Physics-based simulations have accelerated progress in robot learning for driving, manipulation, and locomotion. Yet, a fast, accurate, and robust surgical simulation environment remains a challenge. In this paper, we present Orbit-Surgical, a physics-based surgical robot simulation framework with photorealistic rendering in NVIDIA Omniverse. We provide 14 benchmark surgical tasks for the da Vinci Research Kit (dVRK) and Smart Tissue Autonomous Robot (STAR) which represent common subtasks in surgical training. Orbit-Surgical leverages GPU parallelization to train reinforcement learning and imitation learning algorithms to facilitate study of robot learning to augment human surgical skills. Orbit-Surgical also facilitates realistic synthetic data generation for active perception tasks. We demonstrate Orbit-Surgical sim-to-real transfer of learned policies onto a physical dVRK robot.Project website: orbit-surgical.github.io

Various heuristic objectives for modeling hand-object interaction have been proposed in past work. However, due to the lack of a cohesive framework, these objectives often possess a narrow scope of applicability and are limited by their efficiency or accuracy. In this paper, we propose HANDYPRIORS, a unified and general pipeline for pose estimation in human-object interaction scenes by leveraging recent advances in differentiable physics and rendering. Our approach employs rendering priors to align with input images and segmentation masks along with physics priors to mitigate penetration and relative-sliding across frames. Furthermore, we present two alternatives for hand and object pose estimation. The optimization-based pose estimation achieves higher accuracy, while the filtering-based tracking, which utilizes the differentiable priors as dynamics and observation models, executes faster. We demonstrate that HANDYPRIORS attains comparable or superior results in the pose estimation task, and that the differentiable physics module can predict contact information for pose refinement. We also show that our approach generalizes to perception tasks, including robotic hand manipulation and human-object pose estimation in the wild.

states without platform intervention; 2. offline experiments employing our proposed intervention mechanisms on diverse datasets; and 3. results from a three-week online experiment conducted on Instagram Reels short-video recommendation platform.

On User-Generated Content (UGC) platforms, recommendation algorithms significantly impact creators' motivation to produce content as they compete for algorithmically allocated user traffic. This phenomenon subtly shapes the volume and diversity of the content pool, which is crucial for the platform's sustainability. In this work, we demonstrate, both theoretically and empirically, that a purely relevance-driven policy with low exploration strength boosts short-term user satisfaction but undermines the long-term richness of the content pool. In contrast, a more aggressive exploration policy may slightly compromise user satisfaction but promote higher content creation volume. Our findings reveal a fundamental trade-off between immediate user satisfaction and overall content production on UGC platforms. Building on this finding, we propose an efficient optimization method to identify the optimal exploration strength, balancing user and creator engagement. Our model can serve as a pre-deployment audit tool for recommendation algorithms on UGC platforms, helping to align their immediate objectives with sustainable, long-term goals.

Nan Wang, Qifan Wang, Yi-Chia Wang, Maziar Sanjabi, Jingzhou Liu, Hamed Firooz, Hongning Wang, Shaoliang Nie. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Recent work has demonstrated the ability of deep reinforcement learning (RL) algorithms to learn complex robotic behaviours in simulation, including in the domain of multi-fingered manipulation. However, such models can be challenging to transfer to the real world due to the gap between simulation and reality. In this paper, we present our techniques to train a) a policy that can perform robust dexterous manipulation on an anthropomorphic robot hand and b) a robust pose estimator suitable for providing reliable real-time information on the state of the object being manipulated. Our policies are trained to adapt to a wide range of conditions in simulation. Consequently, our vision-based policies significantly outperform the best vision policies in the literature on the same reorientation task and are competitive with policies that are given privileged state information via motion capture systems. Our work reaffirms the possibilities of sim-to-real transfer for dexterous manipulation in diverse kinds of hardware and simulator setups, and in our case, with the Allegro Hand and Isaac Gym GPU-based simulation. Furthermore, it opens up possibilities for researchers to achieve such results with commonly-available, affordable robot hands and cameras. Videos of the resulting policy and supplementary information, including experiments and demos, can be found on the website.

Supervised summarization has made significant improvements in recent years by leveraging cutting-edge deep learning technologies. However, the true success of supervised methods relies on the availability of large quantity of human-generated summaries of documents, which is highly costly and difficult to obtain in general. This paper proposes an unsupervised approach to extractive text summarization, which uses an automatically constructed sentence graph from each document to select salient sentences for summarization based on both the similarities and relative distances in the neighborhood of each sentences. We further generalize our approach from single-document summarization to a multi-document setting, by aggregating document-level graphs via proximity-based cross-document edges. In our experiments on benchmark datasets, the proposed approach achieved competitive or better results than previous state-of-the-art unsupervised extractive summarization methods in both single-document and multi-document settings, and the performance is competitive to strong supervised baselines.

Large-scale pre-trained language model such as BERT has achieved great success in language understanding tasks.However, it remains an open question how to utilize BERT for language generation.In this paper, we present a novel approach, Conditional Masked Language Modeling (C-MLM), to enable the finetuning of BERT on target generation tasks.The finetuned BERT (teacher) is exploited as extra supervision to improve conventional Seq2Seq models (student) for better text generation performance.By leveraging BERT's idiosyncratic bidirectional nature, distilling knowledge learned in BERT can encourage auto-regressive Seq2Seq models to plan ahead, imposing global sequence-level supervision for coherent text generation.Experiments show that the proposed approach significantly outperforms strong Transformer baselines on multiple language generation tasks such as machine translation and text summarization.Our proposed model also achieves new state of the art on IWSLT German-English and English-Vietnamese MT datasets.1

We introduce a new task, Video-and-Language Inference, for joint multimodal understanding of video and text. Given a video clip with aligned subtitles as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip. A new large-scale dataset, named Violin (VIdeO-and-Language INference), is introduced for this task, which consists of 95,322 video-hypothesis pairs from 15,887 video clips, spanning over 582 hours of video. These video clips contain rich content with diverse temporal dynamics, event shifts, and people interactions, collected from two sources: (i) popular TV shows, and (ii) movie clips from YouTube channels. In order to address our new multimodal inference task, a model is required to possess sophisticated reasoning skills, from surface-level grounding (e.g., identifying objects and characters in the video) to in-depth commonsense reasoning (e.g., inferring causal relations of events in the video). We present a detailed analysis of the dataset and an extensive evaluation over many strong baselines, providing valuable insights on the challenges of this new task.

