Shaofeng Wang

Xianbing Sun, Zhikai Zhu, Zhengyu Lou et al.

Since DUSt3R, models such as VGGT and $π^3$ have shown strong multi-view 3D performance, but their heavy reliance on global self-attention results in high computational cost. Existing sparse-attention variants offer partial speedups, yet lack a systematic analysis of how global attention contributes to multi-view reasoning. In this paper, we first conduct an in-depth investigation of the global attention modules in VGGT and $π^3$ to better understand their roles. Our analysis reveals a clear division of roles in the alternating global-frame architecture: early global layers do not form meaningful correspondences, middle layers perform cross-view alignment, and last layers provide only minor refinements. Guided by these findings, we propose a training-free two-step acceleration scheme: (1) converting early global layers into frame attention, and (2) subsampling global attention by subsampling K/V over patch tokens with diagonal preservation and a mean-fill component. We instantiate this strategy on VGGT and $π^3$ and evaluate across standard pose and point-map benchmarks. Our method achieves up to $8$-$10\times$ speedup in inference time while matching or slightly improving the accuracy of the original models, and remains robust even in extremely dense multi-view settings where prior sparse-attention baselines fail.

He Wang, Yikun Zhang, Jie Chen et al.

Given usefulness of protein language models (LMs) in structure and functional inference, RNA LMs have received increased attentions in the last few years. However, these RNA models are often not compared against the same standard. Here, we divided RNA LMs into three classes (pretrained on multiple RNA types (especially noncoding RNAs), specific-purpose RNAs, and LMs that unify RNA with DNA or proteins or both) and compared 13 RNA LMs along with 3 DNA and 1 protein LMs as controls in zero-shot prediction of RNA secondary structure and functional classification. Results shows that the models doing well on secondary structure prediction often perform worse in function classification or vice versa, suggesting that more balanced unsupervised training is needed.

Jilong Wang, Javokhirbek Rajabov, Chaoyi Xu et al.

Legged robots with advanced manipulation capabilities have the potential to significantly improve household duties and urban maintenance. Despite considerable progress in developing robust locomotion and precise manipulation methods, seamlessly integrating these into cohesive whole-body control for real-world applications remains challenging. In this paper, we present a modular framework for robust and generalizable whole-body loco-manipulation controller based on a single arm-mounted camera. By using reinforcement learning (RL), we enable a robust low-level policy for command execution over 5 dimensions (5D) and a grasp-aware high-level policy guided by a novel metric, Generalized Oriented Reachability Map (GORM). The proposed system achieves state-of-the-art one-time grasping accuracy of 89% in the real world, including challenging tasks such as grasping transparent objects. Through extensive simulations and real-world experiments, we demonstrate that our system can effectively manage a large workspace, from floor level to above body height, and perform diverse whole-body loco-manipulation tasks.