Review

BUS: Brain-Inspired Unsupervised Self-Reflection for Advanced Multimodal Reasoning

Jiacheng Yang Tongying Xiao Yun-Kai Dang Conglin Wang Yue-Kun Yang Qi Fan Wen-Bin Li Feng Miao Yang Gao

· 0 citations · 36 references

TL;DR

This work proposes B rain-inspired Supervised Supervised Reflection (BUS), a label-free training framework to enhance reflective reasoning capability in challenging image analysis and validate that backward prediction capability is critical for VLM reasoning.

Semantic Scholar

View source

Similar papers

Preprint Aug 2026

TRAM: Enhancing Multimodal Reasoning with Trajectory-Derived Auxiliary Memory

TRAM (TRajectory-derived Auxiliary Memory), a training-free method that augments standard decoding with an auxiliary memory pathway derived from the model's own reasoning trajectory, shows that TRAM improves performance over vanilla decoding on mathematical, scientific, and general visual reasoning tasks without additi...

Kang Liu, Zi-Jing Wang, Yongkang Liu et al. · 0 citations

#artificial intelligence Preprint Sep 2026

UniCAR-RL: Seeing Better before Thinking Deeper in Visual Mathematics

Multimodal Large Language Models (MLLMs) often struggle with complex mathematical visual reasoning primarily due to a lack of fine-grained perception, causing initial visual hallucinations to directly trigger cascading reasoning failures. In traditional end-to-end reinforcement learning (RL), sparse rewards fail to dec...

Yu-Zhe Li, Hao Yan, Hao Wang et al. · 0 citations

Jul 2026

Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation

Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen scenes. Although recent multimodal large models and world-model-based methods have improved navigation, they often preserve excessive task-irrelevant detail, weakening ge...

Yihao Wu, Chen-Yi Xu, Li-Qi Yan et al. · arXiv.org · 0 citations

Open access Aug 2026

Mental bootstrapping enables human-level concept learning in self-supervised deep models

A self-supervised framework that trains models on systematically simplified versions of abstract reasoning tasks containing incomplete but structured concept cues enables models to form internal abstractions under limited resources and later apply them to more complex problems.

Lingxiao Yang, Muyang Lyu, Ying-Jie Wang et al. · Science Advances · 0 citations

#artificial intelligence Preprint Aug 2026

BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving

This work proposes BrainWAM, a structured action-space coordination framework that converts semantic reasoning and predictive world modeling into two specialized action-oriented pathways, and aligns them at the level of compact action representations, and introduces an asynchronous rectified-flow inference strategy wit...

Bing Zhan, Shuyao Shang, Shuo Lu et al. · 1 citation

Preprint Aug 2026

Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs

A novel training-free inference strategy for MLLMs that explicitly decouples perception and reasoning is presented, and a novel metric, the vision-to-text attention ratio, is proposed, to dynamically gauge the model's cognitive focus.

Haoqiang Kang, Liupeng Li, Kuo-Feng Gao et al. · 0 citations