AIAny
Icon for item

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

Teaches vision-language models to predict and integrate physical-world state transitions from interaction trajectories (observation → action → next observation). Introduces a three-level curriculum and the LSI-108K dataset, and applies supervised fine-tuning plus on-policy distillation to improve local transition modeling and long-horizon spatial integration.

Introduction

Humans build spatial understanding by observing changes caused by actions and integrating those changes over time. Many VLM training setups focus on static spatial questions and therefore provide weak supervision for state transitions; this paper flips that perspective and trains models directly on interaction trajectories that pair a preceding observation, an action, and the resulting observation, creating explicit supervision for local transitions and their composition over longer horizons.

Key Findings
  • Interaction-centric curriculum: Organizes learning into three levels — passive world-state transitions (L1), active self-state transitions (L2), and long-horizon interaction trajectories (L3) — so the model first masters local transitions before learning to integrate them.
  • LSI-108K dataset: A curated mix of simulated and real interaction trajectories aligned to the three curriculum levels, enabling supervised signals that static QA datasets lack.
  • Two-stage training: Applies Supervised Fine-Tuning (SFT) on L1/L2 to learn local transitions, then On-Policy Distillation (OPD) where a teacher with segment-level transition descriptions guides a student’s on-policy chain-of-thought, improving sequence integration over long trajectories.
  • Empirical gains: Consistent improvements across multiple VLMs and spatial benchmarks, with large per-benchmark uplifts and cross-benchmark generalization, showing the approach helps both local transition accuracy and long-horizon reasoning.
Who it's for and tradeoffs

Great fit if you research multimodal/embodied reasoning or develop VLMs for robotics, navigation, or interactive perception — especially when temporal state updates matter. Look elsewhere if your task is purely static visual QA or you cannot supply interaction-like supervision; OPD requires privileged segment annotations for the teacher and longer training pipelines compared to standard SFT.

Where it fits

Positions itself between static spatial QA datasets and full reinforcement-learning pipelines: it uses supervised signals from interaction data (not reward-driven exploration) to teach state transitions, so it is more data-efficient than RL but more temporally focused than static VQA training.

Short method sketch

The pipeline constructs local transition tasks from trajectories and trains via SFT; for long trajectories, a teacher branch produces segment-level transition descriptions that supervise a student producing on-policy chain-of-thoughts, enabling the student to learn to compose transitions across segments.

Information

  • Websitearxiv.org
  • OrganizationsZhejiang University, SAP
  • AuthorsKaixiang Yao, Xu Wang, Miao Pan, Hu Xiyue, Weishi Wang, Daniel Dahlmeier, Jintao Chen, Yongliang Shen, Xuhong Zhang, Wenqi Zhang
  • Published date2026/09/19

More Items

Introduces a rubric-based approach for video reward modeling that generates explicit, query-adaptive evaluation criteria before scoring to reduce scalar drift; proposes RGPO, a two-stage training (seed warm-up + joint optimization) that achieves strong pointwise and pairwise evaluation with high data efficiency.

Evaluates whether generative world models maintain consistent, controllable, and physically plausible simulated environments under exploration, interaction, and intervention. Introduces a six-level W1–W6 capability taxonomy across three tracks (video, spatial, embodied) with human A/B Arena and automated metrics to measure behavioral correctness.

An all-in-one multilingual scene text recognition approach that pairs a shared visual encoder with a script-aware Mixture-of-Experts (ScriptMoE) decoder to route each image to top-2 script experts. Introduces TextMuSS-10M, a synthetic dataset covering 10 scripts and 229 languages, and reports state-of-the-art accuracy and large end-to-end OCR F1 gains while remaining parameter-efficient.