SpaceR: Reinforcing MLLMs in Video Spatial Reasoning

• URL: http://arxiv.org/abs/2504.01805v2
• Date: Wed, 21 May 2025 09:38:44 GMT
• Title: SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
• Authors: Kun Ouyang, Yuanxin Liu, Haoning Wu, Yi Liu, Hao Zhou, Jie Zhou, Fandong Meng, Xu Sun,
• Abstract summary: Video spatial reasoning poses a significant challenge for existing Multimodal Large Language Models (MLLMs)<n>This limitation stems primarily from 1) the absence of high-quality datasets for this task, and 2) the lack of effective training strategies to develop spatial reasoning capabilities.<n>Motivated by the success of Reinforcement Learning with Verifiable Reward (RLVR) in unlocking spatial reasoning abilities, this aims to improve MLLMs in video spatial reasoning through the RLVR paradigm.
• Score: 70.7401015322983
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video spatial reasoning, which involves inferring the underlying spatial structure from observed video frames, poses a significant challenge for existing Multimodal Large Language Models (MLLMs). This limitation stems primarily from 1) the absence of high-quality datasets for this task, and 2) the lack of effective training strategies to develop spatial reasoning capabilities. Motivated by the success of Reinforcement Learning with Verifiable Reward (RLVR) in unlocking LLM reasoning abilities, this work aims to improve MLLMs in video spatial reasoning through the RLVR paradigm. To this end, we introduce the $\textbf{SpaceR}$ framework. First, we present $\textbf{SpaceR-151k}$, a dataset with 91k questions spanning diverse spatial reasoning scenarios with verifiable answers, and 60k samples for maintaining general multimodal understanding. Second, we propose $\textbf{Spatially-Guided RLVR (SG-RLVR)}$, a novel reinforcement learning approach that extends Group Relative Policy Optimization (GRPO) with a novel map imagination mechanism, which encourages the model to infer spatial layouts in the thinking process, thereby facilitating more effective spatial reasoning. Extensive experiments demonstrate that SpaceR achieves state-of-the-art performance on spatial reasoning benchmarks (e.g., VSI-Bench, STI-Bench, and SPAR-Bench), while maintaining competitive results on video understanding benchmarks (e.g., Video-MME, TempCompass, and LongVideoBench). Remarkably, SpaceR surpasses the advanced GPT-4o by 11.6\% accuracy on VSI-Bench and is on par with the leading proprietary model Gemini-2.0-Flash, highlighting the effectiveness of our SpaceR-151k dataset and SG-RLVR in reinforcing spatial reasoning ability of MLLMs. Code, model, and dataset are available at https://github.com/OuyangKun10/SpaceR.

