Search papers, labs, and topics across Lattice.
Harbin Institute of Technology, Shenzhen
2
0
3
The proposed Attention-Guided Switching method allows MLLMs to dynamically balance between visual fidelity and logical coherence, achieving unprecedented efficiency in reasoning tasks.
Unlock "white-box" reasoning in vision-language models: SegCompass's sparse autoencoder creates an interpretable bridge between visual perception and chain-of-thought, outperforming black-box alignment methods.
