Search

Settling velocity statistics for dilute, non-Brownian suspensions of polydisperse spheres having a log-normal size distribution are analysed by Stokesian Dynamics, as a function of the total volume fraction and width of the size distribution. Several hundred instantaneous configurations are averaged to obtain reliable statistics. Average velocities for each particle class are compared to the models proposed by Batchelor, Richardson & Zaki, Davis & Gecol, and Masliyah-Lockett-Bassoon (MLB). Batchelor's model is shown to give reasonably accurate predictions when the volume fraction is within 5%. Because of its complexity, this model is however hardly used in practice, so lower-order models are needed. We found that while the other hindered settling models can give reasonably accurate predictions of the velocity of the largest particles, all of them overestimate - in certain cases by a large margin - the velocity of the smaller particles. By computing the fluid-particle velocity slip for each particle class and using Batchelor's model, we explain why predicting the lower tail of the particle size distribution is challenging, and propose possible avenues for model improvement. The analysis of velocity fluctuations suggest quantitative similarities between velocity fluctuations in monodisperse and polydisperse suspensions.

Since the invention of polymer networks in the 19th century (e.g., crosslinked natural rubber by Goodyear), it has been a dogma that stiffer networks are less stretchable, a trade-off inherent to the molecular nature of polymer network strands. Here, we report a universal strategy for decoupling the stiffness and extensibility of single-network elastomers. Instead of using linear polymers as network strands, we use foldable bottlebrush polymers, which feature a collapsed backbone grafted with many linear side chains. Upon elongation, the collapsed backbone unfolds to release stored length, enabling remarkable extensibility. By contrast, the network elastic modulus is inversely proportional to the network strand mass and is determined by the side chains. We validate this concept by creating a series of unentangled single-network elastomers with nearly constant Young's modulus (30 kPa) while increasing tensile breaking strain by 40-fold, from 20% to 800%. We show that this strategy applies to networks of different polymer species and topologies. Our discovery opens an avenue for developing polymer networks with extraordinary mechanical properties., Comment: 4 figures

Web browsers have been used widely by users to conduct various online activities, such as information seeking or online shopping. To improve user experience and extend the functionality of browsers, practitioners provide mechanisms to allow users to install third-party-provided plugins (i.e., extensions) on their browsers. However, little is known about the performance implications caused by such extensions. In this paper, we conduct an empirical study to understand the impact of extensions on the user-perceived performance (i.e., energy consumption and page load time) of Google Chrome, the most popular browser. We study a total of 72 representative extensions from 11 categories (e.g., Developer Tools and Sports). We observe that browser performance can be negatively impacted by the use of extensions, even when the extensions are used in unintended circumstances (e.g., when logging into an extension is not granted but required, or when an extension is not used for designated websites). We also identify a set of factors that significantly influence the performance impact of extensions, such as code complexity and privacy practices (i.e., collection of user data) adopted by the extensions. Based on our empirical observations, we provide recommendations for developers and users to mitigate the performance impact of browser extensions, such as conducting performance testing and optimization for unintended usage scenarios of extensions, or adhering to proper usage practices of extensions (e.g., logging into an extension when required).

Refactoring enhances software quality without altering its functional behaviors. Understanding the refactoring activities of developers is crucial to improving software maintainability. With the increasing use of machine learning (ML) libraries and frameworks, maximizing their maintainability is crucial. Due to the data-driven nature of ML projects, they often undergo different refactoring operations (e.g., data manipulation), for which existing refactoring tools lack ML-specific detection capabilities. Furthermore, a large number of ML libraries are written in Python, which has limited tools for refactoring detection. PyRef, a rule-based and state-of-the-art tool for Python refactoring detection, can identify 11 types of refactoring operations. In comparison, Rminer can detect 99 types of refactoring for Java projects. We introduce MLRefScanner, a prototype tool that applies machine-learning techniques to detect refactoring commits in ML Python projects. MLRefScanner identifies commits with both ML-specific and general refactoring operations. Evaluating MLRefScanner on 199 ML projects demonstrates its superior performance compared to state-of-the-art approaches, achieving an overall 94% precision and 82% recall. Combining it with PyRef further boosts performance to 95% precision and 99% recall. Our study highlights the potential of ML-driven approaches in detecting refactoring across diverse programming languages and technical domains, addressing the limitations of rule-based detection methods.

