RESEARCH

→ View original post on X — @shiqi_yang_147

Industrial Research Pipeline Elegance Over Novelty

By

@shiqi_yang_147

–

13 June 2023 7h33

When reviewing, I will give credit to submissions which work well in an elegantly simple pipeline. While other reviewers (always) raise novelty issues (and/or out-of-the-scope questions for the specific task). Look forward to seeing how industrial research looks like.

Transformers Learn Through Gradual Rank Increase

By

–

13 June 2023 6h02

Transformers learn through gradual rank increase paper page: https://
huggingface.co/papers/2306.07
042
… identify incremental learning dynamics in transformers, where the difference between trained and initial weights progressively increases in rank. We rigorously prove this occurs under the

Cap3D: Scalable Automatic 3D Object Text Description System

By

–

13 June 2023 5h56

Scalable 3D Captioning with Pretrained Models paper page: https://
huggingface.co/papers/2306.07
279
…
dataset: https://
huggingface.co/datasets/tiang
e/Cap3D
… introduce Cap3D, an automatic approach for generating descriptive text for 3D objects. This approach utilizes pretrained models from image captioning, image-text

Retrieval-Enhanced Contrastive Vision-Text Models for Improved Concept Recognition

By

–

13 June 2023 5h43

Retrieval-Enhanced Contrastive Vision-Text Models paper page: https://
huggingface.co/papers/2306.07
196
… Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on

FasterViT: Fast Vision Transformers with Hierarchical Attention

By

–

13 June 2023 5h24

FasterViT: Fast Vision Transformers with Hierarchical Attention paper page: https://
huggingface.co/papers/2306.06
189
… design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the