Bohan Zhai

6 papers · 2022–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

ACL (2) CVPR (2) ECCV (1) WACV (1)

Top co-authors

Shijia Yang (3) Chenfeng Xu (2) Kurt Keutzer (2) Ximeng Sun (1) Emad Barsoum (1) Trevor Darrell (1) Masayoshi Tomizuka (1) Sheng Shen (1) Zicheng Liu (1) Kaixin Ma (1)

Research topics

Artificial Intelligence (4) Core AI (4) Deep Learning (2) Natural Language Processing (2) Models (2) Computer Vision (1) Machine Learning (1) Applications (1) Generation (1) Learning Paradigms (1) Learning Types (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

multimodal large language model (2) large language model (2) vision-language model (2) direct preference optimization (1) information extraction (1) multimodal learning (1) image captioning (1) model adaptation (1) sql generation (1) downstream task (1) evaluation benchmark (1) image understanding (1) multimodal understanding (1) multimodal reasoning (1) prompt tuning (1) visual language (1) visual language understanding (1) execution feedback (1) structured generation (1) multi-task learning (1)

Papers

CaptionQA: Is Your Caption as Useful as the Image Itself? CVPR 2026 SO-Bench: A Structural Output Evaluation of Multimodal LLM CVPR 2026 Optimizing Reasoning for Text-to-SQL with Execution Feedback ACL 2025 InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model ACL 2024 Multitask Vision-Language Prompt Tuning WACV 2024 Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models ECCV 2022