Locally generating GRPO-like rollouts with my SLM, and using this tiny RM as the rubric. Next I'll be RL training on free form text and QA.This is- super fast- way better than F1/ROGUE/BertScore- 80% agreement with external judge LM (deepseek)RL with Unverifiable Rewards!
0:24
Locally generating GRPO-like rollouts with my SLM, and using this tiny RM as the rubric. Next I'll be RL training on free form text and QA.This is- super fast- way better than F1/ROGUE/BertScore- 80% agreement with external judge LM (deepseek)RL with Unverifiable Rewards!
6.1K views4 weeks ago
x.comAVB
Automated Metrics Explained: When BLEU, ROUGE, and BERTScore Lie
17:36
Automated Metrics Explained: When BLEU, ROUGE, and BERTScore Lie
53 views2 weeks ago
YouTubeSH AI Academy
Task-Specific Evaluation: Code, SQL, and JSON Correctness
17:00
Task-Specific Evaluation: Code, SQL, and JSON Correctness
35 views2 weeks ago
YouTubeSH AI Academy
LLM as a Judge Explained: How to Evaluate Large Language Models | Chapter 3
2:09:16
LLM as a Judge Explained: How to Evaluate Large Language Models | Chapter 3
61 views2 weeks ago
YouTubeonepagecode
How to Actually Evaluate Fine-Tuned LLMs (3-Tier Framework)
23:07
How to Actually Evaluate Fine-Tuned LLMs (3-Tier Framework)
52 views2 weeks ago
YouTubeSH AI Academy
Why Every AI Benchmark is Lying to You (And How to Find Real Truth)
8:53
Why Every AI Benchmark is Lying to You (And How to Find Real Truth)
7 views3 weeks ago
YouTubeScience & Engineering Explainer
Hitendri Bomble-The Silent Crash:Why Your RAG Evaluation Metrics Are Lying to You | PyData London 26
32:48
Hitendri Bomble-The Silent Crash:Why Your RAG Evaluation Metrics Are Lying to You | PyData London 26
3 weeks ago
YouTubePyData
8:04
AI Evaluation Metrics Explained | Accuracy, Precision, Recall, F1, BLEU & More
1 views1 week ago
YouTubeMicro Learning
1:25
Their RAG pipeline generated compliant docs against a stale vector index. Source drifted with no reconciliation, no eval gate. They thought the fix was smarter agents. Most picture agents as… | Kush Chheda™ | 83 comments
1 week ago
linkedin.comKush Chheda™
0:33
8 LLM Metrics Every AI Engineer Must Know
168 views1 month ago
YouTubeThe Tamil Coder
45:05
GCP GenAI Leadership Exam — 30 MCQ Quiz | LoRA, RLHF, DPO, Fine-Tuning & Evaluation
21 views2 weeks ago
YouTubeAmitAutomates
5:07
#ai #nlp #deeplearning #arabicnlp #machinelearning #graduationproject #cairouniversity #bayan | Youssef Reda | 17 comments
4 days ago
linkedin.comYoussef Reda
0:50
Meet Evalora, the latest project that Omar Khalili and I have been working on. ⠀ Evalora is a domain-agnostic, rubric-based evaluation system designed to make response evaluation faster, more… | Abood Jbr
6 days ago
linkedin.comAbood Jbr
4:16
How "Attention Is All You Need" Sparked the AI Revolution
2 views1 day ago
YouTubeResearchWithRoyal
O Preconceito do "Sempre Foi Assim": Estrutura científica para treinar robôs e pessoas
5 days ago
YouTubeEDUBRIX
See more
Static thumbnail place holder

Short videos

0:24
Locally generating GRPO-like rollouts with my SLM, and using this tiny RM as the
6.1K views4 weeks ago
x.comAVB
17:36
Automated Metrics Explained: When BLEU, ROUGE, and BERTScore Lie
53 views2 weeks ago
YouTubeSH AI Academy
17:00
Task-Specific Evaluation: Code, SQL, and JSON Correctness
35 views2 weeks ago
YouTubeSH AI Academy
2:09:16
LLM as a Judge Explained: How to Evaluate Large Language Models | Chapter 3
61 views2 weeks ago
YouTubeonepagecode
23:07
How to Actually Evaluate Fine-Tuned LLMs (3-Tier Framework)
52 views2 weeks ago
YouTubeSH AI Academy
8:53
Why Every AI Benchmark is Lying to You (And How to Find Real Truth)
7 views3 weeks ago
YouTubeScience & Engineering
32:48
Hitendri Bomble-The Silent Crash:Why Your RAG Evaluation Metrics Are Lying to
3 weeks ago
YouTubePyData
8:04
AI Evaluation Metrics Explained | Accuracy, Precision, Recall, F1, BLEU & More
1 views1 week ago
YouTubeMicro Learning
1:25
Their RAG pipeline generated compliant docs against a stale vector index. Source drifted
1 week ago
linkedin.comKush Chheda™
0:33
8 LLM Metrics Every AI Engineer Must Know
168 views1 month ago
YouTubeThe Tamil Coder
45:05
GCP GenAI Leadership Exam — 30 MCQ Quiz | LoRA, RLHF, DPO, Fine-Tuning &
21 views2 weeks ago
YouTubeAmitAutomates
5:07
#ai #nlp #deeplearning #arabicnlp #machinelearning #graduationproject
4 days ago
linkedin.comYoussef Reda
0:50
Meet Evalora, the latest project that Omar Khalili and I have been working on. ⠀ Evalora is
6 days ago
linkedin.comAbood Jbr
4:16
How "Attention Is All You Need" Sparked the AI Revolution
2 views1 day ago
YouTubeResearchWithRoyal
O Preconceito do "Sempre Foi Assim": Estrutura científica para treinar robôs e pessoas
5 days ago
YouTubeEDUBRIX
Static thumbnail place holder