We introduce the Yi model family, a series of language and multimodal models that demonstrate strong multi-dimensional capabilities. The Yi model family is based on 6B and 34B pretrained language models, then we extend them to chat models, 200K long context models, depth-upscaled models, and vision-language models. Our base models achieve strong performance on a wide range of benchmarks like MMLU, and our finetuned chat models deliver strong human preference rate on major evaluation platforms like AlpacaEval and Chatbot Arena. Building upon our scalable super-computing infrastructure and the classical transformer architecture, we attribute the performance of Yi models primarily to its data quality resulting from our data-engineering efforts. For pretraining, we construct 3.1 trillion tokens of English and Chinese corpora using a cascaded data deduplication and quality filtering pipeline. For finetuning, we polish a small scale (less than 10K) instruction dataset over multiple iterations such that every single instance has been verified directly by our machine learning engineers. For vision-language, we combine the chat language model with a vision transformer encoder and train the model to align visual representations to the semantic space of the language model. We further extend the context length to 200K through lightweight continual pretraining and demonstrate strong needle-in-a-haystack retrieval performance. We show that extending the depth of the pretrained checkpoint through continual pretraining further improves performance. We believe that given our current results, continuing to scale up model parameters using thoroughly optimized data will lead to even stronger frontier models.

Motivation: The gene content regulates the biology of an organism. It varies between species and between individuals of the same species. Although tools have been developed to identify gene content changes in bacterial genomes, none is applicable to collections of large eukaryotic genomes such as the human pangenome. Results: We developed pangene, a computational tool to identify gene orientation, gene order and gene copy-number changes in a collection of genomes. Pangene aligns a set of input protein sequences to the genomes, resolves redundancies between protein sequences and constructs a gene graph with each genome represented as a walk in the graph. It additionally finds subgraphs that encodes gene content changes. Applied to the human pangenome, pangene identifies known gene-level variations and reveals complex haplotypes that are not well studied before. Pangene also works with high-quality bacterial pangenome and reports similar numbers of core and accessory genes in comparison to existing tools. Availability and implementation: Source code at https://github.com/lh3/pangene; pre-built pangene graphs can be downloaded from https://zenodo.org/records/8118576 and visualized at https://pangene.bioinweb.org.

Stimulated Emission Depletion Microscopy (STED) can achieve a spatial resolution as high as several nanometers. As a point scanning imaging method, it requires 3D scanning to complete the imaging of 3D samples. The time-consuming 3D scanning can be compressed into a 2D one in the non-diffracting Bessel-Bessel STED (BB-STED) where samples are effectively excited by an optical needle. However, the image is just the 2D projection, i.e., there is no real axial resolution. Therefore, we propose a method to encode axial information to axially dense emitters by using a detection optical path with single-helix point spread function (SH-PSF), and then predicted the depths of the emitters by means of deep learning. Simulation demonstrated that, for a density 1~ 20 emitters in a depth range of 4 nm, an axial precision of ~35 nm can be achieved. Our method also works for experimental data, and an axial precision of ~63 nm can be achieved.

