Good question. I would say the post-training is usually one of the biggest distinguishing contributors these days
LLMS
-
DeepSeek V3.2 and Arcee Trinity Release Timeline Updates
By
–
It's been two whole months since DeepSeek V3.2 and two whole weeks since Arcee Trinity!
-

GLM-4.5: Notable benchmark performance between o3 and Claude
By
–
I think 4.5 was the first really notable one. Benchmark-wise it sat between between OpenAI o3 and Claude 4 Opus.
I have a brief section about it in my Big LLM Architecture Comparison article: https://
magazine.sebastianraschka.com/i/168650848/11
-glm-45
… -

New Open-Weight Models Coming Soon for Analysis
By
–
And so it begins. Looks like / I hope there will be some fresh open-weight models to analyze and write about soon… It's been a while!
-
Model-Agnostic Approach Recovers 90% Sequence Packing Gains
By
–
5/5 Because this approach is model-agnostic, it applies to any architecture. Even on transformers (like Qwen2.5-7B by @alibaba_cloud
, this method recovers ~90% of the gains of sequence packing, without relying on specific attention implementations. Full breakdown + -

Model-Agnostic Approach: Minimizing Padding with Truncation and Batching
By
–
4/5 So we took a different, model agnostic path: minimize padding before it reaches the model using truncation combined with padding-aware batching.
-

Sequence packing: limitations for hybrid models like Jamba
By
–
3/5 Sequence packing helps for transformers, but it relies on architecture-specific support that is often missing and introduces implementation risks for non-transformer or hybrid models like @AI21Labs' Jamba.
-

AI21 Labs Cuts LLM Online-RL Training Time by 70% with Padding Minimization
By
–
1/5 As part of our work on improving the efficiency of our LLM online-RL training pipelines, we cut policy update step time by ~70% by introducing a model-agnostic padding minimization method.
-
DeepSeek’s Architectural Legacy Dominates Chinese AI Development
By
–
They’re not gone. Most Chinese AI companies are still building on architectures derived from DeepSeek.
If you actually read the research papers, it’s obvious. Hype cycles move fast.
Architectural influence lasts much longer.
