A dexterous hand capable of generalizable grasping objects is fundamental for the development of general-purpose embodied AI. However, previous methods focus narrowly on low-level grasp stability metrics, neglecting affordance-aware positioning and human-like poses which are crucial for downstream manipulation. To address these limitations, we propose AffordDex, a novel framework with two-stage training that learns a universal grasping policy with an inherent understanding of both motion priors and object affordances. In the first stage, a trajectory imitator is pre-trained on a large corpus of human hand motions to instill a strong prior for natural movement. In the second stage, a residual module is trained to adapt these general human-like motions to specific object instances. This refinement is critically guided by two components: our Negative Affordance-aware Segmentation (NAA) module, which identifies functionally inappropriate contact regions, and a privileged teacher-student distillation process that ensures the final vision-based policy is highly successful. Extensive experiments demonstrate that AffordDex not only achieves universal dexterous grasping but also remains remarkably human-like in posture and functionally appropriate in contact location. As a result, AffordDex significantly outperforms state-of-the-art baselines across seen objects, unseen instances, and even entirely novel categories.

Existing studies have proven that pre-trained ranking models outperform pre-trained language models when it comes to ranking tasks. To pre-train such models, researchers have utilized large-scale search logs and clicks as weak-supervised signals of query-document relevance. However, search logs are incomplete and sparse. Different users with the same intent tend to use various forms of queries. It is hard for recorded clicks to sufficiently cover diverse relevance patterns between queries and documents. Moreover, the diverse intentions of a large user base lead to long-tail distributions of search intents. Deriving sufficient relevance signals from sparse clicks of these long-tail intents poses another challenge. Therefore, there is significant potential for exploring richer relevance signals beyond direct clicks to pre-train high-quality ranking models. To tackle this problem, we develop two exploratory data augmentation strategies that consider the diversity of query forms from local and global perspectives, hence mining potential and diverse relevance signals from search logs. A generative augmentation strategy is also devised to create supplementary positive samples, to enhance the ranking ability for long-tail query intents. We leverage a multi-level pairwise ranking objective and a contrastive learning approach to enable our model to capture fine-grained relevance patterns and be robust for noisy training samples. Experimental results on a large-scale public dataset and a commercial dataset confirm that our model, namely PRADA, can yield better ranking effectiveness over existing pre-trained ranking models.

Multi-document summarization (MDS) aims at giving a brief summary for a cluster of related documents. In this paper, we consider the MDS task as an optimization problem with a novel measure named soaking capacity being the objective function. The origin of our method is the classic hypothesis: the summary components are the sinks of information diffusion. We point out that the hypothesis only gives the role of summary but does not cover how well a summary acts as this role. To fill in the gap, soaking capacity is formally defined to quantify the ability of summary to soak up information. We explicitly demonstrate its fitness as an indicator for both the saliency and the diversity goal of MDS. For solving the optimization problem, we propose a greedy algorithm named Soap by adopting a surrogate of soaking capacity to accelerate the computation. Experiments on MDS datasets across various domains show the great potential of Soap as compared with the state-of-the-art MDS systems.

The widespread adoption of reference-based automatic evaluation metrics such as ROUGE has promoted the development of document summarization.In this paper, we consider a new protocol for designing reference-based metrics that require the endorsement of source document(s).Following protocol, we propose an anchored ROUGE metric fixing each summary particle on source document, which bases the computation on more solid ground.Empirical results on benchmark datasets validate that source document helps to induce a higher correlation with human judgments for ROUGE metric.Being self-explanatory and easy-to-implement, the protocol can naturally foster various effective designs of reference-based metrics besides the anchored ROUGE introduced here.

Multi-document summarization (MDS) aims at producing a good-quality summary for several related documents.In this paper, we propose a spectral-based hypothesis, which states that the goodness of summary candidate is closely linked to its so-called spectral impact.Here spectral impact considers the perturbation to the dominant eigenvalue of affinity matrix when dropping the summary candidate from the document cluster.The hypothesis is validated by three theoretical perspectives: semantic scaling, propagation dynamics and matrix perturbation.According to the hypothesis, we formulate the MDS task as the combinatorial optimization of spectral impact and propose an accelerated greedy solution based on a surrogate of spectral impact.The evaluation results on various datasets demonstrate:(1) The performance of the summary candidate is positively correlated with its spectral impact, which accords with our hypothesis; (2) Our spectral-based method has a competitive result as compared to state-of-the-art MDS systems.

