Zishan Xu
YOU?
Author Swipe
View article: Automated mural restoration via semi supervised segmentation and prompt guided diffusion inpainting
Automated mural restoration via semi supervised segmentation and prompt guided diffusion inpainting Open
View article: MuralAgent: Enhancing Ancient Mural Outpainting with RAG-Based Texts and Multimodal Integration
MuralAgent: Enhancing Ancient Mural Outpainting with RAG-Based Texts and Multimodal Integration Open
In the context of the digital age, utilizing cutting-edge technology for the digitization and creative expansion of ancient murals is crucial, aimed at preserving and passing on cultural heritage. Existing image outpainting techniques suff…
View article: EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction
EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction Open
Existing studies explore the explainability of Grammatical Error Correction (GEC) in a limited scenario, where they ignore the interaction between corrections and explanations and have not established a corresponding comprehensive benchmar…
View article: Chinese expert consensus on the application of intravenous immunoglobulin in hematological diseases
Chinese expert consensus on the application of intravenous immunoglobulin in hematological diseases Open
Intravenous immunoglobulin (IVIG), first developed for the treatment of patients with antibody deficiencies, is now widely used in clinical practice, especially in hematological and immune system diseases, and its application in hematologi…
View article: Revisiting Classification Taxonomy for Grammatical Errors
Revisiting Classification Taxonomy for Grammatical Errors Open
Grammatical error classification plays a crucial role in language learning systems, but existing classification taxonomies often lack rigorous validation, leading to inconsistencies and unreliable feedback. In this paper, we revisit previo…
View article: DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens Open
Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs, prompting a focus on compression techniques. While existing semantic vector-based compression methods achieve promis…
View article: Diagnosing Failures in Large Language Models’ Answers: Integrating Error Attribution into Evaluation Framework
Diagnosing Failures in Large Language Models’ Answers: Integrating Error Attribution into Evaluation Framework Open
View article: FaithfulPersona: Balancing Faithfulness and Personalization in Code Explanations through Self-Critique
FaithfulPersona: Balancing Faithfulness and Personalization in Code Explanations through Self-Critique Open
View article: DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens Open
View article: CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction
CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction Open
View article: RAISE: Reinforced Adaptive Instruction Selection For Large Language Models
RAISE: Reinforced Adaptive Instruction Selection For Large Language Models Open
View article: From Critique to Clarity: A Pathway to Faithful and Personalized Code Explanations with Large Language Models
From Critique to Clarity: A Pathway to Faithful and Personalized Code Explanations with Large Language Models Open
In the realm of software development, providing accurate and personalized code explanations is crucial for both technical professionals and business stakeholders. Technical professionals benefit from enhanced understanding and improved pro…
View article: EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction
EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction Open
Existing studies explore the explainability of Grammatical Error Correction (GEC) in a limited scenario, where they ignore the interaction between corrections and explanations and have not established a corresponding comprehensive benchmar…
View article: CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction
CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction Open
The paper focuses on the interpretability of Grammatical Error Correction (GEC) evaluation metrics, which received little attention in previous studies. To bridge the gap, we introduce **CLEME2.0**, a reference-based metric describing four…
View article: Shadclips:When Parameter-Efficient Fine-Tuning with Multimodal Meets Shadow Removal
Shadclips:When Parameter-Efficient Fine-Tuning with Multimodal Meets Shadow Removal Open
Segment Anything Model (SAM), an advanced universal image segmentation model trained on an expansive visual dataset, has set a new benchmark in image segmentation and computer vision. However, it faced challenges when it came to distinguis…
View article: Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters
Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters Open
Writing assistance is an application closely related to human life and is also a fundamental Natural Language Processing (NLP) research field. Its aim is to improve the correctness and quality of input texts, with character checking being …