FlowBench: Counterfactual Imagination Training for Spatial Intelligence
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/liuyifan22/FlowBench
Terminology
Sources
- GPT-4 Technical Report
- LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
- LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
- Zero-shot World Models Are Developmentally Efficient Learners
- Qwen3-VL Technical Report
- Unifying (Machine) Vision via Counterfactual World Modeling
- IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
- What-If World: A Causal Benchmark for General World Models in Embodied Scenarios
- SAM 3: Segment Anything with Concepts
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Classifier-Free Diffusion Guidance
- ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
- LoRA: Low-Rank Adaptation of Large Language Models
- Taming generative video models for zero-shot optical flow extraction
- World Modeling with Probabilistic Structure Integration
- 3D Scene Understanding Through Local Random Access Sequence Modeling
- Depth Anything 3: Recovering the Visual Space from Any Views
- SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models
- IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning
- Gemma 4 Technical Report
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs