1 citations · 1 across the 3 of their papers we have counts for
4 papers
RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning
Yongqiang Yao, Jinru Tan, Kaihuan Liang +5
Reinforcement learning is crucial for improving large language models' reasoning and generalization. It relies on massive rollouts whose lengths become increasingly long-tailed as…
HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling
Rongkun Xue, Yazhe Niu, Shuai Hu +3
Discrete speech tokenization is a fundamental component in speech codecs. However, in large-scale speech-to-speech systems, the complexity of parallel streams from multiple quantiz…
Hierarchical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM
Yongqiang Yao, Jingru Tan, Kaihuan Liang +7
Training Long-Context Large Language Models (LLMs) is challenging, as hybrid training with long-context and short-context data often leads to workload imbalances. Existing works ma…
OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance
Yongqiang Yao, Jingru Tan, Feizhao Zhang +8
Vision-language instruction-tuning models have recently achieved significant performance improvements. In this work, we discover that large-scale 3D parallel training on those mode…