Tangkexian / LEGO-PuzzlesLinks
Benchmarking Multi-Step Spatial Reasoning in MLLMs with LEGO-based VQA & generation tasks.
☆34Updated 7 months ago
Alternatives and similar repositories for LEGO-Puzzles
Users that are interested in LEGO-Puzzles are comparing it to the libraries listed below
Sorting:
- This is a collection of recent papers on reasoning in video generation models.☆95Updated 3 weeks ago
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆148Updated last year
- TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation☆235Updated 5 months ago
- A framework for unified personalized model, achieving mutual enhancement between personalized understanding and generation. Demonstrating…☆128Updated last month
- Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unifie…☆351Updated 3 weeks ago
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆238Updated 5 months ago
- [CVPR 2025] OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?☆116Updated 6 months ago
- The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"☆79Updated 3 months ago
- TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs☆97Updated this week
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆179Updated 2 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".☆83Updated 6 months ago
- Incentivizing "Thinking with Long Videos" via Native Tool Calling☆183Updated this week
- Official repository of "GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"☆305Updated 4 months ago
- 📖 This is a repository for organizing papers, codes, and other resources related to unified multimodal models.☆347Updated 3 weeks ago
- Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning☆232Updated last week
- [NIPS 2025 DB Oral] Official Repository of paper: Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing☆139Updated last month
- 🔥CVPR 2025 Multimodal Large Language Models Paper List☆154Updated 10 months ago
- [NIPS2025] VideoChat-R1 & R1.5: Enhancing Spatio-Temporal Perception and Reasoning via Reinforcement Fine-Tuning☆255Updated 3 months ago
- UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation☆120Updated 3 weeks ago
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆117Updated 2 months ago
- Official codebase for the paper Latent Visual Reasoning☆98Updated 3 months ago
- Doodling our way to AGI ✏️ 🖼️ 🧠☆120Updated 8 months ago
- [CVPR 2025] VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?☆29Updated 8 months ago
- A python script for downloading huggingface datasets and models.☆20Updated 9 months ago
- (ICLR 2026)Official repository of 'ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing’☆58Updated this week
- ☆49Updated last week
- Offline implementation of UniREditBench: A Unified Reasoning-based Image Editing Benchmark.☆52Updated 3 weeks ago
- [ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark☆138Updated 7 months ago
- Official code for MotionBench (CVPR 2025)☆63Updated 10 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆86Updated 6 months ago