19 papers
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
Chenglong Wang, Ziming Zhu, Yifu Huo +9
Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong capabilities in response ranki…
FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models
Kaiyang Ye, Yuan Ge, Junxiang Zhang +8
While on-policy distillation (OPD) effectively addresses sparse rewards and exposure bias in large language model post-training, its extension to flow models remains underexplored.…
MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration
Xinyu Liu, Xin Liu, Bo Jin +8
While chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning tasks, the linear growth of the KV cache leads to substantial memory and inference overhead. Exis…
RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment
Yingfeng Luo, Hongyu Liu, Dingyang Lin +6
Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensive. A widely adopted remedy…
NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
Yingfeng Luo, Ziqiang Xu, Yuxuan Ouyang +9
Large language models have significantly advanced Multilingual Machine Translation (MMT), yet scaling to many languages while keeping quality robust across directions remains chall…
MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning
Chenglong Wang, Yifu Huo, Yang Gan +8
Recent advances in multimodal reward modeling have been largely driven by a paradigm shift from discriminative to generative approaches. Building on this progress, recent studies h…