DualTopo: Spatio-Temporal Lane Graph Generation with Dual Latent World Models and Parallel Query Supervision
cs.CV
Submitted: 2025-07-31
Updated: 2026-11-17
Code: https://github.com/YimingYang23/FASTopoWM
Terminology
Sources
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving
- GAIA-1: A Generative World Model for Autonomous Driving
- TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problem
- Graph-based Topology Reasoning for Driving Scenes
- LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
- Enhancing End-to-End Autonomous Driving with Latent World Model
- End-to-End Driving with Online Trajectory Evaluation via BEV World Model
- MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
- MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
- FASIONAD++ : Integrating High-Level Instruction and Information Bottleneck in FAt-Slow fusION Systems for Enhanced Safety in Autonomous Driving with Adaptive Feedback
- Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
- TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning
- Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning
- Towards Human-Centric Autonomous Driving: A Fast-Slow Architecture Integrating Large Language Model Guidance with Reinforcement Learning
- SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
- TopoStreamer: Temporal Lane Segment Topology Reasoning in Autonomous Driving
- BEVWorld: A Multimodal World Simulator for Autonomous Driving via Scene-Level BEV Latents
- Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction
- AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
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