"downstream tasks" Papers

12 papers found

CleanDIFT: Diffusion Features without Noise

Nick Stracke, Stefan Andreas Baumann, Kolja Bauer et al.

CVPR 2025arXiv:2412.03439
24
citations

Contextures: Representations from Contexts

Runtian Zhai, Kai Yang, Burak VARICI et al.

ICML 2025arXiv:2505.01557
1
citations

Establishing Task Scaling Laws via Compute-Efficient Model Ladders

Akshita Bhagia, Jiacheng Liu, Alexander Wettig et al.

COLM 2025paperarXiv:2412.04403
22
citations

Language Guided Skill Discovery

Seungeun Rho, Laura Smith, Tianyu Li et al.

ICLR 2025arXiv:2406.06615
15
citations

SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity

Chengzhi Wu, Yuxin Wan, Hao Fu et al.

CVPR 2025arXiv:2504.19581
1
citations

THUNDER: Tile-level Histopathology image UNDERstanding benchmark

Pierre Marza, Leo Fillioux, Sofiène Boutaj et al.

NEURIPS 2025spotlightarXiv:2507.07860
3
citations

DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced Learning

Won-Seok Choi, Hyundo Lee, Dong-Sig Han et al.

AAAI 2024paperarXiv:2402.08963
4
citations

Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology

Andrew Song, Richard J. Chen, Tong Ding et al.

CVPR 2024arXiv:2405.11643
79
citations

Parameter-Efficient Fine-Tuning with Controls

Chi Zhang, Jingpu Cheng, Yanyu Xu et al.

ICML 2024

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning

Ruiqian Nai, Zixin Wen, Ji Li et al.

AAAI 2024paperarXiv:2403.00352
2
citations

Robustness Tokens: Towards Adversarial Robustness of Transformers

Brian Pulfer, Yury Belousov, Slava Voloshynovskiy

ECCV 2024arXiv:2503.10191

Transferring Knowledge From Large Foundation Models to Small Downstream Models

Shikai Qiu, Boran Han, Danielle Robinson et al.

ICML 2024arXiv:2406.07337
8
citations