conftrace_

fine-grained visual perception

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multimodal large language model (3) chain-of-captions prompting (1) pixel-wise object perception (1) pixel-level perception (1) zero-shot prompting (1) visual understanding (1) multi-image reasoning (1) spatial reasoning (1) vision encoder (1) cross-modal alignment (1)

Papers

QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models EMNLP 2025 Words Over Pixels? Rethinking Vision in Multimodal Large Language Models IJCAI 2025 Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception CVPR 2024