nvidia/Nemotron-Cascade-2-SFT-Data
Viewer ā¢ Updated ā¢ 15.9M ā¢ 11.5k ā¢ 65
Crypti
CryptoAIM
AI & ML interests
None yet
Recent Activity
liked a dataset 1 day ago
nvidia/Nemotron-Cascade-2-SFT-Data liked a dataset 1 day ago
Modotte/CodeX-2M-Thinking liked a model 2 days ago
armand0e/Qwen3.5-9B-AgentOrganizations
None yet
liked 2
datasets 1 day ago
liked 2
models 2 days ago
reacted to SeaWolf-AI's post with š„ 2 days ago
Post
5143
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-REASON
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-REASON
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
- 3 replies
liked 3
datasets 3 days ago
500 Internal Server Error: unable to load model
4
#1 opened 29 days ago
by 
ArkanFreelance
TeichAI/gemma-4-31B-it-Claude-Opus-Distill-GGUF
#9837 opened 5 days ago
by CryptoAIM
liked a
model 6 days ago
liked a
dataset 6 days ago
website?
12
#1 opened 15 days ago
by CryptoAIM
liked a
dataset 7 days ago
updated a
model 7 days ago
liked a
model 7 days ago
published a
model 7 days ago
liked a
dataset 7 days ago
liked a
model 9 days ago
liked a
dataset 10 days ago