How GRPO trains LLMs to reason - no labeled data needed
0:14
How GRPO trains LLMs to reason - no labeled data needed
38 views4 weeks ago
YouTubeDaily Dose of Data Science
GRPO: how DeepSeek-R1 trained reasoning without a critic, reward model, or human labels
0:55
GRPO: how DeepSeek-R1 trained reasoning without a critic, reward model, or human labels
1K views2 months ago
YouTubeAdam Rosler
Master AI Reasoning: The Ultimate GRPO Secret (2024) #Shorts
1:36
Master AI Reasoning: The Ultimate GRPO Secret (2024) #Shorts
1 views4 weeks ago
YouTubeCollapsedLatents
Dr. GRPO vs GSPO: The Bias-Variance Tradeoff
1:44
Dr. GRPO vs GSPO: The Bias-Variance Tradeoff
2.2K views4 months ago
YouTubeDeep Learning with Yacine
Tracing GRPO's Biased Objective Back to DeepSeek Math
1:39
Tracing GRPO's Biased Objective Back to DeepSeek Math
1.9K views4 months ago
YouTubeDeep Learning with Yacine
Entrena agentes de IA con GRPO 🤖
0:34
Entrena agentes de IA con GRPO 🤖
162 views1 month ago
YouTubelytohlg AI
Master GRPO: The Secret to Efficient AI Agents #Shorts
1:48
Master GRPO: The Secret to Efficient AI Agents #Shorts
6 views2 months ago
YouTubeCollapsedLatents
1:19
Memory-R2: A New Framework for Long-Horizon LLM Memory Training
31 views1 month ago
YouTubeAI Paper Slop
0:38
Microsoft's GMPO swaps the arithmetic mean for the geometric mean in GRPO, stabilizing reasoning RL
546 views1 month ago
YouTubeAgentic Amit
1:16
Flash-GRPO: Efficient Video Diffusion Alignment via One-Step Optimization
34 views1 month ago
YouTubeAI Paper Slop
1:15
Photoshop Style Layers From Flat AI Images?! (Stable-Layers) #Shorts
16 views3 weeks ago
YouTubeQuanta AI Labs
1:28
AI Alignment Secret: 1 Data Point Changes Everything #Shorts
1 month ago
YouTubeCollapsedLatents
0:40
Two AIs Fight in a Cage Match, and Both Get Stronger #science #technology #tech
236 views1 month ago
YouTubeArXiv AI Weekly
1:13
Gemma-3 Just Learned to Solve Math — Here's How
98 views1 week ago
YouTubeRealityDevOps
2:31
Can You Trust an LLM Judge? An RL Researcher's Take
2.5K views4 months ago
YouTubeDeep Learning with Yacine
1:43
Untitled Content #Shorts
4 weeks ago
YouTubeCollapsedLatents
1:05
GRPO Explained: AI Training Secrets Revealed! #shorts
1 week ago
YouTubeIrys AI Clips
0:42
The formula that explains why AI training suddenly fails
2 weeks ago
YouTubeLodeHQ
1:01
Understanding R1-Zero Training From First Principles
2K views4 months ago
YouTubeDeep Learning with Yacine
0:47
Boost AI responses with LA-GRPO prompts!
21 views1 week ago
YouTubePromptProDaily
See more
Static thumbnail place holder