Shan He

Aodi Wu, Haodong Han, Xubo Luo et al.

Autonomous on-orbit servicing demands embodied agents that perceive through visual sensors, reason about 3D spatial situations, and execute multi-phase tasks over extended horizons. We present SpaceMind, a modular and self-evolving vision-language model (VLM) agent framework that decomposes knowledge, tools, and reasoning into three independently extensible dimensions: skill modules with dynamic routing, Model Context Protocol (MCP) tools with configurable profiles, and injectable reasoning-mode skills. An MCP-Redis interface layer enables the same codebase to operate across simulation and physical hardware without modification, and a Skill Self-Evolution mechanism distills operational experience into persistent skill files without model fine-tuning. We validate SpaceMind through 192 closed-loop runs across five satellites, three task types, and two environments, a UE5 simulation and a physical laboratory, deliberately including degraded conditions to stress-test robustness. Under nominal conditions all modes achieve 90--100% navigation success; under degradation, the Prospective mode uniquely succeeds in search-and-approach tasks where other modes fail. A self-evolution study shows that the agent recovers from failure in four of six groups from a single failed episode, including complete failure to 100% success and inspection scores improving from 12 to 59 out of 100. Real-world validation confirms zero-code-modification transfer to a physical robot with 100% rendezvous success. Code: https://github.com/wuaodi/SpaceMind

Rui He, Zeyu Dai, Shan He et al.

In multi-domain learning (MDL) scenarios, high labeling effort is required due to the complexity of collecting data from various domains. Active Learning (AL) presents an encouraging solution to this issue by annotating a smaller number of highly informative instances, thereby reducing the labeling effort. Previous research has relied on conventional AL strategies for MDL scenarios, which underutilize the domain-shared information of each instance during the selection procedure. To mitigate this issue, we propose a novel perturbation-based two-stage multi-domain active learning (P2S-MDAL) method incorporated into the well-regarded ASP-MTL model. Specifically, P2S-MDAL involves allocating budgets for domains and establishing regions for diversity selection, which are further used to select the most cross-domain influential samples in each region. A perturbation metric has been introduced to evaluate the robustness of the shared feature extractor of the model, facilitating the identification of potentially cross-domain influential samples. Experiments are conducted on three real-world datasets, encompassing both texts and images. The superior performance over conventional AL strategies shows the effectiveness of the proposed strategy. Additionally, an ablation study has been carried out to demonstrate the validity of each component. Finally, we outline several intriguing potential directions for future MDAL research, thus catalyzing the field's advancement.

Shan He, Steven Kiyabu, Philip R. Buskohl et al.

This study harnesses the embodied intelligence of mechanical metamaterials to sense and process environmental vibrations with minimal digital computation. Using physical reservoir computing (PRC), we turn the metamaterial and its nonlinear dynamics into a physical neural network that nonlinearly transforms the input vibrations and uses a simple linear training to compute a range of tasks. We introduce a novel metamaterial reservoir composed of a network of unit cells with contact nonlinearities that are the physical equivalent of leaky rectified linear unit (ReLU) activation functions. We experimentally show that the metamaterial reservoir can compute two classes of tasks: independent tasks, such as benchmark functions, and embodied tasks, such as proprioception, which we introduce to describe tasks coupled to the structure's dynamics. By comparing against a linear metamaterial, we demonstrate that nonlinearity is critical for high task performance, and we show that the metamaterial is robust to inputs of varying complexity. Through dimensionality reduction, we uncover the governing information separation mechanism and show that the metamaterial separates the input vibrations into new frequency content spatially distributed across the sensor readouts. We then confirm that frequency content is a key indicator of task performance by conducting an optimal sensor selection study using a frequency-based greedy algorithm. Finally, we demonstrate that a metamaterial's generalized performance for different tasks can be quantified using the memory vs. nonlinearity subspace, providing a design tool for other reservoir abstractions. These results establish the embodied intelligence of mechanical metamaterials and provide a path for sense-assess-response in intelligent systems.

Shan He, Yalong Ma, Tao Song et al.

