5 papers
eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion
Xiang Li, Jiwei Wei, Ke Liu +5
While Large Language Models (LLMs) achieve impressive performance on multi-step reasoning tasks, their reliability is persistently hindered by critical limitations such as unconstr…
Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?
Liyang Li, Muzhi Zhu, Zhiyue Zhao +5
Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has largely been studied as passiv…
Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
Zihui Gao, Ke Liu, Donny Y. Chen +4
Geometric foundation models show promise in 3D reconstruction, yet their progress is severely constrained by the scarcity of diverse, large-scale 3D annotations. While Internet vid…
RSeg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection
Shuaike Shen, Ke Liu, Jiaqing Xie +5
Foundation models for medical image segmentation struggle under out-of-distribution (OOD) shifts, often producing fragmented false positives on OOD tumors. We introduce RSeg,…
From Sentences to Sequences: Rethinking Languages in Biological System
Ke Liu, Shuaike Shen, Hao Chen
The paradigm of large language models in natural language processing (NLP) has also shown promise in modeling biological languages, including proteins, RNA, and DNA. Both the auto-…