Goblin
News
AI news by
promptgoblins.ai
|
News
About
News
About
Filtered by:
Fine-Tuning
Clear
Titles
Summaries
7
Post-Training, Not Architecture, Now Drives Major LLM Capability Gains
Research
1
20h ago
7
Post-Training, Not Architecture, Now Drives Major LLM Capability Gains
Research
· 1 src · 20h ago
Discuss
6
Research Paper Explains Why RL Beats SFT for Multi-Task LLM Training: 20% vs 93% Weight Updates
Research
1
Aug 14
6
Research Paper Explains Why RL Beats SFT for Multi-Task LLM Training: 20% vs 93% Weight Updates
Research
· 1 src · Aug 14
Discuss
6
Alibaba Releases Qwen3 27B Open Weights; Unsloth Ships Day-Zero Support for 17GB Consumer Hardware
Updated Aug 14
Open Source
2
Aug 14
6
Alibaba Releases Qwen3 27B Open Weights; Unsloth Ships Day-Zero Support for 17GB Consumer Hardware
Upd Aug 14
Open Source
· 2 srcs · Aug 14
Discuss
7
NVIDIA and Hugging Face Launch Integrated Fine-Tuning for Frontier Video and Image Diffusion Models
Open Source
1
Jul 17
7
NVIDIA and Hugging Face Launch Integrated Fine-Tuning for Frontier Video and Image Diffusion Models
Open Source
· 1 src · Jul 17
Discuss
6
'Antidoom' Technique Cuts LLM Reasoning Model Loop Failures by 7× Using Final Token Preference Optimization
Research
1
Jul 8
6
'Antidoom' Technique Cuts LLM Reasoning Model Loop Failures by 7× Using Final Token Preference Optimization
Research
· 1 src · Jul 8
Discuss
6
Hugging Face Models Now Deploy to Amazon SageMaker Studio in One Click
Infra
1
Jul 7
6
Hugging Face Models Now Deploy to Amazon SageMaker Studio in One Click
Infra
· 1 src · Jul 7
Discuss
7
Fine-Tuned Model on Expert Annotations Outperforms All Frontier LLMs on Financial Document Triage
Research
1
Jul 2
7
Fine-Tuned Model on Expert Annotations Outperforms All Frontier LLMs on Financial Document Triage
Research
· 1 src · Jul 2
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
