Xirui Li

5 papers · 2024–2026 · 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 (14) ❓ The Questioner

Venues

ICLR (2) AAAI (1) CVPR (1) EMNLP (1)

Top co-authors

Chao Ma (3) Ming-Hsuan Yang (2) Tianyi Zhou (2) Ruochen Wang (2) Cho-jui Hsieh (2) Minhao Cheng (2) Xiaokang Yang (2) Charles Herrmann (1) Yuntian Chen (1) Qinglong Cao (1)

Research topics

Deep Learning (4) Computer Vision (3) Machine Learning (3) Generation (3) Models (3) Artificial Intelligence (2) Core AI (2) Learning Types · Machine Learning (2) Learning Types · Deep Learning (2) Application Areas (1) Architectures (1) Processing (1)

Keywords

diffusion model (2) image generation (1) video generation (1) in-context learning (1) prompt engineering (1) depth estimation (1) conditional generation (1) image translation (1) optical flow (1) adversarial attack (1) fluid dynamics (1) video editing (1) multimodal large language model (1) jailbreak attack (1) refusal behavior (1) masked autoencoder (1) video diffusion (1) temporal consistency (1) token merging (1) safety mechanism (1)

Papers

Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame AAAI 2026 A Simple Approach to Unifying Diffusion-based Conditional Generation ICLR 2025 Is Your Multimodal Language Model Oversensitive to Safe Queries? ICLR 2025 DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLMs Jailbreakers EMNLP 2024 VidToMe: Video Token Merging for Zero-Shot Video Editing CVPR 2024