14 citations · 31 across the 28 of their papers we have counts for
29 papers
PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition
Ziyan Gan, Fangxin Liu, Chenyang Guan +10
Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However, modern MoE inference remai…
Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training
Hanfeng Lu, Tianyu Feng, Suyi Li +8
Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions. Reinforcement learning (RL) post-training enhances these…
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL
Wei Gao, Yuheng Zhao, Dilxat Muhtar +13
Agentic reinforcement learning (RL) is reshaping LLM post-training, but end-to-end training time is dominated by compute-intensive, multi-turn rollouts whose resource demand varies…
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…
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…
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
Yunze Tong, Mushui Liu, Canyu Zhao +7
Deploying GRPO on Flow Matching models has proven effective for text-to-image generation. However, existing paradigms typically propagate an outcome-based reward to all preceding d…
AMAP Agentic Planning Technical Report
AMAP AI Agent Team, Yulan Hu, Xiangwen Zhang +22
We present STAgent, an agentic large language model tailored for spatio-temporal understanding, designed to solve complex tasks such as constrained point-of-interest discovery and…
RollMux: Phase-Level Multiplexing for Disaggregated RL Post-Training
Tianyuan Wu, Lunxi Cao, Yining Wei +11
Rollout-training disaggregation is emerging as the standard architecture for Reinforcement Learning (RL) post-training, where memory-bound rollout and compute-bound training are ph…
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Weixun Wang, XiaoXiao Xu, Wanhe An +86
Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its impo…
RollArt: Disaggregated Multi-Task Agentic RL Training at Scale
Wei Gao, Yuheng Zhao, Tianyuan Wu +15
Agentic Reinforcement Learning (RL) trains LLMs through multi-turn interactions with environments, producing workloads that mix compute-bound prefill, bandwidth-bound decoding, CPU…
Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers
Hongzhan Lin, Zhiqi Bai, Xinmiao Zhang +10
Transformer decoders have achieved strong results across tasks, but the memory required for the KV cache becomes prohibitive at long sequence lengths. Although Cross-layer KV Cache…
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…
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
Yang Li, Zhichen Dong, Yuhan Sun +9
The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the dis…
RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training
Wei Gao, Yuheng Zhao, Dakai An +11
Reinforcement Learning (RL) is a pivotal post-training technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, synchronous RL post-training oft…
RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models
Hua Zong, Qingtao Zeng, Zhengxiong Zhou +31
In this paper, we propose RecIS, a unified Sparse-Dense training framework designed to achieve two primary goals: 1. Unified Framework To create a Unified sparse-dense training fra…
Ovis2.5 Technical Report
Shiyin Lu, Yang Li, Yu Xia +39
We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer…
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…
RecGPT Technical Report
Chao Yi, Dian Chen, Gaoyang Guo +51
Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, mo…
Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
Weixun Wang, Shaopan Xiong, Gengru Chen +38
We introduce ROLL, an efficient, scalable, and user-friendly library designed for Reinforcement Learning Optimization for Large-scale Learning. ROLL caters to three primary user gr…
Adaptra: Straggler-Resilient Hybrid-Parallel Training with Pipeline Adaptation
Tianyuan Wu, Lunxi Cao, Hanfeng Lu +8
Training large Deep Neural Network (DNN) models at scale often encounters straggler issues, mostly in communications due to network congestion, RNIC/switch defects, or topological…
CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
Peng Chen, Pi Bu, Yingyao Wang +9
Recent advances in Vision-Language-Action models (VLAs) have expanded the capabilities of embodied intelligence. However, significant challenges remain in real-time decision-making…
FALCON: Pinpointing and Mitigating Stragglers for Large-Scale Hybrid-Parallel Training
Tianyuan Wu, Wei Wang, Yinghao Yu +7
Fail-slows, or stragglers, are common but largely unheeded problems in large-scale hybrid-parallel training that spans thousands of GPU servers and runs for weeks to months. Yet, t…
DDK: Distilling Domain Knowledge for Efficient Large Language Models
Jiaheng Liu, Chenchen Zhang, Jinyang Guo +13
Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distil…
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
Haoran Que, Jiaheng Liu, Ge Zhang +13
Continual Pre-Training (CPT) on Large Language Models (LLMs) has been widely used to expand the model's fundamental understanding of specific downstream domains (e.g., math and cod…