The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as LLM-as-a-Judge, have proven their effectiveness in addressing this but suffer from prohibitive computational costs and lack of interpretability. To bridge this gap, we propose One-Step-Train (OST), a framework that reformulates data selection as an incremental optimization utility ranking problem. Instead of relying on semantic heuristics, OST estimates the marginal utility of each sample via a simulated single-step update on a lightweight proxy. Experiments on the Qwen series across multimodal mathematical reasoning benchmarks demonstrate that OST achieves Pareto-optimal efficiency. By selecting the top-50 subset, OST reduces training costs by 43% (and total time consumption by 17) while surpassing the strong LLM-as-a-Judge baseline by 1.8 points. Furthermore, under a fixed compute budget, our method using only the top-20 subset achieves a 5.6 point gain over LLM-as-a-Judge, improves upon heuristic scoring baselines like DEITA, and outperforms the Full-SFT baseline by 8.8 points. Notably, while Full-SFT suffers from performance degradation due to noise, our optimization-grounded approach effectively identifies toxic samples, successfully reversing the negative transfer frequently observed in complex reasoning tasks.
Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies(广东省新型安全智能技术重点实验室)
Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning
School of Computer Science and Engineering, Central South University(计算机科学与工程学院,中南大学);School of Automation, Central South University(自动化学院,中南大学);School of Computer Science and Technology, Beijing Jiaotong University(计算机科学与技术学院,北京交通大学)
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机学院);State Key Laboratory of Complex & Critical Software Environment(复杂与关键软件环境国家重点实验室);School of Computer Science, Wuhan University(武汉大学计算机学院)
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
University of Science and Technology of China(中国科学技术大学);National University of Singapore(新加坡国立大学);The Hong Kong Polytechnic University(香港理工大学);Huawei(华为)
An Early Investigation into the Utility of Multimodal Large Language Models in Medical Imaging
Faculty of Computing and Information Technology, Sohar University(苏哈尔大学计算与信息技术学院);Foundation University School of Sciences and Technology(基础大学科学与技术学院);College of Science and Engineering, Hamad Bin Khalifa University(哈马德·本·哈利法大学科学与工程学院)
Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment
Elmore Family School of Electrical and Computer Engineering, Purdue University(普渡大学埃尔莫尔电气与计算机工程学院);Yonsei University(延世大学);University at Buffalo–SUNY(纽约州立大学布法罗分校)
BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal Perception
HFIPS, Chinese Academy of Sciences(中国科学院合肥物质科学研究院);University of Science and Technology of China(中国科学技术大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校)
Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval
NASK National Research Institute(NASK国家研究院);IDEAS Research Institute(IDEAS研究所);Warsaw University of Technology(华沙技术大学);Universitat Autonoma de Barcelona(巴塞罗那自治大学)
Harmony: A Unified Framework for Modality Incremental Learning
Peng Cheng Laboratory(鹏城实验室);State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA)(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)(中国科学院大学人工智能学院)
Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
Shanghai Jiao Tong University(上海交通大学);OpenDataLab, Shanghai Artificial Intelligence Laboratory(OpenDataLab,上海人工智能实验室);The University of Hong Kong(香港大学);Peking University(北京大学)