Valts Blukis
NVIDIA
収録論文 26本 ・ フィジカルAI/ロボット学習
VQA/操作計画
※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。
論文
- PROBE: VLMエージェントによる操作基盤の視覚質問応答VQA/操作計画2026/8/17
ロボットが隠れた物体を探すために操作が必要な動的シーンでの視覚質問応答(MG-VQA)を提案し、シミュレータとベンチマークを構築、VLMエージェントの性能を評価・微調整する手法を示した。
- Vesta: A Generalist Embodied Reasoning Model2026/6/1
- VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation2026/6/1
- SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL2025/12/1
- BOP-ASK: Object-Interaction Reasoning for Vision-Language Models2025/11/1
- VLA-0: Building State-of-the-Art VLAs with Zero Modification2025/10/1
- OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model2025/6/1
- RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics2024/11/1
- GRS: Generating Robotic Simulation Tasks from Real-World Images2024/10/1
- 3D-MVP: 3D Multiview Pretraining for Robotic Manipulation2024/6/1
- RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics2024/6/1
- RVT-2: Learning Precise Manipulation from Few Demonstrations2024/6/1
- Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects2024/4/1
- Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces2024/3/1
- cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generation2023/10/1
- Diff-DOPE: Differentiable Deep Object Pose Estimation2023/10/1
- RVT: Robotic View Transformer for 3D Object Manipulation2023/6/1
- BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects2023/3/1
- One-Shot Neural Fields for 3D Object Understanding2022/10/1
- ProgPrompt: Generating Situated Robot Task Plans using Large Language Models2022/9/1
- Correcting Robot Plans with Natural Language Feedback2022/4/1
- A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution2021/7/1
- Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following2020/11/1
- Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight2019/10/1
- Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction2018/11/1
- Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning2018/6/1