Including results for grupo sft.
Do you want results only for Grpo SFT?
🔥 VibeThinker-3B: SFT+GRPO로 Opus 4.5 추론 성능을 넘긴 3B 모델
1:00
🔥 VibeThinker-3B: SFT+GRPO로 Opus 4.5 추론 성능을 넘긴 3B 모델
24 views1 week ago
YouTubeICBM
SFT vs DPO vs GRPO vs PPO (In 30 Seconds) #LLM #ML #AI
0:10
SFT vs DPO vs GRPO vs PPO (In 30 Seconds) #LLM #ML #AI
96 views4 months ago
YouTubeNeurons Decoded
gemma3_1b reasoning capability improvement
2:51
gemma3_1b reasoning capability improvement
7 views5 months ago
YouTubeVrush
【RLT强化学习项目实战】基于教师-学生范式训练数学大模型，全面提升推理能力！用GRPO训练Qwen3模型｜SFT+RL两阶段训练全流程
4:23
【RLT强化学习项目实战】基于教师-学生范式训练数学大模型，全面提升 …
813 views11 months ago
bilibili唐国梁Tommy
SFT to GRPO - Our Solution to Google Tunix Hackathon
1:59
SFT to GRPO - Our Solution to Google Tunix Hackathon
5 views5 months ago
YouTubeAdson Machine
3B Model Beats Claude Opus 4.5 at Reasoning
0:39
3B Model Beats Claude Opus 4.5 at Reasoning
153 views2 weeks ago
YouTubeUnbearable TechTips
From Token Reward to Embedding Reward: GRPO, SCP & the Future of AI Training
2:50
From Token Reward to Embedding Reward: GRPO, SCP & the Future …
132 views5 months ago
YouTubeXiaol.x
4:20
The Secret to General AI Anomaly Detection (Anomaly-R1)
4 views2 months ago
YouTubeCollapsedLatents
4:56
TP-GRPO: Improving Flow-Based Image Generation
17 views4 months ago
YouTubeAI Research Roundup
2:42
New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn t…
38.9K viewsMay 21, 2025
FacebookAndrew Ng
0:55
GRPO: how DeepSeek-R1 trained reasoning without a critic, reward …
1K views2 months ago
YouTubeAdam Rosler
4:02
Understanding GRPO: The Technique Behind DeepSeek’s Re…
8 views2 months ago
YouTubePraveen Reddy Learnings
4:10
GDPO Paper Review | Fixing GRPO Reward Normalization Collapse in …
4 views5 months ago
YouTubeCosmoX
3:45
Lumi- AI voice companion for dementia and Alzheimer's care
7 views1 month ago
YouTubeDebdeep Banerjee
1:44
Dr. GRPO vs GSPO: The Bias-Variance Tradeoff
2.2K views4 months ago
YouTubeDeep Learning with Yacine
1:39
Tracing GRPO's Biased Objective Back to DeepSeek Math
1.9K views3 months ago
YouTubeDeep Learning with Yacine
1:16
Flash-GRPO: Efficient Video Diffusion Alignment via One-Step …
33 views1 month ago
YouTubeAI Paper Slop
1:43
FireRed-OCR: The AI That Masters Document Structure (Open-Sourc…
7 views3 months ago
YouTubeCollapsedLatents
See more videos
Static thumbnail place holder