6 papers
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
Qifan Yu, Xinyu Ma, Zhijian Zhuo +7
Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively explored depth expansion, width expansio…
LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
Xu Ouyang, Deyi Liu, Yuhang Cai +5
Existing scaling laws for Large Language Models (LLMs), predominantly monotonic power laws, fail to explain emerging non-monotonic phenomena such as catastrophic overtraining and q…
GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models
Chen Zheng, Yuhang Cai, Deyi Liu +7
Modern large language models leverage Mixture-of-Experts (MoE) architectures for efficient scaling, but face a critical challenge: functionally similar experts are often selected s…
Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models
Chen Zheng, Yiyuan Ma, Yuan Yang +11
The development of alignment and reasoning capabilities in large language models has seen remarkable progress through two paradigms: instruction tuning and reinforcement learning f…
Model Merging in Pre-training of Large Language Models
Yunshui Li, Yiyuan Ma, Shen Yan +23
Model merging has emerged as a promising technique for enhancing large language models, though its application in large-scale pre-training remains relatively unexplored. In this pa…
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…