Planning a safe and feasible trajectory for autonomous vehicles in real-time by fully utilizing perceptual information in complex urban environments is challenging. In this paper, we propose a spatio-temporal trajectory planning method based on graph optimization. It efficiently extracts the multi-modal information of the perception module by constructing a semantic spatio-temporal map through separation processing of static and dynamic obstacles, and then quickly generates feasible trajectories via sparse graph optimization based on a semantic spatio-temporal hypergraph. Extensive experiments have proven that the proposed method can effectively handle complex urban public road scenarios and perform in real time. We will also release our codes to accommodate benchmarking for the research community

Yuzhe Weng, Haotian Wang, Xinyi Yu et al.

Audio-driven human video generation has achieved remarkable success in monologue scenarios, largely driven by advancements in powerful video generation foundation models. Moving beyond monologues, authentic human communication is inherently a full-duplex interactive process, requiring virtual agents not only to articulate their own speech but also to react naturally to incoming conversational audio. Most existing methods simply extend conventional audio-driven paradigms to listening scenarios. However, relying on strict frame-to-frame alignment renders the model's response to long-range conversational dynamics rigid, whereas directly introducing global attention catastrophically degrades lip synchronization. Recognizing the unique temporal Scale Discrepancy between talking and listening behaviors, we introduce a multi-head Gaussian kernel to explicitly inject this physical intuition into the model as a progressive temporal inductive bias. Building upon this, we construct a full-duplex interactive virtual agent capable of simultaneously processing dual-stream audio inputs for both talking and listening. Furthermore, we introduce a rigorously cleaned Talking-Listening dataset VoxHear featuring perfectly decoupled speech and background audio tracks. Extensive experiments demonstrate that our approach successfully fuses strong temporal alignment with deep contextual semantics, setting a new state-of-the-art for generating highly natural and responsive full-duplex interactive digital humans. The project page is available at https://warmcongee.github.io/beyond-monologue/ .

Qingyun Sun, Jiaqi Yuan, Shan He et al.

Graph Retrieval-Augmented Generation has emerged as a powerful paradigm for grounding large language models with external structured knowledge. However, existing Graph RAG methods struggle with temporal reasoning, due to their inability to model the evolving structure and order of real-world events. In this work, we introduce DyG-RAG, a novel event-centric dynamic graph retrieval-augmented generation framework designed to capture and reason over temporal knowledge embedded in unstructured text. To eliminate temporal ambiguity in traditional retrieval units, DyG-RAG proposes Dynamic Event Units (DEUs) that explicitly encode both semantic content and precise temporal anchors, enabling accurate and interpretable time-aware retrieval. To capture temporal and causal dependencies across events, DyG-RAG constructs an event graph by linking DEUs that share entities and occur close in time, supporting efficient and meaningful multi-hop reasoning. To ensure temporally consistent generation, DyG-RAG introduces an event timeline retrieval pipeline that retrieves event sequences via time-aware traversal, and proposes a Time Chain-of-Thought strategy for temporally grounded answer generation. This unified pipeline enables DyG-RAG to retrieve coherent, temporally ordered event sequences and to answer complex, time-sensitive queries that standard RAG systems cannot resolve. Extensive experiments on temporal QA benchmarks demonstrate that DyG-RAG significantly improves the accuracy and recall of three typical types of temporal reasoning questions, paving the way for more faithful and temporal-aware generation. DyG-RAG is available at https://github.com/RingBDStack/DyG-RAG.

Chengbin Hou, Han Zhang, Shan He et al.

Learning low-dimensional topological representation of a network in dynamic environments is attracting much attention due to the time-evolving nature of many real-world networks. The main and common objective of Dynamic Network Embedding (DNE) is to efficiently update node embeddings while preserving network topology at each time step. The idea of most existing DNE methods is to capture the topological changes at or around the most affected nodes (instead of all nodes) and accordingly update node embeddings. Unfortunately, this kind of approximation, although can improve efficiency, cannot effectively preserve the global topology of a dynamic network at each time step, due to not considering the inactive sub-networks that receive accumulated topological changes propagated via the high-order proximity. To tackle this challenge, we propose a novel node selecting strategy to diversely select the representative nodes over a network, which is coordinated with a new incremental learning paradigm of Skip-Gram based embedding approach. The extensive experiments show GloDyNE, with a small fraction of nodes being selected, can already achieve the superior or comparable performance w.r.t. the state-of-the-art DNE methods in three typical downstream tasks. Particularly, GloDyNE significantly outperforms other methods in the graph reconstruction task, which demonstrates its ability of global topology preservation. The source code is available at https://github.com/houchengbin/GloDyNE

Chengbin Hou, Han Zhang, Ke Tang et al.

