Search

Optimizing the learning rate remains a critical challenge in machine learning, essential for achieving model stability and efficient convergence. The Vector Auxiliary Variable (VAV) algorithm introduces a novel energy-based self-adjustable learning rate optimization method designed for unconstrained optimization problems. It incorporates an auxiliary variable $r$ to facilitate efficient energy approximation without backtracking while adhering to the unconditional energy dissipation law. Notably, VAV demonstrates superior stability with larger learning rates and achieves faster convergence in the early stage of the training process. Comparative analyses demonstrate that VAV outperforms Stochastic Gradient Descent (SGD) across various tasks. This paper also provides rigorous proof of the energy dissipation law and establishes the convergence of the algorithm under reasonable assumptions. Additionally, $r$ acts as an empirical lower bound of the training loss in practice, offering a novel scheduling approach that further enhances algorithm performance.

Introducing structural and/or chemical heterogeneity into otherwise ordered crystals can dramatically alter material properties. Lead-based relaxor ferroelectrics are a prototypical example, with decades of investigation having connected chemical and structural heterogeneity to their unique properties. While theory has pointed to the formation of an ensemble of ``slush''-like polar domains, the lack of direct, spatially resolved volumetric data comparable to simulations presents a significant challenge in measuring the spatial distribution and correlation of local chemistry and structure with the physics underlying relaxor behavior. Here, we address this challenge through three-dimensional volumetric characterization of the prototypical relaxor ferroelectric \ce{0.68Pb(Mg$_{1/3}$Nb$_{2/3}$)O3-0.32PbTiO$_3$} using multislice electron ptychography. Direct comparison with molecular dynamics simulations reveals the intimate relationship between the polar structure and unit-cell level charge imbalance induced by chemical disorder. Further, polar nanodomains are maintained through local correlations arising from residual short-range chemical order. Acting in concert with the chemical heterogeneities, it is also shown that compressive strain enhances out-of-plane correlations and ferroelectric-like order without affecting the in-plane relaxor-like structure. Broadly, these findings provide a pathway to enable detailed atomic scale understanding for hierarchical control of polar domains in relaxor ferroelectric materials and devices, and also present significant opportunities to tackle other heterogeneous systems using complementary theoretical and experimental studies.

As Large Language Models (LLMs) are increasingly being deployed in safety-critical applications, their vulnerability to potential jailbreaks -- malicious prompts that can disable the safety mechanism of LLMs -- has attracted growing research attention. While alignment methods have been proposed to protect LLMs from jailbreaks, many have found that aligned LLMs can still be jailbroken by carefully crafted malicious prompts, producing content that violates policy regulations. Existing jailbreak attacks on LLMs can be categorized into prompt-level methods which make up stories/logic to circumvent safety alignment and token-level attack methods which leverage gradient methods to find adversarial tokens. In this work, we introduce the concept of Ensemble Jailbreak and explore methods that can integrate prompt-level and token-level jailbreak into a more powerful hybrid jailbreak attack. Specifically, we propose a novel EnJa attack to hide harmful instructions using prompt-level jailbreak, boost the attack success rate using a gradient-based attack, and connect the two types of jailbreak attacks via a template-based connector. We evaluate the effectiveness of EnJa on several aligned models and show that it achieves a state-of-the-art attack success rate with fewer queries and is much stronger than any individual jailbreak.

