activity
20242026
most citedDistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Models

13 citations · 21 across the 38 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

KITE: KV-Invariant Transformer Expansion for Efficient Agentic LLM Scaling

Zhiheng Hu, Yixun Wei, Jian Zhou +8

Scaling a language model is not only a question of final quality: the architectural choice determines how much computation is spent during training, prompt processing, and autoregr…

cs.LG2026

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

Jingcheng Hu, Yinmin Zhang, Shijie Shang +17

We introduce Parallel Coordinated Reasoning (PaCoRe), a training-and-inference framework designed to overcome a central limitation of contemporary language models: their inability…

cs.LG2025

Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding

StepFun, :, Bin Wang +195

Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hard…

cs.LG2025

Predictable Scale: Part II, Farseer: A Refined Scaling Law in Large Language Models

Houyi Li, Wenzhen Zheng, Qiufeng Wang +8

Training Large Language Models (LLMs) is prohibitively expensive, creating a critical scaling gap where insights from small-scale experiments often fail to transfer to resource-int…

cs.LG2025★ 1 cited

StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation

Yinmin Zhong, Zili Zhang, Xiaoniu Song +11

Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first ge…

cs.LG2025

Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Jingcheng Hu, Yinmin Zhang, Qi Han +3

We introduce Open-Reasoner-Zero, the first open source implementation of large-scale reasoning-oriented RL training on the base model focusing on scalability, simplicity and access…