activity
20222026
most citedVirtual histological staining of unlabeled autopsy tissue

63 citations · 82 across the 16 of their papers we have counts for

collaborators
Showing 2024Show all

7 papers · 1 filter

cs.CL2024

BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression

Yuankai Li, Jia-Chen Gu, Di Wu +2

Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge. However, as the number of retrieved documents increases, the inp…

cs.CL2024★ 3 cited

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

Di Wu, Hongwei Wang, Wenhao Yu +3

Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized re…

cs.CL2024

The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention

Yixin Wan, Di Wu, Haoran Wang +1

Prompt-based "diversity interventions" are commonly adopted to improve the diversity of Text-to-Image (T2I) models depicting individuals with various racial or gender traits. Howev…

cs.CL2024

MetaKP: On-Demand Keyphrase Generation

Di Wu, Xiaoxian Shen, Kai-Wei Chang

Traditional keyphrase prediction methods predict a single set of keyphrases per document, failing to cater to the diverse needs of users and downstream applications. To bridge the…

cs.CL2024★ 1 cited

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation

Di Wu, Jia-Chen Gu, Fan Yin +2

Retrieval-augmented language models (RALMs) have shown strong performance and wide applicability in knowledge-intensive tasks. However, there are significant trustworthiness concer…

cs.SE2024★ 3 cited

Repoformer: Selective Retrieval for Repository-Level Code Completion

Di Wu, Wasi Uddin Ahmad, Dejiao Zhang +2

Recent advances in retrieval-augmented generation (RAG) have initiated a new era in repository-level code completion. However, the invariable use of retrieval in existing methods e…

cs.CL2024★ 1 cited

On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generation

Di Wu, Wasi Uddin Ahmad, Kai-Wei Chang

This study addresses the application of encoder-only Pre-trained Language Models (PLMs) in keyphrase generation (KPG) amidst the broader availability of domain-tailored encoder-onl…