| ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge | May 28, 2025 | Imitation LearningMath | CodeCode Available | 1 |
| VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models | May 27, 2025 | Spatial ReasoningVisual Tracking | —Unverified | 0 |
| Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models | May 27, 2025 | DiagnosticSpatial Reasoning | —Unverified | 0 |
| MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents | May 26, 2025 | BenchmarkingMinecraft | CodeCode Available | 1 |
| VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction | May 26, 2025 | 3D ReconstructionSpatial Reasoning | CodeCode Available | 3 |
| MEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Models | May 26, 2025 | Spatial Reasoning | —Unverified | 0 |
| Agentic 3D Scene Generation with Spatially Contextualized VLMs | May 26, 2025 | Multimodal ReasoningScene Generation | —Unverified | 0 |
| ViTaPEs: Visuotactile Position Encodings for Cross-Modal Alignment in Multimodal Transformers | May 26, 2025 | cross-modal alignmentPosition | —Unverified | 0 |
| Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps | May 24, 2025 | Scene UnderstandingSpatial Reasoning | —Unverified | 0 |
| U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding | May 23, 2025 | BenchmarkingSpatial Reasoning | —Unverified | 0 |
