Scholar
Ruihua Song
Google Scholar ID: v5LctN8AAAAJ
Renmin University of China
AI based creation
multi-modaltiy chitchat
natural language understanding
information retrieval
information extraction
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
4,193
H-index
27
i10-index
60
Publications
20
Co-authors
0
Publications
40 items
ROMA: LLM System for Real-World Object-Centric Multi-Sensory Active Perception
2026
Cited
0
Can Computation from Earlier Problems Help LLMs Solve New Ones?
2026
Cited
0
Informed Masking: Structure-Aware Perturbation for Reinforcement Learning in Diffusion Large Language Models
2026
Cited
0
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
2026
Cited
0
FATE: Frame-Level Audio-Visual Temporal Embedding
2026
Cited
0
AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression
2026
Cited
0
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch
2026
Cited
0
Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts
2026
Cited
0
Load more
