REVIEW 14 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
read the original abstract
World models can foresee the outcomes of different actions, which is of paramount importance for autonomous driving. Nevertheless, existing driving world models still have limitations in generalization to unseen environments, prediction fidelity of critical details, and action controllability for flexible application. In this paper, we present Vista, a generalizable driving world model with high fidelity and versatile controllability. Based on a systematic diagnosis of existing methods, we introduce several key ingredients to address these limitations. To accurately predict real-world dynamics at high resolution, we propose two novel losses to promote the learning of moving instances and structural information. We also devise an effective latent replacement approach to inject historical frames as priors for coherent long-horizon rollouts. For action controllability, we incorporate a versatile set of controls from high-level intentions (command, goal point) to low-level maneuvers (trajectory, angle, and speed) through an efficient learning strategy. After large-scale training, the capabilities of Vista can seamlessly generalize to different scenarios. Extensive experiments on multiple datasets show that Vista outperforms the most advanced general-purpose video generator in over 70% of comparisons and surpasses the best-performing driving world model by 55% in FID and 27% in FVD. Moreover, for the first time, we utilize the capacity of Vista itself to establish a generalizable reward for real-world action evaluation without accessing the ground truth actions.
Forward citations
Cited by 14 Pith papers
-
Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators
Generative world models used as closed-loop test oracles require a five-level admissibility ladder (L0-L4) because visual fidelity does not predict action-robustness.
-
Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure
DreamerV3's imagined rollouts are insensitive to friction changes that cause real gait collapse, revealing that world models extrapolate kinematically rather than dynamically.
-
MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
MiraBench defines action-conditioned reliability via three levels (physics adherence, action-following fidelity, optimism bias detection) and applies it to 12 model configurations using a 16,000-judgment human corpus,...
-
HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control
HandsOnWorld creates a hand-controlled egocentric video generator from unconstrained monocular video via a new EgoVid-Pro dataset from monocular reconstruction and a Plücker Hand Map that disentangles camera and hand motion.
-
Action with Visual Primitives
AVP architecture has VLM emit visual-primitive tokens to condition flow-matching action expert, yielding 27.61% higher success rate than pi_0.5 on real-robot pick-and-place tasks.
-
PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning
PhysEdit introduces adaptive reasoning depth and spatial masking to make image editing faster and more instruction-aligned without retraining the base model.
-
LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving
LMGenDrive unifies LLM-based multimodal understanding with generative world models to output both future driving videos and control signals for end-to-end closed-loop autonomous driving.
-
Flux4D: Flow-based Unsupervised 4D Reconstruction
Flux4D reconstructs large-scale dynamic 4D scenes unsupervised by predicting moving 3D Gaussians from photometric losses and static regularization when trained across multiple scenes.
-
How Far is Video Generation from World Model: A Physical Law Perspective
Video generation models generalize perfectly inside the training distribution but fail out-of-distribution and rely on case-based mimicking of nearest training examples instead of abstracting physical laws.
-
Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
PhyGenBench supplies 160 prompts across 27 physical laws and an automated LLM/VLM evaluation pipeline to measure physical commonsense compliance in current text-to-video models.
-
RetailSMV: Exocentric vs. Egocentric Adaptation of Foundation Video World Models in Retail
Exocentric-only LoRA adaptation of Cosmos3-Nano on a new synchronized retail video dataset matches or exceeds combined ego+exo training on most held-out metrics.
-
InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving
InfiniVerse reconstructs 3D occupancy from one frame, extends scenes autoregressively, converts to video via diffusion, and uses re-projection feedback to achieve SOTA FID 6.4 and FVD 67.97 on Waymo and nuScenes.
-
LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
LVDrive improves closed-loop driving on Bench2Drive by adding latent future scene prediction to VLA models via unified embedding space processing and two-stage trajectory decoding.
-
AutoAWG: Adverse Weather Generation with Adaptive Multi-Controls for Automotive Videos
AutoAWG generates controllable adverse weather automotive videos via semantics-guided adaptive multi-control fusion and vanishing-point-anchored temporal synthesis from static images, reducing FID by 50% and FVD by 16...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.