arXiv Computer Vision
GenDSR: Transferring Representations from Video Generation Models for Dynamic Spatial Reasoning
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 10
A Progressive Training Strategy for Embodied Vision-Language Models to Mitigate Spatio-Temporal Hallucinations
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.
arXiv AI
Oct 16
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
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.
arXiv AI
Oct 9
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
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.
arXiv Computer Vision
Oct 1
VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning
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...
arXiv Computer Vision
Sep 22
INTCORT: Training-Free Spatial Reasoning Enhancement for Vision-Language Models via Input Transformations and Confidence Routing
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....
arXiv Computer Vision
Oct 8
Flow-of-Thought: A Framework for Visual Reasoning
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...