ChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded Planning
cs.AI
Submitted: 2026-09-30
Updated: 2026-10-03
Terminology
Sources
- EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning
- SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
- VeriGraph: Scene Graphs for Execution Verifiable Robot Planning
- Hoi! - A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation
- Beyond Flatlands: Unlocking Spatial Intelligence by Decoupling 3D Reasoning from Numerical Regression
- Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces
- VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
- ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
- MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning
- Depth Anything 3: Recovering the Visual Space from Any Views
- SQA3D: Situated Question Answering in 3D Scenes
- RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots
- LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning
- SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
- SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence
- Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models
- Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems