Multimodal sentiment analysis (MSA) aims to predict human sentiments by integrating signals from different modalities such as text, video, and audio. However, raw multimodal sequences often suffer from semantic inconsistency--exhibiting redundancy or conflicts within and across modalities--which hinders robust understa...
Pan Wang, Li-Peng Ke, Hua-Jun Ying et al.· 0 citations
Smart glasses are a promising platform for vision-language assistants, but private split inference remains expensive: protecting visual representations before transmission does not remove the cost of on-device vision encoding, wide protected tokens, or hardware-unaware execution. We present SAGE (Smart-glasses-Aware Gu...
Zhi-Min Li, Pan Wang, Jing-Xiang Chen et al.· 0 citations
Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic tasks suggest potential for aggressive model pruning without performance drop, empirical results show existing methods proposed for question answering tasks severely deg...
Yuan-Zhe Li, Peng-Xin Wang, Yuxin Ren et al.· 0 citations
A quantization-robust unlearning framework that makes forgetting robust to quantization while maintaining overall model utility is proposed, and a curvature-based criteria that pinpoints sensitive weights in the unlearned model that leads to both non-robust forgetting and reduced utility is revealed.
Jia-Lu Wang, Jia-Ning Deng, Shu-Qing Luo et al.· 1 citation
Token-Guided Attribute Privacy (TGAP), a pre-LLM token disentangler that learns a residual transformation of visual tokens before they leave the trusted boundary, is proposed, suggesting that securing the compact token interface is a practical path toward privacy-preserving wearable multimodal AI.
Zhi-Min Li, Pan Wang, Jing-Xiang Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.