Arnas Uselis

Arnas Uselis on Hugging Face Daily Papers: 9 papers, 0 in the top 3 of their day, 77 upvotes.

1. How can embedding models bind concepts? 8 upvotes, #36 of 2026-06-01
2. Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models 8 upvotes, #24 of 2026-05-18
3. MEME: Multi-entity & Evolving Memory Evaluation 7 upvotes, #36 of 2026-05-13
4. When Do Diffusion Models learn to Generate Multiple Objects? 8 upvotes, #12 of 2026-05-04
5. Half-Truths Break Similarity-Based Retrieval 6 upvotes, #21 of 2026-03-03
6. Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models 14 upvotes, #8 of 2026-03-02
7. Does Data Scaling Lead to Visual Compositional Generalization? 1 upvotes, #26 of 2025-07-09
8. On the rankability of visual embeddings 15 upvotes, #12 of 2025-07-08
9. Diffusion Classifiers Understand Compositionality, but Conditions Apply 19 upvotes, #13 of 2025-05-26

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.