BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender
☆124Nov 13, 2026Updated this week
Alternatives and similar repositories for BVB
Users that are interested in BVB are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2025] A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness☆14Oct 27, 2026Updated 3 weeks ago
- ☆336Oct 20, 2026Updated 3 weeks ago
- 4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes☆216Oct 8, 2026Updated last month
- Code World Model Official Repo☆586Aug 27, 2026Updated 2 months ago
- [CVPR 2025] VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?☆31Oct 27, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [CVPR 2026] Reinforcing Text-Rich Video Reasoning with Visual Rumination☆29Oct 30, 2026Updated 2 weeks ago
- Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning☆454Aug 31, 2026Updated 2 months ago
- Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System☆130Aug 6, 2026Updated 3 months ago
- [Arxiv'25] DINO-Tok: Adapting DINO for Visual Tokenizers☆44Apr 11, 2026Updated 7 months ago
- Official repository for SceneCode, a framework that turns natural language prompts into executable, editable indoor world programs with a…☆64Jun 18, 2026Updated 5 months ago
- [ECCV2026] Visual Spatial Tuning☆217Mar 25, 2026Updated 7 months ago
- A Blender extension for automated, editable, and inter-shot consistent 3D storyboard production.☆38Oct 19, 2026Updated last month
- 3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models☆25Oct 28, 2026Updated 3 weeks ago
- [NeurIPS 2026] Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".☆445Sep 24, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [TPAMI 2026] Ego-R1: Agentic Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning☆172Jun 10, 2026Updated 5 months ago
- BlenderLore: Learning 3D Coding from Internet Tutorial Videos.☆101Oct 14, 2026Updated last month
- [CVPR 2026] LoST: Level of Semantics Tokenization for 3D Shapes☆85Sep 5, 2026Updated 2 months ago
- Open data and scalable training for long-horizon video world models.☆926Nov 7, 2026Updated last week
- [Tech Report] Context Scaling: Scaling Properties of Text Conditioning in Visual Generation☆191Aug 7, 2026Updated 3 months ago
- Programmable World Model: explicit world state, generative rendering.☆213Oct 13, 2026Updated last month
- ☆35Aug 15, 2026Updated 3 months ago
- Official implementation of "Learning to Code the World: Harness Evolution for Compositional 3D Reconstruction".☆31Oct 28, 2026Updated 3 weeks ago
- Cuti Harness: An open-source, plugin-based video world harness☆74Oct 11, 2026Updated last month
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Articraft research dataset. Current development: https://github.com/articraftresearch/Articraft☆22Jul 30, 2026Updated 3 months ago
- [NeurIPS 2026] Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence☆83Oct 15, 2026Updated last month
- [CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations☆614Apr 22, 2026Updated 6 months ago
- WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World☆58Oct 14, 2026Updated last month
- ☆20May 11, 2025Updated last year
- Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction☆231Nov 6, 2026Updated last week
- Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning (Text-to-3D, Image-to-3D, Assembly-3D)☆56Sep 26, 2026Updated last month
- Cambrian-S: Towards Spatial Supersensing in Video☆573Apr 3, 2026Updated 7 months ago
- 🐧 Unify-Agent: An end-to-end unified multimodal agent for faithful, knowledge-grounded image generation.☆95May 2, 2026Updated 6 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆366Oct 27, 2026Updated 3 weeks ago
- A MLLM-based agentic system converts a single room image into executable Blender code for 3D room reconstruction.☆264Oct 21, 2026Updated 3 weeks ago
- This is the official implementation of AlloSpatial and World2Mind toolkit. [AlloSpatial: Agentic Harness Framework for Spatial Reasoning …☆23May 31, 2026Updated 5 months ago
- Official Implementation of PixelBench and Pixel Reconstruction Tuning☆15Updated this week
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆506Apr 16, 2026Updated 7 months ago
- Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond☆338Nov 5, 2026Updated 2 weeks ago
- [NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.☆278Jul 7, 2026Updated 4 months ago
Are these results useful?