The decay of sunspot plays a key role in magnetic flux transportation in solar active regions (ARs). To better understand the physical mechanism of the entire decay process of a sunspot, an {\alpha}-configuration sunspot in AR NOAA 12411 was studied. Based on the continuum intensity images and vector magnetic field data with stray light correction from Solar Dynamics Observatory/Helioseismic and Magnetic Imager, the area, vector magnetic field and magnetic flux in the umbra and penumbra are calculated with time, respectively. Our main results are as follows: (1) The decay curves of the sunspot area in its umbra, penumbra, and whole sunspot take the appearance of Gaussian profiles. The area decay rates of the umbra, penumbra and whole sunspot are -1.56 MSH/day, -12.61 MSH/day and -14.04 MSH/day, respectively; (2) With the decay of the sunspot, the total magnetic field strength and the vertical component of the penumbra increase, and the magnetic field of the penumbra becomes more vertical. Meanwhile, the total magnetic field strength and vertical magnetic field strength for the umbra decrease, and the inclination angle changes slightly with an average value of about 20{\deg}; (3) The magnetic flux decay curves of the sunspot in its umbra, penumbra, and whole sunspot exhibit quadratic patterns, their magnetic flux decay rates of the umbra, penumbra and whole sunspot are -9.84 * 10^19 Mx/day, -1.59 * 10^20 Mx/day and -2.60 * 10^20 Mx/day , respectively. The observation suggests that the penumbra may be transformed into the umbra, resulting in the increase of the average vertical magnetic field strength and the reduction of the inclination angle in the penumbra during the decay of the sunspot.

Domain adaptation is crucial in aerial imagery, as the visual representation of these images can significantly vary based on factors such as geographic location, time, and weather conditions. Additionally, high-resolution aerial images often require substantial storage space and may not be readily accessible to the public. To address these challenges, we propose a novel Source-Free Object Detection (SFOD) method. Specifically, our approach is built upon a self-training framework; however, self-training can lead to inaccurate learning in the absence of labeled training data. To address this issue, we further integrate Contrastive Language-Image Pre-training (CLIP) to guide the generation of pseudo-labels, termed CLIP-guided Aggregation. By leveraging CLIP's zero-shot classification capability, we use it to aggregate scores with the original predicted bounding boxes, enabling us to obtain refined scores for the pseudo-labels. To validate the effectiveness of our method, we constructed two new datasets from different domains based on the DIOR dataset, named DIOR-C and DIOR-Cloudy. Experiments demonstrate that our method outperforms other comparative algorithms., Comment: Submitted to IGARSS2024

In the conventional change detection (CD) pipeline, two manually registered and labeled remote sensing datasets serve as the input of the model for training and prediction. However, in realistic scenarios, data from different periods or sensors could fail to be aligned as a result of various coordinate systems. Geometric distortion caused by coordinate shifting remains a thorny issue for CD algorithms. In this paper, we propose a reusable self-supervised framework for bitemporal geometric distortion in CD tasks. The whole framework is composed of Pretext Representation Pre-training, Bitemporal Image Alignment, and Down-stream Decoder Fine-Tuning. With only single-stage pre-training, the key components of the framework can be reused for assistance in the bitemporal image alignment, while simultaneously enhancing the performance of the CD decoder. Experimental results in 2 large-scale realistic scenarios demonstrate that our proposed method can alleviate the bitemporal geometric distortion in CD tasks.

One goal of technical online communities is to help developers find the right answer in one place. A single question can be asked in different ways with different wordings, leading to the existence of duplicate posts on technical forums. The question of how to discover and link duplicate posts has garnered the attention of both developer communities and researchers. For example, Stack Overflow adopts a voting-based mechanism to mark and close duplicate posts. However, addressing these constantly emerging duplicate posts in a timely manner continues to pose challenges. Therefore, various approaches have been proposed to detect duplicate posts on technical forum posts automatically. The existing methods suffer from limitations either due to their reliance on handcrafted similarity metrics which can not sufficiently capture the semantics of posts, or their lack of supervision to improve the performance. Additionally, the efficiency of these methods is hindered by their dependence on pair-wise feature generation, which can be impractical for large amount of data. In this work, we attempt to employ and refine the GPT-3 embeddings for the duplicate detection task. We assume that the GPT-3 embeddings can accurately represent the semantics of the posts. In addition, by training a Siamese-based network based on the GPT-3 embeddings, we obtain a latent embedding that accurately captures the duplicate relation in technical forum posts. Our experiment on a benchmark dataset confirms the effectiveness of our approach and demonstrates superior performance compared to baseline methods. When applied to the dataset we constructed with a recent Stack Overflow dump, our approach attains a Top-1, Top-5, and Top-30 accuracy of 23.1%, 43.9%, and 68.9%, respectively. With a manual study, we confirm our approach's potential of finding unlabelled duplicates on technical forums., Comment: SANER 2024

