← Back to all news
arXiv Machine Learning By Haolong Hu, Hanyu Li, Tiancheng He, Huahui Yi, An Zhang, Qiankun Li, Kun Wang, Yang Liu, Zhigang Zeng

SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics

Read the original on arXiv Machine Learning →

SaFeR-Steer is a progressive multi‑turn alignment framework that uses staged synthetic bootstrapping and tutor‑in‑the‑loop GRPO to train a single student model against adaptive, on‑policy attacks. It introduces Trajectory‑Consistent Summative Reward (TCSR) to ensure that low‑quality turns impact the overall trajectory reward. The authors release the STEER dataset and demonstrate that SaFeR‑Steer significantly improves safety and helpfulness on both single‑turn and multi‑turn benchmarks for Qwen2.5‑VL models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computation and Language
Sep 4

Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment

The paper introduces MINT‑Safe, a new open‑source dataset of 11,270 multi‑image dialogues and 500 refusal VQA pairs designed to expose safety risks in multi‑modal large language models during open‑ended conversations. It also proposes TAD‑Align, a turn‑aware dual‑objective reward framework that dynamically up‑weights dialogue turns with inconsistent safety behavior, improving safety metrics on Qwen2.5‑VL‑7B‑Instruct and LLaVA‑Next‑7B. The results show over 10% reduction in attack success rate and notable gains in harmlessness and helpfulness while maintaining overall model performance.

By Han Zhu, Jiale Chen, Chengkun Cai, Shengjie Sun, Haoran Li, Yujin Zhou, Chi-Min Chan, Pengcheng Wen, Lei Li, Yike Guo, Sirui Han
llmsagentsdiffusionreinforcement-learningmultimodalbenchmarkssafety
More like this →
arXiv Computation and Language
Oct 27

SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy

arXiv:2610.35743v1 Announce Type: new Abstract: Existing jailbreak attackers fall into two classes: static planners fix their single- or multi-turn adversarial plans in advance, remaining simple but...

By Mingqian Feng, Xiaodong Liu, Weiwei Yang, Chenliang Xu, Jialin Song, Qiyao Ma, Chengquan Guo, Carolyn Buractaon, Christopher White, Jianfeng Gao
llmsreinforcement-learningfine-tuningmultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
5d ago

Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model

The paper introduces NegWAM, a safety post‑training framework for unified world‑action models (WAMs) used in end‑to‑end autonomous driving. NegWAM generates negative trajectories that are close to expert paths but contain safety risks, using them as repulsive anchors to steer predictions away from dangerous behavior while encoding scene‑trajectory compatibility via rider tokens. The method achieves a 4.1% relative improvement on the NAVSIM v2 navhard benchmark and 93.3 EPDMS on navtest, demonstrating strong safety performance without sacrificing routine driving, and shows cross‑benchmark generalization in zero‑shot closed‑loop tests on HUGSIM.

By Zihao Zhang, Xinyu Zhang, Bing Zeng, Xingyu Chen, Zhenning Li, Bin Yu, Ziyuan Pu
agentsroboticsbenchmarkssafety
More like this →