ProReason: Multi-modal proactive reasoning with decoupled eyesight and wisdom

Jan 1, 2025·

Jingqi Zhou

Sheng Wang

Co-Corresponding Author

Jingwei Dong

Lei Li

Jiahui Gao

Lingpeng Kong

Chuan Wu

Co-Corresponding Author

· 0 min read

Preprint Preprint

Abstract

ProReason proposes a framework to decouple visual and reasoning capabilities, leveraging LLMs to enhance multi-modal reasoning performance.

Type

Conference paper

Publication

In The 2025 Conference on Empirical Methods in Natural Language Processing

Last updated on Jan 1, 2025

Multi-Modal Reasoning EMNLP 2025 Main Co-Corresponding Author

Authors

Jingqi Zhou

Authors

Sheng Wang (Forence)

PhD Graduate in Computer Science

Sheng Wang is a PhD graduate from The University of Hong Kong, supervised by Prof. Chuan Wu and Prof. Lingpeng Kong. His research focuses on Agent, LLM Super-Alignment, and Data Synthesis. He has published 14+ papers in top-tier conferences including NIPS2025 (Spotlight), ICLR2025, ACL2024/2025, EMNLP2025.

Authors

Authors

Authors

Authors

Authors

← MoS: Unleashing parameter efficiency of low-rank adaptation with mixture of shards Jan 1, 2025

QSpec: Speculative decoding with complementary quantization schemes Jan 1, 2025 →