# Learning to Inference Adaptively for Multimodal Large Language Models

Source: [Learning to Inference Adaptively for Multimodal Large Language Models](<https://www.sota2.com/research/paper/68fa7a651e209131cea82e7e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:58:49.434Z

Authors: Zhuoyan Xu, Khoi Duc Nguyen, Preeti Mukherjee, Saurabh Bagchi, Somali Chaterji, Yingyu Liang, Yin Li

Published: 2025-03-13T21:39:38.000Z

## Abstract

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in visual reasoning, yet come with substantial computational cost, limiting their deployment in resource-constrained settings. Despite recent effort on improving the efficiency of MLLMs, prior solutions fall short in responding to varying runtime conditions, in particular changing resource availability (e.g., contention due to the execution of other programs on the device). To bridge this gap, we introduce AdaLLaVA, an adaptive inference framework that learns to dynamically reconfigure operations in an MLLM during inference, accounting for the input data and a latency budget. We conduct extensive experiments across benchmarks involving question-answering, reasoning, and hallucination. Our results show that AdaLLaVA effectively adheres to input latency budget, achieving varying accuracy and latency tradeoffs at runtime. Further, we demonstrate that AdaLLaVA adapts to both input latency and content, can be integrated with token selection for enhanced efficiency, and generalizes across MLLMs. Our project webpage with code release is at https://zhuoyan-xu.github.io/ada-llava/.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.10905>)

[PDF](<https://arxiv.org/pdf/2503.10905.pdf>)
