arXiv cs.CV: handwriting/OCR
Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs
이중초점: 훈련 불필요 혼합 입도 비주얼 토큰 프루닝을 이용한 멀티모달 LLM
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.