Jiacheng Li

Jiacheng Li

Auto-generated profile, based on publicly available information

Jiacheng Li

Department of Computer Science & Engineering University of California San Diego

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2019
Verified
Conference Paper
Open access
PDF file
JNJianmo Ni
Jianmo Ni
JLJiacheng Li
Jiacheng Li
JMJulian J. McAuley
Julian J. McAuley
Jianmo Ni, Jiacheng Li, Julian McAuley. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

26 October 2023
Verified
Conference Paper
Open access
ZNZixuan Ni
Zixuan Ni
LWLonghui Wei
Longhui Wei
JLJiacheng Li
Jiacheng Li
STSiliang Tang
Siliang Tang
YZYueting Zhuang
Yueting Zhuang
QTQi Tian
Qi Tian
Owing to the unrestricted nature of the content in the training data, large text-to-image diffusion models, such as Stable Diffusion (SD), are capable of generating images with potentially copyrighted or dangerous content based on corresponding textual concepts information. This includes specific intellectual property (IP), human faces, and various artistic styles. However, Negative Prompt, a widely used method for content removal, frequently fails to conceal this content due to inherent limitations in its inference logic. In this work, we propose a novel strategy named Degeneration-Tuning (DT) to shield contents of unwanted concepts from SD weights. By utilizing Scrambled Grid to reconstruct the correlation between undesired concepts and their corresponding image domain, we guide SD to generate meaningless content when such textual concepts are provided as input. As this adaptation occurs at the level of the model's weights, the SD, after DT, can be grafted onto other conditional diffusion frameworks like ControlNet to shield unwanted concepts. In addition to qualitatively showcasing the effectiveness of our DT method in protecting various types of concepts, a quantitative comparison of the SD before and after DT indicates that the DT method does not significantly impact the generative quality of other contents. The FID and IS scores of the model on COCO-30K exhibit only minor changes after DT, shifting from 12.61 and 39.20 to 13.04 and 38.25, respectively, which clearly outperforms the previous methods.

1 January 2023
Verified
Conference Paper
Open access
PDF file
William J. HoganWilliam J. Hogan
William J. Hogan
JLJiacheng Li
Jiacheng Li
JSJingbo Shang
Jingbo Shang
William Hogan, Jiacheng Li, Jingbo Shang. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

9 November 2026
Verified
Conference Paper
Open access
WBWendong Bu
Wendong Bu
KPKaihang Pan
Kaihang Pan
YLYuze Lin
Yuze Lin
JLJiacheng Li
Jiacheng Li
KSKai Shen
Kai Shen
STSiliang Tang
Siliang Tang

6 April 2023 in arXiv
Verified
Preprint
Open access
PDF file
AYAn Yan
An Yan
ZHZhankui He
Zhankui He
JLJiacheng Li
Jiacheng Li
TZTianyang Zhang
Tianyang Zhang
JMJulian J. McAuley
Julian J. McAuley
Existing explanation models generate only text for recommendations but still struggle to produce diverse contents. In this paper, to further enrich explanations, we propose a new task named personalized showcases, in which we provide both textual and visual information to explain our recommendations. Specifically, we first select a personalized image set that is the most relevant to a user's interest toward a recommended item. Then, natural language explanations are generated accordingly given our selected images. For this new task, we collect a large-scale dataset from Google Local (i.e.,~maps) and construct a high-quality subset for generating multi-modal explanations. We propose a personalized multi-modal framework which can generate diverse and visually-aligned explanations via contrastive learning. Experiments show that our framework benefits from different modalities as inputs, and is able to produce more diverse and expressive explanations compared to previous methods on a variety of evaluation metrics.

1 November 2023 in arXiv
Verified
Preprint
Open access
PDF file
William J. HoganWilliam J. Hogan
William J. Hogan
JLJiacheng Li
Jiacheng Li
JSJingbo Shang
Jingbo Shang
Open-world Relation Extraction (OpenRE) has recently garnered significant attention. However, existing approaches tend to oversimplify the problem by assuming that all unlabeled texts belong to novel classes, thereby limiting the practicality of these methods. We argue that the OpenRE setting should be more aligned with the characteristics of real-world data. Specifically, we propose two key improvements: (a) unlabeled data should encompass known and novel classes, including hard-negative instances; and (b) the set of novel classes should represent long-tail relation types. Furthermore, we observe that popular relations such as titles and locations can often be implicitly inferred through specific patterns, while long-tail relations tend to be explicitly expressed in sentences. Motivated by these insights, we present a novel method called KNoRD (Known and Novel Relation Discovery), which effectively classifies explicitly and implicitly expressed relations from known and novel classes within unlabeled data. Experimental evaluations on several Open-world RE benchmarks demonstrate that KNoRD consistently outperforms other existing methods, achieving significant performance gains.