collaborators

8 papers

cs.CL2026

ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns

Ziyu Zhao, Tong Zhu, Zhi Zhang +6

Mixture-of-Experts (MoE) effectively scales model capacity while preserving computational efficiency through sparse expert activation. However, training high-quality MoEs from scra…

cs.LG2025

Virtual Width Networks

Seed, Baisheng Li, Banggu Wu +115

We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN d…

cs.LG2025

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation

Xin Yu, Cong Xie, Ziyu Zhao +4

Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational capacity often lags behind full…

cs.AI2025

Truncated Proximal Policy Optimization

Tiantian Fan, Lingjun Liu, Yu Yue +20

Recently, test-time scaling Large Language Models (LLMs) have demonstrated exceptional reasoning capabilities across scientific and professional tasks by generating long chains-of-…

cs.LG2025

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Qiying Yu, Zheng Zhang, Ruofei Zhu +32

Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details…

cs.CL2025

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

ByteDance Seed, :, Jiaze Chen +267

We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 8…