Yuhong Dai — accepted AI-conference papers

2026

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Weicai Yan, Yuhong Dai, Qi Ran, Haodong Li, Wang Lin, Hao Liao +3

ICML 2026poster

Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous streaming inputs, (2) autonomously deciding when to respond, and (3) controlling both quality and quantity of generated cont…

Cited by 0 Source ↗Scholar ↗

2025

Pretraining Context Compressor for Large Language Models with Embedding-Based Memory

Yuhong Dai, Jianxun Lian, Yitian Huang, Wei Zhang, Mingyang Zhou, Mingqi Wu +2

ACL 2025long

Efficient processing of long contexts in large language models (LLMs) is essential for real-world applications like retrieval-augmented generation and in-context learning, especially in resource-constrained environments such as edge computing. This paper explores the embedding-based context compress…

Cited by 0 Source ↗PDF ↗Scholar ↗