Shuaihang Yuan

Jie Qin, Shuaihang Yuan, Jiaxin Chen et al.

Sketch-based 3D shape retrieval (SBSR) is an important yet challenging task, which has drawn more and more attention in recent years. Existing approaches address the problem in a restricted setting, without appropriately simulating real application scenarios. To mimic the realistic setting, in this track, we adopt large-scale sketches drawn by amateurs of different levels of drawing skills, as well as a variety of 3D shapes including not only CAD models but also models scanned from real objects. We define two SBSR tasks and construct two benchmarks consisting of more than 46,000 CAD models, 1,700 realistic models, and 145,000 sketches in total. Four teams participated in this track and submitted 15 runs for the two tasks, evaluated by 7 commonly-adopted metrics. We hope that, the benchmarks, the comparative results, and the open-sourced evaluation code will foster future research in this direction among the 3D object retrieval community.

Yu Hao, Fan Yang, Hao Huang et al.

People with blindness and low vision (pBLV) encounter substantial challenges when it comes to comprehensive scene recognition and precise object identification in unfamiliar environments. Additionally, due to the vision loss, pBLV have difficulty in accessing and identifying potential tripping hazards on their own. In this paper, we present a pioneering approach that leverages a large vision-language model to enhance visual perception for pBLV, offering detailed and comprehensive descriptions of the surrounding environments and providing warnings about the potential risks. Our method begins by leveraging a large image tagging model (i.e., Recognize Anything (RAM)) to identify all common objects present in the captured images. The recognition results and user query are then integrated into a prompt, tailored specifically for pBLV using prompt engineering. By combining the prompt and input image, a large vision-language model (i.e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing the environmental objects and scenes, relevant to the prompt. We evaluate our approach through experiments conducted on both indoor and outdoor datasets. Our results demonstrate that our method is able to recognize objects accurately and provide insightful descriptions and analysis of the environment for pBLV.

Yan Luo, Min Shi, Muhammad Osama Khan et al.

Fairness is a critical concern in deep learning, especially in healthcare, where these models influence diagnoses and treatment decisions. Although fairness has been investigated in the vision-only domain, the fairness of medical vision-language (VL) models remains unexplored due to the scarcity of medical VL datasets for studying fairness. To bridge this research gap, we introduce the first fair vision-language medical dataset Harvard-FairVLMed that provides detailed demographic attributes, ground-truth labels, and clinical notes to facilitate an in-depth examination of fairness within VL foundation models. Using Harvard-FairVLMed, we conduct a comprehensive fairness analysis of two widely-used VL models (CLIP and BLIP2), pre-trained on both natural and medical domains, across four different protected attributes. Our results highlight significant biases in all VL models, with Asian, Male, Non-Hispanic, and Spanish being the preferred subgroups across the protected attributes of race, gender, ethnicity, and language, respectively. In order to alleviate these biases, we propose FairCLIP, an optimal-transport-based approach that achieves a favorable trade-off between performance and fairness by reducing the Sinkhorn distance between the overall sample distribution and the distributions corresponding to each demographic group. As the first VL dataset of its kind, Harvard-FairVLMed holds the potential to catalyze advancements in the development of machine learning models that are both ethically aware and clinically effective. Our dataset and code are available at https://ophai.hms.harvard.edu/datasets/harvard-fairvlmed10k.

Congcong Wen, Yisiyuan Huang, Hao Huang et al.

Object navigation is crucial for robots, but traditional methods require substantial training data and cannot be generalized to unknown environments. Zero-shot object navigation (ZSON) aims to address this challenge, allowing robots to interact with unknown objects without specific training data. Language-driven zero-shot object navigation (L-ZSON) is an extension of ZSON that incorporates natural language instructions to guide robot navigation and interaction with objects. In this paper, we propose a novel Vision Language model with a Tree-of-thought Network (VLTNet) for L-ZSON. VLTNet comprises four main modules: vision language model understanding, semantic mapping, tree-of-thought reasoning and exploration, and goal identification. Among these modules, Tree-of-Thought (ToT) reasoning and exploration module serves as a core component, innovatively using the ToT reasoning framework for navigation frontier selection during robot exploration. Compared to conventional frontier selection without reasoning, navigation using ToT reasoning involves multi-path reasoning processes and backtracking when necessary, enabling globally informed decision-making with higher accuracy. Experimental results on PASTURE and RoboTHOR benchmarks demonstrate the outstanding performance of our model in LZSON, particularly in scenarios involving complex natural language as target instructions.

Congcong Wen, Jiazhao Liang, Shuaihang Yuan et al.

