Qingyang Liu

7 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 (13)

Venues

CVPR (4) AAAI (1) ACL (1) ICML (1)

Top co-authors

Li Niu (5) Xinhao Tao (2) Xiaofeng Zhang (2) Shuochen Chang (2) Zhaohe Liao (2) Hongfei Zhang (1) Harold Haodong Chen (1) Wen-Jie Shu (1) Qianli Ma (1) Shengyu Zhang (1)

Research topics

Artificial Intelligence (5) Core AI (5) Computer Vision (4) Generation (3) Processing (3) Deep Learning (2) Machine Learning (1) Application Areas (1) Core Methods (1) Learning Types (1) Models (1)

Keywords

diffusion model (3) shadow generation (2) image composition (2) image editing (2) image-to-image translation (1) multimodal large language model (1) evaluation benchmark (1) mechanistic interpretability (1) inference acceleration (1) visual token (1) data pipeline (1) reasoning benchmark (1) token merging (1) denoising step (1) recursive division (1) geometry prior (1) image-to-video generation (1) latent reasoning (1) reasoning accuracy (1) training-free intervention (1)

Papers

D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs AAAI 2026 TiViBench: Benchmarking Think-in-Video Reasoning for Video Generation CVPR 2026 UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Edits CVPR 2026 Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention ACL 2026 Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering ICML 2025 Shadow Generation Using Diffusion Model with Geometry Prior CVPR 2025 Shadow Generation for Composite Image Using Diffusion Model CVPR 2024