Scholar
Ke Li
Google Scholar ID: mfWsFM0AAAAJ
Principal Researcher, Tencent
Citations & Impact
Citations
6,470
H-index
30
i10-index
55
Publications
20
Co-authors
14
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Selected Publications:
- - Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
- - VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model
- - VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
- - MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
- - LTD-Bench: Evaluating Large Language Models by Letting Them Draw
- - Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
- - Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
- - Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment
- - FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression
- - Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models
- - PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
Research Experience
- Principal Researcher and Team Manager at Tencent Youtu Lab.
Education
- Master's degree: 2018 from Xiamen University, supervised by Prof. Rongrong Ji; Bachelor's degree: 2015 from Zhengzhou University, advised by Prof. Mingliang Xu.
Background
- Research interests: deep learning and its application in computer vision and natural language processing. Previously a Principal Researcher and Team Manager at Tencent Youtu Lab.
Miscellany
- Reviewer for ICML, ICLR, NeurIPS, CVPR, ICCV, ECCV, AAAI and TPAMI.