Large language models (LLMs) have recently showcased remarkable capabilities, spanning a wide range of tasks and applications, including those in the medical domain. Models like GPT-4 excel in medical question answering but may face challenges in the lack of interpretability when handling complex tasks in real clinical settings. We thus introduce the diagnostic reasoning dataset for clinical notes (DiReCT), aiming at evaluating the reasoning ability and interpretability of LLMs compared to human doctors. It contains 511 clinical notes, each meticulously annotated by physicians, detailing the diagnostic reasoning process from observations in a clinical note to the final diagnosis. Additionally, a diagnostic knowledge graph is provided to offer essential knowledge for reasoning, which may not be covered in the training data of existing LLMs. Evaluations of leading LLMs on DiReCT bring out a significant gap between their reasoning ability and that of human doctors, highlighting the critical need for models that can reason effectively in real-world clinical scenarios., Comment: 9 pages,6 figures

We study the challenging problem of simultaneously localizing a sequence of queries in the form of instructional diagrams in a video. This requires understanding not only the individual queries but also their interrelationships. However, most existing methods focus on grounding one query at a time, ignoring the inherent structures among queries such as the general mutual exclusiveness and the temporal order. Consequently, the predicted timespans of different step diagrams may overlap considerably or violate the temporal order, thus harming the accuracy. In this paper, we tackle this issue by simultaneously grounding a sequence of step diagrams. Specifically, we propose composite queries, constructed by exhaustively pairing up the visual content features of the step diagrams and a fixed number of learnable positional embeddings. Our insight is that self-attention among composite queries carrying different content features suppress each other to reduce timespan overlaps in predictions, while the cross-attention corrects the temporal misalignment via content and position joint guidance. We demonstrate the effectiveness of our approach on the IAW dataset for grounding step diagrams and the YouCook2 benchmark for grounding natural language queries, significantly outperforming existing methods while simultaneously grounding multiple queries.

The imperative to comprehend the behaviors of deep learning models is of utmost importance. In this realm, Explainable Artificial Intelligence (XAI) has emerged as a promising avenue, garnering increasing interest in recent years. Despite this, most existing methods primarily depend on gradients or input perturbation, which often fails to embed explanations directly within the model's decision-making process. Addressing this gap, we introduce ESCOUTER, a visually explainable classifier based on the modified slot attention mechanism. ESCOUTER distinguishes itself by not only delivering high classification accuracy but also offering more transparent insights into the reasoning behind its decisions. It differs from prior approaches in two significant aspects: (a) ESCOUTER incorporates explanations into the final confidence scores for each category, providing a more intuitive interpretation, and (b) it offers positive or negative explanations for all categories, elucidating "why an image belongs to a certain category" or "why it does not." A novel loss function specifically for ESCOUTER is designed to fine-tune the model's behavior, enabling it to toggle between positive and negative explanations. Moreover, an area loss is also designed to adjust the size of the explanatory regions for a more precise explanation. Our method, rigorously tested across various datasets and XAI metrics, outperformed previous state-of-the-art methods, solidifying its effectiveness as an explanatory tool., Comment: 16 pages, 12 figures

Given the increasing complexity of AI applications, traditional spatial architectures frequently fall short. Our analysis identifies a pattern of interconnected, multi-faceted tasks encompassing both AI and general computational processes. In response, we have conceptualized "Orchestrated AI Workflows," an approach that integrates various tasks with logic-driven decisions into dynamic, sophisticated workflows. Specifically, we find that the intrinsic Dual Dynamicity of Orchestrated AI Workflows, namely dynamic execution times and frequencies of Task Blocks, can be effectively represented using the Orchestrated Workflow Graph. Furthermore, the intrinsic Dual Dynamicity poses challenges to existing spatial architecture, namely Indiscriminate Resource Allocation, Reactive Load Rebalancing, and Contagious PEA Idleness. To overcome these challenges, we present Octopus, a scale-out spatial architecture and a suite of advanced scheduling strategies optimized for executing Orchestrated AI Workflows, such as the Discriminate Dual-Scheduling Mechanism, Adaptive TBU Scheduling Strategy, and Proactive Cluster Scheduling Strategy. Our evaluations demonstrate that Octopus significantly outperforms traditional architectures in handling the dynamic demands of Orchestrated AI Workflows, and possesses robust scalability in large scale hardware such as wafer-scale chip.

