"linear probing" Papers

13 papers found

Assessing and Learning Alignment of Unimodal Vision and Language Models

Le Zhang, Qian Yang, Aishwarya Agrawal

CVPR 2025highlightarXiv:2412.04616
15
citations

Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels

Hyeonsu Jeong, Hye Won Chung

ICLR 2025arXiv:2402.10482
1
citations

Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning

Achleshwar Luthra, Tianbao Yang, Tomer Galanti

NEURIPS 2025arXiv:2506.04411
2
citations

The Dynamic Duo of Collaborative Masking and Target for Advanced Masked Autoencoder Learning

Shentong Mo

AAAI 2025paperarXiv:2412.17566
1
citations

Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models

Jun Zhao, Yongzhuo Yang, Xiang Hu et al.

NEURIPS 2025spotlight

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers

Omer Sahin Tas, Royden Wagner

ICLR 2025arXiv:2406.11624
4
citations

A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models

Julio Silva-Rodríguez, Sina Hajimiri, Ismail Ben Ayed et al.

CVPR 2024arXiv:2312.12730
65
citations

Physics of Language Models: Part 3.1, Knowledge Storage and Extraction

Zeyuan Allen-Zhu, Yuanzhi Li

ICML 2024spotlightarXiv:2309.14316
244
citations

Q-Probe: A Lightweight Approach to Reward Maximization for Language Models

Kenneth Li, Samy Jelassi, Hugh Zhang et al.

ICML 2024arXiv:2402.14688
15
citations

Stochastic positional embeddings improve masked image modeling

Amir Bar, Florian Bordes, Assaf Shocher et al.

ICML 2024arXiv:2308.00566
6
citations

The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?

Qinyu Zhao, Ming Xu, Kartik Gupta et al.

ECCV 2024arXiv:2403.09037
15
citations

The Linear Representation Hypothesis and the Geometry of Large Language Models

Kiho Park, Yo Joong Choe, Victor Veitch

ICML 2024arXiv:2311.03658
363
citations

What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks

Ching-Yun (Irene) Ko, Pin-Yu Chen, Payel Das et al.

ICML 2024