[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@liuzhuang1234 Avatar @liuzhuang1234 Zhuang Liu

Zhuang Liu posts on X about ai the most. They currently have XXXXXX followers and XX posts still getting attention that total XXXXXX engagements in the last XX hours.

Engagements: XXXXXX #

Engagements Line Chart

Mentions: X #

Mentions Line Chart

Followers: XXXXXX #

Followers Line Chart

CreatorRank: XXXXXXX #

CreatorRank Line Chart

Social Influence

Social topic influence ai

Top Social Posts

Top posts by engagements in the last XX hours

"Stronger Normalization-Free Transformers new paper. We introduce Derf (Dynamic erf) a simple point-wise layer that lets norm-free Transformers not only work but actually outperform their normalized counterparts"
X Link 2025-12-12T03:31Z 11.1K followers, 40.9K engagements

"Derf matches or outperforms normalization layers and consistently beats DyT with the same training recipe across domains. X. ImageNet - higher top-1 in ViT-B/L X. Diffusion Transformers - lower FID across the DiT family X. Genomics (HyenaDNA Caduceus) - higher DNA classification accuracy X. Speech (wav2vec 2.0) - lower validation loss X. Language (GPT-2) - matches LayerNorm clearly beats DyT. A simple point-wise layer can make Transformers stronger not just as good"
X Link 2025-12-12T03:31Z 11.1K followers, 1348 engagements

"Excited to work with new PhD students (Fall 2026) on multimodal models AI for automated scientific research and foundation model architectures at Princeton. If this resonates with you please apply to the CS PhD program and mention my name"
X Link 2025-12-09T23:58Z 11.1K followers, 46.8K engagements

"Is Derf just fitting better Surprisingly no. When we measure training loss in eval mode on the training set: Norm-based models have the lowest train loss Derf has a higher train loss Yet Derf has better test performance This suggests Derfs gains mainly come from stronger generalization than norm layers"
X Link 2025-12-12T03:31Z 11.1K followers, 3311 engagements