ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
- URL: http://arxiv.org/abs/2605.23270v1
- Date: Fri, 22 May 2026 06:17:35 GMT
- Title: ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
- Abstract summary: Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal reasoning and global trajectory consistency.<n>We propose ChainFlow-VLA, which unifies causal generation and global refinement within a unified probabilistic framework.<n> Experiments demonstrate that ChainFlow-VLA achieves robust planning in ambiguous and long-tail scenarios, achieving a state-of-the-art score of 94.85 on the NAVSIM v1 leaderboard.
- Score: 7.814547378443577
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal reasoning and global trajectory consistency. Autoregressive (AR) models capture interaction-aware temporal dependencies via causal factorization, but their step-wise decoding leads to error accumulation and suboptimal global structure. In contrast, diffusion models optimize trajectories globally but lack explicit causal constraints, making them unreliable in interactive and safety-critical scenarios. This dichotomy reveals a deeper issue: existing methods treat causal modeling and global optimization as separate paradigms, without a principled way to unify them within a single trajectory distribution. To address this, we propose ChainFlow-VLA, which unifies causal generation and global refinement within a unified probabilistic framework. We formulate planning as a mixture over AR-induced modes and learn Vision-Language Model (VLM)-conditioned residual distributions over these modes. An autoregressive generator (Chain) produces a discrete set of causal trajectory modes, followed by a diffusion-based refiner (Flow) that leverages VLM hidden states as semantic priors to perform mode-conditioned correction in residual space while preserving causal structure. This straightforward conditioning seamlessly injects high-level scene understanding into fine-grained trajectory adjustments. Experiments demonstrate that ChainFlow-VLA achieves robust planning in ambiguous and long-tail scenarios, achieving a state-of-the-art score of 94.85 on the NAVSIM v1 leaderboard, matching human-level performance (94.8). Code will be available at https://github.com/AFARI-Research/ChainFlow-VLA.
Related papers
- S-squared-VLA: Decoupling Semantic and Spatial Streams in Vision-Language-Action Models for Autonomous Driving [8.813976817688605]
Vision-Language Models (VLMs) have demonstrated remarkable potential for high-level reasoning in autonomous driving.<n>VLMs struggle to generate precise, low-level control actions due to mismatch between discrete language tokens and continuous trajectory planning.<n>We propose the S-squared-VLA, which explicitly decouples the semantic and spatial streams in Vision-Language-Action models.
arXiv Detail & Related papers (2026-07-15T15:07:02Z) - dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models [49.497309561043004]
We propose textbfdVLA-RL, shifting the learning objective from the marginal action probability to the joint probability of the sampled generation path.<n>Our approach achieves a success rate of textbf99.7% on LIBERO.<n>It also establishes strong VLA-based results on RoboTwin 2.0 by delivering a textbf30.6% improvement over the SFT baseline.
arXiv Detail & Related papers (2026-06-22T17:19:03Z) - Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space [99.30250506439678]
This work reformulates language generation as an optimal control problem.<n>It provides a unified theoretical perspective to analyze autoregressive and diffusion models.
arXiv Detail & Related papers (2026-05-14T08:13:43Z) - Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models [65.89572755202245]
Diffusion Language Models (DLMs) offer stronger global awareness and highly parallel generation.<n>Post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient.<n>We propose a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference.
arXiv Detail & Related papers (2026-05-12T09:39:06Z) - MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving [23.013043338076745]
MeanFuser is an end-to-end autonomous driving method.<n>We introduce GMN to guide generative sampling and adapt MeanFlow Identity" to end-to-end planning.<n>Experiments on the NAVSIM closed-loop benchmark demonstrate that MeanFuser achieves outstanding performance without the supervision of the PDM Score.
arXiv Detail & Related papers (2026-02-23T17:17:26Z) - WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving [9.719456684859606]
We introduce WAM-Flow, a vision--action (VLA) model that casts ego-trajectory planning as discrete flow matching over a structured token space.<n>WAM-Flow performs fully parallel, bidirectional denoising, enabling coarse-to-fine refinement with a tunable compute-accuracy trade-off.<n>These results establish discrete flow matching as a new promising paradigm for end-to-end autonomous driving.
arXiv Detail & Related papers (2025-12-05T19:36:46Z) - Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
arXiv Detail & Related papers (2025-12-02T14:42:54Z) - ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
arXiv Detail & Related papers (2025-10-09T17:59:36Z) - Solving Inverse Problems with FLAIR [68.87167940623318]
We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
arXiv Detail & Related papers (2025-06-03T09:29:47Z) - Stragglers-Aware Low-Latency Synchronous Federated Learning via Layer-Wise Model Updates [71.81037644563217]
Synchronous federated learning (FL) is a popular paradigm for collaborative edge learning.
As some of the devices may have limited computational resources and varying availability, FL latency is highly sensitive to stragglers.
We propose straggler-aware layer-wise federated learning (SALF) that leverages the optimization procedure of NNs via backpropagation to update the global model in a layer-wise fashion.
arXiv Detail & Related papers (2024-03-27T09:14:36Z) - AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies [21.024480978703288]
We propose AdaFlow, an imitation learning framework based on flow-based generative modeling.
AdaFlow represents the policy with state-conditioned ordinary differential equations (ODEs)
We show that AdaFlow achieves high performance with fast inference speed.
arXiv Detail & Related papers (2024-02-06T10:15:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.