Yezhou Yang
16 papers · 0 citations
Most-cited papers
- Injecting Semantic Concepts Into End-to-end Image Captioning2021 · 113 citations
- Modularized Textual Grounding For Counterfactual Resilience2019 · 17 citations
- Getting It Right: Improving Spatial Consistency In Text-to-image Models2024 · 11 citations
- On The Robustness Of Language Guidance For Low-level Vision Tasks: Findings From Depth Estimation2024 · 6 citations
- REVISION: Rendering Tools Enable Spatial Fidelity In Vision-language Models2024 · 3 citations
- Interact-video: Reasoning-rich Video QA For Urban Traffic2025
- Sepose: A Synthetic Event-based Human Pose Estimation Dataset For Pedestrian Monitoring2025
- Vibetoken: Scaling 1D Image Tokenizers And Autoregressive Models For Dynamic Resolution Generations2026
Topics