Subgraph Atlas · centered on entity
DeepSeek-R1
ai model9 mentions· velocity: stableDeepSeek-R1 is a 671-billion-parameter reasoning model developed by DeepSeek, trained via reinforcement learning to achieve state-of-the-art performance on coding and reasoning benchmarks.
Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.
0 nodes · 0 edges · loading…
companypersonai_modelproductresearch_labbenchmarkframework
drag to move · scroll to zoom · click a node
Top connections
DeepSeekcompany
48 mentions
→ Center atlas here
Mixture of Experts (Sparse MoE for LLMs)technique
12 mentions
→ Center atlas here
Group Relative Policy Optimization (GRPO)technology
7 mentions
→ Center atlas here
Chain-of-Thought Promptingtechnique
4 mentions
→ Center atlas here
Reinforcement Learning from Human Feedback (RLHF)technique
4 mentions
→ Center atlas here
SVoTtechnology
1 mentions
→ Center atlas here
GPT4Allproduct
1 mentions
→ Center atlas here