Xurui Song

5 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 (13) ⭐ Rising Star (5) ❓ The Questioner

Venues

AAAI (3) EMNLP (1) ICCV (1)

Top co-authors

Jun Luo (5) Shuo Huai (3) Zhixin Xie (2) Jiayi Kong (2) Chao Ma (1) Jingjing Jiang (1) Ying He (1) Hanwang Zhang (1) Baixin Xu (1) Kangqiao Zhao (1)

Research topics

Artificial Intelligence (4) Core AI (4) Machine Learning (3) Computer Vision (2) Analysis (2) Domain-Specific (2) Learning Types (2) Generation (1) Optimization & Theory (1)

Keywords

3d reconstruction (1) reinforcement learning (1) chain-of-thought reasoning (1) autonomous driving (1) privacy preservation (1) visual reasoning (1) instruction following (1) model safety (1) neural rendering (1) safety alignment (1) stereo matching (1) neural reconstruction (1) multimodal large language model (1) jailbreak attack (1) adversarial prompt (1) prompt injection (1) geometric data (1) diffusion language model (1) facial recognition (1) physical adversarial attack (1)

Papers

Cheating Stereo Matching in Full-Scale: Physical Adversarial Attack Against Binocular Depth Estimation in Autonomous Driving AAAI 2026 Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position AAAI 2026 Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning ICCV 2025 Dagger Behind Smile: Fool LLMs with a Happy Ending Story EMNLP 2025 Do Not DeepFake Me: Privacy-Preserving Neural 3D Head Reconstruction Without Sensitive Images AAAI 2025