Alternatives and similar repositories for STI-Bench

Users that are interested in STI-Bench are comparing it to the libraries listed below

• OuyangKun10 / SpaceR
  SpaceR: The first MLLM empowered by SG-RLVR for video spatial reasoning
  ☆99Updated 5 months ago
• zhijie-group / R1-Zero-VSI
  ☆42Updated 6 months ago
• mll-lab-nu / MindCube
  ☆108Updated last month
• AntResearchNLP / ViLaSR
  Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
  ☆84Updated 4 months ago
• LogosRoboticsGroup / SPAR
  From Flatland to Space (SPAR). Accepted to NeurIPS 2025 Datasets & Benchmarks. A large-scale dataset & benchmark for 3D spatial perceptio…
  ☆67Updated 2 months ago
• qizekun / OmniSpatial
  OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models
  ☆76Updated 2 months ago
• Haochen-Wang409 / ross3d
  [ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness
  ☆63Updated 4 months ago
• LaVi-Lab / Video-3D-LLM
  [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.
  ☆187Updated 6 months ago
• Visual-AI / 3DRS
  [NeurIPS 2025] 3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
  ☆134Updated last week
• PzySeere / MetaSpatial
  MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …
  ☆196Updated 7 months ago
• VinceOuti / Open3DVQA
  ☆30Updated last month
• ZJU-REAL / ViewSpatial-Bench
  ViewSpatial-Bench:Evaluating Multi-perspective Spatial Localization in Vision-Language Models
  ☆66Updated 6 months ago
• Yangr116 / VST
  Visual Spatial Tuning
  ☆154Updated 2 weeks ago
• hmxiong / StreamChat
  Official repo for "Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge" ICLR2025
  ☆91Updated 9 months ago
• haoningwu3639 / SpatialScore
  SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding
  ☆59Updated 5 months ago
• Gabesarch / grounded-rl
  ☆111Updated 4 months ago
• ZCMax / ScanReason
  [ECCV 2024] Empowering 3D Visual Grounding with Reasoning Capabilities
  ☆80Updated last year
• AnjieCheng / SpatialRGPT
  [NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"
  ☆296Updated last year
• jiayuww / SpatialEval
  [NeurIPS'24] SpatialEval: a benchmark to evaluate spatial reasoning abilities of MLLMs and LLMs
  ☆57Updated 10 months ago
• 3DLLM-Mem / 3DLLM-Mem
  ☆19Updated 6 months ago
• cambrian-mllm / cambrian-s
  Cambrian-S: Towards Spatial Supersensing in Video
  ☆429Updated this week
• Haochen-Wang409 / ross
  [ICLR'25] Reconstructive Visual Instruction Tuning
  ☆132Updated 8 months ago
• TencentARC / Video-Holmes
  Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
  ☆81Updated 5 months ago
• diankun-wu / Spatial-MLLM
  Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
  ☆408Updated 2 weeks ago
• AdaCheng / EgoThink
  [CVPR'24 Highlight] The official code and data for paper "EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Lan…
  ☆63Updated 8 months ago
• penghao-wu / visual_jigsaw
  ☆65Updated last month
• zhang9302002 / ThinkingWithVideos
  The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"
  ☆70Updated 2 months ago
• sming256 / BOLT
  [CVPR2025] BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
  ☆35Updated 8 months ago
• yu-rp / VisualPerceptionToken
  ☆133Updated 8 months ago
• egolife-ai / Ego-R1
  Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
  ☆133Updated 4 months ago