1 citations · 3 across the 21 of their papers we have counts for
22 papers
How to "train" a surgeon? Benchmarking generalist agents in surgical scene understanding
Gengyuan Zhang, Xiao Han, Shijie Zhou +7
Evaluating general-purpose multimodal large language models (MLLMs) for surgical scene understanding remains limited due to scarce surgical data and fragmented evaluation protocols…
Conformalized Large Language Models under Configuration Shift
Yuqicheng Zhu, Jialin Yu, Lin Li +7
Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets…
AWM: Answerable Working Memory for Long-Document VQA Agents
Dongzhuoran Zhou, Yuqicheng Zhu, Yule Liu +5
Long-document visual question answering increasingly relies on VLM agents that retrieve candidate pages, inspect page images, write findings to working memory, and synthesize answe…
SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs
Prateek Chaturvedi, Yuqicheng Zhu, Hongkuan Zhou +6
Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) enables natural language interaction with structured enterprise knowledge, yet existing agentic approaches that perfor…
EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
Boer Zhang, Mingyan Wu, Dongzhuoran Zhou +6
Deep research requires reasoning over web evidence to answer open-ended questions, and it is a core capability for AI agents. Yet many deep research agents still rely on implicit,…
GR-Agent: Adaptive Graph Reasoning Agent under Incomplete Knowledge
Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang +5
Large language models (LLMs) achieve strong results on knowledge graph question answering (KGQA), but most benchmarks assume complete knowledge graphs (KGs) where direct supporting…
Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learning
Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka +5
Open-domain visual entity recognition aims to identify and link entities depicted in images to a vast and evolving set of real-world concepts, such as those found in Wikidata. Unli…
Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guarantees
Yuqicheng Zhu, Jingcheng Wu, Yizhen Wang +4
Uncertain knowledge graph embedding (UnKGE) methods learn vector representations that capture both structural and uncertainty information to predict scores of unseen triples. Howev…
Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning
Zifeng Ding, Shenyang Huang, Zeyu Cao +11
Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural appro…
ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation
Yuqicheng Zhu, Nico Potyka, Daniel Hernández +6
Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sen…
What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge
Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang +5
Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the struct…
Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings
Yuqicheng Zhu, Daniel Hernández, Yuan He +4
Uncertainty quantification in Knowledge Graph Embedding (KGE) methods is crucial for ensuring the reliability of downstream applications. A recent work applies conformal prediction…
Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness
Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang +4
Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) is a technique that enhances Large Language Model (LLM) inference in tasks like Question Answering (QA) by retrieving…
Supposedly Equivalent Facts That Aren't? Entity Frequency in Pre-training Induces Asymmetry in LLMs
Yuan He, Bailan He, Zifeng Ding +8
Understanding and mitigating hallucinations in Large Language Models (LLMs) is crucial for ensuring reliable content generation. While previous research has primarily focused on "w…
DAGE: DAG Query Answering via Relational Combinator with Logical Constraints
Yunjie He, Bo Xiong, Daniel Hernández +3
Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding m…
Robust Visual Representation Learning with Multi-modal Prior Knowledge for Image Classification Under Distribution Shift
Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka +4
Despite the remarkable success of deep neural networks (DNNs) in computer vision, they fail to remain high-performing when facing distribution shifts between training and testing d…
Generating Ontologies via Knowledge Graph Query Embedding Learning
Yunjie He, Daniel Hernandez, Mojtaba Nayyeri +4
Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, r…
Conformalized Answer Set Prediction for Knowledge Graph Embedding
Yuqicheng Zhu, Nico Potyka, Jiarong Pan +4
Knowledge graph embeddings (KGE) apply machine learning methods on knowledge graphs (KGs) to provide non-classical reasoning capabilities based on similarities and analogies. The l…
Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction
Yuqicheng Zhu, Nico Potyka, Mojtaba Nayyeri +4
Knowledge graph embedding (KGE) models are often used to predict missing links for knowledge graphs (KGs). However, multiple KG embeddings can perform almost equally well for link…
Approximating Probabilistic Inference in Statistical EL with Knowledge Graph Embeddings
Yuqicheng Zhu, Nico Potyka, Bo Xiong +4
Statistical information is ubiquitous but drawing valid conclusions from it is prohibitively hard. We explain how knowledge graph embeddings can be used to approximate probabilisti…
Robust Knowledge Extraction from Large Language Models using Social Choice Theory
Nico Potyka, Yuqicheng Zhu, Yunjie He +2
Large-language models (LLMs) can support a wide range of applications like conversational agents, creative writing or general query answering. However, they are ill-suited for quer…
Active Transfer Prototypical Network: An Efficient Labeling Algorithm for Time-Series Data
Yuqicheng Zhu, Mohamed-Ali Tnani, Timo Jahnz +1
The paucity of labeled data is a typical challenge in the automotive industry. Annotating time-series measurements requires solid domain knowledge and in-depth exploratory data ana…