Hugging Face Trending Papers June 2, 2026

$A^2$: Smaller Self-Supervised ViTs Localize Better than Larger Ones

Read the original on Hugging Face Trending Papers →

Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we find that the attention maps of smaller self-supervised ViTs localize foreground objects better than those of larger ViTs.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jun 2

Self-Improving Small Object Grounding in LVLMs

arXiv:2606. 01612v1 Announce Type: cross Abstract: Can internal attention patterns in Large Vision Language Models (LVLMs) identify reliable small-object boxes without fine-tuning?

By Tianze Yang, Yucheng Shi, Ruitong Sun, Ninghao Liu, Jin Sun

llms fine-tuning safety

arXiv Machine Learning

Jul 16

Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models

arXiv:2607. 13395v1 Announce Type: new Abstract: The pursuit of autonomously self-improving models has attracted growing interest in the era of large-scale foundation models.

By Jing-Xiao Liao, Tianwei Zhang, Yu-Hao Jiang, Feifei Zhang, Hang-Cheng Dong, Feng-Lei Fan

llms fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 3

Object-centric LeJEPA

arXiv:2607. 02404v1 Announce Type: cross Abstract: Image encoders trained with LeJEPA can deliver strong features for downstream tasks, but, like other image-level self-supervised methods, typically require large training datasets.

By Jakob Geusen, Ender Konukoglu

computer-vision

arXiv AI

Jun 16

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.

By Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja

llms rag efficiency multimodal benchmarks

arXiv AI

Jul 17

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging

arXiv:2506. 08297v2 Announce Type: replace-cross Abstract: Attention is the critical component of a transformer.

By Nhat Thanh Tran, Fanghui Xue, Shuai Zhang, Jiancheng Lyu, Yunling Zheng, Yingyong Qi, Jack Xin

llms computer-vision

arXiv AI

Jun 29

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models

arXiv:2604. 00757v2 Announce Type: replace-cross Abstract: Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens.

By Dong-Jae Lee, Sunghyun Baek, Junmo Kim

llms efficiency

Related stories

Self-Improving Small Object Grounding in LVLMs

Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models

Object-centric LeJEPA

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models