4 papers
PACE: Pareto-Adaptive Compression for Efficient Native MLLMs
Lei Tian, Chunzheng Zhu, Kai Wu +2
Native multimodal large language models (native MLLMs) jointly encode visual and linguistic sequences within a unified autoregressive Transformer, emerging as a promising paradigm…
Learning from Medical Entity Trees: An Entity-Centric Medical Data Engineering Framework for MLLMs
Jianghang Lin, Haihua Yang, Deli Yu +6
Multimodal Large Language Models (MLLMs) have shown transformative potential in medical applications, yet their performance is hindered by conventional data curation strategies tha…
BaseReward: A Strong Baseline for Multimodal Reward Model
Yi-Fan Zhang, Haihua Yang, Huanyu Zhang +11
The rapid advancement of Multimodal Large Language Models (MLLMs) has made aligning them with human preferences a critical challenge. Reward Models (RMs) are a core technology for…
GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
Hongze Tan, Zihan Wang, Jianfei Pan +7
Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained cr…