LogosIntelligenceLab

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

[CVPR 2021 & IJCV 2024] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

[ICLR 2024] Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

[ICLR 2023 & IJCV 2025] SeaFormer: Squeeze-enhanced Axial Transformer

[IJCV 2026] Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering

[NeurIPS 2021 Spotlight] & [IJCV 2024] SOFT: Softmax-free Transformer with Linear Complexity

[NeurIPS 2022 & TPAMI 2025] DeepInteraction: 3D Object Detection via Modality Interaction

[CVPR 2023] Official repository of Generative Semantic Segmentation

[ICLR 2023 & TPAMI 2025] S-NeRF: Neural Radiance Fields for Street Views

[NeurIPS 2024 Spotlight] Tetrahedron Splatting for 3D Generation

[AAAI 2023] PolarFormer: Multi-camera 3D Object Detection with Polar Transformers

[CVPR 2025] IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing

[ICLR 2025] GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting

[NeurIPS 2024] DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States

[ICCV2025] BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting

[ICLR 2025] Reflective Gaussian Splatting

[ECCV 2024] WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation

[CVPR 2025] Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning

[IJCV 2026] Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video

[ECCV 2022] Learning Ego 3D Representation as Ray Tracing

[ECCV 2024] Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving

[AAAI 2024] NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields

[NeurIPS 2025] From Flatland to Space (SPAR). A large-scale dataset & benchmark for 3D spatial perception and reasoning in VLMs.

[TPAMI 2025 & AAAI 2024 & ICCV2023 Oral] RoadNetworkTRansformer & LaneGraph2Seq

[AAAI 2026] Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving

3D Gaussian Ray Tracer

[NeurIPS 2024] DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization

[ICLR 2024] Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping

[NeurIPS 2025] Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution

[CVPR2026] SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving

Harnessing Diffusion Models for Visual Perception with Meta Prompts

[ICLR 2026] UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding

[ECCV 2022 & IJCV 2025] Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling

[ICLR 2025] Diffusion²: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models

[NeurIPS 2024 Spotlight] Motion Forecasting in Continuous Driving

[NeurIPS 2025] 4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration