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/.

Several recent works seek to create lightweight deep net-works for video object detection on mobiles. We observe that many existing detectors, previously deemed computationally costly for mobiles, intrinsically support adaptive inference, and offer a multi-branch object detection frame-work (MBODF). Here, an MBODF is referred to as a so-lution that has many execution branches and one can dy-namically choose from among them at inference time to sat-isfy varying latency requirements (e.g. by varying resolution of an input frame). In this paper, we ask, and answer, the wide-ranging question across all MBODFs: How to expose the right set of execution branches and then how to sched-ule the optimal one at inference time? In addition, we un-cover the importance of making a content-aware decision on which branch to run, as the optimal one is conditioned on the video content. Finally, we explore a content-aware scheduler, an Oracle one, and then a practical one, leveraging various lightweight feature extractors. Our evaluation shows that layered on Faster R-CNN-based MBODF, compared to 7 baselines, our Smartadapt achieves a higher Pareto optimal curve in the accuracy-vs-latency space for the ILSVRC VID dataset.