The nature of the "failed" ferroelectric transition in SrTiO3 has been a long-standing puzzle in condensed matter physics. A compelling explanation is the competition between ferroelectricity and an instability with a mesoscopic modulation of the polarization. These polarization density waves, which should become especially strong near the quantum critical point, break local inversion symmetry and are difficult to probe with conventional x-ray scattering methods. Here we combine a femtosecond x-ray free electron laser (XFEL) with THz coherent control methods to probe inversion symmetry breaking at finite momenta and visualize the instability of the polarization on nanometer lengthscales in SrTiO3. We find polar-acoustic collective modes that are soft particularly at the tens of nanometer lengthscale. These precursor collective excitations provide evidence for the conjectured mesoscopic modulated phase in SrTiO3.

Decentralized Storage Network (DSN) is an emerging technology that challenges traditional cloud-based storage systems by consolidating storage capacities from independent providers and coordinating to provide decentralized storage and retrieval services. However, current DSNs face several challenges associated with data privacy and efficiency of the proof systems. To address these issues, we propose FileDES (\uline{D}ecentralized \uline{E}ncrypted \uline{S}torage), which incorporates three essential elements: privacy preservation, scalable storage proof, and batch verification. FileDES provides encrypted data storage while maintaining data availability, with a scalable Proof of Encrypted Storage (PoES) algorithm that is resilient to Sybil and Generation attacks. Additionally, we introduce a rollup-based batch verification approach to simultaneously verify multiple files using publicly verifiable succinct proofs. We conducted a comparative evaluation on FileDES, Filecoin, Storj and Sia under various conditions, including a WAN composed of up to 120 geographically dispersed nodes. Our protocol outperforms the others in terms of proof generation/verification efficiency, storage costs, and scalability., Comment: 10 pages, 8 figures, 1 table. Accepted by 2024 IEEE INFOCOM

Graph Neural Networks (GNNs) have achieved remarkable success in various real-world applications. However, GNNs may be trained on undesirable graph data, which can degrade their performance and reliability. To enable trained GNNs to efficiently unlearn unwanted data, a desirable solution is retraining-based graph unlearning, which partitions the training graph into subgraphs and trains sub-models on them, allowing fast unlearning through partial retraining. However, the graph partition process causes information loss in the training graph, resulting in the low model utility of sub-GNN models. In this paper, we propose GraphRevoker, a novel graph unlearning framework that better maintains the model utility of unlearnable GNNs. Specifically, we preserve the graph property with graph property-aware sharding and effectively aggregate the sub-GNN models for prediction with graph contrastive sub-model aggregation. We conduct extensive experiments to demonstrate the superiority of our proposed approach., Comment: 8 pages, 3 figures, accepted by The Web Conference 2024 (PhD Symposium Track)

In an era of information explosion, recommender systems are vital tools to deliver personalized recommendations for users. The key of recommender systems is to forecast users' future behaviors based on previous user-item interactions. Due to their strong expressive power of capturing high-order connectivities in user-item interaction data, recent years have witnessed a rising interest in leveraging Graph Neural Networks (GNNs) to boost the prediction performance of recommender systems. Nonetheless, classic Matrix Factorization (MF) and Deep Neural Network (DNN) approaches still play an important role in real-world large-scale recommender systems due to their scalability advantages. Despite the existence of GNN-acceleration solutions, it remains an open question whether GNN-based recommender systems can scale as efficiently as classic MF and DNN methods. In this paper, we propose a Linear-Time Graph Neural Network (LTGNN) to scale up GNN-based recommender systems to achieve comparable scalability as classic MF approaches while maintaining GNNs' powerful expressiveness for superior prediction accuracy. Extensive experiments and ablation studies are presented to validate the effectiveness and scalability of the proposed algorithm. Our implementation based on PyTorch is available., Comment: 12 pages, 5 figures, accepted by The Web Conference 2024

