VQAv2

anchor

Findings

• IC-1496A single frozen transformer block from LLaMA-7B consistently improves performance across diverse visual tasks when appended to existing visual encoders [eval]
• IC-414LLaVA-1.5-7B and LLaVA-1.5-13B exhibit severe performance degradation when H2O KV cache compression is applied in multimodal settings [eval]
• IC-900BLIP-2, MiniGPT-4, and LLaVA-1.5 show degraded zero-shot VQA accuracy on underspecified questions, with absolute improvements of 1.14–7.94% when questions are augmented with visually-grounded details [eval]
• IC-901BLIP-2's LLM-only VQA performance improves with more specified questions while the image remains essential, revealing asymmetric strength between the LLM and vision components [eval]
• IC-902BLIP-2 and MiniGPT-4 confidence-based question selection underperforms the original question for paraphrased candidates but succeeds for semantically enriched REPARe questions [eval]