6 papers
LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video Recommendation
Haichao Zhang, Yao Lu, Lichen Wang +4
Video Large Language Models (VLLMs) unlock world-knowledge-aware video understanding through pretraining on internet-scale data and have already shown promise on tasks such as movi…
Reward Model Routing in Alignment
Xinle Wu, Yao Lu
Reinforcement learning from human or AI feedback (RLHF / RLAIF) has become the standard paradigm for aligning large language models (LLMs). However, most pipelines rely on a single…
TRACER: Efficient Object Re-Identification in Networked Cameras through Adaptive Query Processing
Pramod Chunduri, Yao Lu, Joy Arulraj
Efficiently re-identifying and tracking objects across a network of cameras is crucial for applications like traffic surveillance. Spatula is the state-of-the-art video database ma…
Collaborative Editable Model
Kaiwen Tang, Aitong Wu, Yao Lu +1
Vertical-domain large language models (LLMs) play a crucial role in specialized scenarios such as finance, healthcare, and law; however, their training often relies on large-scale…
OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing
Yulong Hui, Yihao Liu, Yao Lu +1
Large Language Models (LLMs) encounter challenges in efficiently processing long-text queries, as seen in applications like enterprise document analysis and financial report compre…
PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks
Feng Ni, Kui Huang, Yao Lu +4
With the rapid advancement of digitalization, various document images are being applied more extensively in production and daily life, and there is an increasingly urgent need for…