TPS-Drive uses an agent-centric tokenizer supervised by a frozen 3D detection head to purify VLM spatial representations, enabling better scene forecasting and lower collision rates on nuScenes and NAVSIM benchmarks.
Occllama: An occupancy-language-action generative world model for au- tonomous driving
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 11roles
background 2polarities
background 2representative citing papers
GEM represents driving scenes as explicit continuous 4D Gaussian primitives with learned dynamics to enable direct querying at arbitrary timestamps for semantic occupancy forecasting and motion planning.
AnyScene is an occupancy-centric framework using a Spatial-Temporal Occupancy Diffusion Transformer and Geometry-Grounded View Expansion to generate controllable driving scenes and videos from BEV layouts.
DriveFuture achieves SOTA results on NAVSIM by conditioning latent world model states on future predictions to directly inform trajectory planning.
HERMES++ unifies 3D scene understanding and future geometry prediction in driving scenes via BEV representations, LLM-enhanced queries, a temporal link, and joint geometric optimization.
Chat-Scene++ improves 3D scene understanding in multimodal LLMs by representing scenes as context-rich object sequences with identifier tokens and grounded chain-of-thought reasoning, reaching state-of-the-art on five benchmarks using pre-trained encoders.
A 3D Language-Embedded Gaussians framework with opacity-aware Poisson volumetric aggregation and progressive temperature decay achieves 59.50 IoU and 21.05 mIoU on Occ-ScanNet for open-vocabulary indoor occupancy.
CascadeOcc uses cascaded VQ representations in an autoregressive framework with a TimeMixer for multi-scale spatial and temporal modeling, achieving top results among vision-centric methods on 4D occupancy and planning benchmarks.
Discrete-WAM unifies world modeling and policy learning for autonomous driving by representing observations, states, decisions, and actions as tokens in one space and using hierarchical token editing for planning.
This survey synthesizes AI techniques for mixed autonomy traffic simulation and introduces a taxonomy spanning agent-level behavior models, environment-level methods, and cognitive/physics-informed approaches.
A sparse transformer predicts multi-frame 3D occupancy from images without BEV or VAE tokenization and reports SOTA results on nuScenes for 1-3s forecasting under arbitrary trajectories.
citing papers explorer
-
TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving
TPS-Drive uses an agent-centric tokenizer supervised by a frozen 3D detection head to purify VLM spatial representations, enabling better scene forecasting and lower collision rates on nuScenes and NAVSIM benchmarks.
-
GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planning
GEM represents driving scenes as explicit continuous 4D Gaussian primitives with learned dynamics to enable direct querying at arbitrary timestamps for semantic occupancy forecasting and motion planning.
-
AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond
AnyScene is an occupancy-centric framework using a Spatial-Temporal Occupancy Diffusion Transformer and Geometry-Grounded View Expansion to generate controllable driving scenes and videos from BEV layouts.
-
DriveFuture: Future-Aware Latent World Models for Autonomous Driving
DriveFuture achieves SOTA results on NAVSIM by conditioning latent world model states on future predictions to directly inform trajectory planning.
-
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
HERMES++ unifies 3D scene understanding and future geometry prediction in driving scenes via BEV representations, LLM-enhanced queries, a temporal link, and joint geometric optimization.
-
Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM
Chat-Scene++ improves 3D scene understanding in multimodal LLMs by representing scenes as context-rich object sequences with identifier tokens and grounded chain-of-thought reasoning, reaching state-of-the-art on five benchmarks using pre-trained encoders.
-
Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes
A 3D Language-Embedded Gaussians framework with opacity-aware Poisson volumetric aggregation and progressive temperature decay achieves 59.50 IoU and 21.05 mIoU on Occ-ScanNet for open-vocabulary indoor occupancy.
-
CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations
CascadeOcc uses cascaded VQ representations in an autoregressive framework with a TimeMixer for multi-scale spatial and temporal modeling, achieving top results among vision-centric methods on 4D occupancy and planning benchmarks.
-
Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
Discrete-WAM unifies world modeling and policy learning for autonomous driving by representing observations, states, decisions, and actions as tokens in one space and using hierarchical token editing for planning.
-
Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic
This survey synthesizes AI techniques for mixed autonomy traffic simulation and introduces a taxonomy spanning agent-level behavior models, environment-level methods, and cognitive/physics-informed approaches.
-
SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model
A sparse transformer predicts multi-frame 3D occupancy from images without BEV or VAE tokenization and reports SOTA results on nuScenes for 1-3s forecasting under arbitrary trajectories.