Jingdi Lei

4 papers · 2025–2026 · 3 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 (10)

Venues

CVPR (2) AAAI (1) NAACL (1)

Top co-authors

Di Zhang (4) Wanli Ouyang (3) Dongzhan Zhou (3) Junxian Li (3) Jiatong Li (3) Jianbo Wu (2) Shufei Zhang (2) Yuqiang Li (2) Xunzhi Wang (2) Mao Su (1)

Research topics

Artificial Intelligence (4) Core AI (4) Deep Learning (2) Natural Language Processing (1) Reinforcement Learning (1) Learning Paradigms (1) Learning Types (1) Methods (1) Models (1) Resources & Methods (1)

Keywords

vision-language model (2) mathematical reasoning (1) direct preference optimization (1) preference optimization (1) visual grounding (1) reinforcement learning from human feedback (1) monte carlo tree search (1) backdoor attack (1) adversarial attack (1) multimodal large language model (1) multimodal reasoning (1) pairwise preference (1) optical character recognition (1) critic model (1) molecular structure (1) chemical reasoning (1) chemical domain (1) language critique (1) molecule understanding (1) bilingual multimodal dataset (1)

Papers

IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding CVPR 2026 ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area AAAI 2025 Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning CVPR 2025 LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search NAACL 2025