Research map / Label-efficient and robust learning / Recognition and long-tail
MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving
Zhijing Cheng, Xuancheng Zhang, Donglin Di, Lei Fan, Baorui Ma, Hao Li, Xun Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LiDAR input with PillarGroup tokenization to the camera-only model (ablation) | MOJITO · NAVSIM-v1 navtest | PDMS: 86.8 -> 88.9 | Improved |
| use PillarGroup instead of FPS+KNN LiDAR tokenization (ablation) | MOJITO · NAVSIM-v1 navtest | PDMS: 86.1 -> 88.9 | Improved |
| add LiDAR with FPS+KNN tokenization to camera-only model (ablation) | MOJITO · NAVSIM-v1 navtest | PDMS: 86.8 -> 86.1 | Hurt |
| use joint self-attention instead of cross-attention (sensor tokens attend to action tokens) (ablation) | MOJITO · NAVSIM-v1 navtest | PDMS: 85.7 -> 88.9 | Improved |
| increase blocks from 3 to 12 (ablation) | MOJITO · NAVSIM-v1 navtest | PDMS: 80.5 -> 88.9 | Improved |
| increase blocks from 3 to 6 (ablation) | MOJITO · NAVSIM-v1 navtest | PDMS: 80.5 -> 80.5 | No clear effect |
| increase blocks from 6 to 9 (ablation) | MOJITO · NAVSIM-v1 navtest | PDMS: 80.5 -> 83.0 | Improved |
| increase blocks from 9 to 12 (ablation) | MOJITO · NAVSIM-v1 navtest | PDMS: 83.0 -> 88.9 | Improved |
| add RL fine-tuning to ReCogDrive-Base | ReCogDrive-Base · NAVSIM-v1 navtest | PDMS: 86.5 -> 90.8 | Improved |
| add RL fine-tuning to AutoVLA | AutoVLA · NAVSIM-v1 navtest | PDMS: 80.5 -> 89.1 | Improved |
| add RL fine-tuning to AdaThinkDrive | AdaThinkDrive · NAVSIM-v1 navtest | PDMS: 86.2 -> 90.3 | Improved |
| remove LiDAR branch (camera-only) on navhard | MOJITO · NAVSIM-v2 navhard | EPDMS | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- Transfuser — TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving (TPAMI 2022) · better on 2 of 2 shared results
- VADv2 — VADv2: End-to-End Autonomous Driving via Probabilistic Planning (ICLR 2026) · better on 1 of 1 shared result
- DriveSuprim — DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning (AAAI 2026) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DiffE2E: Rethinking End-to-End Driving with a Hybrid Diffusion-Regression-Classification Policy (NeurIPS 2025 · similarity 0.89)
- DualAD: Disentangling the Dynamic and Static World for End-to-End Driving (CVPR 2024 · similarity 0.87)
- AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning (NeurIPS 2025 · similarity 0.87)
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.87)
- SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving (CVPR 2025 · similarity 0.87)
- Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning (AAAI 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
