We introduce Reasoning via Video, a new paradigm that uses maze-solving video generation to probe multimodal reasoning; our VR-Bench shows that fine-tuned video models consistently outperform strong VLMs on long-horizon spatial planning tasks.
☆66Feb 4, 2026Updated 6 months ago
Alternatives and similar repositories for VR-Bench
Users that are interested in VR-Bench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Scaling Agentic Environments Automatically.☆67Mar 26, 2026Updated 4 months ago
- A Python runtime for multi-entity AI collaboration — agents, humans, and tools on a shared protocol layer.☆52Jun 18, 2026Updated last month
- An automatic prompt iteration and optimization generator suitable for any scenario☆16Jan 31, 2025Updated last year
- This is a collection of recent papers on reasoning in video generation models.☆164Jul 30, 2026Updated last week
- A lightweight and highly extensible Agent framework☆26Jun 26, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆231Apr 13, 2026Updated 3 months ago
- Self Supervised Prompt Optimization.☆75Oct 19, 2025Updated 9 months ago
- [EMNLP 2024 Findings] Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information☆13Oct 1, 2024Updated last year
- Official repository for "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models", https://arxiv.org/abs/2601.1983…☆100Mar 9, 2026Updated 5 months ago
- Github repository for "Internalizing World Models via Self-Play Finetuning for Agentic RL"☆36Nov 1, 2025Updated 9 months ago
- [ECCV 2026] An official implementation of "EndoCoT". Scaling endogenous Chain-of-Thought (CoT) reasoning in diffusion models for complex …☆44Jun 26, 2026Updated last month
- The code and weight for LoVA. LoVA is a novel model for Long-form Video-to-Audio generation. Based on the Diffusion Transformer (DiT) arc…☆16Feb 27, 2025Updated last year
- Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934☆271Oct 28, 2025Updated 9 months ago
- ☆36Feb 18, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [NeurIPS 2025 Spotlight] EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling☆19Oct 18, 2025Updated 9 months ago
- Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.☆562Apr 21, 2026Updated 3 months ago
- ☆16Jun 19, 2026Updated last month
- The code of the paper "DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects"☆19May 2, 2025Updated last year
- ☆17Jun 10, 2025Updated last year
- We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that S…☆316Jun 21, 2026Updated last month
- 🔥An open-source survey of the latest video reasoning tasks, paradigms, and benchmarks.☆190Jun 14, 2026Updated last month
- 「ECCV 2024」 PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation☆21Jul 2, 2024Updated 2 years ago
- ☆25Jul 10, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Forecasting scientific progress with AI☆30May 31, 2026Updated 2 months ago
- Code for paper "ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation"☆28Jul 17, 2026Updated 3 weeks ago
- Code for "Predicting What Matters: Robust Generalist Robot Policy Learning via Future Semantic Mask".☆36Jun 8, 2026Updated 2 months ago
- [ICML 2026] Stable Velocity: A Variance Perspective on Flow Matching☆30Feb 19, 2026Updated 5 months ago
- Are Video Models Ready as Zero-shot Reasoners?☆87Nov 24, 2025Updated 8 months ago
- 🌟 手把手教你在论文中插入代码链接☆25Aug 2, 2025Updated last year
- ☆15Jul 11, 2025Updated last year
- A multi-agent framework to help with your homework.☆11Mar 1, 2025Updated last year
- ☆15Mar 4, 2022Updated 4 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Official Repository of VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents☆114May 3, 2026Updated 3 months ago
- ☆14Jun 20, 2023Updated 3 years ago
- Official implementation of V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising (ECCV 2026)☆27Jun 29, 2026Updated last month
- ☆13Feb 25, 2025Updated last year
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆208Jan 30, 2026Updated 6 months ago
- [ICLR 2026] VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models☆21Feb 18, 2026Updated 5 months ago
- Automating Sub-Agent Creation for Agentic Orchestration☆156May 25, 2026Updated 2 months ago