Related papers: Any2Any: Efficient Cross-Embodiment Transfer for H…

Hyperparameter tuning can dramatically impact training stability and final performance of large-scale models. Recent works on neural network parameterisations, such as $\mu$P, have enabled transfer of optimal global hyperparameters across…

High-fidelity motion tracking serves as the ultimate litmus test for generalizable, human-level motor skills. However, current policies often hit a "generality barrier": as motion libraries scale in diversity, tracking fidelity inevitably…

We propose a novel adaptive transfer learning framework, learning to transfer learn (L2TL), to improve performance on a target dataset by careful extraction of the related information from a source dataset. Our framework considers…

Restoring multiple degradations efficiently via just one model has become increasingly significant and impactful, especially with the proliferation of mobile devices. Traditional solutions typically involve training dedicated models per…

Goal-conditioned navigation models for ground robots trained using supervised learning show promising zero-shot transfer, but their collision-avoidance capability nevertheless degrades under distribution shift, i.e. environmental, robot or…

Robots operating in human environments need various skills, like slow and fast walking, turning, side-stepping, and many more. However, building robot controllers that can exhibit such a large range of behaviors is a challenging problem…

Recently, humanoid robots have made significant advances in their ability to perform challenging tasks due to the deployment of Reinforcement Learning (RL), however, the inherent complexity of humanoid robots, including the difficulty of…

We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI…

Image matching, which aims to identify corresponding pixel locations between images, is crucial in a wide range of scientific disciplines, aiding in image registration, fusion, and analysis. In recent years, deep learning-based image…

Robust training and validation of Autonomous Driving Systems (ADS) require massive, diverse datasets. Proprietary data collected by Autonomous Vehicle (AV) fleets, while high-fidelity, are limited in scale, diversity of sensor…

The increasing of pre-trained models has significantly facilitated the performance on limited data tasks with transfer learning. However, progress on transfer learning mainly focuses on optimizing the weights of pre-trained models, which…

Frozen pretrained models have become a viable alternative to the pretraining-then-finetuning paradigm for transfer learning. However, with frozen models there are relatively few parameters available for adapting to downstream tasks, which…

Designing agents that acquire knowledge autonomously and use it to solve new tasks efficiently is an important challenge in reinforcement learning. Knowledge acquired during an unsupervised pre-training phase is often transferred by…

Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…

Vision-language-action (VLA) models have significantly advanced robotic learning, enabling training on large-scale, cross-embodiment data and fine-tuning for specific robots. However, state-of-the-art autoregressive VLAs struggle with…

Recent advances in whole-body robot control have enabled humanoid and legged robots to execute increasingly agile and coordinated movements. However, standardized benchmarks for evaluating robotic athletic performance in real-world settings…

Adapting pre-trained foundation models for various downstream tasks has been prevalent in artificial intelligence. Due to the vast number of tasks and high costs, adjusting all parameters becomes unfeasible. To mitigate this, several…

It is well-known that inverse dynamics models can improve tracking performance in robot control. These models need to precisely capture the robot dynamics, which consist of well-understood components, e.g., rigid body dynamics, and effects…

In this paper, we propose a novel hybrid representation and end-to-end trainable network architecture to model fully editable and customizable neural avatars. At the core of our work lies a representation that combines the modeling power of…

This work studies the challenge of transfer animations between characters whose skeletal topologies differ substantially. While many techniques have advanced retargeting techniques in decades, transfer motions across diverse topologies…