Yizhou Zhao

Ran Gong, Jiangyong Huang, Yizhou Zhao et al. · berkeley

Understanding the continuous states of objects is essential for task learning and planning in the real world. However, most existing task learning benchmarks assume discrete (e.g., binary) object goal states, which poses challenges for the learning of complex tasks and transferring learned policy from simulated environments to the real world. Furthermore, state discretization limits a robot's ability to follow human instructions based on the grounding of actions and states. To tackle these challenges, we present ARNOLD, a benchmark that evaluates language-grounded task learning with continuous states in realistic 3D scenes. ARNOLD is comprised of 8 language-conditioned tasks that involve understanding object states and learning policies for continuous goals. To promote language-instructed learning, we provide expert demonstrations with template-generated language descriptions. We assess task performance by utilizing the latest language-conditioned policy learning models. Our results indicate that current models for language-conditioned manipulations continue to experience significant challenges in novel goal-state generalizations, scene generalizations, and object generalizations. These findings highlight the need to develop new algorithms that address this gap and underscore the potential for further research in this area. Project website: https://arnold-benchmark.github.io.

Yizhou Zhao, Steven Gong, Xiaofeng Gao et al.

With the recent progress of simulations by 3D modeling software and game engines, many researchers have focused on Embodied AI tasks in the virtual environment. However, the research community lacks a platform that can easily serve both indoor scene synthesis and model benchmarking with various algorithms. Meanwhile, computer graphics-related tasks need a toolkit for implementing advanced synthesizing techniques. To facilitate the study of indoor scene building methods and their potential robotics applications, we introduce INDOORKIT: a built-in toolkit for NVIDIA OMNIVERSE that provides flexible pipelines for indoor scene building, scene randomizing, and animation controls. Besides, combining Python coding in the animation software INDOORKIT assists researchers in creating real-time training and controlling avatars and robotics. The source code for this toolkit is available at https://github.com/realvcla/VRKitchen2.0-Tutorial, and the tutorial along with the toolkit is available at https://vrkitchen20-tutorial.readthedocs.io/en/

Yizhou Zhao, Liang Qiu, Wensi Ai et al. · amazon-science, stanford

Dramatic progress has been made in animating individual characters. However, we still lack automatic control over activities between characters, especially those involving interactions. In this paper, we present a novel energy-based framework to sample and synthesize animations by associating the characters' body motions, facial expressions, and social relations. We propose a Spatial-Temporal And-Or graph (ST-AOG), a stochastic grammar model, to encode the contextual relationship between motion, emotion, and relation, forming a triangle in a conditional random field. We train our model from a labeled dataset of two-character interactions. Experiments demonstrate that our method can recognize the social relation between two characters and sample new scenes of vivid motion and emotion using Markov Chain Monte Carlo (MCMC) given the social relation. Thus, our method can provide animators with an automatic way to generate 3D character animations, help synthesize interactions between Non-Player Characters (NPCs), and enhance machine emotion intelligence (EQ) in virtual reality (VR).

Yizhou Zhao, Qiaozi Gao, Liang Qiu et al. · amazon-science

We introduce OPEND, a benchmark for learning how to use a hand to open cabinet doors or drawers in a photo-realistic and physics-reliable simulation environment driven by language instruction. To solve the task, we propose a multi-step planner composed of a deep neural network and rule-base controllers. The network is utilized to capture spatial relationships from images and understand semantic meaning from language instructions. Controllers efficiently execute the plan based on the spatial and semantic understanding. We evaluate our system by measuring its zero-shot performance in test data set. Experimental results demonstrate the effectiveness of decision planning by our multi-step planner for different hands, while suggesting that there is significant room for developing better models to address the challenge brought by language understanding, spatial reasoning, and long-term manipulation. We will release OPEND and host challenges to promote future research in this area.

