Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning

• URL: http://arxiv.org/abs/2606.11683v1
• Date: Wed, 10 Jun 2026 05:52:14 GMT
• Title: Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
• Abstract summary: We argue that spatial reasoning should be revisitable.<n>We propose ReRe, a training-free, inferencetime framework with two phases.<n>We show that ReRe substantially boosts open-source MLLMs to rival proprietary state-of-the-art performance.
• Score: 37.09676301107883
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory. Existing methods rely on single-turn inference, forcing models to resolve geometric ambiguity through semantic priors rather than verifiable evidence. We argue that spatial reasoning should be revisitable: conclusions formed under limited evidence should remain open to revision when complementary viewpoints become available. Building on this insight, we propose Reason, then Re-reason (ReRe), a training-free, inference-time framework with two phases: in the Reason Phase, an MLLM forms a spatial hypothesis from the original video; in the Re-reason Phase, it verifies or revises the hypothesis by observing a synthesized novel-view video. To enable effective cross-view revisiting, we design a Geometry-to-Video pipeline that renders strategically complementary novel views from predicted 3D geometry. These views feature an elevated, oblique perspective with scene-spanning coverage, while preserving the MLLM's native video interface without architectural modifications. Extensive evaluations on VSI-Bench and STI-Bench demonstrate that ReRe substantially boosts open-source MLLMs to rival proprietary state-of-the-art performance. Project page: https://zhenjiemao.github.io/ReRe/

Related papers

• PRISM: Predictive Recomposition via Semantic Latent Decomposition for View-invariant Video Representation Learning [57.66429303062003]
  Cross-view video representation learning aims to capture viewpoint-invariant action semantics.<n>We propose PRISM, that decomposes video into view-invariant and view-variant latents and recompose them under language supervision.<n> PRISM achieves state-of-the-art results on EgoExo4D, EgoExoLearn, AE2, even surpassing in-domain models under zero-shot setting.
  arXiv  Detail & Related papers  (2026-08-31T07:43:02Z)
• ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning [22.393717134409012]
  ConsiSpace is a geometry-consistency-aware framework for geometry-sensitive video spatial reasoning.<n>We build a geometry-consistent memory (GCM) including implicit evidence tokens and explicit geometric cues.<n>We utilize unified self-supervised reinforcement learning (UCSSRL) to improve cross-view stability.
  arXiv  Detail & Related papers  (2026-07-20T06:40:45Z)
• Evidence-Backed Video Question Answering [90.93225758130426]
  Existing explainability efforts rely on textual rationales or sparse bounding boxes.<n>We propose Evidence-Backed Video Question Answering (E-VQA)<n>To support this, we introduce ST-Evidence, the first human-verified benchmark for both discriminative and generative pixel-level grounding.
  arXiv  Detail & Related papers  (2026-07-13T17:49:10Z)
• SER: Learning to Ground Video Reasoning with Semantic Evidence Rewards [8.705689021755221]
  We propose Semantic Evidence Reward (SER) to reform RL as a constrained task.<n>Instead of computing pixel-level annotations, SER uses a referee enhancing a VLM to evaluate model-generated evidence claims.<n>On the VLM benchmark, SER achieves 49.6%, improving by 3.0 points over the strong evidence-ground baseline.
  arXiv  Detail & Related papers  (2026-06-23T15:50:33Z)
• STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models [81.32710031596591]
  Video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames.<n>Existing methods built on vision-language models (LVLMs) often address this challenge by externalizing reasoning through chain-of-thought (CoT)<n>We propose STORMS, a two-stage framework that teaches LVLMs to reason through bounded continuous latent trajectories instead of explicit textual CoT.
  arXiv  Detail & Related papers  (2026-05-25T16:33:00Z)
• Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models [54.76242207842981]
  We identify video syphancy, a failure mode in which Vid-LLMs retract correct, visually grounded judgments under negation-based gaslighting.<n>Rather than merely changing their answers, the models often fabricate unsupported temporal or spatial explanations to justify incorrect revisions.<n>We introduce GasVideo-1000, a curated benchmark designed to probe videotemporal sycophancy with clear visual grounding and temporal reasoning requirements.
  arXiv  Detail & Related papers  (2026-04-20T06:35:26Z)
• Make Geometry Matter for Spatial Reasoning [62.61667611352403]
  Vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes and dynamic videos remains limited.<n>Recent advances try to handle this limitation by injecting geometry tokens from pretrained 3D foundation models into VLMs.<n>We propose GeoSR, a framework designed to make geometry matter by encouraging VLMs to actively reason with geometry tokens.
  arXiv  Detail & Related papers  (2026-03-27T17:45:12Z)
• Process-of-Thought Reasoning for Videos [33.74677144833003]
  Process-of-Thought (PoT) Reasoning for Videos is a framework that makes the reasoning process explicit by structuring video inference into a sequence of lightweight, verifiable steps.<n>PoT interleaves (i) temporal evidence selection, (ii) step-wise state updates, and (iii) constrained answer synthesis, enabling the model to progressively refine hypotheses while maintaining traceability to video evidence.
  arXiv  Detail & Related papers  (2026-02-07T20:25:46Z)
• CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning [40.654048754955404]
  CamReasoner is a framework that reformulates camera movement understanding as a structured inference process.<n>We are the first to employ RL for logical alignment in this domain, ensuring motion inferences are grounded in physical geometry.
  arXiv  Detail & Related papers  (2026-01-30T04:45:43Z)
• Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective [17.592210658831902]
  spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments.<n>Current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency for spatial reasoning in multi-view settings.<n>We present ReMindView-Bench, a cognitively grounded benchmark for evaluating how VLMs construct, align and maintain spatial mental models across complementary viewpoints.
  arXiv  Detail & Related papers  (2025-12-02T02:21:29Z)
• Video Spatial Reasoning with Object-Centric 3D Rollout [58.12446467377404]
  We propose Object-Centric 3D Rollout (OCR) to enable robust video spatial reasoning.<n>OCR introduces structured perturbations to the 3D geometry of selected objects during training.<n>OCR compels the model to reason holistically across the entire scene.
  arXiv  Detail & Related papers  (2025-11-17T09:53:41Z)
• Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark [124.00111584020834]
  We conduct an empirical study to investigate whether video models are ready to serve as zero-shot reasoners.<n>We focus on the leading and popular Veo-3.<n>We evaluate its reasoning behavior across 12 dimensions, including spatial, geometric, physical, temporal, and embodied logic.
  arXiv  Detail & Related papers  (2025-10-30T17:59:55Z)
• RIGID: Recurrent GAN Inversion and Editing of Real Face Videos [73.97520691413006]
  GAN inversion is indispensable for applying the powerful editability of GAN to real images. Existing methods invert video frames individually often leading to undesired inconsistent results over time. We propose a unified recurrent framework, named textbfRecurrent vtextbfIdeo textbfGAN textbfInversion and etextbfDiting (RIGID) Our framework learns the inherent coherence between input frames in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-08-11T12:17:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.