5 papers
Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
Huanran Chen, Huaqing Zhang, Xiao Li +3
The foundational capabilities of large language models are acquired during pretraining on internet-scale, highly heterogeneous data mixtures. In this work, we investigate an intere…
Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective
Chengyin Xu, Kaiyuan Chen, Xiao Li +2
The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for comprehensive understanding o…
Reformulation for Pretraining Data Augmentation
Xintong Hao, Ruijie Zhu, Ge Zhang +2
Despite the impressive capabilities of large language models across various tasks, their continued scaling is severely hampered not only by data scarcity but also by the performanc…
Seed1.5-VL Technical Report
Dong Guo, Faming Wu, Feida Zhu +194
We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter v…
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…