In the field of robotics and automation, navigation systems based on Large Language Models (LLMs) have recently demonstrated impressive performance. However, the security aspects of these systems have received relatively less attention. This paper pioneers the exploration of vulnerabilities in LLM-based navigation models in urban outdoor environments, a critical area given the widespread application of this technology in autonomous driving, logistics, and emergency services. Specifically, we introduce a novel Navigational Prompt Attack that manipulates LLM-based navigation models by perturbing the original navigational prompt, leading to incorrect actions. Based on the method of perturbation, our attacks are divided into two types: Navigational Prompt Insert (NPI) Attack and Navigational Prompt Swap (NPS) Attack. We conducted comprehensive experiments on an LLM-based navigation model that employs various LLMs for reasoning. Our results, derived from the Touchdown and Map2Seq street-view datasets under both few-shot learning and fine-tuning configurations, demonstrate notable performance declines across seven metrics in the face of both white-box and black-box attacks. Moreover, our attacks can be easily extended to other LLM-based navigation models with similarly effective results. These findings highlight the generalizability and transferability of the proposed attack, emphasizing the need for enhanced security in LLM-based navigation systems. As an initial countermeasure, we propose the Navigational Prompt Engineering (NPE) Defense strategy, which concentrates on navigation-relevant keywords to reduce the impact of adversarial attacks. While initial findings indicate that this strategy enhances navigational safety, there remains a critical need for the wider research community to develop stronger defense methods to effectively tackle the real-world challenges faced by these systems.

Hao Huang, Shuaihang Yuan, Yu Hao et al.

A large-scale vision and language model that has been pretrained on massive data encodes visual and linguistic prior, which makes it easier to generate images and language that are more natural and realistic. Despite this, there is still a significant domain gap between the modalities of vision and language, especially when training data is scarce in few-shot settings, where only very limited data are available for training. In order to mitigate this issue, a multi-modal meta-learning framework has been proposed to bridge the gap between two frozen pretrained large vision and language models by introducing a tunable prompt connecting these two large models. For few-shot image captioning, the existing multi-model meta-learning framework utilizes a one-step prompting scheme to accumulate the visual features of input images to guide the language model, which struggles to generate accurate image descriptions with only a few training samples. Instead, we propose a chain-of-thought (CoT) meta-learning scheme as a multi-step image captioning procedure to better imitate how humans describe images. In addition, we further propose to learn different meta-parameters of the model corresponding to each CoT step in distinct subspaces to avoid interference. We evaluated our method on three commonly used image captioning datasets, i.e., MSCOCO, Flickr8k, and Flickr30k, under few-shot settings. The results of our experiments indicate that our chain-of-thought subspace meta-learning strategy is superior to the baselines in terms of performance across different datasets measured by different metrics.

Congcong Wen, Geeta Chandra Raju Bethala, Yu Hao et al.

Humanoid loco-manipulation, which integrates whole-body locomotion with dexterous manipulation, remains a fundamental challenge in robotics. Beyond whole-body coordination and balance, a central difficulty lies in understanding human instructions and translating them into coherent sequences of embodied actions. Recent advances in foundation models provide transferable multimodal representations and reasoning capabilities, yet existing efforts remain largely restricted to either locomotion or manipulation in isolation, with limited applicability to humanoid settings. In this paper, we propose Humanoid-COA, the first humanoid agent framework that integrates foundation model reasoning with an Embodied Chain-of-Action (CoA) mechanism for zero-shot loco-manipulation. Within the perception--reasoning--action paradigm, our key contribution lies in the reasoning stage, where the proposed CoA mechanism decomposes high-level human instructions into structured sequences of locomotion and manipulation primitives through affordance analysis, spatial inference, and whole-body action reasoning. Extensive experiments on two humanoid robots, Unitree H1-2 and G1, in both an open test area and an apartment environment, demonstrate that our framework substantially outperforms prior baselines across manipulation, locomotion, and loco-manipulation tasks, achieving robust generalization to long-horizon and unstructured scenarios. Project page: https://humanoid-coa.github.io/

Yijie Deng, Shuaihang Yuan, Yi Fang

Image Goal Navigation (ImageNav) is evaluated by a coarse success criterion, the agent must stop within 1m of the target, which is sufficient for finding objects but falls short for downstream tasks such as grasping that require precise positioning. We introduce AnyImageNav, a training-free system that pushes ImageNav toward this more demanding setting. Our key insight is that the goal image can be treated as a geometric query: any photo of an object, a hallway, or a room corner can be registered to the agent's observations via dense pixel-level correspondences, enabling recovery of the exact 6-DoF camera pose. Our method realizes this through a semantic-to-geometric cascade: a semantic relevance signal guides exploration and acts as a proximity gate, invoking a 3D multi-view foundation model only when the current view is highly relevant to the goal image; the model then self-certifies its registration in a loop for an accurate recovered pose. Our method sets state-of-the-art navigation success rates on Gibson (93.1%) and HM3D (82.6%), and achieves pose recovery that prior methods do not provide: a position error of 0.27m and heading error of 3.41 degrees on Gibson, and 0.21m / 1.23 degrees on HM3D, a 5-10x improvement over adapted baselines.

