29 citations · 31 across the 32 of their papers we have counts for
4 papers · 1 filter
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
Daize Dong, Junlin Chen, Haolong Jia +9
Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs often suffers from training instab…
APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation
Yuzhen Zhou, Jiajun Li, Yusheng Su +15
Reinforcement learning (RL) has become a cornerstone in advancing large-scale pre-trained language models (LLMs). Successive generations, including GPT-o series, DeepSeek-R1, Kimi-…
SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
Zijian Wu, Jinjie Ni, Xiangyan Liu +3
Vision-language models (VLMs) trained via reinforcement learning with verifiable reward (RLVR) have shown notable progress in scaling test-time compute effectively. In this work, w…
A robust assessment for invariant representations
Wenlu Tang, Zicheng Liu
The performance of machine learning models can be impacted by changes in data over time. A promising approach to address this challenge is invariant learning, with a particular foc…