52 citations · 76 across the 69 of their papers we have counts for
15 papers · 1 filter
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Jing Liang, Hongyao Tang, Yi Ma +9
Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. O…
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
Zhichen Dong, Yang Li, Yuhan Sun +9
Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing t…
Complementary RL: Towards Efficient Experience-Driven Agent Learning
Dilxat Muhtar, Jiashun Liu, Wei Gao +8
Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome fe…
Expert Divergence Learning for MoE-based Language Models
Jiaang Li, Haibin Chen, Langming Liu +9
The Mixture-of-Experts (MoE) architecture is a powerful technique for scaling language models, yet it often suffers from expert homogenization, where experts learn redundant functi…
Dissecting Outlier Dynamics in LLM NVFP4 Pretraining
Peijie Dong, Ruibo Fan, Yuechen Tao +11
Training large language models using 4-bit arithmetic enhances throughput and memory efficiency. Yet, the limited dynamic range of FP4 increases sensitivity to outliers. While NVFP…
SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion
Chengting Yu, Xiaobo Shu, Yadao Wang +8
Recursive (looped) Transformers decouple computational depth from parameter depth by repeatedly applying shared layers, providing an explicit architectural primitive for iterative…
CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
Runsong Zhao, Shilei Liu, Jiwei Tang +8
The quadratic complexity and indefinitely growing key-value (KV) cache of standard Transformers pose a major barrier to long-context processing. To overcome this, we introduce the…
One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning
Yiyuan Li, Zhen Huang, Yanan Wu +6
The reasoning ability of large language models (LLMs) can be unleashed with reinforcement learning (RL) (OpenAI, 2024; DeepSeek-AI et al., 2025a; Zeng et al., 2025). The success of…
Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
Jiashun Liu, Johan Obando-Ceron, Han Lu +7
Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely pragmatic: conventional value functions are…
Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony
Han Lu, Zichen Liu, Shaopan Xiong +19
Synchronous Reinforcement Learning (RL) post-training has emerged as a crucial step for enhancing Large Language Models (LLMs) with diverse capabilities. However, many systems desi…
MeSH: Memory-as-State-Highways for Recursive Transformers
Chengting Yu, Xiaobo Shu, Yadao Wang +8
Recursive transformers reuse parameters and iterate over hidden states multiple times, decoupling compute depth from parameter depth. However, under matched compute, recursive mode…
Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
Zihe Liu, Jiashun Liu, Yancheng He +13
Reinforcement learning for LLM reasoning has rapidly emerged as a prominent research area, marked by a significant surge in related studies on both algorithmic innovations and prac…
Weight Spectra Induced Efficient Model Adaptation
Chongjie Si, Xuankun Yang, Muqing Liu +5
Large-scale foundation models have demonstrated remarkable versatility across a wide range of downstream tasks. However, fully fine-tuning these models incurs prohibitive computati…
NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
Chongjie Si, Kangtao Lv, Jingjing Jiang +6
Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existin…
Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment
Yanshi Li, Shaopan Xiong, Gengru Chen +6
Reinforcement Learning (RL) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. Typical RL methods optimize under an overall sequence rewar…