Profiles2022-2026
Meishan Zhang
Harbin Institute of Technology
17Papers
0Last author
27Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers17
- AOEB: Benchmarking Agent-Oriented Multimodal EmbeddingsAuthor 8 of 11ICML 2026
- Video-of-Thought: Step-by-Step Video Reasoning from Perception to CognitionAuthor 5 of 7ICML 2024 · 182 citations
- A Two-Stage Adaptation of Large Language Models for Text RankingAuthor 5 of 6ACL Findings 2024 · 12 citations
- Recognizing Everything from All Modalities at Once: Grounded Multimodal Universal Information ExtractionAuthor 1 of 7ACL Findings 2024 · 12 citations
- Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-imageAuthor 7 of 9NeurIPS 2024 · 2 citations
- Towards Demonstration-Aware Large Language Models for Machine TranslationAuthor 2 of 6ACL Findings 2024 · 2 citations
- SpeechEE: A Novel Benchmark for Speech Event ExtractionAuthor 2 of 9ACM MM 2024 · 1 citation
- Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene HallucinationAuthor 3 of 5ACL 2023 · 45 citations
- Generating Visual Spatial Description via Holistic 3D Scene UnderstandingAuthor 5 of 7ACL 2023 · 40 citations
- Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role LabelingAuthor 5 of 10ACM MM 2023 · 31 citations
- Improving Simultaneous Machine Translation with Monolingual DataAuthor 4 of 6AAAI 2023 · 19 citations
- Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation ExtractionAuthor 2 of 4ACL Findings 2023 · 7 citations
- PromptST: Abstract Prompt Learning for End-to-End Speech TranslationAuthor 5 of 7EMNLP 2023 · 3 citations
- LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language ModelAuthor 7 of 9NeurIPS 2022 · 114 citations
- Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text GenerationAuthor 5 of 6EMNLP 2022 · 10 citations
- Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence LabelingAuthor 5 of 6EMNLP 2022 · 9 citations
- Extending Phrase Grounding with Pronouns in Visual DialoguesAuthor 3 of 4EMNLP 2022 · 5 citations
