Vision-language models lag human performance on physical dynamics and intent reasoning
cs.CV, cs.AI, cs.LG
Submitted: 2026-01-04
Updated: 2026-11-13
Code: https://github.com/Grady10086/EscherVerse
Terminology
Sources
- GPT-4 Technical Report
- RT-1: Robotics Transformer for Real-World Control at Scale
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- MMBench: Is Your Multi-modal Model an All-around Player?
- OpenAI GPT-5 System Card
- Gemini: A Family of Highly Capable Multimodal Models
- Qwen3 Technical Report
- Qwen Technical Report
- LLaVA-Video: Video Instruction Tuning With Synthetic Data
- LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
- MiniCPM-V: A GPT-4V Level MLLM on Your Phone
- Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts
- gpt-oss-120b & gpt-oss-20b Model Card
- CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
Related papers
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs
- From Formulas to Protocols: A Compositional View of Binary Target Segmentation Metrics
- Traffic Sign Recognition in Autonomous Driving: Dataset, Benchmark, and Field Experiment
- Efficient All-in-One Weather Restoration using Spectral Harmonization