Learning topological representation of a network in dynamic environments has recently attracted considerable attention due to the time-evolving nature of many real-world networks i.e. nodes/links might be added/removed as time goes on. Dynamic network embedding aims to learn low dimensional embeddings for unseen and seen nodes by using any currently available snapshots of a dynamic network. For seen nodes, the existing methods either treat them equally important or focus on the $k$ most affected nodes at each time step. However, the former solution is time-consuming, and the later solution that relies on incoming changes may lose the global topology---an important feature for downstream tasks. To address these challenges, we propose a dynamic network embedding method called DynWalks, which includes two key components: 1) An online network embedding framework that can dynamically and efficiently learn embeddings based on the selected nodes; 2) A novel online node selecting scheme that offers the flexible choices to balance global topology and recent changes, as well as to fulfill the real-time constraint if needed. The empirical studies on six real-world dynamic networks under three different slicing ways show that DynWalks significantly outperforms the state-of-the-art methods in graph reconstruction tasks, and obtains comparable results in link prediction tasks. Furthermore, the wall-clock time and complexity analysis demonstrate its excellent time and space efficiency. The source code of DynWalks is available at https://github.com/houchengbin/DynWalks

Yuzhe Weng, Haotian Wang, Yuanhong Yu et al.

Audio-driven talking head generation aims to create vivid and realistic videos from a static portrait and speech. Existing AR-based methods rely on intermediate facial representations, which limit their expressiveness and realism. Meanwhile, diffusion-based methods generate clip-by-clip, lacking fine-grained control and causing inherent latency due to overall denoising across the window. To address these limitations, we propose EARTalking, a novel end-to-end, GPT-style autoregressive model for interactive audio-driven talking head generation. Our method introduces a novel frame-by-frame, in-context, audio-driven streaming generation paradigm. For inherently supporting variable-length video generation with identity consistency, we propose the Sink Frame Window Attention (SFA) mechanism. Furthermore, to avoid the complex, separate networks that prior works required for diverse control signals, we propose a streaming Frame Condition In-Context (FCIC) scheme. This scheme efficiently injects diverse control signals in a streaming, in-context manner, enabling interactive control at every frame and at arbitrary moments. Experiments demonstrate that EARTalking outperforms existing autoregressive methods and achieves performance comparable to diffusion-based methods. Our work demonstrates the feasibility of in-context streaming autoregressive control, unlocking a scalable direction for flexible, efficient generation. The code will be released for reproducibility.

Haotian Wang, Yuzhe Weng, Jun Du et al.

Diffusion models have significantly advanced the field of talking head generation (THG). However, slow inference speeds and prevalent non-autoregressive paradigms severely constrain the application of diffusion-based THG models. In this study, we propose REST, a pioneering diffusion-based, real-time, end-to-end streaming audio-driven talking head generation framework. To support real-time end-to-end generation, a compact video latent space is first learned through a spatiotemporal variational autoencoder with a high compression ratio. Additionally, to enable semi-autoregressive streaming within the compact video latent space, we introduce an ID-Context Cache mechanism, which integrates ID-Sink and Context-Cache principles into key-value caching for maintaining identity consistency and temporal coherence during long-term streaming generation. Furthermore, an Asynchronous Streaming Distillation (ASD) strategy is proposed to mitigate error accumulation and enhance temporal consistency in streaming generation, leveraging a non-streaming teacher with an asynchronous noise schedule to supervise the streaming student. REST bridges the gap between autoregressive and diffusion-based approaches, achieving a breakthrough in efficiency for applications requiring real-time THG. Experimental results demonstrate that REST outperforms state-of-the-art methods in both generation speed and overall performance.

