Songyuan Yang
4 papers · 2026–2026 · 2 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
(10)
Top co-authors
Research topics
Keywords
large multimodal model
(2)
video reasoning
(2)
motion generation
(1)
risk estimation
(1)
3d human motion
(1)
multimodal large language model
(1)
retrieval-augmented generation
(1)
reasoning trace
(1)
knowledge fusion
(1)
key frame
(1)
event segmentation
(1)
attention routing
(1)
video hallucination
(1)
token calibration
(1)
evidence consistency
(1)
reinforcement learning
(1)
video knowledge graph
(1)
scene understanding
(1)
Papers
Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning
CVPR 2026
MMG-VL: A Vision-Language Driven Approach for Multi-Person Motion Generation
AAAI 2026
Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning
CVPR 2026
Unstitching the Chimera: Frame-Level Risk and Train-Free Mitigation for Video Hallucination
CVPR 2026