Table-to-text generation aims to generate a description for a factual table which can be viewed as a set of field-value records. To encode both the content and the structure of a table, we propose a novel structure-aware seq2seq architecture which consists of field-gating encoder and description generator with dual attention. In the encoding phase, we update the cell memory of the LSTM unit by a field gate and its corresponding field value in order to incorporate field information into table representation. In the decoding phase, dual attention mechanism which contains word level attention and field level attention is proposed to model the semantic relevance between the generated description and the table. We conduct experiments on the WIKIBIO dataset which contains over 700k biographies and corresponding infoboxes from Wikipedia. The attention visualizations and case studies show that our model is capable of generating coherent and informative descriptions based on the comprehensive understanding of both the content and the structure of a table. Automatic evaluations also show our model outperforms the baselines by a great margin. Code for this work is available on https://github.com/tyliupku/wiki2bio.

Distant-supervised relation extraction inevitably suffers from wrong labeling problems because it heuristically labels relational facts with knowledge bases.Previous sentence level denoise models don't achieve satisfying performances because they use hard labels which are determined by distant supervision and immutable during training.To this end, we introduce an entity-pair level denoise method which exploits semantic information from correctly labeled entity pairs to correct wrong labels dynamically during training.We propose a joint score function which combines the relational scores based on the entity-pair representation and the confidence of the hard label to obtain a new label, namely a soft label, for certain entity pair.During training, soft labels instead of hard labels serve as gold labels.Experiments on the benchmark dataset show that our method dramatically reduces noisy instances and outperforms the state-of-the-art systems.

Multi-document summarization provides users with a short text that summarizes the information in a set of related documents.This paper introduces affinitypreserving random walk to the summarization task, which preserves the affinity relations of sentences by an absorbing random walk model.Meanwhile, we put forward adjustable affinity-preserving random walk to enforce the diversity constraint of summarization in the random walk process.The ROUGE evaluations on DUC 2003 topic-focused summarization task and DUC 2004 generic summarization task show the good performance of our method, which has the best ROUGE-2 recall among the graph-based ranking methods.

This paper develops a novel volumetric parameterization and spline construction framework, which is an effective modeling tool for converting surface meshes to volumetric splines. Our new splines are defined upon a novel parametric domain called generalized polycubes (GPCs). A GPC comprises a set of regular cube domains topologically glued together. Compared with conventional polycubes (CPCs), the GPC is much more powerful and flexible and has improved numerical accuracy and computational efficiency when serving as a parametric domain. We design an automatic algorithm to construct the GPC domain while also permitting the user to improve shape abstraction via interactive intervention. We then parameterize the input model on the GPC domain. Finally, we devise a new volumetric spline scheme based on this seamless volumetric parameterization. With a hierarchical fitting scheme, the proposed splines can fit data accurately using reduced number of superfluous control points. Our volumetric modeling scheme has great potential in shape modeling, engineering analysis, and reverse engineering applications.

This paper presents a volumetric modeling framework to construct a novel spline scheme called restricted trivariate polycube splines (RTP-splines). The RTP-spline aims to generalize both trivariate T-splines and tensor-product B-splines; it uses solid polycube structure as underlying parametric domains and strictly bounds blending functions within such domains. We construct volumetric RTP-splines in a top-down fashion in four steps: 1) Extending the polycube domain to its bounding volume via space filling; 2) building the B-spline volume over the extended domain with restricted boundaries; 3) inserting duplicate knots by adding anchor points and performing local refinement; and 4) removing exterior cells and anchors. Besides local refinement inherited from general T-splines, the RTP-splines have a few attractive properties as follows: 1) They naturally model solid objects with complicated topologies/bifurcations using a one-piece continuous representation without domain trimming/patching/merging. 2) They have guaranteed semistandardness so that the functions and derivatives evaluation is very efficient. 3) Their restricted support regions of blending functions prevent control points from influencing other nearby domain regions that stay opposite to the immediate boundaries. These features are highly desirable for certain applications such as isogeometric analysis. We conduct extensive experiments on converting complicated solid models into RTP-splines, and demonstrate the proposed spline to be a powerful and promising tool for volumetric modeling and other scientific/engineering applications where data sets with multiattributes are prevalent.

This paper develops a new trivariate hierarchical spline scheme for volumetric data representation. Unlike conventional spline formulations and techniques, our new framework is built upon a novel parametric domain called Generalized PolyCube (GPC), comprising a set of regular cubes being glued together. Compared with the conventional PolyCube (PC) that could serve as a "one-piece'' 3-manifold domain, GPC has more powerful and flexible representation ability. We develop an effective framework that parameterizes a solid model onto a topologically equivalent GPC domain, and design a hierarchical fitting scheme based on trivariate T-splines. The entire data-spline-conversion modeling framework provides high-accuracy data fitting and greatly reduce the number of superfluous control points. It is a powerful toolkit with broader application appeal in shape modeling, engineering analysis, and reverse engineering.