Xinquan Chen, Zhenyun Yin, Shan He et al.

As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment interaction. Existing agenticinfrastructure remain fragmented across evaluation, data management, and agent evolution, making it difficult to discover risks systematically and improve models in a continuous closed loop. In this report, we present \textbf{Safactory}, a scalable agent factory for trustworthy autonomous intelligence. Safactory integrates three tightly coupled platforms: a \textbf{Parallel Simulation Platform} for trajectory generation, a \textbf{Trustworthy Data Platform} for trajectory storage and experience extraction, and an \textbf{Autonomous Evolution Platform} for asynchronous reinforcement learning and on-policy distillation. As far as we know, Safactory is the first framework to propose a unified evolutionary pipeline for next-generation trustworthy autonomous intelligence.

Haotian Wang, Yuzhe Weng, Yueyan Li et al.

Diffusion models have revolutionized the field of talking head generation, yet still face challenges in expressiveness, controllability, and stability in long-time generation. In this research, we propose an EmotiveTalk framework to address these issues. Firstly, to realize better control over the generation of lip movement and facial expression, a Vision-guided Audio Information Decoupling (V-AID) approach is designed to generate audio-based decoupled representations aligned with lip movements and expression. Specifically, to achieve alignment between audio and facial expression representation spaces, we present a Diffusion-based Co-speech Temporal Expansion (Di-CTE) module within V-AID to generate expression-related representations under multi-source emotion condition constraints. Then we propose a well-designed Emotional Talking Head Diffusion (ETHD) backbone to efficiently generate highly expressive talking head videos, which contains an Expression Decoupling Injection (EDI) module to automatically decouple the expressions from reference portraits while integrating the target expression information, achieving more expressive generation performance. Experimental results show that EmotiveTalk can generate expressive talking head videos, ensuring the promised controllability of emotions and stability during long-time generation, yielding state-of-the-art performance compared to existing methods.

Shan He, Runze Wang, Zhuoyun Du et al.

Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat prompt tuning, lack the structural awareness to debug the intricate web of interactions in MAS. More critically, these optimizers are static; they do not learn from experience to improve their own optimization strategies. To address these gaps, we introduce Textual Parameter Graph Optimization (TPGO), a framework that enables a multi-agent system to learn to evolve. TPGO first models the MAS as a Textual Parameter Graph (TPG), where agents, tools, and workflows are modular, optimizable nodes. To guide evolution, we derive "textual gradients," structured natural language feedback from execution traces, to pinpoint failures and suggest granular modifications. The core of our framework is Group Relative Agent Optimization (GRAO), a novel meta-learning strategy that learns from historical optimization experiences. By analyzing past successes and failures, GRAO becomes progressively better at proposing effective updates, allowing the system to learn how to optimize itself. Extensive experiments on complex benchmarks like GAIA and MCP-Universe show that TPGO significantly enhances the performance of state-of-the-art agent frameworks, achieving higher success rates through automated, self-improving optimization.

Dongfang Li, Baotian Hu, Qingcai Chen et al.

Feature attribution methods highlight the important input tokens as explanations to model predictions, which have been widely applied to deep neural networks towards trustworthy AI. However, recent works show that explanations provided by these methods face challenges of being faithful and robust. In this paper, we propose a method with Robustness improvement and Explanation Guided training towards more faithful EXplanations (REGEX) for text classification. First, we improve model robustness by input gradient regularization technique and virtual adversarial training. Secondly, we use salient ranking to mask noisy tokens and maximize the similarity between model attention and feature attribution, which can be seen as a self-training procedure without importing other external information. We conduct extensive experiments on six datasets with five attribution methods, and also evaluate the faithfulness in the out-of-domain setting. The results show that REGEX improves fidelity metrics of explanations in all settings and further achieves consistent gains based on two randomization tests. Moreover, we show that using highlight explanations produced by REGEX to train select-then-predict models results in comparable task performance to the end-to-end method.

