Manipulation, locomotion, sim-to-real transfer and autonomous driving: learning systems that have to survive physics.
arXiv:2607. 22999v1 Announce Type: cross Abstract: Language agents can now interact fluently with users in software, but robots still struggle to bring comparable interaction to physical tasks.
arXiv:2512. 01031v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks.
arXiv:2607. 24692v1 Announce Type: cross Abstract: Inference systems increasingly combine a fast path that returns predictions within the application's latency deadline together with a higher-accuracy slow path that runs higher-compute methods on stronger, remote hardware, so its results can be returned on time and combined with the fast path predictions.
arXiv:2607. 22890v1 Announce Type: cross Abstract: Domain Randomization (DR) is a standard technique for closing the Sim-to-Real gap, yet traditional DR pipelines rely on classical computer graphics rendering driven by polygon meshes.
arXiv:2607. 23537v1 Announce Type: new Abstract: Autonomous driving under adverse weather remains a critical challenge, yet existing vision-language benchmarks mainly evaluate under standard conditions, synthetic corruptions, or single modality.
arXiv:2607. 24113v1 Announce Type: cross Abstract: Previous research has shown that a human-like robot's acceptance heavily depends on the setting in which it operates and its ability to perform relevant tasks.
arXiv:2607. 23565v1 Announce Type: cross Abstract: Safe quadrotor navigation in cluttered and dynamic environments depends not only on instantaneous geometric perception, but more critically on anticipating collision risks induced by relative motion.
arXiv:2604. 25897v2 Announce Type: replace-cross Abstract: Contact variability, sensing uncertainty, and external disturbances make grasp execution stochastic.
arXiv:2607. 22721v1 Announce Type: cross Abstract: Cognitive remediation tasks often require patients to perform structured actions involving object manipulation and sequential reasoning.
arXiv:2607. 22832v1 Announce Type: new Abstract: Long-horizon embodied tasks require policies that execute many dependent actions before task success can be observed.
arXiv:2607. 23045v1 Announce Type: new Abstract: AI is evaluated through knowledge, reasoning and plan generation, yet scientific agency requires reliable physical action and adaptation to evidence.
arXiv:2607. 22702v1 Announce Type: cross Abstract: Text-motion representation learning has advanced rapidly, with growing interest in multi person interactions for animation, AR/VR, and embodied AI.
arXiv:2607. 18985v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge.
arXiv:2607. 23332v1 Announce Type: new Abstract: Creating a reusable tool is an investment: an agent pays a fixed cost now in exchange for the potential of future reuse.
arXiv:2607. 22697v1 Announce Type: new Abstract: Deployed AI systems are often trained from broad candidate data pools, necessitating data curation towards the deployment test distribution.
arXiv:2607. 24577v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents are increasingly deployed in safety-critical domains such as robotics, autonomous driving, and drone control, where unexpected behaviors may lead to severe real-world consequences.
arXiv:2512. 24125v3 Announce Type: replace-cross Abstract: General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action execution, a combination that remains challenging for existing Vision-Language-Action (VLA) models.
arXiv:2607. 23899v1 Announce Type: cross Abstract: This exploratory study examines whether a large multimodal language model, GPT-5.
We introduce CameraAnything, the first unified framework for camera controlled video editing that enables joint control of both intrinsic and extrinsic camera parameters. Existing approaches either rely on expensive 3D reconstruction to achieve full camera functionality or restrict editing to extrinsic parameter manipulation.
The warning shots will continue until civilization wakes up
