Hanrong Ye
Scholar

Hanrong Ye

Google Scholar ID: 1XbRknQAAAAJ
NVIDIA Research
multi-task multi-modal models
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
569
 
H-index
12
 
i10-index
13
 
Publications
20
 
Co-authors
0
 
Contact
No contact links provided.
Publications
14 items
Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing
2026
Cited
0
Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception
2026
Cited
0
GSPN-2: Efficient Parallel Sequence Modeling
2025
Cited
0
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
2025
Cited
0
Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
2025
Cited
0
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
2025
Cited
0
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
2025
Cited
0
UALM: Unified Audio Language Model for Understanding, Generation and Reasoning
2025
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)