Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning

arXiv:2610.27341 · cs.CV · Submitted 2026-10-19 · Read on arXiv

cs.CV

Submitted: 2026-10-19

Updated: 2026-10-19

Comments: Accepted by NeurIPS 2026. Project Page: https://zerchen.github.io/projects/lore.html

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Multimodal Reasoning — 1× in this paper · explained in 5 episodes

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models