activity
20242026
collaborators

8 papers

cs.LG2026

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Songhao Wu, Ang Lv, Ruobing Xie +1

Router is the cornerstone component to the Mixture-of-Experts models. Serving as expert proxies, the rows of the router matrix compute their similarity to the MoE inputs to determi…

cs.CL2026

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Songhao Wu, Zhongxin Chen, Yuxuan Liu +3

Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leadi…

cs.LG2026

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration

Songhao Wu, Ang Lv, Xiao Feng +5

The KV cache in large language models is a dominant factor in memory usage, limiting their broader applicability. Quantizing the cache to lower bit widths is an effective way to re…

cs.CL2025

Autonomy-of-Experts Models

Ang Lv, Ruobing Xie, Yining Qian +5

Mixture-of-Experts (MoE) models mostly use a router to assign tokens to specific expert modules, activating only partial parameters and often outperforming dense models. We argue t…

cs.CL2025

From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment

Jia-Nan Li, Jian Guan, Songhao Wu +2

Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in…

cs.IR2025

Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking

Songhao Wu, Quan Tu, Mingjie Zhong +4

In the realm of information retrieval, users often engage in multi-turn interactions with search engines to acquire information, leading to the formation of sequences of user feedb…