With the rapid growth of the developer community, the amount of posts on online technical forums has been growing rapidly, which poses difficulties for users to filter useful posts and find important information. Tags provide a concise feature dimension for users to locate their interested posts and for search engines to index the most relevant posts according to the queries. However, most tags are only focused on the technical perspective (e.g., program language, platform, tool). In most cases, forum posts in online developer communities reveal the author's intentions to solve a problem, ask for advice, share information, etc. The modeling of the intentions of posts can provide an extra dimension to the current tag taxonomy. By referencing previous studies and learning from industrial perspectives, we create a refined taxonomy for the intentions of technical forum posts. Through manual labeling and analysis on a sampled post dataset extracted from online forums, we understand the relevance between the constitution of posts (code, error messages) and their intentions. Furthermore, inspired by our manual study, we design a pre-trained transformer-based model to automatically predict post intentions. The best variant of our intention prediction framework, which achieves a Micro F1-score of 0.589, Top 1-3 accuracy of 62.6% to 87.8%, and an average AUC of 0.787, outperforms the state-of-the-art baseline approach. Our characterization and automated classification of forum posts regarding their intentions may help forum maintainers or third-party tool developers improve the organization and retrieval of posts on technical forums. We have released our annotated dataset and codes in our supplementary material package., Comment: Journal of Empirical Software Engineering, 40 pages

The diversity of tables makes table detection a great challenge, leading to existing models becoming more tedious and complex. Despite achieving high performance, they often overfit to the table style in training set, and suffer from significant performance degradation when encountering out-of-distribution tables in other domains. To tackle this problem, we start from the essence of the table, which is a set of text arranged in rows and columns. Based on this, we propose a novel, light-weighted and robust Table Detection method based on Learning Text Arrangement, namely TDeLTA. TDeLTA takes the text blocks as input, and then models the arrangement of them with a sequential encoder and an attention module. To locate the tables precisely, we design a text-classification task, classifying the text blocks into 4 categories according to their semantic roles in the tables. Experiments are conducted on both the text blocks parsed from PDF and extracted by open-source OCR tools, respectively. Compared to several state-of-the-art methods, TDeLTA achieves competitive results with only 3.1M model parameters on the large-scale public datasets. Moreover, when faced with the cross-domain data under the 0-shot setting, TDeLTA outperforms baselines by a large margin of nearly 7%, which shows the strong robustness and transferability of the proposed model., Comment: AAAI 2024

Medical imaging provides many valuable clues involving anatomical structure and pathological characteristics. However, image degradation is a common issue in clinical practice, which can adversely impact the observation and diagnosis by physicians and algorithms. Although extensive enhancement models have been developed, these models require a well pre-training before deployment, while failing to take advantage of the potential value of inference data after deployment. In this paper, we raise an algorithm for source-free unsupervised domain adaptive medical image enhancement (SAME), which adapts and optimizes enhancement models using test data in the inference phase. A structure-preserving enhancement network is first constructed to learn a robust source model from synthesized training data. Then a teacher-student model is initialized with the source model and conducts source-free unsupervised domain adaptation (SFUDA) by knowledge distillation with the test data. Additionally, a pseudo-label picker is developed to boost the knowledge distillation of enhancement tasks. Experiments were implemented on ten datasets from three medical image modalities to validate the advantage of the proposed algorithm, and setting analysis and ablation studies were also carried out to interpret the effectiveness of SAME. The remarkable enhancement performance and benefits for downstream tasks demonstrate the potential and generalizability of SAME. The code is available at https://github.com/liamheng/Annotation-free-Medical-Image-Enhancement., Comment: 14 pages, 9 figures, in IEEE Transactions on Medical Imaging

