Recorruption arises from visual attention suppression and positional bias in multimodal RAG; BAIR mitigates it via bottleneck attention intervention at inference time.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DiDi-Merging achieves dynamic model merging performance matching or exceeding prior methods while using only 1.24x to 1.4x the parameters of a single fine-tuned model.
citing papers explorer
-
The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation
Recorruption arises from visual attention suppression and positional bias in multimodal RAG; BAIR mitigates it via bottleneck attention intervention at inference time.
-
Dynamic Model Merging Made Slim
DiDi-Merging achieves dynamic model merging performance matching or exceeding prior methods while using only 1.24x to 1.4x the parameters of a single fine-tuned model.