4 citations · 6 across the 14 of their papers we have counts for
7 papers · 1 filter
Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder
Zhen Xu, Zhen Tan, Song Wang +2
Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable…
HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Prediction
Shuwei Chen, Jiajun Cui, Zhengqi Xu +4
Click-through rate (CTR) prediction, which models behavior sequence and non-sequential features (e.g., user/item profiles or cross features) to infer user interest, underpins indus…
Staircase Streaming for Low-Latency Multi-Agent Inference
Junlin Wang, Jue Wang, Zhen +5
Recent advances in large language models (LLMs) opened up new directions for leveraging the collective expertise of multiple LLMs. These methods, such as Mixture-of-Agents, typical…
Omnidirectional Spatial Modeling from Correlated Panoramas
Xinshen Zhang, Tongxi Fu, Xu Zheng
Omnidirectional scene understanding is vital for various downstream applications, such as embodied AI, autonomous driving, and immersive environments, yet remains challenging due t…
When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework
Zhen Xu, Shang Zhu, Jue Wang +5
We investigate the challenge of applying Large Language Models (LLMs) to long texts. We propose a theoretical framework that distinguishes the failure modes of long context tasks i…
LLM-Sketch: Enhancing Network Sketches with LLM
Yuanpeng Li, Zhen Xu, Zongwei Lv +3
Network stream mining is fundamental to many network operations. Sketches, as compact data structures that offer low memory overhead with bounded accuracy, have emerged as a promis…
Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models
Xumeng Wen, Shun Zheng, Zhen Xu +2
Recent studies have shown that large language models (LLMs), when customized with post-training on tabular data, can acquire general tabular in-context learning (TabICL) capabiliti…