Today's robot policies exhibit subpar performance when faced with the challenge of generalizing to novel environments. Human corrective feedback is a crucial form of guidance to enable such generalization. However, adapting to and learning from online human corrections is a non-trivial endeavor: not only do robots need to remember human feedback over time to retrieve the right information in new settings and reduce the intervention rate, but also they would need to be able to respond to feedback that can be arbitrary corrections about high-level human preferences to low-level adjustments to skill parameters. In this work, we present Distillation and Retrieval of Online Corrections (DROC), a large language model (LLM)-based system that can respond to arbitrary forms of language feedback, distill generalizable knowledge from corrections, and retrieve relevant past experiences based on textual and visual similarity for improving performance in novel settings. DROC is able to respond to a sequence of online language corrections that address failures in both high-level task plans and low-level skill primitives. We demonstrate that DROC effectively distills the relevant information from the sequence of online corrections in a knowledge base and retrieves that knowledge in settings with new task or object instances. DROC outperforms other techniques that directly generate robot code via LLMs by using only half of the total number of corrections needed in the first round and requires little to no corrections after two iterations. We show further results, videos, prompts and code on https://sites.google.com/stanford.edu/droc ., Comment: 8 pages, 4 figures, videos and code links on website https://sites.google.com/stanford.edu/droc

AIOps (Artificial Intelligence for IT Operations) solutions leverage the massive data produced during the operation of large-scale systems and machine learning models to assist software engineers in their system operations. As operation data produced in the field are constantly evolving due to factors such as the changing operational environment and user base, the models in AIOps solutions need to be constantly maintained after deployment. While prior works focus on innovative modeling techniques to improve the performance of AIOps models before releasing them into the field, when and how to update AIOps models remain an under-investigated topic. In this work, we performed a case study on three large-scale public operation data and empirically assessed five different types of model update strategies for supervised learning regarding their performance, updating cost, and stability. We observed that active model update strategies (e.g., periodical retraining, concept drift guided retraining, time-based model ensembles, and online learning) achieve better and more stable performance than a stationary model. Particularly, applying sophisticated model update strategies could provide better performance, efficiency, and stability than simply retraining AIOps models periodically. In addition, we observed that, although some update strategies can save model training time, they significantly sacrifice model testing time, which could hinder their applications in AIOps solutions where the operation data arrive at high pace and volume and where immediate inferences are required. Our findings highlight that practitioners should consider the evolution of operation data and actively maintain AIOps models over time. Our observations can also guide researchers and practitioners in investigating more efficient and effective model update strategies that fit in the context of AIOps.

Ensuring the safety, quality, and timely completion of construction projects is paramount, with construction inspections serving as a vital instrument towards these goals. Nevertheless, the predominantly manual approach of present-day inspections frequently results in inefficiencies and inadequate information management. Such methods often fall short of providing holistic, exhaustive assessments, consequently engendering regulatory oversights and potential safety hazards. To address this issue, this paper presents a novel framework named AutoRepo for automated generation of construction inspection reports. The unmanned vehicles efficiently perform construction inspections and collect scene information, while the multimodal large language models (LLMs) are leveraged to automatically generate the inspection reports. The framework was applied and tested on a real-world construction site, demonstrating its potential to expedite the inspection process, significantly reduce resource allocation, and produce high-quality, regulatory standard-compliant inspection reports. This research thus underscores the immense potential of multimodal large language models in revolutionizing construction inspection practices, signaling a significant leap forward towards a more efficient and safer construction management paradigm., Comment: We believe that keeping this version of the paper publicly available may lead to confusion or misinterpretation regarding our current research direction and findings

