How can robots learn dexterous grasping skills efficiently and apply them adaptively based on user instructions? This work tackles two key challenges: efficient skill acquisition from limited human demonstrations and context-driven skill selection. We introduce AdaDexGrasp, a framework that learns a library of grasping skills from a single human demonstration per skill and selects the most suitable one using a vision-language model (VLM). To improve sample efficiency, we propose a trajectory following reward that guides reinforcement learning (RL) toward states close to a human demonstration while allowing flexibility in exploration. To learn beyond the single demonstration, we employ curriculum learning, progressively increasing object pose variations to enhance robustness. At deployment, a VLM retrieves the appropriate skill based on user instructions, bridging low-level learned skills with high-level intent. We evaluate AdaDexGrasp in both simulation and real-world settings, showing that our approach significantly improves RL efficiency and enables learning human-like grasp strategies across varied object configurations. Finally, we demonstrate zero-shot transfer of our learned policies to a real-world PSYONIC Ability Hand, with a 90% success rate across objects, significantly outperforming the baseline.

Multi-view image diffusion models have significantly advanced open-domain 3D object generation. However, most existing models rely on 2D network architectures that lack inherent 3D biases, resulting in compromised geometric consistency. To address this challenge, we introduce 3D-Adapter, a plug-in module designed to infuse 3D geometry awareness into pretrained image diffusion models. Central to our approach is the idea of 3D feedback augmentation: for each denoising step in the sampling loop, 3D-Adapter decodes intermediate multi-view features into a coherent 3D representation, then re-encodes the rendered RGBD views to augment the pretrained base model through feature addition. We study two variants of 3D-Adapter: a fast feed-forward version based on Gaussian splatting and a versatile training-free version utilizing neural fields and meshes. Our extensive experiments demonstrate that 3D-Adapter not only greatly enhances the geometry quality of text-to-multi-view models such as Instant3D and Zero123++, but also enables high-quality 3D generation using the plain text-to-image Stable Diffusion. Furthermore, we showcase the broad application potential of 3D-Adapter by presenting high quality results in text-to-3D, image-to-3D, text-to-texture, and text-to-avatar tasks.

Simulation has enabled unprecedented compute-scalable approaches to robot learning. However, many existing simulation frameworks typically support a narrow range of scenes/tasks and lack features critical for scaling generalizable robotics and sim2real. We introduce and open source ManiSkill3, the fastest state-visual GPU parallelized robotics simulator with contact-rich physics targeting generalizable manipulation. ManiSkill3 supports GPU parallelization of many aspects including simulation+rendering, heterogeneous simulation, pointclouds/voxels visual input, and more. Simulation with rendering on ManiSkill3 can run 10-1000x faster with 2-3x less GPU memory usage than other platforms, achieving up to 30,000+ FPS in benchmarked environments due to minimal python/pytorch overhead in the system, simulation on the GPU, and the use of the SAPIEN parallel rendering system. Tasks that used to take hours to train can now take minutes. We further provide the most comprehensive range of GPU parallelized environments/tasks spanning 12 distinct domains including but not limited to mobile manipulation for tasks such as drawing, humanoids, and dextrous manipulation in realistic scenes designed by artists or real-world digital twins. In addition, millions of demonstration frames are provided from motion planning, RL, and teleoperation. ManiSkill3 also provides a comprehensive set of baselines that span popular RL and learning-from-demonstrations algorithms.

Fact-checking based on commercial LLMs has become mainstream. Although these methods offer high explainability, it falls short in accuracy compared to traditional fine-tuning approaches, and data security is also a significant concern. In this paper, we propose a self-instruction based fine-tuning approach for fact-checking that balances accuracy and explainability. Our method consists of Data Augmentation and Improved DPO fine-tuning. The former starts by instructing the model to generate both positive and negative explanations based on claim-evidence pairs and labels, then sampling the dataset according to our customized difficulty standards. The latter employs our proposed improved DPO to fine-tune the model using the generated samples. We fine-tune the smallest-scale LLaMA-7B model and evaluate it on the challenging fact-checking datasets FEVEROUS and HOVER, utilizing four fine-tuning methods and three few-shot learning methods for comparison. The experiments demonstrate that our approach not only retains accuracy comparable to, or even surpassing, traditional fine-tuning methods, but also generates fluent explanation text. Moreover, it also exhibit high generalization performance. Our method is the first to leverage self-supervised learning for fact-checking and innovatively combines contrastive learning and improved DPO in fine-tuning LLMs, as shown in the experiments.

Currently, there are no convincing proxies for the fundamentals of cryptocurrency assets. We propose a new market-to-fundamental ratio, the price-to-utility (PU) ratio, utilizing unique blockchain accounting methods. We then proxy various fundamental-to-market ratios by Bitcoin historical data and find they have little predictive power for short-term bitcoin returns. However, PU ratio effectively predicts long-term bitcoin returns. We verify PU ratio valuation by unsupervised and supervised machine learning. The valuation method informs investment returns and predicts bull markets effectively. Finally, we present an automated trading strategy advised by the PU ratio that outperforms the conventional buy-and-hold and market-timing strategies. We distribute the trading algorithms as open-source software via Python Package Index for future research.

Creating large scale high-quality annotations is a known challenge in medical imaging. In this work, based on the CycleGAN algorithm, we propose leveraging annotations from one modality to be useful in other modalities. More specifically, the proposed algorithm creates highly realistic synthetic CT images (SynCT) from prostate MR images using unpaired data sets. By using SynCT images (without segmentation labels) and MR images (with segmentation labels available), we have trained a deep segmentation network for precise delineation of prostate from real CT scans. For the generator in our CycleGAN, the cycle consistency term is used to guarantee that SynCT shares the identical manually-drawn, high-quality masks originally delineated on MR images. Further, we introduce a cost function based on structural similarity index (SSIM) to improve the anatomical similarity between real and synthetic images. For segmentation followed by the SynCT generation from CycleGAN, automatic delineation is achieved through a 2.5D Residual U-Net. Quantitative evaluation demonstrates comparable segmentation results between our SynCT and radiologist drawn masks for real CT images, solving an important problem in medical image segmentation field when ground truth annotations are not available for the modality of interest.

Reliable 4D aircraft trajectory prediction, whether in a real-time setting or for analysis of counterfactuals, is important to the efficiency of the aviation system. Toward this end, we first propose a highly generalizable efficient tree-based matching algorithm to construct image-like feature maps from high-fidelity meteorological datasets - wind, temperature and convective weather. We then model the track points on trajectories as conditional Gaussian mixtures with parameters to be learned from our proposed deep generative model, which is an end-to-end convolutional recurrent neural network that consists of a long short-term memory (LSTM) encoder network and a mixture density LSTM decoder network. The encoder network embeds last-filed flight plan information into fixed-size hidden state variables and feeds the decoder network, which further learns the spatiotemporal correlations from the historical flight tracks and outputs the parameters of Gaussian mixtures. Convolutional layers are integrated into the pipeline to learn representations from the high-dimension weather features. During the inference process, beam search, adaptive Kalman filter, and Rauch-Tung-Striebel smoother algorithms are used to prune the variance of generated trajectories.