arXiv:2610. 32177v1 Announce Type: new Abstract: Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds.
arXiv:2608. 04575v1 Announce Type: cross Abstract: Reliable physical reasoning from video requires understanding how objects move, interact, and respond to interventions.
arXiv:2604.13993v2 Announce Type: replace-cross Abstract: Physical reasoning over images requires integrating perception, domain knowledge, and multi-step symbolic inference, yet Vision-Language Mode...
arXiv:2606. 03988v1 Announce Type: new Abstract: Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable.
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:2607. 22864v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably.
arXiv:2606. 17539v1 Announce Type: cross Abstract: Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains challenging.
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.
arXiv:2609.34826v2 Announce Type: replace Abstract: Humans often solve spatial problems by mentally simulating visual transformations. In contrast, conventional vision-language models (VLMs) reason p...
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.
arXiv:2607. 08375v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving.
arXiv:2606. 15753v1 Announce Type: new Abstract: Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding throughout multi-step reasoning.
The paper introduces a framework that combines world models, which generate concrete visual rollouts of possible futures, with multimodal large language models (MLLMs) that perform abstract reasoning. It proposes a controlled concrete reasoning approach and a new training method called Privileged‑Future On‑Policy Self‑Distillation (PF‑OPSD), which uses ground‑truth future videos as privileged teacher context during training while the student model never sees true futures at test time. Experiments on two human‑verified benchmarks, VRQABench and OpenWorldQA, show that PF‑OPSD improves performance by about 10–11% over baselines and enhances robustness to noisy or conflicting rollouts.