Related papers

• RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization [86.30192066451256]
  We propose RL-PLUS, a novel hybrid-policy optimization approach for Large Language Models (LLMs)<n> RL-PLUS synergizes internal exploitation with external data to achieve stronger reasoning capabilities and surpass the boundaries of base models.<n>We provide both theoretical analysis and extensive experiments to demonstrate the superiority and generalizability of our approach.
  arXiv  Detail & Related papers  (2025-07-31T23:55:29Z)
• Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency [56.475612147721264]
  We propose a dual-reward formulation that supervises both semantic and temporal reasoning through discrete and continuous reward signals.<n>We evaluate our approach across eight representative video understanding tasks, including VideoQA, Temporal Video Grounding, and Grounded VideoQA.<n>Results underscore the importance of reward design and data selection in advancing reasoning-centric video understanding with MLLMs.
  arXiv  Detail & Related papers  (2025-06-02T17:28:26Z)
• SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization [57.484274282231226]
  We propose SVQA-R1, the first framework to extend R1-style training to spatial VQA.<n>In particular, we introduce Spatial-GRPO, a novel group-wise RL strategy that constructs view-consistent rewards by perturbing spatial relations between objects.<n>Our model, SVQA-R1, not only dramatically improved accuracy on spatial VQA benchmarks but also exhibits interpretable reasoning paths even without using supervised fine-tuning data.
  arXiv  Detail & Related papers  (2025-06-02T06:58:43Z)
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence [13.168559963356952]
  We present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations.<n>Our key insight is to unleash the strong structure prior to the feed-forward visual geometry foundation model.<n>A connector then integrates both features into unified visual tokens for enhanced spatial understanding.
  arXiv  Detail & Related papers  (2025-05-29T17:59:04Z)
• STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs [49.41782982417187]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, yet they lag significantly behind humans in spatial reasoning.<n>We investigate this gap through Transformation-Driven Visual Reasoning (TVR), a challenging task requiring identification of object transformations across images under varying viewpoints.<n>We propose STAR-R1, a novel framework that integrates a single-stage RL paradigm with a fine-grained reward mechanism tailored for TVR.
  arXiv  Detail & Related papers  (2025-05-21T17:57:38Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning [29.053899071144976]
  We propose OThink-MR1, an advanced MLLM equipped with profound comprehension and reasoning capabilities across multimodal tasks.<n>Specifically, we introduce Group Relative Policy Optimization with a dynamic Kullback-Leibler strategy.<n> GRPO-D achieves a relative improvement of more than 5.72% over SFT and more than 13.59% over GRPO in same-task evaluation.
  arXiv  Detail & Related papers  (2025-03-20T12:22:18Z)
• SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability [58.46310813774538]
  Large language models (LMLMs) have made remarkable progress in either temporal or spatial localization.<n>However they struggle to perform-temporal video grounding.<n>This limitation stems from two major challenges.<n>We introduce SpaceLM, a MLLMVL endowed with temporal-temporal video grounding.
  arXiv  Detail & Related papers  (2025-03-18T07:40:36Z)
• Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space [44.42918139949761]
  We propose a novel benchmark, Open3DVQA, to comprehensively evaluate the spatial reasoning capacities of state-of-the-art (SOTA) foundation models in open 3D space.<n>Open3DVQA consists of 9k VQA samples, collected using an efficient semi-automated tool in a high-fidelity urban simulator.
  arXiv  Detail & Related papers  (2025-03-14T05:35:38Z)
• Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models [24.45348222168512]
  We propose the reasoning MLLM, Vision-R1, to improve multimodal reasoning capability.<n>Our model achieves an average improvement of $sim$6% across various multimodal math reasoning benchmarks.<n>Vision-R1-7B achieves a 73.5% accuracy on the widely used MathVista benchmark, which is only 0.4% lower than the leading reasoning model, OpenAI O1.
  arXiv  Detail & Related papers  (2025-03-09T20:06:45Z)
• RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization [53.63439735067081]
  Large language models (LLMs) have achieved impressive performance but face high computational costs and latency.<n>Retrieval-augmented generation (RAG) helps by integrating external knowledge, but imperfect retrieval can introduce distracting noise that misleads SLMs.<n>We propose RoseRAG, a robust RAG framework for SLMs via Margin-aware Preference Optimization.
  arXiv  Detail & Related papers  (2025-02-16T04:56:53Z)
• RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception [20.01853641155509]
  Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-enabled autonomous systems.<n>We propose a new generalizable framework to improve VLM fine-tuning by integrating it with a reinforcement learning (RL) agent.
  arXiv  Detail & Related papers  (2025-01-31T04:30:42Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization [65.64108848398696]
  We introduce a preference optimization process to enhance the multimodal reasoning capabilities of MLLMs. We develop a simple yet effective method, termed Mixed Preference Optimization (MPO), which boosts multimodal CoT performance. Our model, InternVL2-8B-MPO, achieves an accuracy of 67.0 on MathVista, outperforming InternVL2-8B by 8.7 points and achieving performance comparable to the 10x larger InternVL2-76B.
  arXiv  Detail & Related papers  (2024-11-15T18:59:27Z)
• DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution [114.61347672265076]
  Development of MLLMs for real-world robots is challenging due to the typically limited computation and memory capacities available on robotic platforms. We propose a Dynamic Early-Exit Framework for Robotic Vision-Language-Action Model (DeeR) that automatically adjusts the size of the activated MLLM. DeeR demonstrates significant reductions in computational costs of LLM by 5.2-6.5x and GPU memory of LLM by 2-6x without compromising performance.
  arXiv  Detail & Related papers  (2024-11-04T18:26:08Z)
• SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains [45.349645606978434]
  Retrieval-augmented generation (RAG) enhances the question-answering abilities of large language models (LLMs) We propose SimRAG, a self-training approach that equips the LLM with joint capabilities of question answering and question generation for domain adaptation. Experiments on 11 datasets, spanning two backbone sizes and three domains, demonstrate that SimRAG outperforms baselines by 1.2%--8.6%.
  arXiv  Detail & Related papers  (2024-10-23T15:24:16Z)
• RAVEN: Multitask Retrieval Augmented Vision-Language Learning [5.1583788731239455]
  The scaling of large language models to encode all the world's knowledge is unsustainable and has exacerbated resource barriers. Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to vision-language models (VLMs) is under explored. This paper introduces RAVEN, a retrieval augmented VLM framework that enhances base VLMs through efficient, task specific fine-tuning.
  arXiv  Detail & Related papers  (2024-06-27T13:08:35Z)
• Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models [56.256069117502385]
  Chain of Thought (CoT) approaches can be used to enhance the capability of Large Language Models (LLMs) on complex reasoning tasks. However, the selection of optimal CoT demonstration examples in multi-modal reasoning remains less explored. We introduce a novel approach that addresses this challenge by using retrieval mechanisms to automatically select demonstration examples.
  arXiv  Detail & Related papers  (2023-12-04T08:07:21Z)

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.