Yijie Deng, Shuaihang Yuan, Geeta Chandra Raju Bethala et al.

Instance Image-Goal Navigation (IIN) requires autonomous agents to identify and navigate to a target object or location depicted in a reference image captured from any viewpoint. While recent methods leverage powerful novel view synthesis (NVS) techniques, such as three-dimensional Gaussian splatting (3DGS), they typically rely on randomly sampling multiple viewpoints or trajectories to ensure comprehensive coverage of discriminative visual cues. This approach, however, creates significant redundancy through overlapping image samples and lacks principled view selection, substantially increasing both rendering and comparison overhead. In this paper, we introduce a novel IIN framework with a hierarchical scoring paradigm that estimates optimal viewpoints for target matching. Our approach integrates cross-level semantic scoring, utilizing CLIP-derived relevancy fields to identify regions with high semantic similarity to the target object class, with fine-grained local geometric scoring that performs precise pose estimation within promising regions. Extensive evaluations demonstrate that our method achieves state-of-the-art performance on simulated IIN benchmarks and real-world applicability.

Halil Utku Unlu, Shuaihang Yuan, Congcong Wen et al.

We introduce an innovative approach to advancing semantic understanding in zero-shot object goal navigation (ZS-OGN), enhancing the autonomy of robots in unfamiliar environments. Traditional reliance on labeled data has been a limitation for robotic adaptability, which we address by employing a dual-component framework that integrates a GLIP Vision Language Model for initial detection and an InstructionBLIP model for validation. This combination not only refines object and environmental recognition but also fortifies the semantic interpretation, pivotal for navigational decision-making. Our method, rigorously tested in both simulated and real-world settings, exhibits marked improvements in navigation precision and reliability.

Shuaihang Yuan, Congcong Wen, Muhammad Shafique et al.

The rapid advances in audio analysis underscore its vast potential for humancomputer interaction, environmental monitoring, and public safety; yet, existing audioonly datasets often lack spatial context. To address this gap, we present two novel audiospatial scene datasets, AudioScanNet and AudioRoboTHOR, designed to explore audioconditioned tasks within 3D environments. By integrating audio clips with spatially aligned 3D scenes, our datasets enable research on how audio signals interact with spatial context. To associate audio events with corresponding spatial information, we leverage the common sense reasoning ability of large language models and supplement them with rigorous human verification, This approach offers greater scalability compared to purely manual annotation while maintaining high standards of accuracy, completeness, and diversity, quantified through inter annotator agreement and performance on two benchmark tasks audio based 3D visual grounding and audio based robotic zeroshot navigation. The results highlight the limitations of current audiocentric methods and underscore the practical challenges and significance of our datasets in advancing audio guided spatial learning.

Hao Huang, Geeta Chandra Raju Bethala, Shuaihang Yuan et al.

Whole-body humanoid motion represents a cornerstone challenge in robotics, integrating balance, coordination, and adaptability to enable human-like behaviors. However, existing methods typically require multiple training samples per motion category, rendering the collection of high-quality human motion datasets both labor-intensive and costly. To address this, we propose a novel approach that trains effective humanoid motion policies using only a single non-walking target motion sample alongside readily available walking motions. The core idea lies in leveraging order-preserving optimal transport to compute distances between walking and non-walking sequences, followed by interpolation along geodesics to generate new intermediate pose skeletons, which are then optimized for collision-free configurations and retargeted to the humanoid before integration into a simulated environment for policy training via reinforcement learning. Experimental evaluations on the CMU MoCap dataset demonstrate that our method consistently outperforms baselines, achieving superior performance across metrics. Code will be released upon acceptance.

Yijie Deng, Shuaihang Yuan, Congcong Wen et al.

