activity
20242026
collaborators

6 papers

cs.CV2026

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Zimo Wen, Boxiu Li, Wanbo Zhang +11

Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear. Existing benchmarks lac…

cs.AI2026

SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training

Qi Zhang, Yifei Wang, Xiaohan Wang +4

In recent years, pre-trained large language models have achieved remarkable success across diverse tasks. Besides the pivotal role of self-supervised pre-training, their effectiven…

cs.LG2025

An Augmentation Overlap Theory of Contrastive Learning

Qi Zhang, Yifei Wang, Yisen Wang

Recently, self-supervised contrastive learning has achieved great success on various tasks. However, its underlying working mechanism is yet unclear. In this paper, we first provid…

cs.LG2025

On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy

Jingyi Cui, Qi Zhang, Yifei Wang +1

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the features learned by large language models (LLMs). By reconstructing features with sparsely…

cs.LG2025

Projection Head is Secretly an Information Bottleneck

Zhuo Ouyang, Kaiwen Hu, Qi Zhang +2

Recently, contrastive learning has risen to be a promising paradigm for extracting meaningful data representations. Among various special designs, adding a projection head on top o…

cs.LG2024

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

Qi Zhang, Yifei Wang, Jingyi Cui +4

Deep learning models often suffer from a lack of interpretability due to polysemanticity, where individual neurons are activated by multiple unrelated semantics, resulting in uncle…