作者位次 #8/9ECCV 2026Poster
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
Linquan Wu · Tianxiang Jiang · Yifei Dong · Haoyu Yang · Fengji Zhang · Shichang Meng · AI Xuan · Linqi Song · Jacky Keung
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。
Linquan Wu · Tianxiang Jiang · Yifei Dong · Haoyu Yang · Fengji Zhang · Shichang Meng · AI Xuan · Linqi Song · Jacky Keung
Yang Zerui · Weichuan Wang · Yanwei XU · Linqi Song · Yudai Matsuda · Wei Han · Bo Bai
Existing NL2SQL systems face two critical limitations : (1) they rely on in-context learning with only correct examples, overlooking the rich signal in historical error–fix pairs that could guide more robust self-correction; and (2) test-time scaling (TTS) approaches often decompose questions arb...
Weichuan Wang · Mingyang Liu · Chen Ma · Linqi Song
In recent years, the non-deterministic properties of language models have garnered considerable attention and have shown a significant influence on real-world applications. However, such properties remain under-explored in machine translation (MT), a complex, non-deterministic NLP task. In this s...