Aquileo | Vladlen Koltun

Aquileo | Paper published at ICLR 2026

Thu, 16 Apr 2026 13:02:19 +0000

The paper Sharp Monocular View Synthesis in Less Than a Second was published at ICLR 2026.

The post Paper published at ICLR 2026 appeared first on Vladlen Koltun.

]]>

Aquileo | Paper accepted to ICML 2025

Sat, 19 Jul 2025 22:44:27 +0000

The paper Robust Autonomy Emerges from Self-Play was accepted to ICML 2025.

The post Paper accepted to ICML 2025 appeared first on Vladlen Koltun.

]]>

Aquileo | Four papers accepted to ICLR 2025

Thu, 13 Feb 2025 12:40:00 +0000

Four papers were accepted to the International Conference on Learning Representations (ICLR): Does Spatial Cognition Emerge in Frontier Models?, Depth Pro: Sharp Monocular Metric Depth in Less Than a Second, CoMotion: Concurrent Multi-person 3D Motion, and Cut Your Losses in Large-Vocabulary Language Models. Cut Your Losses was selected for oral presentation at the conference (1.8% acceptance rate).

The post Four papers accepted to ICLR 2025 appeared first on Vladlen Koltun.

]]>

Aquileo | Paper published in Science Robotics and featured on the cover

Tue, 10 Oct 2023 14:23:50 +0000

Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning was published in Science Robotics and featured on the journal’s cover. The paper presents a systematic study of control system design methodologies, focusing on reinforcement learning and optimal control in the context of autonomous drone racing. We show that neural networks trained with reinforcement learning (RL) outperform optimal control methods and trace the root cause to the flexibility afforded by RL in the formulation of the controller’s objective. In conjunction with the study, we push autonomous drones to unprecedented performance regimes, demonstrating superhuman control while reaching accelerations greater than 12g and velocities greater than 100 km/h.

The post Paper published in Science Robotics and featured on the cover appeared first on Vladlen Koltun.

]]>

Aquileo | Paper published in Nature and featured on the cover

Tue, 10 Oct 2023 14:22:23 +0000

Champion-level Drone Racing using Deep Reinforcement Learning was published in Nature and featured on the journal’s cover. The paper presents an autonomous system that outraced human world champions in first-person view (FPV) drone racing, a televised sport. This is the first time that an autonomous mobile robot achieved world-champion-level performance in a real-world competitive physical sport. Here is a video created by Nature to highlight the work and here is an accompanying article that provides a good overview.

The post Paper published in Nature and featured on the cover appeared first on Vladlen Koltun.

]]>

Aquileo | SIGGRAPH Test-of-Time Award

Sat, 12 Aug 2023 11:12:58 +0000

The paper Optimizing Locomotion Controllers Using Biologically-Based Actuators and Objectives received the ACM SIGGRAPH Test-of-Time Award at SIGGRAPH 2023. The award “recognizes highly influential papers published in SIGGRAPH conferences that have made a significant impact over the past 10 years or more”. This is the first year of this annual award, for which all papers presented at SIGGRAPH conferences from 2011 to 2013 were considered. Four papers were selected for the award.

The post SIGGRAPH Test-of-Time Award appeared first on Vladlen Koltun.

]]>

Aquileo | Paper accepted to SIGGRAPH 2023

Sat, 12 Aug 2023 10:57:13 +0000

The paper An Extensible, Data-Oriented Architecture for High-Performance, Many-World Simulation was accepted to SIGGRAPH 2023.

The post Paper accepted to SIGGRAPH 2023 appeared first on Vladlen Koltun.

]]>

Aquileo | Two papers accepted to PAMI

Thu, 20 Oct 2022 23:54:36 +0000

Two papers were accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence: Drinking from a Firehose: Continual Learning with Web-scale Natural Language and ASH: A Modern Framework for Parallel Spatial Hashing in 3D Perception.

The post Two papers accepted to PAMI appeared first on Vladlen Koltun.

]]>

Aquileo | Four papers accepted to NeurIPS 2022

Sat, 01 Oct 2022 19:30:55 +0000

Four papers were accepted to Neural Information Processing Systems (NeurIPS): Non-deep Networks, Domain Generalization without Excess Empirical Risk, Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics, and Scale-invariant Learning by Physics Inversion. Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics was selected for oral presentation at the conference.

The post Four papers accepted to NeurIPS 2022 appeared first on Vladlen Koltun.

]]>

Aquileo | Enhancing Photorealism Enhancement accepted to PAMI

Mon, 21 Mar 2022 21:06:18 +0000

The paper Enhancing Photorealism Enhancement was accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence.

The post Enhancing Photorealism Enhancement accepted to PAMI appeared first on Vladlen Koltun.

]]>