Prior studies on mobile app analysis often analyze apps across different categories or focus on a small set of apps within a category. These studies either provide general insights for an entire app store which consists of millions of apps, or provide specific insights for a small set of apps. However, a single app category can often contain tens of thousands to hundreds of thousands of apps. For example, according to AppBrain, there are 46,625 apps in the "Sports" category of Google Play apps. Analyzing such a targeted category of apps can provide more specific insights than analyzing apps across categories while still benefiting many app developers interested in the category. This work aims to study a large number of apps from a single category (i.e., the sports category). We performed an empirical study on over two thousand sports apps in the Google Play Store. We study the characteristics of these apps (e.g., their targeted sports types and main functionalities) through manual analysis, the topics in the user review through topic modeling, as well as the aspects that contribute to the negative opinions of users through analysis of user ratings and sentiment. It is concluded that analyzing a targeted category of apps (e.g., sports apps) can provide more specific insights than analyzing apps across different categories while still being relevant for a large number (e.g., tens of thousands) of apps. Besides, as a rapid-growing and competitive market, sports apps provide rich opportunities for future research, for example, to study the integration of data science or machine learning techniques in software applications or to study the factors that influence the competitiveness of the apps., Comment: Journal paper

Annotating remote sensing images (RSIs) presents a notable challenge due to its labor-intensive nature. Semi-supervised object detection (SSOD) methods tackle this issue by generating pseudo-labels for the unlabeled data, assuming that all classes found in the unlabeled dataset are also represented in the labeled data. However, real-world situations introduce the possibility of out-of-distribution (OOD) samples being mixed with in-distribution (ID) samples within the unlabeled dataset. In this paper, we delve into techniques for conducting SSOD directly on uncurated unlabeled data, which is termed Open-Set Semi-Supervised Object Detection (OSSOD). Our approach commences by employing labeled in-distribution data to dynamically construct a class-wise feature bank (CFB) that captures features specific to each class. Subsequently, we compare the features of predicted object bounding boxes with the corresponding entries in the CFB to calculate OOD scores. We design an adaptive threshold based on the statistical properties of the CFB, allowing us to filter out OOD samples effectively. The effectiveness of our proposed method is substantiated through extensive experiments on two widely used remote sensing object detection datasets: DIOR and DOTA. These experiments showcase the superior performance and efficacy of our approach for OSSOD on RSIs.

Recognition and localization of surgical detailed actions is an essential component of developing a context-aware decision support system. However, most existing detection algorithms fail to provide high-accuracy action classes even having their locations, as they do not consider the surgery procedure's regularity in the whole video. This limitation hinders their application. Moreover, implementing the predictions in clinical applications seriously needs to convey model confidence to earn entrustment, which is unexplored in surgical action prediction. In this paper, to accurately detect fine-grained actions that happen at every moment, we propose an anchor-context action detection network (ACTNet), including an anchor-context detection (ACD) module and a class conditional diffusion (CCD) module, to answer the following questions: 1) where the actions happen; 2) what actions are; 3) how confidence predictions are. Specifically, the proposed ACD module spatially and temporally highlights the regions interacting with the extracted anchor in surgery video, which outputs action location and its class distribution based on anchor-context interactions. Considering the full distribution of action classes in videos, the CCD module adopts a denoising diffusion-based generative model conditioned on our ACD estimator to further reconstruct accurately the action predictions. Moreover, we utilize the stochastic nature of the diffusion model outputs to access model confidence for each prediction. Our method reports the state-of-the-art performance, with improvements of 4.0% mAP against baseline on the surgical video dataset., Comment: Accepted early by MICCAI2023 (Oral)

