Enhancing Pre-trained Representation Classifiability can Boost its Interpretability

Enhancing Pre-trained Representation Classifiability can Boost its Interpretability

International Conference on Learning Representations (ICLR), 2025

28 October 2025

ArXiv (abs)PDF HTML Github (55842★)

Papers citing "Enhancing Pre-trained Representation Classifiability can Boost its Interpretability"

4 / 4 papers shown

Title
Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models Shufan Shen Junshu Sun Shuhui Wang Qingming Huang 0 0 0 28 Oct 2025
Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs Jinzhe Liu Junshu Sun Shufan Shen Chenxue Yang Shuhui Wang KELM CLL 108 1 0 25 Oct 2025
VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set Shufan Shen Junshu Sun Qingming Huang Shuhui Wang 12 1 0 24 Oct 2025
Relieving the Over-Aggregating Effect in Graph Transformers Junshu Sun Wanxing Chang Chenxue Yang Qingming Huang Shuhui Wang 11 0 0 24 Oct 2025