作者位次 #3/6ICML 2026Spotlight· Applications / Computer Vision
Real-Time Visual Attribution Streaming in Thinking Model
Seil Kang · Woojung Han · Junhyeok Kim · Jinyeong Kim · Youngeun Kim · Seong Jae Hwang
多模态OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Seil Kang · Woojung Han · Junhyeok Kim · Jinyeong Kim · Youngeun Kim · Seong Jae Hwang
Tae Eun Choi · Sumin Shim · Junhyeok Kim · Seong Jae Hwang
Junhyeok Kim · Jaewoo Park · Junhee Park · Sangeyl Lee · Jiwan Chung · Jisung Kim · Ji Hoon Joung · Youngjae Yu
For people affected by blindness and low vision (BLV), safe and independent navigation remains a major challenge, impacting over 2.2 billion individuals worldwide. Although multimodal large language models (MLLMs) offer new opportunities for assistive navigation, progress has been limited by the...