-
[ICCV 2023 Oral] UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning
We propose a novel, object-agnostic method for learning a universal policy for dexterous object grasping from realistic point cloud observations and proprioceptive information under a table-top setting, namely UniDexGrasp++.
Aug 17 / 2023 -
[ICML 2023] Which Invariance Should We Transfer? A Causal Minimax Approach
Compared to previous methods, the obtained stable predictors are more effective in identifying stable information. However, a key question remains: which subset of this whole stable information should the model transfer, in order to achieve optimal generalization ability?
Aug 15 / 2023 -
[ICML 2023] Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets
We propose algorithms that guarantee every client a higher utility than the best she can get under independent bidding.
Jul 21 / 2023 -
[ICCV 2023] MotionBERT: A Unified Perspective on Learning Human Motion Representations
We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources.
Jul 18 / 2023 -
[ICML 2023] Near-Optimal Quantum Coreset Construction Algorithms for Clustering
Our coreset reduces the input size from n to poly(kϵ^{−1}d), so that existing α-approximation algorithms for clustering can run on top of it and yield (1+ϵ)α-approximation.
Jul 12 / 2023 -
[ICML 2023] Are Equivariant Equilibrium Approximators Beneficial?
In this paper, we theoretically characterize benefits and limitations of equivariant equilibrium approximators.
Jun 20 / 2023 -
[Eurocrypt 2023] New Ways to Garble Arithmetic Circuits
In this work, we present new ways to garble arithmetic circuits, which improve the state-of-the-art on efficiency, modularity, and functionality.
May 25 / 2023 -
[CVPR 2023] 3D Human Mesh Estimation from Virtual Markers
In this work, we present an intermedi- ate representation, named virtual markers, which learns 64 landmark keypoints on the body surface based on the large-scale mocap data in a generative style, mimicking the effects of physical markers.
May 23 / 2023 -
[RA-L 2023] Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation
We propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation.
May 08 / 2023 -
[ICML 2023] The Power of Uniform Sampling for k-Median
We show that any algorithm must make Ω(1/β) queries to the point set in order to achieve O(1)-approximation for k-Median.
May 05 / 2023 -
[ICLR 2023] On The Relative Error of Random Fourier Features for Preserving Kernel Distance
We show that for a significant range of kernels, including the well-known Laplacian kernels, RFF cannot approximate the kernel distance with small relative error using low dimensions.
Apr 28 / 2023 -
[CVPR 2023] UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
In this work, we tackle the problem of learning universal robotic dexterous grasping from a point cloud observation under a table-top setting.
Apr 17 / 2023 -
[CVPR 2023] GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts
We propose a robust 3D segmentation method from the perspective of domain generalization by integrating adversarial learning techniques.
Apr 06 / 2023 -
[CVPR 2023] GFPose: Learning 3D Human Pose Prior with Gradient Fields
Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose, a versatile framework to model plausible 3D human poses for various applications.
Mar 22 / 2023 -
[Physical Review Letter] Low-Depth Hamiltonian Simulation by an Adaptive Product Formula
Here, focusing on the time evolution of a fixed input quantum state, we propose an adaptive approach to construct a low-depth time evolution circuit.
Mar 14 / 2023 -
[ICRA 2023] DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation
本文是国际机器人和自动化顶级会议 ICRA 2023入选论文 DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation 的解读。
Mar 11 / 2023 -
Dr. Xiao Yuan is Selected as APS Outstanding Referees for 2022
On February 24th, 2023, the American Physical Society (APS) announces 153 Outstanding Referees for 2022 that have demonstrated exceptional work in the assessment of manuscripts published in the Physical Review journals.
Mar 03 / 2023 -
[AAMAS 2023] Is Nash Equilibrium Approximator Learnable?
In this paper, we investigate the learnability of the function approximator that approximates Nash equilibrium (NE) for games generated from a distribution.
Feb 17 / 2023 -
[AAAI 2023 Oral] Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild
In this work, we tackle the challenging task of jointly tracking hand object pose and reconstructing their shapes from depth point cloud sequences in the wild, given the initial poses at frame 0.
Feb 15 / 2023 -
[ICLR 2023] Near-optimal Coresets for Robust Clustering
We consider robust clustering problems in Rd, specifically k-clustering problems (e.g., k-Median and k-Means with m outliers, where the cost for a given center set C⊂Rd aggregates the distances from C to all but the furthest m data points.
Feb 14 / 2023