We introduce a novel architecture for dependency parsing: stack-pointer networks (STACKPTR).Combining pointer networks (Vinyals et al., 2015) with an internal stack, the proposed model first reads and encodes the whole sentence, then builds the dependency tree top-down (from root-to-leaf) in a depth-first fashion.The stack tracks the status of the depthfirst search and the pointer networks select one child for the word at the top of the stack at each step.The STACKPTR parser benefits from the information of the whole sentence and all previously derived subtree structures, and removes the leftto-right restriction in classical transitionbased parsers.Yet, the number of steps for building any (including non-projective) parse tree is linear in the length of the sentence just as other transition-based parsers, yielding an efficient decoding algorithm with O(n 2 ) time complexity.We evaluate our model on 29 treebanks spanning 20 languages and different dependency annotation schemas, and achieve state-of-theart performance on 21 of them.

Extreme multi-label text classification (XMTC) refers to the problem of assigning to each document its most relevant subset of class labels from an extremely large label collection, where the number of labels could reach hundreds of thousands or millions. The huge label space raises research challenges such as data sparsity and scalability. Significant progress has been made in recent years by the development of new machine learning methods, such as tree induction with large-margin partitions of the instance spaces and label-vector embedding in the target space. However, deep learning has not been explored for XMTC, despite its big successes in other related areas. This paper presents the first attempt at applying deep learning to XMTC, with a family of new Convolutional Neural Network (CNN) models which are tailored for multi-label classification in particular. With a comparative evaluation of 7 state-of-the-art methods on 6 benchmark datasets where the number of labels is up to 670,000, we show that the proposed CNN approach successfully scaled to the largest datasets, and consistently produced the best or the second best results on all the datasets. On the Wikipedia dataset with over 2 million documents and 500,000 labels in particular, it outperformed the second best method by 11.7%~15.3% in [email protected] and by 11.5%~11.7% in [email protected] for K = 1,3,5.

We study the problem of visualizing large-scale and high-dimensional data in a low-dimensional (typically 2D or 3D) space. Much success has been reported recently by techniques that first compute a similarity structure of the data points and then project them into a low-dimensional space with the structure preserved. These two steps suffer from considerable computational costs, preventing the state-of-the-art methods such as the t-SNE from scaling to large-scale and high-dimensional data (e.g., millions of data points and hundreds of dimensions). We propose the LargeVis, a technique that first constructs an accurately approximated K-nearest neighbor graph from the data and then layouts the graph in the low-dimensional space. Comparing to t-SNE, LargeVis significantly reduces the computational cost of the graph construction step and employs a principled probabilistic model for the visualization step, the objective of which can be effectively optimized through asynchronous stochastic gradient descent with a linear time complexity. The whole procedure thus easily scales to millions of high-dimensional data points. Experimental results on real-world data sets demonstrate that the LargeVis outperforms the state-of-the-art methods in both efficiency and effectiveness. The hyper-parameters of LargeVis are also much more stable over different data sets.

Aspect-oriented software development (AOSD) has been developed for supporting a long-standing idea of Separation of Concerns (SoC) and enhancing software non-functional attributes including modularity, reusability, and maintainability. Many architectural description languages (ADLs) also provide software developers with support in specifying aspects in software architectures. However, when applied to describe trustworthy software systems, these ADLs face difficulties in using aspects to specify trustworthy attributes and maintaining consistency between the architectures before and after weaving of aspects. In this paper, we extend Breeze, a graph grammar supported ADL, to AspectBreeze. AspectBreeze allows trustworthiness aspects to be easily defined and seamlessly woven into base architectures. Further, architectures are defined along with graph grammars that allow any change to a base architecture to be reflected in the corresponding architecture in which aspects are woven. This paper also presents a case study of an online auction system to show how AspectBreeze is used and how graph grammars can maintain the consistency between the architectures before and after weaving of trustworthiness aspects.

Previous game-theoretic studies of vaccination behavior typically have often assumed that populations are homogeneously mixed and that individuals are fully rational. In reality, there is heterogeneity in the number of contacts per individual, and individuals tend to imitate others who appear to have adopted successful strategies. Here, we use network-based mathematical models to study the effects of both imitation behavior and contact heterogeneity on vaccination coverage and disease dynamics. We integrate contact network epidemiological models with a framework for decision-making, within which individuals make their decisions either based purely on payoff maximization or by imitating the vaccination behavior of a social contact. Simulations suggest that when the cost of vaccination is high imitation behavior may decrease vaccination coverage. However, when the cost of vaccination is small relative to that of infection, imitation behavior increases vaccination coverage, but, surprisingly, also increases the magnitude of epidemics through the clustering of non-vaccinators within the network. Thus, imitation behavior may impede the eradication of infectious diseases. Calculations that ignore behavioral clustering caused by imitation may significantly underestimate the levels of vaccination coverage required to attain herd immunity.