Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language Models

arXiv:2604.11399v2 Announce Type: replace-cross Abstract: Multimodal adaptation can erode temporal reasoning (TR) in video-language models (VLMs), leaving models able to perceive salient events yet unable to infer their temporal and causal structure. We introduce MERIT, a gradient-free framework that repairs this capability through layer-selective model merging. MERIT assigns each self-attention layer a VLM-dominant or LLM-dominant interpolation and uses the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to search the resulting combinatorial space under an objective that rewards TR gains while penalizing temporal perception (TP) degradation. Across three VLM families and five video benchmarks, MERIT consistently improves TR while preserving TP; recipes selected on a compact diagnostic set transfer to four unseen benchmarks, with relative gains of up to 27.8%. Interventional masking and frame-level attribution further show that the selected layers are functionally important for reasoning and that MERIT shifts decisions toward temporally distributed, causally relevant evidence. These results establish layer-selective merging as a practical post-hoc mechanism for repairing video temporal reasoning degraded during multimodal adaptation, without learning new parameters.

Abstract:Multimodal adaptation can erode temporal reasoning (TR) in video-language models (VLMs), leaving models able to perceive salient events yet unable to infer their temporal and causal structure. We introduce MERIT, a gradient-free framework that repairs this capability through layer-selective model merging. MERIT assigns each self-attention layer a VLM-dominant or LLM-dominant interpolation and uses the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to search the resulting combinatorial space under an objective that rewards TR gains while penalizing temporal perception (TP) degradation. Across three VLM families and five video benchmarks, MERIT consistently improves TR while preserving TP; recipes selected on a compact diagnostic set transfer to four unseen benchmarks, with relative gains of up to 27.8%. Interventional masking and frame-level attribution further show that the selected layers are functionally important for reasoning and that MERIT shifts decisions toward temporally distributed, causally relevant evidence. These results establish layer-selective merging as a practical post-hoc mechanism for repairing video temporal reasoning degraded during multimodal adaptation, without learning new parameters.

Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)

arXiv:2604.11399 [cs.CV]

(or arXiv:2604.11399v2 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2604.11399 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language Models

Related coverage