Weikai Huang

5 papers · 2024–2026 · 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 👥 Mega-Team · Squad

Venues

CVPR (3) ECCV (1) NeurIPS (1)

Top co-authors

Jieyu Zhang (5) Ranjay Krishna (5) Zixian Ma (3) Chenhao Zheng (2) Ziqi Gao (2) Ali Farhadi (2) Tanmay Gupta (2) Jae Sung Park (2) Vincent Shao (1) Dong He (1)

Research topics

Computer Vision (3) Artificial Intelligence (2) Deep Learning (2) Core AI (2) Processing (2) Machine Learning (1) Natural Language Processing (1) Analysis (1) Application Areas (1) Learning Types (1) Models (1) Resources & Methods (1)

Keywords

video understanding (2) vision-language model (2) visual grounding (2) referring expression (1) object tracking (1) instance segmentation (1) synthetic data generation (1) multimodal language model (1) video question answering (1) token merging (1) perceptual capability (1) object trajectory (1) benchmark generation (1) object detection (1) trajectory token (1) visual question answering (1) video captioning (1)

Papers

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding CVPR 2026 Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding CVPR 2026 TrajTok: Learning Trajectory Tokens Enhances Video Understanding CVPR 2026 m&m’s: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks ECCV 2024 Task Me Anything NeurIPS 2024