Shan He, Ruiyang Zhang

Accurate prediction of seismic responses and quantification of structural damage are critical in civil engineering. Traditional approaches such as finite element analysis could lack computational efficiency, especially for complex structural systems under extreme hazards. Recently, artificial intelligence has provided an alternative to efficiently model highly nonlinear behaviors. However, existing models face challenges in generalizing across diverse structural systems. This paper proposes a novel multi-channel gated recurrent unit (MC-GRU) network aimed at achieving generalized nonlinear structural response prediction for varying structures. The key concept lies in the integration of a multi-channel input mechanism to GRU with an extra input of structural information to the candidate hidden state, which enables the network to learn the dynamic characteristics of diverse structures and thus empower the generalizability and adaptiveness to unseen structures. The performance of the proposed MC-GRU is validated through a series of case studies, including a single-degree-of-freedom linear system, a hysteretic Bouc-Wen system, and a nonlinear reinforced concrete column from experimental testing. Results indicate that the proposed MC-GRU overcomes the major generalizability issues of existing methods, with capability of accurately inferring seismic responses of varying structures. Additionally, it demonstrates enhanced capabilities in representing nonlinear structural dynamics compared to traditional models such as GRU and LSTM.

Zhangfan Yang, Junkai Ji, Shan He et al.

Molecular docking is a crucial step in drug development, which enables the virtual screening of compound libraries to identify potential ligands that target proteins of interest. However, the computational complexity of traditional docking models increases as the size of the compound library increases. Recently, deep learning algorithms can provide data-driven research and development models to increase the speed of the docking process. Unfortunately, few models can achieve superior screening performance compared to that of traditional models. Therefore, a novel deep learning-based docking approach named Dockformer is introduced in this study. Dockformer leverages multimodal information to capture the geometric topology and structural knowledge of molecules and can directly generate binding conformations with the corresponding confidence measures in an end-to-end manner. The experimental results show that Dockformer achieves success rates of 90.53% and 82.71% on the PDBbind core set and PoseBusters benchmarks, respectively, and more than a 100-fold increase in the inference process speed, outperforming almost all state-of-the-art docking methods. In addition, the ability of Dockformer to identify the main protease inhibitors of coronaviruses is demonstrated in a real-world virtual screening scenario. Considering its high docking accuracy and screening efficiency, Dockformer can be regarded as a powerful and robust tool in the field of drug design.

Haotian Wang, Yuzhe Weng, Jun Du et al.

The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely limits the practical implementation of diffusion-based talking head generation models. In this study, we propose READ, a real-time diffusion-transformer-based talking head generation framework. Our approach first learns a spatiotemporal highly compressed video latent space via a temporal VAE, significantly reducing the token count to accelerate generation. To achieve better audio-visual alignment within this compressed latent space, a pre-trained Speech Autoencoder (SpeechAE) is proposed to generate temporally compressed speech latent codes corresponding to the video latent space. These latent representations are then modeled by a carefully designed Audio-to-Video Diffusion Transformer (A2V-DiT) backbone for efficient talking head synthesis. Furthermore, to ensure temporal consistency and accelerated inference in extended generation, we propose a novel asynchronous noise scheduler (ANS) for both the training and inference processes of our framework. The ANS leverages asynchronous add-noise and asynchronous motion-guided generation in the latent space, ensuring consistency in generated video clips. Experimental results demonstrate that READ outperforms state-of-the-art methods by generating competitive talking head videos with significantly reduced runtime, achieving an optimal balance between quality and speed while maintaining robust metric stability in long-time generation.

Guozhi Yuan, Youfeng Liu, Jingli Yang et al.

