Zhiyang Zhang
12 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Cross-Pollinator (14) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (4) π Renaissance Researcher (8)
π
Renaissance Researcher
(8)
πΊοΈ
Taxonomy Completionist
(37)
π
Keyword Champion
(5)
π
Century Club
(12)
β‘
Prolific Year
(7)
ποΈ
Keyword Collector
(61)
Conferences
ACL (5)
EMNLP (4)
COLING (2)
NAACL (1)
Top co-authors
Keywords
document image translation
(5)
multimodal learning
(4)
information retrieval
(3)
layout understanding
(3)
multimodal large language model
(3)
machine translation
(3)
optical character recognition
(3)
large language model
(2)
retrieval-augmented generation
(2)
multi-modal learning
(2)
pre-trained model
(1)
language model
(1)
semantic similarity
(1)
end-to-end learning
(1)
transfer learning
(1)
modality alignment
(1)
multi-hop question answering
(1)
document retrieval
(1)
multilingual translation
(1)
end-to-end training
(1)
Papers
AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents
ACL 2025
Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation
ACL 2025
Re3Syn: A Dependency-Based Data Synthesis Framework for Long-Context Post-training
ACL 2025
A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration
ACL 2025
Improving MLLMβs Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency
ACL 2025
From Chaotic OCR Words to Coherent Document: A Fine-to-Coarse Zoom-Out Network for Complex-Layout Document Image Translation
COLING 2025
SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translation
EMNLP 2025
EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
EMNLP 2024
Born a BabyNet with Hierarchical Parental Supervision for End-to-End Text Image Machine Translation
COLING 2024
Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling
NAACL 2024
LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder
EMNLP 2023
An Empirical Investigation of Implicit and Explicit Knowledge-Enhanced Methods for Ad Hoc Dataset Retrieval
EMNLP 2023