Spatial awareness is a critical capability for embodied agents, as it enables them to anticipate and reason about unobserved regions. The primary challenge arises from learning the distribution of indoor semantics, complicated by sparse, imbalanced object categories and diverse spatial scales. Existing methods struggle to robustly generate unobserved areas in real time and do not generalize well to new environments. To this end, we propose \textbf{MapBERT}, a novel framework designed to effectively model the distribution of unseen spaces. Motivated by the observation that the one-hot encoding of semantic maps aligns naturally with the binary structure of bit encoding, we, for the first time, leverage a lookup-free BitVAE to encode semantic maps into compact bitwise tokens. Building on this, a masked transformer is employed to infer missing regions and generate complete semantic maps from limited observations. To enhance object-centric reasoning, we propose an object-aware masking strategy that masks entire object categories concurrently and pairs them with learnable embeddings, capturing implicit relationships between object embeddings and spatial tokens. By learning these relationships, the model more effectively captures indoor semantic distributions crucial for practical robotic tasks. Experiments on Gibson benchmarks show that MapBERT achieves state-of-the-art semantic map generation, balancing computational efficiency with accurate reconstruction of unobserved regions.

Yu Hao, Hao Huang, Shuaihang Yuan et al.

Learning robust 3D shape segmentation functions with deep neural networks has emerged as a powerful paradigm, offering promising performance in producing a consistent part segmentation of each 3D shape. Generalizing across 3D shape segmentation functions requires robust learning of priors over the respective function space and enables consistent part segmentation of shapes in presence of significant 3D structure variations. Existing generalization methods rely on extensive training of 3D shape segmentation functions on large-scale labeled datasets. In this paper, we proposed to formalize the learning of a 3D shape segmentation function space as a meta-learning problem, aiming to predict a 3D segmentation model that can be quickly adapted to new shapes with no or limited training data. More specifically, we define each task as unsupervised learning of shape-conditioned 3D segmentation function which takes as input points in 3D space and predicts the part-segment labels. The 3D segmentation function is trained by a self-supervised 3D shape reconstruction loss without the need for part labels. Also, we introduce an auxiliary deep neural network as a meta-learner which takes as input a 3D shape and predicts the prior over the respective 3D segmentation function space. We show in experiments that our meta-learning approach, denoted as Meta-3DSeg, leads to improvements on unsupervised 3D shape segmentation over the conventional designs of deep neural networks for 3D shape segmentation functions.

Shuaihang Yuan, Xiang Li, Anthony Tzes et al.

In this paper, we deal with the problem to predict the future 3D motions of 3D object scans from previous two consecutive frames. Previous methods mostly focus on sparse motion prediction in the form of skeletons. While in this paper we focus on predicting dense 3D motions in the from of 3D point clouds. To approach this problem, we propose a self-supervised approach that leverages the power of the deep neural network to learn a continuous flow function of 3D point clouds that can predict temporally consistent future motions and naturally bring out the correspondences among consecutive point clouds at the same time. More specifically, in our approach, to eliminate the unsolved and challenging process of defining a discrete point convolution on 3D point cloud sequences to encode spatial and temporal information, we introduce a learnable latent code to represent the temporal-aware shape descriptor which is optimized during model training. Moreover, a temporally consistent motion Morpher is proposed to learn a continuous flow field which deforms a 3D scan from the current frame to the next frame. We perform extensive experiments on D-FAUST, SCAPE and TOSCA benchmark data sets and the results demonstrate that our approach is capable of handling temporally inconsistent input and produces consistent future 3D motion while requiring no ground truth supervision.

Shuaihang Yuan, Xiang Li, Yi Fang

This paper deals with the problem of 3D tracking, i.e., to find dense correspondences in a sequence of time-varying 3D shapes. Despite deep learning approaches have achieved promising performance for pairwise dense 3D shapes matching, it is a great challenge to generalize those approaches for the tracking of 3D time-varying geometries. In this paper, we aim at handling the problem of 3D tracking, which provides the tracking of the consecutive frames of 3D shapes. We propose a novel unsupervised 3D shape registration framework named DeepTracking-Net, which uses the deep neural networks (DNNs) as auxiliary functions to produce spatially and temporally continuous displacement fields for 3D tracking of objects in a temporal order. Our key novelty is that we present a novel temporal-aware correspondence descriptor (TCD) that captures spatio-temporal essence from consecutive 3D point cloud frames. Specifically, our DeepTracking-Net starts with optimizing a randomly initialized latent TCD. The TCD is then decoded to regress a continuous flow (i.e. a displacement vector field) which assigns a motion vector to every point of time-varying 3D shapes. Our DeepTracking-Net jointly optimizes TCDs and DNNs' weights towards the minimization of an unsupervised alignment loss. Experiments on both simulated and real data sets demonstrate that our unsupervised DeepTracking-Net outperforms the current supervised state-of-the-art method. In addition, we prepare a new synthetic 3D data, named SynMotions, to the 3D tracking and recognition community.