With the rapid development of blockchain and its applications, the amount of data stored on decentralized storage networks (DSNs) has grown exponentially. DSNs bring together affordable storage resources from around the world to provide robust, decentralized storage services for tens of thousands of decentralized applications (dApps). However, existing DSNs do not offer verifiability when implementing erasure coding for redundant storage, making them vulnerable to Byzantine encoders. Additionally, there is a lack of Byzantine fault-tolerant consensus for optimal resilience in DSNs. This paper introduces BFT-DSN, a Byzantine fault-tolerant decentralized storage network designed to address these challenges. BFT-DSN combines storage-weighted BFT consensus with erasure coding and incorporates homomorphic fingerprints and weighted threshold signatures for decentralized verification. The implementation of BFT-DSN demonstrates its comparable performance in terms of storage cost and latency as well as superior performance in Byzantine resilience when compared to existing industrial decentralized storage networks., Comment: 11 pages, 8 figures

Quantization is a crucial technique for deploying deep learning models on resource-constrained devices, such as embedded FPGAs. Prior efforts mostly focus on quantizing matrix multiplications, leaving other layers like BatchNorm or shortcuts in floating-point form, even though fixed-point arithmetic is more efficient on FPGAs. A common practice is to fine-tune a pre-trained model to fixed-point for FPGA deployment, but potentially degrading accuracy. This work presents QFX, a novel trainable fixed-point quantization approach that automatically learns the binary-point position during model training. Additionally, we introduce a multiplier-free quantization strategy within QFX to minimize DSP usage. QFX is implemented as a PyTorch-based library that efficiently emulates fixed-point arithmetic, supported by FPGA HLS, in a differentiable manner during backpropagation. With minimal effort, models trained with QFX can readily be deployed through HLS, producing the same numerical results as their software counterparts. Our evaluation shows that compared to post-training quantization, QFX can quantize models trained with element-wise layers quantized to fewer bits and achieve higher accuracy on both CIFAR-10 and ImageNet datasets. We further demonstrate the efficacy of multiplier-free quantization using a state-of-the-art binarized neural network accelerator designed for an embedded FPGA (AMD Xilinx Ultra96 v2). We plan to release QFX in open-source format.

Recent advancements in large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. The majority of existing approaches rely on temporal architectures that reuse hardware units for different network layers and operators. However, these methods often encounter challenges in achieving low latency due to considerable memory access overhead. This paper investigates the feasibility and potential of model-specific spatial acceleration for LLM inference on FPGAs. Our approach involves the specialization of distinct hardware units for specific operators or layers, facilitating direct communication between them through a dataflow architecture while minimizing off-chip memory accesses. We introduce a comprehensive analytical model for estimating the performance of a spatial LLM accelerator, taking into account the on-chip compute and memory resources available on an FPGA. Through our analysis, we can determine the scenarios in which FPGA-based spatial acceleration can outperform its GPU-based counterpart. To enable more productive implementations of an LLM model on FPGAs, we further provide a library of high-level synthesis (HLS) kernels that are composable and reusable. This library will be made available as open-source. To validate the effectiveness of both our analytical model and HLS library, we have implemented BERT and GPT2 on an AMD Alveo U280 FPGA device. Experimental results demonstrate our approach can achieve up to 13.4x speedup when compared to previous FPGA-based accelerators for the BERT model. For GPT generative inference, we attain a 2.2x speedup compared to DFX, an FPGA overlay, in the prefill stage, while achieving a 1.9x speedup and a 5.7x improvement in energy efficiency compared to the NVIDIA A100 GPU in the decode stage., Comment: Accepted for publication in the FCCM'24 Journal Track and will appear in ACM Transactions on Reconfigurable Technology and Systems (TRETS)