Yizhou Zhao, Xun Guo, Yan Lu

One-shot object detection aims at detecting novel objects according to merely one given instance. With extreme data scarcity, current approaches explore various feature fusions to obtain directly transferable meta-knowledge. Yet, their performances are often unsatisfactory. In this paper, we attribute this to inappropriate correlation methods that misalign query-support semantics by overlooking spatial structures and scale variances. Upon analysis, we leverage the attention mechanism and propose a simple but effective architecture named Semantic-aligned Fusion Transformer (SaFT) to resolve these issues. Specifically, we equip SaFT with a vertical fusion module (VFM) for cross-scale semantic enhancement and a horizontal fusion module (HFM) for cross-sample feature fusion. Together, they broaden the vision for each feature point from the support to a whole augmented feature pyramid from the query, facilitating semantic-aligned associations. Extensive experiments on multiple benchmarks demonstrate the superiority of our framework. Without fine-tuning on novel classes, it brings significant performance gains to one-stage baselines, lifting state-of-the-art results to a higher level.

Yizhou Zhao, Zhenyang Li, Xun Guo et al.

Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more efficient in computation, the latter often obtains better performance. In this paper, we attribute this to a dilemma between the sufficiency and the efficiency of interactions among various positions in different frames. These interactions affect the extraction of task-relevant information shared among frames. To resolve this issue, we prove that frame-by-frame alignments have the potential to increase the mutual information between frame representations, thereby including more task-relevant information to boost effectiveness. Then we propose Alignment-guided Temporal Attention (ATA) to extend 1-dimensional temporal attention with parameter-free patch-level alignments between neighboring frames. It can act as a general plug-in for image backbones to conduct the action recognition task without any model-specific design. Extensive experiments on multiple benchmarks demonstrate the superiority and generality of our module.

Yizhou Zhao, Liang Qiu, Pan Lu et al.

Current pre-training methods in computer vision focus on natural images in the daily-life context. However, abstract diagrams such as icons and symbols are common and important in the real world. This work is inspired by Tangram, a game that requires replicating an abstract pattern from seven dissected shapes. By recording human experience in solving tangram puzzles, we present the Tangram dataset and show that a pre-trained neural model on the Tangram helps solve some mini visual tasks based on low-resolution vision. Extensive experiments demonstrate that our proposed method generates intelligent solutions for aesthetic tasks such as folding clothes and evaluating room layouts. The pre-trained feature extractor can facilitate the convergence of few-shot learning tasks on human handwriting and improve the accuracy in identifying icons by their contours. The Tangram dataset is available at https://github.com/yizhouzhao/Tangram.

Yizhou Zhao, Tuanfeng Y. Wang, Bhiksha Raj et al.

Remarkable strides have been made in reconstructing static scenes or human bodies from monocular videos. Yet, the two problems have largely been approached independently, without much synergy. Most visual SLAM methods can only reconstruct camera trajectories and scene structures up to scale, while most HMR methods reconstruct human meshes in metric scale but fall short in reasoning with cameras and scenes. This work introduces Synergistic Camera and Human Reconstruction (SynCHMR) to marry the best of both worlds. Specifically, we design Human-aware Metric SLAM to reconstruct metric-scale camera poses and scene point clouds using camera-frame HMR as a strong prior, addressing depth, scale, and dynamic ambiguities. Conditioning on the dense scene recovered, we further learn a Scene-aware SMPL Denoiser to enhance world-frame HMR by incorporating spatio-temporal coherency and dynamic scene constraints. Together, they lead to consistent reconstructions of camera trajectories, human meshes, and dense scene point clouds in a common world frame. Project page: https://paulchhuang.github.io/synchmr

Runmin Jiang, Genpei Zhang, Yuntian Yang et al. · cmu, harvard

Single-particle cryo-electron microscopy (cryo-EM) has become a cornerstone of structural biology, enabling near-atomic resolution analysis of macromolecules through advanced computational methods. However, the development of cryo-EM processing tools is constrained by the scarcity of high-quality annotated datasets. Synthetic data generation offers a promising alternative, but existing approaches lack thorough biophysical modeling of heterogeneity and fail to reproduce the complex noise observed in real imaging. To address these limitations, we present CryoCCD, a synthesis framework that unifies versatile biophysical modeling with the first conditional cycle-consistent diffusion model tailored for cryo-EM. The biophysical engine provides multi-functional generation capabilities to capture authentic biological organization, and the diffusion model is enhanced with cycle consistency and mask-guided contrastive learning to ensure realistic noise while preserving structural fidelity. Extensive experiments demonstrate that CryoCCD generates structurally faithful micrographs, enhances particle picking and pose estimation, as well as achieves superior performance over state-of-the-art baselines, while also generalizing effectively to held-out protein families.

