a Living, Multimodal Fork of the HF Model Atlas
š Try it: FINAL-Bench/model-galaxy
This Space is a fork of the brilliant Eliahu/Model-Atlas, the official demo of "Charting and Navigating Hugging Face's Model Atlas" (Horwitz et al., arXiv 2503.10633). Their pre-computed HF model graph is the foundation of every node and edge you see, and we are deeply grateful for its open release.
The original atlas is a static snapshot of early 2025. Model Galaxy turns it into a living, multimodal map. We injected the 2026 trending originals that did not exist when the atlas was frozen ā DeepSeek-V4, Hy3-preview, GLM-5.1, Kimi-K2, gpt-oss, Nemotron-3 Super / Nano / Omni, Hermes-4.3, Qwen3-Coder-Next, Llama-3.3, Granite-4.1, plus the latest multimodal releases (FLUX.2, ERNIE-Image, HunyuanImage / Video, LTX-2.3, Wan2.2, Kokoro-82M, VoxCPM2, Voxtral-TTS, whisper-v3-turbo, Gemma-4, Qwen3-Omni, Phi-4-mm) ā each with proper base_model lineage edges.
We also added the complete VIDRAFT Darwin family ontology: 120 nodes covering Darwin Core, AETHER, every brand variant (Rogue, AWAXIS, TenOS, Warecube), NOESIS-Darwin multimodal extensions, and 40+ community quantizations ā the most complete Darwin lineage view anywhere.
The name "Galaxy" is now literal: our three injected clusters are re-laid out as logarithmic spiral galaxies, with bigger models near the bright cores and quantizations scattering to the outer arms ā just like real star mass distribution. A top-right toggle switches between Galaxy mode (deep-space gradient with 220 animated stars) and Atlas mode (clean white panels for reports). A 15-second progress bar narrates the render, and per-modality / per-company colors make every cluster legible at a glance.
Final scale: 22,480 nodes in the default Modalities atlas, 137,324 in the Large NLP atlas, and a 277-node compact Darwin + Trending view for instant exploration. Feedback and PRs welcome.
š Try it: FINAL-Bench/model-galaxy
This Space is a fork of the brilliant Eliahu/Model-Atlas, the official demo of "Charting and Navigating Hugging Face's Model Atlas" (Horwitz et al., arXiv 2503.10633). Their pre-computed HF model graph is the foundation of every node and edge you see, and we are deeply grateful for its open release.
The original atlas is a static snapshot of early 2025. Model Galaxy turns it into a living, multimodal map. We injected the 2026 trending originals that did not exist when the atlas was frozen ā DeepSeek-V4, Hy3-preview, GLM-5.1, Kimi-K2, gpt-oss, Nemotron-3 Super / Nano / Omni, Hermes-4.3, Qwen3-Coder-Next, Llama-3.3, Granite-4.1, plus the latest multimodal releases (FLUX.2, ERNIE-Image, HunyuanImage / Video, LTX-2.3, Wan2.2, Kokoro-82M, VoxCPM2, Voxtral-TTS, whisper-v3-turbo, Gemma-4, Qwen3-Omni, Phi-4-mm) ā each with proper base_model lineage edges.
We also added the complete VIDRAFT Darwin family ontology: 120 nodes covering Darwin Core, AETHER, every brand variant (Rogue, AWAXIS, TenOS, Warecube), NOESIS-Darwin multimodal extensions, and 40+ community quantizations ā the most complete Darwin lineage view anywhere.
The name "Galaxy" is now literal: our three injected clusters are re-laid out as logarithmic spiral galaxies, with bigger models near the bright cores and quantizations scattering to the outer arms ā just like real star mass distribution. A top-right toggle switches between Galaxy mode (deep-space gradient with 220 animated stars) and Atlas mode (clean white panels for reports). A 15-second progress bar narrates the render, and per-modality / per-company colors make every cluster legible at a glance.
Final scale: 22,480 nodes in the default Modalities atlas, 137,324 in the Large NLP atlas, and a 277-node compact Darwin + Trending view for instant exploration. Feedback and PRs welcome.
liked 3
models 16 days ago
liked 6
models 20 days ago
FINAL-Bench/Darwin-28B-KR
Text Generation ā¢ 27B ā¢ Updated ā¢ 401 ā¢ 10
mradermacher/Darwin-9B-NEG-GGUF
9B ā¢ Updated ā¢ 2.56k ā¢ 11
Cheuv/Darwin-4B-Genesis-Q8_0-GGUF
Text Generation ā¢ 8B ā¢ Updated ā¢ 109 ā¢ 10
mradermacher/Darwin-4B-Genesis-GGUF
8B ā¢ Updated ā¢ 2.71k ā¢ 13
mradermacher/Darwin-4B-David-i1-GGUF
8B ā¢ Updated ā¢ 3.24k ā¢ 12
bartowski/FINAL-Bench_Darwin-36B-Opus-GGUF
Text Generation ā¢ 35B ā¢ Updated ā¢ 12.4k ā¢ 34
updated a
model 20 days ago
published a
model 20 days ago
liked a
model 21 days ago