Search the catalog and eLibrary.

Print oa_green

Antichain of ordinals in intuitionistic set theory

Shuwei Wang • 2025

In classical set theory, the ordinals form a linear chain that we often think of as a very thin portion of the set-theoretic universe. In intuitionistic set theory, however, this is not the case and there can be incompar...

Stored fulltext Fulltext available from the library desk. View record

Print oa_green

EffiReasonTrans: RL-Optimized Reasoning for Code Translation

Yanlin Wang, Rongyi Ou, Yanli Wang, Mingwei Liu, Jiachi Chen, Ensheng Shi, Xilin Liu, Yuchi Ma, Zibin Zheng • 2025

Code translation is a crucial task in software development and maintenance. While recent advancements in large language models (LLMs) have improved automated code translation accuracy, these gains often come at the cost...

Stored fulltext Fulltext available from the library desk. View record

Print oa_green

LightMem: Lightweight and Efficient Memory-Augmented Generation

Jizhan Fang, Xinle Deng, Haoming Xu, Ziyan Jiang, Yuqi Tang, Ziwen Xu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Huajun Chen, Ningyu Zhang • 2025

Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory systems enable LLMs to move beyond state...

Stored fulltext Fulltext available from the library desk. View record

Print oa_green

New flexible and inexact Golub-Kahan algorithms for inverse problems

Malena Sabaté Landman, Silvia Gazzola • 2025

This paper introduces a new class of algorithms for solving large-scale linear inverse problems based on new flexible and inexact Golub-Kahan factorizations. The proposed methods iteratively compute regularized solutions...

Stored fulltext Fulltext available from the library desk. View record

Print oa_green

How Do LLMs Use Their Depth?

Akshat Gupta, Jay Yeung, Gopala Anumanchipalli, Anna Ivanova • 2025

Growing evidence suggests that large language models do not use their depth uniformly, yet we still lack a fine-grained understanding of their layer-wise prediction dynamics. In this paper, we trace the intermediate repr...

Stored fulltext Fulltext available from the library desk. View record

Print oa_green

Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs

Haochen Wang, Yuhao Wang, Tao Zhang, Yikang Zhou, Yanwei Li, Jiacong Wang, Ye Tian, Jiahao Meng, Zilong Huang, Guangcan Mai, Anran Wang, Yunhai Tong, Zhuochen Wang, Xiangtai Li, Zhaoxiang Zhang • 2025

While Multimodal Large Language Models (MLLMs) excel at holistic understanding, they struggle in capturing the dense world with complex scenes, requiring fine-grained analysis of intricate details and object inter-relati...

Stored fulltext Fulltext available from the library desk. View record

Print oa_green

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting

Howard Chen, Noam Razin, Karthik Narasimhan, Danqi Chen • 2025

Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines...

Stored fulltext Fulltext available from the library desk. View record

Print oa_green

DSI-Bench: A Benchmark for Dynamic Spatial Intelligence

Ziang Zhang, Zehan Wang, Guanghao Zhang, Weilong Dai, Yan Xia, Ziang Yan, Minjie Hong, Zhou Zhao • 2025

Reasoning about dynamic spatial relationships is essential, as both observers and objects often move simultaneously. Although vision-language models (VLMs) and visual expertise models excel in 2D tasks and static scenari...

Stored fulltext Fulltext available from the library desk. View record