The success of Bayesian persuasion relies on the key assumption that the sender will commit to a predetermined information disclosure policy (signaling scheme). However, in practice, it is usually difficult for the receiver to monitor whether the sender sticks to the disclosure policy, which makes the credibility of the sender's disclosure policy questionable. The sender's credibility is particularly tenuous when there are obvious deviations that benefit the sender. In this work, we identify such a deviation: the sender may be unwilling to send a signal that will lead to a less desirable outcome compared to no information disclosure. We thus propose the notion of ex-post individually rational (ex-post IR) Bayesian persuasion: after observing the state, the sender is never required to send a signal that will make the outcome worse off (compared to no information disclosure). An ex-post IR Bayesian persuasion policy is more likely to be truthfully followed by the sender, and thus more credible for the receiver. Our contribution is threefold. Firstly, we demonstrate that the optimal ex-post IR Bayesian persuasion policy can be efficiently computed through a linear program, while also offering geometric characterizations of this optimal policy. Second, we show that surprisingly, for non-trivial classes of games, the imposition of ex-post IR constraints does not affect the sender's expected utility. Finally, we compare ex-post IR Bayesian persuasion to other information disclosure models that ensure different notions of credibility., Comment: 21 pages

In this paper, we investigate a problem of actively learning threshold in latent space, where the unknown reward $g(\gamma, v)$ depends on the proposed threshold $\gamma$ and latent value $v$ and it can be $only$ achieved if the threshold is lower than or equal to the unknown latent value. This problem has broad applications in practical scenarios, e.g., reserve price optimization in online auctions, online task assignments in crowdsourcing, setting recruiting bars in hiring, etc. We first characterize the query complexity of learning a threshold with the expected reward at most $\epsilon$ smaller than the optimum and prove that the number of queries needed can be infinitely large even when $g(\gamma, v)$ is monotone with respect to both $\gamma$ and $v$. On the positive side, we provide a tight query complexity $\tilde{\Theta}(1/\epsilon^3)$ when $g$ is monotone and the CDF of value distribution is Lipschitz. Moreover, we show a tight $\tilde{\Theta}(1/\epsilon^3)$ query complexity can be achieved as long as $g$ satisfies one-sided Lipschitzness, which provides a complete characterization for this problem. Finally, we extend this model to an online learning setting and demonstrate a tight $\Theta(T^{2/3})$ regret bound using continuous-arm bandit techniques and the aforementioned query complexity results., Comment: 18 pages

Large-scale models trained on extensive datasets, have emerged as the preferred approach due to their high generalizability across various tasks. In-context learning (ICL), a popular strategy in natural language processing, uses such models for different tasks by providing instructive prompts but without updating model parameters. This idea is now being explored in computer vision, where an input-output image pair (called an in-context pair) is supplied to the model with a query image as a prompt to exemplify the desired output. The efficacy of visual ICL often depends on the quality of the prompts. We thus introduce a method coined Instruct Me More (InMeMo), which augments in-context pairs with a learnable perturbation (prompt), to explore its potential. Our experiments on mainstream tasks reveal that InMeMo surpasses the current state-of-the-art performance. Specifically, compared to the baseline without learnable prompt, InMeMo boosts mIoU scores by 7.35 and 15.13 for foreground segmentation and single object detection tasks, respectively. Our findings suggest that InMeMo offers a versatile and efficient way to enhance the performance of visual ICL with lightweight training. Code is available at https://github.com/Jackieam/InMeMo., Comment: Accepted at WACV 2024

Nowadays, artificial intelligence (AI) technology with large models plays an increasingly important role in both academia and industry. It also brings a rapidly increasing demand for the computing power of the hardware. As the computing demand for AI continues to grow, the growth of hardware computing power has failed to keep up. This has become a significant factor restricting the development of AI. The augmentation of hardware computing power is mainly propelled by the escalation of transistor density and chip area. However, the former is impeded by the termination of the Moore's Law and Dennard scaling, and the latter is significantly restricted by the challenge of disrupting the legacy fabrication equipment and process. In recent years, advanced packaging technologies that have gradually matured are increasingly used to implement bigger chips that integrate multiple chiplets, while still providing interconnections with chip-level density and bandwidth. Compared to conventional high-performance computing paradigms such as multi-accelerator and datacenter-scale computing, Wafer-scale Computing shows remarkable advantages in communication bandwidth, integration density, and programmability potential. Not surprisingly, disruptive Wafer-scale Computing also brings unprecedented design challenges for hardware architecture, design-system-technology co-optimization, power and cooling systems, and compiler tool chain. At present, there are no comprehensive surveys summarizing the current state and design insights of Wafer-scale Computing. This paper aims to take the first step to help academia and industry review existing wafer-scale chips and essential technologies in a one-stop manner. So that people can conveniently grasp the basic knowledge and key points, understand the achievements and shortcomings of existing research, and contribute to this promising research direction.

We present a novel optimization algorithm, element-wise relaxed scalar auxiliary variable (E-RSAV), that satisfies an unconditional energy dissipation law and exhibits improved alignment between the modified and the original energy. Our algorithm features rigorous proofs of linear convergence in the convex setting. Furthermore, we present a simple accelerated algorithm that improves the linear convergence rate to super-linear in the univariate case. We also propose an adaptive version of E-RSAV with Steffensen step size. We validate the robustness and fast convergence of our algorithm through ample numerical experiments., Comment: 25 pages, 7 figures

While many piezoelectric materials are known, there is still great potential to improve on the figures of merit of existing materials through compositional doping, forming solid solutions. Specifically, it has been shown that doping and alloying wurtzite-structured materials can improve the piezoelectric response; however, a vast compositional space has remained unexplored. In this work, we apply a multi-level screening protocol combining machine learning, chemical intuition, and thermodynamics to systematically discover dopant combinations in wurtzite material space that improve the desired piezoelectric response. Through our protocol, we use computationally inexpensive screening calculations to consider more than 3000 possible ternary wurtzite solid solutions from 9 different wurtzite base systems: AlN, BeO, CdS, CdSe, GaN, ZnO, ZnS, ZnSe, and AgI. Finally, based on thermodynamic analysis and explicit piezoelectric response calculations, we predict 11 materials with improved piezoelectric response, due to the incorporation of electropositive dopants.

Multi-hop question answering (QA) involves finding multiple relevant passages and step-by-step reasoning to answer complex questions, indicating a retrieve-and-read paradigm. However, previous retrievers were customized for two-hop questions, and most of them were trained separately across different hops, resulting in a lack of supervision over the entire multi-hop retrieval process and leading to poor performance in complicated scenarios beyond two hops. In this work, we introduce Beam Retrieval, an end-to-end beam retrieval framework for multi-hop QA. This approach models the multi-hop retrieval process in an end-to-end manner by jointly optimizing an encoder and two classification heads across all hops. Moreover, Beam Retrieval maintains multiple partial hypotheses of relevant passages at each step, expanding the search space and reducing the risk of missing relevant passages. To establish a complete QA system, we incorporate a supervised reader or a large language model (LLM). Experimental results demonstrate that Beam Retrieval achieves a nearly 50% improvement compared with baselines on challenging MuSiQue-Ans, and it also surpasses all previous retrievers on HotpotQA and achieves 99.9% precision on 2WikiMultiHopQA. Providing high-quality context, Beam Retrieval helps our supervised reader achieve new state-of-the-art performance and substantially improves the few-shot QA performance of LLMs., Comment: Accepted by NAACL 2024 Main Conference. Code is available at https://github.com/canghongjian/beam_retriever

