activity
20242026
collaborators

11 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.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.CL2026

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss

Ang Lv, Jin Ma, Yiyuan Ma +1

Mixture-of-Experts (MoE) models lack explicit constraints to ensure the router's decisions align well with the experts' capabilities, which ultimately limits model performance. To…

cs.AI2025

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason

Kaiyi Zhang, Ang Lv, Jinpeng Li +4

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving the complex reasoning abilities of large language models (LLMs). However, current RLVR m…

cs.LG2025

Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games

Xiaoqing Zhang, Huabin Zheng, Ang Lv +5

Large language models (LLMs) have been observed to suddenly exhibit advanced reasoning abilities during reinforcement learning (RL), resembling an ``aha moment'' triggered by simpl…

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…