Synthetic aperture radar (SAR) image change detection is a critical task and has received increasing attentions in the remote sensing community. However, existing SAR change detection methods are mainly based on convolutional neural networks (CNNs), with limited consideration of global attention mechanism. In this letter, we explore Transformer-like architecture for SAR change detection to incorporate global attention. To this end, we propose a convolution and attention mixer (CAMixer). First, to compensate the inductive bias for Transformer, we combine self-attention with shift convolution in a parallel way. The parallel design effectively captures the global semantic information via the self-attention and performs local feature extraction through shift convolution simultaneously. Second, we adopt a gating mechanism in the feed-forward network to enhance the non-linear feature transformation. The gating mechanism is formulated as the element-wise multiplication of two parallel linear layers. Important features can be highlighted, leading to high-quality representations against speckle noise. Extensive experiments conducted on three SAR datasets verify the superior performance of the proposed CAMixer. The source codes will be publicly available at https://github.com/summitgao/CAMixer ., Comment: Accepted by IEEE GRSL

Visual Odometry (VO) plays a pivotal role in autonomous systems, with a principal challenge being the lack of depth information in camera images. This paper introduces OCC-VO, a novel framework that capitalizes on recent advances in deep learning to transform 2D camera images into 3D semantic occupancy, thereby circumventing the traditional need for concurrent estimation of ego poses and landmark locations. Within this framework, we utilize the TPV-Former to convert surround view cameras' images into 3D semantic occupancy. Addressing the challenges presented by this transformation, we have specifically tailored a pose estimation and mapping algorithm that incorporates Semantic Label Filter, Dynamic Object Filter, and finally, utilizes Voxel PFilter for maintaining a consistent global semantic map. Evaluations on the Occ3D-nuScenes not only showcase a 20.6% improvement in Success Ratio and a 29.6% enhancement in trajectory accuracy against ORB-SLAM3, but also emphasize our ability to construct a comprehensive map. Our implementation is open-sourced and available at: https://github.com/USTCLH/OCC-VO., Comment: 7pages, 3 figures

Gestures serve as a fundamental and significant mode of non-verbal communication among humans. Deictic gestures (such as pointing towards an object), in particular, offer valuable means of efficiently expressing intent in situations where language is inaccessible, restricted, or highly specialized. As a result, it is essential for robots to comprehend gestures in order to infer human intentions and establish more effective coordination with them. Prior work often rely on a rigid hand-coded library of gestures along with their meanings. However, interpretation of gestures is often context-dependent, requiring more flexibility and common-sense reasoning. In this work, we propose a framework, GIRAF, for more flexibly interpreting gesture and language instructions by leveraging the power of large language models. Our framework is able to accurately infer human intent and contextualize the meaning of their gestures for more effective human-robot collaboration. We instantiate the framework for interpreting deictic gestures in table-top manipulation tasks and demonstrate that it is both effective and preferred by users, achieving 70% higher success rates than the baseline. We further demonstrate GIRAF's ability on reasoning about diverse types of gestures by curating a GestureInstruct dataset consisting of 36 different task scenarios. GIRAF achieved 81% success rate on finding the correct plan for tasks in GestureInstruct. Website: https://tinyurl.com/giraf23, Comment: CoRL 2023

Fundus photography is prone to suffer from image quality degradation that impacts clinical examination performed by ophthalmologists or intelligent systems. Though enhancement algorithms have been developed to promote fundus observation on degraded images, high data demands and limited applicability hinder their clinical deployment. To circumvent this bottleneck, a generic fundus image enhancement network (GFE-Net) is developed in this study to robustly correct unknown fundus images without supervised or extra data. Levering image frequency information, self-supervised representation learning is conducted to learn robust structure-aware representations from degraded images. Then with a seamless architecture that couples representation learning and image enhancement, GFE-Net can accurately correct fundus images and meanwhile preserve retinal structures. Comprehensive experiments are implemented to demonstrate the effectiveness and advantages of GFE-Net. Compared with state-of-the-art algorithms, GFE-Net achieves superior performance in data dependency, enhancement performance, deployment efficiency, and scale generalizability. Follow-up fundus image analysis is also facilitated by GFE-Net, whose modules are respectively verified to be effective for image enhancement., Comment: Accepted by Medical Image Analysis in Auguest, 2023