Spatial architecture is a high-performance architecture that uses control flow graphs and data flow graphs as the computational model and producer/consumer models as the execution models. However, existing spatial architectures suffer from control flow handling challenges. Upon categorizing their PE execution models, we find that they lack autonomous, peer-to-peer, and temporally loosely-coupled control flow handling capability. This leads to limited performance in intensive control programs. A spatial architecture, Marionette, is proposed, with an explicit-designed control flow plane. The Control Flow Plane enables autonomous, peer-to-peer and temporally loosely-coupled control flow handling. The Proactive PE Configuration ensures timely and computation-overlapped configuration to improve handling Branch Divergence. The Agile PE Assignment enhance the pipeline performance of Imperfect Loops. We develop full stack of Marionette (ISA, compiler, simulator, RTL) and demonstrate that in a variety of challenging intensive control programs, compared to state-of-the-art spatial architectures, Marionette outperforms Softbrain, TIA, REVEL, and RipTide by geomean 2.88x, 3.38x, 1.55x, and 2.66x.

Energy-Dissipative Evolutionary Deep Operator Neural Network is an operator learning neural network. It is designed to seed numerical solutions for a class of partial differential equations instead of a single partial differential equation, such as partial differential equations with different parameters or different initial conditions. The network consists of two sub-networks, the Branch net and the Trunk net. For an objective operator G, the Branch net encodes different input functions u at the same number of sensors, and the Trunk net evaluates the output function at any location. By minimizing the error between the evaluated output q and the expected output G(u)(y), DeepONet generates a good approximation of the operator G. In order to preserve essential physical properties of PDEs, such as the Energy Dissipation Law, we adopt a scalar auxiliary variable approach to generate the minimization problem. It introduces a modified energy and enables unconditional energy dissipation law at the discrete level. By taking the parameter as a function of time t, this network can predict the accurate solution at any further time with feeding data only at the initial state. The data needed can be generated by the initial conditions, which are readily available. In order to validate the accuracy and efficiency of our neural networks, we provide numerical simulations of several partial differential equations, including heat equations, parametric heat equations and Allen-Cahn equations., Comment: 18 pages

The current transformation towards smart manufacturing has led to a growing demand for human-robot collaboration (HRC) in the manufacturing process. Perceiving and understanding the human co-worker's behaviour introduces challenges for collaborative robots to efficiently and effectively perform tasks in unstructured and dynamic environments. Integrating recent data-driven machine vision capabilities into HRC systems is a logical next step in addressing these challenges. However, in these cases, off-the-shelf components struggle due to generalisation limitations. Real-world evaluation is required in order to fully appreciate the maturity and robustness of these approaches. Furthermore, understanding the pure-vision aspects is a crucial first step before combining multiple modalities in order to understand the limitations. In this paper, we propose GoferBot, a novel vision-based semantic HRC system for a real-world assembly task. It is composed of a visual servoing module that reaches and grasps assembly parts in an unstructured multi-instance and dynamic environment, an action recognition module that performs human action prediction for implicit communication, and a visual handover module that uses the perceptual understanding of human behaviour to produce an intuitive and efficient collaborative assembly experience. GoferBot is a novel assembly system that seamlessly integrates all sub-modules by utilising implicit semantic information purely from visual perception.

Multimodal alignment facilitates the retrieval of instances from one modality when queried using another. In this paper, we consider a novel setting where such an alignment is between (i) instruction steps that are depicted as assembly diagrams (commonly seen in Ikea assembly manuals) and (ii) video segments from in-the-wild videos; these videos comprising an enactment of the assembly actions in the real world. To learn this alignment, we introduce a novel supervised contrastive learning method that learns to align videos with the subtle details in the assembly diagrams, guided by a set of novel losses. To study this problem and demonstrate the effectiveness of our method, we introduce a novel dataset: IAW for Ikea assembly in the wild consisting of 183 hours of videos from diverse furniture assembly collections and nearly 8,300 illustrations from their associated instruction manuals and annotated for their ground truth alignments. We define two tasks on this dataset: First, nearest neighbor retrieval between video segments and illustrations, and, second, alignment of instruction steps and the segments for each video. Extensive experiments on IAW demonstrate superior performances of our approach against alternatives., Comment: Project website: https://academic.davidz.cn/en/publication/zhang-cvpr-2023/