15 citations · 36 across the 18 of their papers we have counts for
19 papers
Label Collapse in Diffusion Language Model In-Context Learning
Ziye Guo, Ye Yuan
In-context learning (ICL) applies large language models to new tasks by prepending a few labeled demonstrations to a query. Prior work has studied how demonstration ordering affect…
SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models
Yiyang Gu, Junwei Yang, Junyu Luo +15
Large language models (LLMs) are increasingly applied to scientific research, yet existing evaluations often fail to reflect the fine-grained capabilities required in practice. Mos…
Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4
Chengwu Liu, Yichun Yin, Ye Yuan +7
Most ATP benchmarks embed the final answer within the formal statement -- a convention we call "Easy Mode" -- a design that simplifies the task relative to what human competitors f…
Modular Layout Synthesis (MLS): Front-end Code via Structure Normalization and Constrained Generation
Chong Liu, Ming Zhang, Fei Li +3
Automated front-end engineering drastically reduces development cycles and minimizes manual coding overhead. While Generative AI has shown promise in translating designs to code, c…
FMC: Formalization of Natural Language Mathematical Competition Problems
Jiaxuan Xie, Chengwu Liu, Ye Yuan +3
Efficient and accurate autoformalization methods, which leverage large-scale datasets of extensive natural language mathematical problems to construct formal language datasets, are…
Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
Chengwu Liu, Ye Yuan, Yichun Yin +7
Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that…
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Junyu Luo, Weizhi Zhang, Ye Yuan +23
The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic a…
Efficient Diffusion Models: A Survey
Hui Shen, Jingxuan Zhang, Boning Xiong +11
Diffusion models have emerged as powerful generative models capable of producing high-quality contents such as images, videos, and audio, demonstrating their potential to revolutio…
A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
Ye Yuan, Chengwu Liu, Jingyang Yuan +3
Retrieval-augmented generation (RAG) is a framework enabling large language models (LLMs) to enhance their accuracy and reduce hallucinations by integrating external knowledge base…
AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies
Bo-Wen Zhang, Liangdong Wang, Ye Yuan +24
In recent years, with the rapid application of large language models across various fields, the scale of these models has gradually increased, and the resources required for their…
Vision-Braille: A Curriculum Learning Toolkit and Braille-Chinese Corpus for Braille Translation
Alan Wu, Ye Yuan, Zhiping Xiao +1
We present Vision-Braille, the first publicly available end-to-end system for translating Chinese Braille extracted from images into written Chinese. This system addresses the uniq…
MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation
Jinsheng Huang, Liang Chen, Taian Guo +13
Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, often assessed through multiple-choice questions (MCQs) that include an image,…
Measuring Social Norms of Large Language Models
Ye Yuan, Kexin Tang, Jianhao Shen +2
We present a new challenge to examine whether large language models understand social norms. In contrast to existing datasets, our dataset requires a fundamental understanding of s…
Preparing Lessons for Progressive Training on Language Models
Yu Pan, Ye Yuan, Yichun Yin +6
The rapid progress of Transformers in artificial intelligence has come at the cost of increased resource consumption and greenhouse gas emissions due to growing model sizes. Prior…
Measuring Vision-Language STEM Skills of Neural Models
Jianhao Shen, Ye Yuan, Srbuhi Mirzoyan +2
We introduce a new challenge to test the STEM skills of neural models. The problems in the real world often require solutions, combining knowledge from STEM (science, technology, e…
TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models
Jing Xiong, Jianhao Shen, Ye Yuan +11
Automated theorem proving (ATP) has become an appealing domain for exploring the reasoning ability of the recent successful generative language models. However, current ATP benchma…
Reusing Pretrained Models by Multi-linear Operators for Efficient Training
Yu Pan, Ye Yuan, Yichun Yin +4
Training large models from scratch usually costs a substantial amount of resources. Towards this problem, recent studies such as bert2BERT and LiGO have reused small pretrained mod…
FIMO: A Challenge Formal Dataset for Automated Theorem Proving
Chengwu Liu, Jianhao Shen, Huajian Xin +9
We present FIMO, an innovative dataset comprising formal mathematical problem statements sourced from the International Mathematical Olympiad (IMO) Shortlisted Problems. Designed t…
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion
Jianhao Shen, Chenguang Wang, Ye Yuan +5
This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM…