Pith. sign in

REVIEW 21 cited by

Improved Visual-Spatial Reasoning via R1-Zero-Like Training

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.00883 v2 pith:QBUSGPPT submitted 2025-04-01 cs.CV cs.AI

Improved Visual-Spatial Reasoning via R1-Zero-Like Training

classification cs.CV cs.AI
keywords reasoningvisual-spatialmodelmllmstrainingcapacitiesdatasetfine-tuned
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Increasing attention has been placed on improving the reasoning capacities of multi-modal large language models (MLLMs). As the cornerstone for AI agents that function in the physical realm, video-based visual-spatial intelligence (VSI) emerges as one of the most pivotal reasoning capabilities of MLLMs. This work conducts a first, in-depth study on improving the visual-spatial reasoning of MLLMs via R1-Zero-like training. Technically, we first identify that the visual-spatial reasoning capacities of small- to medium-sized Qwen2-VL models cannot be activated via Chain of Thought (CoT) prompts. We then incorporate GRPO training for improved visual-spatial reasoning, using the carefully curated VSI-100k dataset, following DeepSeek-R1-Zero. During the investigation, we identify the necessity to keep the KL penalty (even with a small value) in GRPO. With just 120 GPU hours, our vsGRPO-2B model, fine-tuned from Qwen2-VL-2B, can outperform the base model by 12.1% and surpass GPT-4o. Moreover, our vsGRPO-7B model, fine-tuned from Qwen2-VL-7B, achieves performance comparable to that of the best open-source model LLaVA-NeXT-Video-72B. Additionally, we compare vsGRPO to supervised fine-tuning and direct preference optimization baselines and observe strong performance superiority. The code and dataset will be available soon.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 21 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?

    cs.CV 2026-05 accept novelty 8.0

    Introduces the TVR active viewpoint-matching task and TVRBench indoor simulation benchmark, where foundation models start at low single-digit success rates but reach 51.4% after visual-action SFT and multi-turn GRPO p...

  2. CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 7.0

    Proposes Spatial Narrative Score (SNS) evaluation for VLMs' camera motion understanding and introduces CaMo model achieving consistent performance on SNS and direct QA.

  3. Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning

    cs.CV 2026-04 unverdicted novelty 7.0

    A training-free Visual Chain-of-Thought framework reconstructs high-fidelity 3D meshes from single images and iteratively synthesizes optimal novel views to enhance MLLM spatial comprehension on benchmarks like 3DSRBench.

  4. Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

    cs.CV 2025-05 conditional novelty 7.0

    Video-Holmes benchmark shows top MLLMs achieve at most 45% accuracy on tasks needing integration of multiple clues from suspense films, unlike existing perception-focused tests.

  5. Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding

    cs.CV 2026-07 conditional novelty 6.0

    ViPS fuses five complementary visual priors into an MLLM via lightweight distillation proxies and query-conditioned dynamic weighting, reporting state-of-the-art results on VSI-Bench and ScanNet-series benchmarks.

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

    cs.CV 2026-06 unverdicted novelty 6.0

    ReRe boosts open-source MLLMs on spatial reasoning benchmarks VSI-Bench and STI-Bench to rival proprietary SOTA by using a two-phase Reason then Re-reason process with Geometry-to-Video novel view synthesis.

  7. SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models

    cs.CV 2026-04 unverdicted novelty 6.0

    SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.

  8. Robotic Manipulation is Vision-to-Geometry Mapping ($f(v) \rightarrow G$): Vision-Geometry Backbones over Language and Video Models

    cs.RO 2026-04 unverdicted novelty 6.0

    Vision-geometry backbones using pretrained 3D world models outperform vision-language and video models for robotic manipulation by enabling direct mapping from visual input to geometric actions.

  9. EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs

    cs.CV 2026-04 unverdicted novelty 6.0

    EgoMind activates spatial cognition in MLLMs via linguistic Role-Play Caption and Progressive Spatial Analysis, reaching competitive results on VSI-Bench, SPAR-Bench, SITE-Bench and SPBench with only 5K SFT and 20K RL...

  10. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

    cs.CV 2026-03 conditional novelty 6.0

    Fusing intermediate-layer, mid-noise features of a video diffusion model with semantic tokens via learned gating improves MLLMs on 3D scene understanding benchmarks.

  11. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

    cs.CV 2026-03 unverdicted novelty 6.0

    VEGA-3D extracts intermediate spatiotemporal features from a pretrained video diffusion model and fuses them into MLLMs to improve geometric and embodied reasoning without explicit 3D supervision.

  12. Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models

    cs.CV 2026-03 unverdicted novelty 6.0

    Attention dispersion during extended reasoning impairs MLLM perception on images, and a training-free VRGA framework mitigates it by selecting and reweighting visual attention heads using an entropy-focus criterion.

  13. From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models

    cs.CV 2026-02 conditional novelty 6.0

    A 3B multimodal LLM trained with patch-level cross-view alignment plus explicit viewpoint-action reasoning outperforms much larger models on two multi-image spatial reasoning benchmarks.

  14. VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs

    cs.CV 2025-11 conditional novelty 6.0

    A 1,680-question video benchmark shows leading multimodal models lag humans by ~15 points on visual knowledge, and a See-Think-Answer RL-trained model narrows the gap.

  15. EgoExo-Con: Exploring View-Invariant Video Temporal Understanding

    cs.CV 2025-10 conditional novelty 6.0

    Most Video-LLMs answer temporal questions far less consistently when the same event is shown from ego and exo views, and a GRPO variant with a reasoning-similarity reward partially closes the gap.

  16. EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs

    cs.CV 2026-04 unverdicted novelty 5.0

    EgoMind uses Role-Play Caption and Progressive Spatial Analysis to give MLLMs competitive multi-frame spatial reasoning without 3D priors, using only 5K SFT and 20K RL samples.

  17. Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

    cs.CV 2025-03 unverdicted novelty 5.0

    Time-R1 applies RL with verifiable rewards to post-train LVLMs for temporal video grounding, reaching state-of-the-art results on multiple datasets using only 2.5K samples while also improving general video capabilities.

  18. Watch, Remember, Reason: Human-View Video Understanding with MLLMs

    cs.CV 2026-06 unverdicted novelty 4.0

    This is a survey that frames video MLLM research via a human-view formulation of perceptual representations, memory states, reasoning traces, and predictions, then reviews methods, datasets, benchmarks, and open problems.

  19. Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning

    cs.CV 2025-07 unverdicted novelty 4.0

    A pipeline of chain-of-thought data synthesis, LoRA-based supervised fine-tuning, rejection sampling, and rule-based reinforcement learning raises multi-image grounding accuracy by 9.04% on MIG-Bench and 4.41% on aver...

  20. SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video

    cs.CV 2026-07 unverdicted novelty 3.0

    SpaceEra++ adds ScenePick frame sampling and SpaceAlign pairwise constraints to the prior SpaceEra system, claiming consistent benchmark gains for 3D video spatial reasoning.

  21. Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle

    cs.CL 2025-09 conditional novelty 3.0

    A survey that maps reinforcement learning methods, datasets, benchmarks, and open-source tools across the full training lifecycle of large language models, focusing on verifiable-reward reasoning.