In this paper, we propose a post-training quantization framework of large vision-language models (L VLMs) for efficient multi-modal inference. Conventional quantization methods sequentially search the layer-wise rounding functions by minimizing activation discretization errors, which fails to acquire optimal quantization strategy without considering cross-layer dependency.

Formally, DA-Ada introduces a Domain-Invariant Adapter (DIA) and Domain-Specific Adapter (DSA) to exploit domain-invariant and domain-specific knowledge, respectively, as shown in Figure 1(c).

The data split details are presented in Tab 3.

Video understanding relies on accurate action detection for temporal analysis.

Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task that has many real-world applications.

Requests for name changes in the electronic proceedings will be accepted with no questions asked. However name changes may cause bibliographic tracking issues. Authors are asked to consider this carefully and discuss it with their co-authors prior to requesting a name change in the electronic proceedings. Use the Report an Issue link to request a name change.