Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks17 from public data
- MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding193
MuirBench is introduced, a comprehensive benchmark that focuses on robust multi-image understanding capabilities of multimodal LLMs, and results reveal that even the best-performing models like GPT-4o and Gemini Pro find it challenging to solve MuirBench, achieving 68.0% and 49.3% in accuracy.
- 77
- 3D and 4D World Modeling: A Survey71
This survey addresses gaps in 3D and 4D world modeling and generation by establishing precise definitions, introducing a structured taxonomy spanning video-based (VideoGen), occupancy-based (OccGen), and LiDAR-based (LiDARGen) approaches, and systematically summarize datasets and evaluation metrics tailored to 3D/4D settings.
- WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World29
This work introduces WorldLens, a full-spectrum benchmark evaluating how well a model builds, understands, and behaves within its generated world, and develops WorldLens-Agent, an evaluation model distilled from these annotations to enable scalable, explainable scoring.
- UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving17
UniDriveVLA is proposed, a Unified Driving Vision-Language-Action model based on Mixture-of-Transformers that addresses the perception-reasoning conflict via expert decoupling and demonstrates strong performance across a broad range of perception, prediction, and understanding tasks, including 3D detection, online mapping, motion forecasting, and driving-oriented VQA.
- Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation14
WorldDrive is presented, a holistic framework that couples scene generation and real-time planning via unifying vision and motion representation and proposes a Future-aware Rewarder, which distills future latent representation from the frozen world model to evaluate and select optimal trajectories in real-time.
- Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation12
Qwen-RobotWorld is introduced, a language-conditioned video world model for embodied intelligence that predicts physically grounded future visual trajectories from current observations across robotic manipulation, autonomous driving, indoor navigation, and human-to-robot transfer.
- OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving9
This work proposes OminiGen, which generates aligned multimodal sensor data in a unified framework and designs a novel generalizable multimodal reconstruction method, UAE, to jointly decode LiDAR and multi-view camera data.
- 8
- Is Your Driving World Model an All-Around Player?5
WorldLens is introduced, a unified benchmark that measures world-model fidelity across the full spectrum, from pixel quality and 4D geometry to closed-loop driving and human perceptual alignment, through five complementary aspects and 24 standardized dimensions and forms a unified ecosystem for assessing generated worlds not merely by visual appeal, but by physical and behavioral fidelity.
- LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)5
This paper reports on the LoViF 2026 PhyScore challenge, a competition on holistic quality assessment of world-model-generated videos across both 2D and 4D generation settings, and provides method-level insights from submitted solutions.
- Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving4
The JWM is introduced, which deeply integrates WorldRec and WorldGen to achieve synergistic gains in generation stability, cross-frame consistency, and visual fidelity, providing a solid foundation for closed-loop simulation, data synthesis, and end-to-end training in autonomous driving.
- RoboPearls: Editable Video Simulation for Robot Manipulation4
RoboPearls, an editable video simulation framework for robotic manipulation that automates the simulation production process in a user-friendly manner through flexible command interpretation and execution, and employs a vision-language model (VLM) to analyze robotic learning issues to close the simulation loop for performance enhancement.
- 2
- 1
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.