جدیدترین مقالات تحقیقاتی هوش مصنوعی از arXiv را کشف کنید — به‌روزرسانی خودکار روزانه برای پژوهشگران و علاقه‌مندان.
Video generation models can now depict remarkably realistic motion. Yet it is unclear how to use this motion beyond pixels: to animate a specific 3D asset and replay the animation in its 3D scene. For instance, a video m…
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled study on 22 benchmarks s…
Multimodal reinforcement learning with verifiable rewards (RLVR) provides reliable task-level supervision, yet offers limited guidance for localizing errors in visual reasoning. On-policy self-distillation (OPSD) complem…
Reinforcement learning enables mobile robots to make fast and scalable navigation decisions in constrained human-shared environments. However, directly extending single-robot approaches to multi-robot settings often fail…
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify physical RSI through a five-axis metric: Fir…
شخصی‌سازی برای انتقال ربات‌های عمومی به محیط‌های خانگی و دستیابی به قابلیت عملیاتی واقعی، ضروری است. در حالی که دستکاری رباتیک عمومی به‌طور گسترده مورد مطالعه قرار گرفته است، دستکاری رباتیک شخصی‌سازی‌شده (PeRM) فاقد بنچم…
Significant efforts are currently being directed toward the implementation of large-scale quantum information processors, but realizing useful quantum advantage also requires the development of efficient quantum algorith…
Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitly specified, from physical properties su…
Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environments that address a policy's failures and…
Mixture-of-experts (MoE) models have become an important approach for scaling model parameters. Modern MoE architectures increasingly combine two design choices: fine-grained expert segmentation and shared experts. The f…