3 papers
cs.CV2026
Test-Time Logit Prompting for Source-Free Missing Modality Adaptation
Taixi Chen, Nancy Guo
Vision-language models (VLMs) have achieved remarkable performance by leveraging complementary information from large-scale image-text pairs. However, missing-modality inputs are c…
cs.CV2026
Learning from Reliable Latent Prompts for Visual Recognition with Missing Modalities
Taixi Chen, Nancy Guo
Large-scale multimodal models (LMMs) have achieved superior performance in visual recognition by synergizing information across diverse, massive-scale paired modalities. In real-wo…
cs.CV2025
UAM: A Unified Attention-Mamba Backbone of Multimodal Framework for Tumor Cell Classification
Taixi Chen, Jingyun Chen, Nancy Guo
Inspired by the recent success of the Mamba architecture in vision and language domains, we introduce a Unified Attention-Mamba (UAM) backbone. Unlike previous hybrid approaches th…