On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs

Vision-language models suffer significant accuracy drops under common corruptions. While test-time adaptation (TTA) successfully mitigates these shifts in CLIP-like contrastive models, its application to generative multimodal large language models (MLLMs) remains underexplored and uniquely challenging due to their sequential token generation. In this work, we demonstrate that representation-based TTA fails to recover performance in MLLMs. Our experiments reveal that even when violating standard TTA assumptions by leveraging target data offline, sample-blind feature alignment recovers only marginal accuracy. We attribute this failure to the nature of corruption shifts: unlike CLIP-like architectures, which benefit from a shared domain-shift direction within a single pooled classification embedding, MLLM visual token sequence shifts are nearly orthogonal and span the full embedding space. These findings bound what any sample-blind, position-shared correction at a single encoder site can achieve, establishing that representation-space interventions alone might be insufficient to ensure corruption robustness in MLLMs.