Scholar
Junyi Li
Google Scholar ID: zQ0P3JAAAAAJ
The University of Hong Kong
Computer Vision
Multimodal Understanding
Multimodal Agent
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
294
H-index
2
i10-index
1
Publications
4
Co-authors
5
list available
Publications
19 items
Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies
2026
Cited
0
Persona Following Is Not Selective Control: The Neutrality Gap in LLM User Simulation
2026
Cited
0
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
2026
Cited
0
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
2026
Cited
0
R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search
2026
Cited
0
Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization
2026
Cited
0
Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models
2026
Cited
0
RAGR: Review-Augmented Generative Recommendation
2026
Cited
0
Load more
Co-authors
5 total
Junfeng Wu
Huazhong University of Science and Technology
Xiang Bai
Huazhong University of Science and Technology (HUST)
Xin Lai
ByteDance
Hengshuang Zhao
The University of Hong Kong
Senqiao Yang
The Chinese University of Hong Kong
