The Secret to o1 Reasoning: RLVR Explained (DeepSeek R1) #Shorts
1:39
The Secret to o1 Reasoning: RLVR Explained (DeepSeek R1) #Shorts
5 views2 months ago
YouTubeCollapsedLatents
Reducing RLVR Training Costs via Rank-1 Trajectories
1:14
Reducing RLVR Training Costs via Rank-1 Trajectories
38 views1 month ago
YouTubeAI Paper Slop
Beyond Supervised Fine-Tuning: RLVR for Better LLM Performance
1:05
Beyond Supervised Fine-Tuning: RLVR for Better LLM Performance
236 views2 months ago
YouTubeMrinal Rawat
Master AI Reasoning: The 2-Axis RL Training Secret #Shorts
1:05
Master AI Reasoning: The 2-Axis RL Training Secret #Shorts
1 views3 weeks ago
YouTubeCollapsedLatents
INSANE ILLEGAL FACTS 1 🤯
0:12
INSANE ILLEGAL FACTS 1 🤯
1.5K views1 month ago
YouTubeRailover RLVR
did you know this? crazy facts in 17 seconds 😳
0:17
did you know this? crazy facts in 17 seconds 😳
1 views1 month ago
YouTubeRailover RLVR
The Weirdest Laws You've Actually Broken 2 #facts #trending #viral
0:16
The Weirdest Laws You've Actually Broken 2 #facts #trending #viral
1.4K views1 month ago
YouTubeRailover RLVR
0:25
Craziest facts in 25 seconds 😨
59 views1 month ago
YouTubeRailover RLVR
0:16
These Countries Have INSANE Laws 5 😱 #facts #viral #shorts
2.1K views1 month ago
YouTubeRailover RLVR
0:18
These Countries Have INSANE Food Laws 😭 #facts #viral #shorts
464 views1 month ago
YouTubeRailover RLVR
0:15
These Countries Have INSANE Laws 😭 #facts #viral #shorts
25 views1 month ago
YouTubeRailover RLVR
0:16
These Countries Have INSANE Laws 4 😱 #facts #viral #shorts
27.9K views1 month ago
YouTubeSmart Rigby
0:21
These Food Laws Are Actually INSANE 😭💀
29.3K views1 month ago
YouTubeSmart Rigby
1:27
North Mini Code 1.0: Cohere's Powerful Open Source Coding AI is Here! #ai #aimodel #llm #tamiltech
1K views2 weeks ago
YouTubeTamil AI Hub
3:01
Ak47
533 views3 weeks ago
YouTubeskinwalker13 - Topic
0:36
The "DeepSeek" Moment- RLVR & GRPO #ai #podcast
871 views5 months ago
YouTubeThe MAD Podcast with Matt Turck
2:43
Holo3.1, Self-Aware LLMs, Consilium Protocol & More AI News
3 weeks ago
YouTubeLodeHQ
0:39
Decoding RLVR: From DeepSeq R one to academic impact. See how it reshapes the conversation. Source: Lex Fridman Podcast (CC BY) #RLVR #DeepSeq #AcademicInfluence #Innovation #Research
4 months ago
TikToktecnologiainteresante
2:25
AI Explains AI: Post-training
37 views1 month ago
YouTubeTK-421 Presents
1:04
Day 39/42: What Is RLVR? Yesterday, we used opinions. Today, we use facts. RLVR means Reinforcement Learning from Verifiable Rewards. The model gets rewarded only if: the code passes tests, the math checks out, the answer matches evidence. No vibes. No preferences. Just correctness. This works best when truth can be checked. Missed Day 38? Start there. Tomorrow, we use randomness to improve answers: self-consistency. I’m Louis-François, PhD dropout, now CTO & co-founder at Towards AI. Follow me
489 views5 months ago
TikTokwhats_ai
See more
Static thumbnail place holder