Zhiwei Jia, Kaixiang Lin, Yizhou Zhao et al.

Recent years have witnessed an emerging paradigm shift toward embodied artificial intelligence, in which an agent must learn to solve challenging tasks by interacting with its environment. There are several challenges in solving embodied multimodal tasks, including long-horizon planning, vision-and-language grounding, and efficient exploration. We focus on a critical bottleneck, namely the performance of planning and navigation. To tackle this challenge, we propose a Neural SLAM approach that, for the first time, utilizes several modalities for exploration, predicts an affordance-aware semantic map, and plans over it at the same time. This significantly improves exploration efficiency, leads to robust long-horizon planning, and enables effective vision-and-language grounding. With the proposed Affordance-aware Multimodal Neural SLAM (AMSLAM) approach, we obtain more than 40% improvement over prior published work on the ALFRED benchmark and set a new state-of-the-art generalization performance at a success rate of 23.48% on the test unseen scenes.

Pan Lu, Liang Qiu, Jiaqi Chen et al.

Current visual question answering (VQA) tasks mainly consider answering human-annotated questions for natural images. However, aside from natural images, abstract diagrams with semantic richness are still understudied in visual understanding and reasoning research. In this work, we introduce a new challenge of Icon Question Answering (IconQA) with the goal of answering a question in an icon image context. We release IconQA, a large-scale dataset that consists of 107,439 questions and three sub-tasks: multi-image-choice, multi-text-choice, and filling-in-the-blank. The IconQA dataset is inspired by real-world diagram word problems that highlight the importance of abstract diagram understanding and comprehensive cognitive reasoning. Thus, IconQA requires not only perception skills like object recognition and text understanding, but also diverse cognitive reasoning skills, such as geometric reasoning, commonsense reasoning, and arithmetic reasoning. To facilitate potential IconQA models to learn semantic representations for icon images, we further release an icon dataset Icon645 which contains 645,687 colored icons on 377 classes. We conduct extensive user studies and blind experiments and reproduce a wide range of advanced VQA methods to benchmark the IconQA task. Also, we develop a strong IconQA baseline Patch-TRM that applies a pyramid cross-modal Transformer with input diagram embeddings pre-trained on the icon dataset. IconQA and Icon645 are available at https://iconqa.github.io.

Yizhou Zhao, Hua Sun

In the robust secure aggregation problem, a server wishes to learn and only learn the sum of the inputs of a number of users while some users may drop out (i.e., may not respond). The identity of the dropped users is not known a priori and the server needs to securely recover the sum of the remaining surviving users. We consider the following minimal two-round model of secure aggregation. Over the first round, any set of no fewer than $U$ users out of $K$ users respond to the server and the server wants to learn the sum of the inputs of all responding users. The remaining users are viewed as dropped. Over the second round, any set of no fewer than $U$ users of the surviving users respond (i.e., dropouts are still possible over the second round) and from the information obtained from the surviving users over the two rounds, the server can decode the desired sum. The security constraint is that even if the server colludes with any $T$ users and the messages from the dropped users are received by the server (e.g., delayed packets), the server is not able to infer any additional information beyond the sum in the information theoretic sense. For this information theoretic secure aggregation problem, we characterize the optimal communication cost. When $U \leq T$, secure aggregation is not feasible, and when $U > T$, to securely compute one symbol of the sum, the minimum number of symbols sent from each user to the server is $1$ over the first round, and $1/(U-T)$ over the second round.