The paper introduces a progressive training strategy for embodied vision‑language models aimed at reducing spatio‑temporal hallucinations. It first creates a Chain‑of‑Thought dataset that breaks complex reasoning into detailed spatiotemporal steps, then uses supervised pre‑training on this dataset followed by fine‑tuning with weakly‑labeled data. Experiments show the method improves backbone accuracy and narrows the forward‑backward performance gap from over 70% to 6.53%, indicating stronger dynamic reasoning and fewer temporal biases.
By Xiaoda Yang, Shuai Yang, Can Wang, Jingyang Xue, Menglan Tang, Checheng Yu, Xunzhe Zhou, Sashuai Zhou, Tao Jin, Lixin Yang, Xiangyu Yue, Zhou Zhao
CoWorld Reasoner is an agentic framework that leverages a Video World Model (VWM) as a unified visual reasoning engine for Vision‑Language Models (VLMs). It exposes multiple visual operations through tools and skills, allowing the VLM to decide when to imagine, select an operation, generate visual content, and interpret the resulting evidence. The framework includes a VLM‑VWM Harness Co‑Evolution mechanism that jointly refines tools, skills, and execution code based on feedback, while keeping model weights fixed. Across seven benchmarks covering spatial, temporal, causal, and perceptual reasoning, CoWorld Reasoner outperforms direct VLM reasoning and improves accuracy on all benchmarks, achieving notable gains on MMSI and ERQA.
By Dongjie Cheng, Ruifeng Yuan, Ran Wei, Ning Song, Yongqi Li, Wenjie Li
The paper introduces Spatial Alignment via Geometric Evolution (SAGE), a self‑evolving framework designed to strengthen robust spatial reasoning in Vision‑Language Models (VLMs). SAGE leverages geometric and linguistic duality operations, incorporating duality consistency into training to ensure coherent answers across original and transformed inputs. The method dynamically updates its operation pool, focusing on challenging dualities while retiring mastered ones, and is model‑agnostic, data‑efficient, and applicable as a lightweight adaptation stage to existing VLMs, yielding consistent improvements on video and spatial reasoning benchmarks.
By Junming Liu, Yuqi Li, Yifei Sun, Maonan Wang, Yiming Cheng, Rui Qian, Piotr Koniusz, Yirong Chen, Ding Wang
arXiv:2609.40129v1 Announce Type: new
Abstract: Reasoning through video generation offers a promising path toward visual intelligence by modeling latent visual states and their dynamics. However, cur...
By Zehua Ma, Kun Xiang, Yunshuang Nie, Quanlin Chen, Haoyuan Li, Xiuwei Chen, Jiang Ji, Haijun Wu, Zhenyu Xie, Michael Kampffmeyer, Hanhui Li, Xiaodan Liang
arXiv:2609.24813v1 Announce Type: new
Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities in multimodal tasks, yet they still exhibit poor ability in spatial reasoning....
By Haoran Sun, Jingqi Xu, Yanhui Li, Enci Liu, Kaidi Xu, Yanwei Liu
arXiv:2610.09746v1 Announce Type: new
Abstract: Mental imagery, ``seeing with the mind's eye'' is an essential aspect of human cognition. Despite rapid progress Large Language Models (LLMs) and Visio...
By Mariia Baidachna, Nicolas Pugeault
The paper introduces IG‑VLA, a vision‑language‑action framework that learns to imagine task‑relevant future scene evolution in a latent spatiotemporal space, guiding action prediction without generating full pixel‑level videos. It further compresses this future reasoning into a compact Scene Gist Token via Scene Gist Memory, enabling efficient inference. Experiments on LIBERO, LIBERO‑Plus, and VLABench show that IG‑VLA improves success rates by nearly 6% and speeds up inference up to 6.38× compared to strong baselines.
By Shenglan Li, Zhendong Mi, Hengyi Zhu, Jingwu Luo, Chun Kit Chan, Geng Yuan, Yanzhi Wang, Pu Zhao, Shaoyi Huang
arXiv:2608. 14138v1 Announce Type: cross Abstract: Spatial perception and reasoning from visual observations require recovering geometric structure, establishing correspondences, and understanding spatial relations.
By Jinsheng Quan, Jianhua Li, Siyi Xie, Xuanke Shi, Kewang Deng, Zukai Chen, Feifei Shao, Lei Yang, Quan Wang, Yawei Luo
SpatialASM is a framework that teaches Large Vision‑Language Models (LVLMs) to perform Active Spatial Mentalization (ASM), enabling them to proactively plan and imagine viewpoints during spatial reasoning tasks. The method uses an allocentric novel‑view generator to create explicit ASM trajectories and perspective‑taking tasks, providing two forms of supervision that guide LVLMs in adaptive view planning and scene imagination. Experiments on seven spatial benchmarks show that SpatialASM improves performance across four LVLM backbones while preserving their general vision capabilities.
By Yuhong Liu, Shenxi Wu, Junyi Chi, Beichen Zhang, Xuanlang Dai, Jiaqi Wang, Yuhang Zang, Dahua Lin
Soft Spatial Reasoning introduces a post‑training framework for Large Vision‑Language Models that replaces hard, token‑by‑token chain‑of‑thought reasoning with a soft, continuous state formed by mixing token embeddings at each intermediate step. The method employs AdaptSoft, a controller that adjusts the degree of softness based on hidden states and predictive uncertainty, guided by a gradient‑alignment learning objective that requires no intermediate supervision. Experiments on diverse spatial benchmarks show that this approach outperforms both hard and fixed‑soft chain‑of‑thought baselines and several existing LVLMs.
By Rafi Ibn Sultan, Md. Sajid Alam Chowdhury, Saleh Zare Zade, Chengyin Li, Prashant Khanduri, Marco Brocanelli, Dongxiao Zhu
The paper introduces structured video prompting, a training‑free inference‑time technique that augments input videos with lightweight spatial and temporal structure to provide explicit anchors for evidence organization. By applying this method to two video benchmarks and two open video‑language models, the authors demonstrate performance improvements across several tasks, with gains varying by model and task. The study suggests that failures in video‑language models stem not only from reasoning capacity but also from how video evidence is presented during inference.
By Sadegh Mohammadian
SpaceCast-Bench is a new benchmark that evaluates predictive spatial reasoning in vision‑language models, moving beyond simple spatial perception to tasks that require constructing scenes, anticipating interventions, and reasoning about unseen outcomes. It contains 3,862 questions from 182 real‑world scenes across 16 task types and three difficulty levels—static perception, local prediction, and global prediction—testing scene understanding, spatial state updating, and relational inference. Evaluation of 21 models shows a large performance gap, with the best model achieving only 58.0% versus 87.2% human accuracy, and fine‑tuning on the benchmark’s programmatically generated data can substantially improve model performance.
By Hongxing Li, Jinyue Su, Dingming Li, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen