Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features

• URL: http://arxiv.org/abs/2608.06008v1
• Date: Thu, 06 Aug 2026 13:13:07 GMT
• Title: Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features
• Abstract summary: Planning performance is largely insensitive to the tested video-noise levels, whereas strong trajectories can already be decoded from intermediate layers.<n>We introduce Adaptive-WAM, a quality-aware multi-exit planner built on a Wan2.2-5B backbone.
• Score: 4.996631858286914
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large video diffusion models provide rich spatiotemporal priors for autonomous driving, but existing world-action models often inherit the cost of iterative future-video generation even though deployment only requires an ego trajectory. We ask a more basic question: how much of a video diffusion model must be executed to make a reliable driving decision? Through a controlled study of video denoising timesteps and Diffusion Transformer (DiT) depth, we find that planning performance is largely insensitive to the tested video-noise levels, whereas strong trajectories can already be decoded from intermediate layers. Based on this observation, we introduce Adaptive-WAM, a quality-aware multi-exit planner built on a Wan2.2-5B backbone. Trajectory diffusion heads are attached to selected DiT blocks, and a lightweight trajectory-quality scorer terminates inference once the best trajectory decoded so far satisfies a quality threshold; otherwise, computation continues from the cached hidden state to a deeper exit. The deployed planner therefore avoids the iterative classifier-free denoising loop and VAE decoding required for future-video synthesis, while dynamically allocating backbone depth according to trajectory quality. On NAVSIM, the adaptive single-trajectory planner achieves 90.8 PDMS; a separate fixed-exit variant reaches 92.6 PDMS with 64 proposals. It further obtains 89.9 EPDMS on NAVSIM v2, yielding the best reported results among the compared front-view video world-model planners. Without target-domain fine-tuning, Adaptive-WAM transfers to nuScenes with 0.88 m average L2 error and a 0.08\% collision rate. On an A100, adaptive routing improves PDMS from 90.62 to 90.79 while averaging 170 ms end-to-end planning latency, approximately 10\% below the 190 ms fixed block-15 planner and 47\% below the 320 ms fixed full-depth planner. Code will be released.

Related papers

• AlphaRoute: Large Language Models as Semantic Optimizers for Multi-Objective Routing [0.0]
  Very Large Scale Integration (VLSI) global routing is an NP-hard optimization problem requiring signal net assignment across 3D grids.<n>Because traditional overflows rely on static penalty schedules that fail on complex congestion topologies, we present AlphaRoute.<n>We introduce SHAP-based overflow decomposition to isolate per-net congestion, driving targeted subgraph extraction via 3D maze routing.
  arXiv  Detail & Related papers  (2026-07-22T05:27:55Z)
• DRIFT: Drift and Aggregation for Motion Planning [20.309189828710362]
  DRIFT is a fixed-depth trajectory planner that combines one-step drifting in a compact trajectory latent space with scene-aware proposal aggregation.<n>A lightweight Aggregation Head integrates these features with scene, navigation, and ego-state information and directly predicts the final trajectory.<n>Its output is trained with expert-trajectory imitation and a map-derived boundary regularizer that penalizes waypoints outside the drivable polygon.
  arXiv  Detail & Related papers  (2026-07-16T02:43:13Z)
• PARE: Pruning and Adaptive Routing for Efficient Video Generation [71.54959622788608]
  Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling.<n>Recent methods reduce cost by compressing width, depth, or sampling steps, but typically commit to a fixed architecture that cannot adapt to individual inputs or denoising stages.<n>We propose PARE, which jointly compresses width and depth with structure-aware pruning and input-adaptive routing.
  arXiv  Detail & Related papers  (2026-05-26T17:43:25Z)
• Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers [12.948398661304184]
  Diffusion-APO is a trajectory-aware algorithm for aligning video diffusion models with human intent.<n>We introduce a unified and modular RLHF framework that integrates online ranking, half-online anchoring, offline refinement, and distillation-aware drift correction.<n>We demonstrate that Diffusion-APO consistently outperforms standard baselines in visual quality and instruction following.
  arXiv  Detail & Related papers  (2026-05-08T09:37:46Z)
• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving [51.268878540511054]
  We propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy.<n>We show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM.
  arXiv  Detail & Related papers  (2026-04-04T04:12:47Z)
• A Two-stage Transformer Framework for Temporal Localization of Distracted Driver Behaviors [0.0]
  We develop and evaluate a temporal action localization framework tailored for driver monitoring scenarios.<n>Our approach follows a two-stage pipeline that combines VideoMAE-based feature extraction with an Augmented Self-Mask Attention (AMA) detector.<n> Experimental results reveal a distinct trade-off between model capacity and efficiency.
  arXiv  Detail & Related papers  (2026-03-22T04:09:47Z)
• DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving [65.7087560656003]
  Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse.<n>We propose DiffusionDriveV2, which leverages reinforcement learning to constrain low-quality modes and explore for superior trajectories.<n>This significantly enhances the overall output quality while preserving the inherent multimodality of its core Gaussian Mixture Model.
  arXiv  Detail & Related papers  (2025-12-08T17:29:52Z)
• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving.<n>Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.<n>Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• Hierarchical Patch Diffusion Models for High-Resolution Video Generation [50.42746357450949]
  We develop deep context fusion, which propagates context information from low-scale to high-scale patches in a hierarchical manner. We also propose adaptive computation, which allocates more network capacity and computation towards coarse image details. The resulting model sets a new state-of-the-art FVD score of 66.32 and Inception Score of 87.68 in class-conditional video generation.
  arXiv  Detail & Related papers  (2024-06-12T01:12:53Z)
• Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [56.38386580040991]
  Consistency Trajectory Model (CTM) is a generalization of Consistency Models (CM) CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance. Unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods.
  arXiv  Detail & Related papers  (2023-10-01T05:07:17Z)
• Optimizing Anchor-based Detectors for Autonomous Driving Scenes [22.946814647030667]
  This paper summarizes model improvements and inference-time optimizations for the popular anchor-based detectors in autonomous driving scenes. Based on the high-performing RCNN-RS and RetinaNet-RS detection frameworks, we study a set of framework improvements to adapt the detectors to better detect small objects in crowd scenes.
  arXiv  Detail & Related papers  (2022-08-11T22:44:59Z)
• StreamYOLO: Real-time Object Detection for Streaming Perception [84.2559631820007]
  We endow the models with the capacity of predicting the future, significantly improving the results for streaming perception. We consider multiple velocities driving scene and propose Velocity-awared streaming AP (VsAP) to jointly evaluate the accuracy. Our simple method achieves the state-of-the-art performance on Argoverse-HD dataset and improves the sAP and VsAP by 4.7% and 8.2% respectively.
  arXiv  Detail & Related papers  (2022-07-21T12:03:02Z)
• Convex Hull Prediction for Adaptive Video Streaming by Recurrent Learning [38.574550778712236]
  We propose a deep learning based method of content aware convex hull prediction. We employ a recurrent convolutional network (RCN) to implicitly analyze the complexity of video shots in order to predict their convex hulls. Our proposed model better approximations of the optimal convex hulls, and offers competitive time savings as compared to existing approaches.
  arXiv  Detail & Related papers  (2022-06-10T05:11:02Z)

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.