Based on their superior comprehension and reasoning capabilities, Large Language Model (LLM) driven agent frameworks have achieved significant success in numerous complex reasoning tasks. ReAct-like agents can solve various intricate problems step-by-step through progressive planning and tool calls, iteratively optimizing new steps based on environmental feedback. However, as the planning capabilities of LLMs improve, the actions invoked by tool calls in ReAct-like frameworks often misalign with complex planning and challenging data organization. Code Action addresses these issues while also introducing the challenges of a more complex action space and more difficult action organization. To leverage Code Action and tackle the challenges of its complexity, this paper proposes Policy and Action Dual-Control Agent (PoAct) for generalized applications. The aim is to achieve higher-quality code actions and more accurate reasoning paths by dynamically switching reasoning policies and modifying the action space. Experimental results on the Agent Benchmark for both legal and generic scenarios demonstrate the superior reasoning capabilities and reduced token consumption of our approach in complex tasks. On the LegalAgentBench, our method shows a 20 percent improvement over the baseline while requiring fewer tokens. We conducted experiments and analyses on the GPT-4o and GLM-4 series models, demonstrating the significant potential and scalability of our approach to solve complex problems.

Rui He, Shengcai Liu, Jiahao Wu et al.

Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of models on datasets collected from different domains. Conventional approaches emphasize domain-shared information extraction and domain-private information preservation, following the shared-private framework (SP models), which offers significant advantages over single-domain learning. However, the limited availability of annotated data in each domain considerably hinders the effectiveness of conventional supervised MDL approaches in real-world applications. In this paper, we introduce a novel method called multi-domain contrastive learning (MDCL) to alleviate the impact of insufficient annotations by capturing both semantic and structural information from both labeled and unlabeled data.Specifically, MDCL comprises two modules: inter-domain semantic alignment and intra-domain contrast. The former aims to align annotated instances of the same semantic category from distinct domains within a shared hidden space, while the latter focuses on learning a cluster structure of unlabeled instances in a private hidden space for each domain. MDCL is readily compatible with many SP models, requiring no additional model parameters and allowing for end-to-end training. Experimental results across five textual and image multi-domain datasets demonstrate that MDCL brings noticeable improvement over various SP models.Furthermore, MDCL can further be employed in multi-domain active learning (MDAL) to achieve a superior initialization, eventually leading to better overall performance.

Gourab Ghosh Roy, Nicholas Geard, Karin Verspoor et al.

Survival risk prediction using gene expression data is important in making treatment decisions in cancer. Standard neural network (NN) survival analysis models are black boxes with lack of interpretability. More interpretable visible neural network (VNN) architectures are designed using biological pathway knowledge. But they do not model how pathway structures can change for particular cancer types. We propose a novel Mutated Pathway VNN or MPVNN architecture, designed using prior signaling pathway knowledge and gene mutation data-based edge randomization simulating signal flow disruption. As a case study, we use the PI3K-Akt pathway and demonstrate overall improved cancer-specific survival risk prediction results of MPVNN over standard non-NN and other similar sized NN survival analysis methods. We show that trained MPVNN architecture interpretation, which points to smaller sets of genes connected by signal flow within the PI3K-Akt pathway that are important in risk prediction for particular cancer types, is reliable.

Yingying Wang, Cunliang Kong, Liner Yang et al.

Learner corpus collects language data produced by L2 learners, that is second or foreign-language learners. This resource is of great relevance for second language acquisition research, foreign-language teaching, and automatic grammatical error correction. However, there is little focus on learner corpus for Chinese as Foreign Language (CFL) learners. Therefore, we propose to construct a large-scale, multidimensional annotated Chinese learner corpus. To construct the corpus, we first obtain a large number of topic-rich texts generated by CFL learners. Then we design an annotation scheme including a sentence acceptability score as well as grammatical error and fluency-based corrections. We build a crowdsourcing platform to perform the annotation effectively (https://yaclc.wenmind.net). We name the corpus YACLC (Yet Another Chinese Learner Corpus) and release it as part of the CUGE benchmark (http://cuge.baai.ac.cn). By analyzing the original sentences and annotations in the corpus, we found that YACLC has a considerable size and very high annotation quality. We hope this corpus can further enhance the studies on Chinese International Education and Chinese automatic grammatical error correction.

Rui He, Shengcai Liu, Shan He et al.

Multi-domain learning (MDL) refers to learning a set of models simultaneously, where each model is specialized to perform a task in a particular domain. Generally, a high labeling effort is required in MDL, as data needs to be labeled by human experts for every domain. Active learning (AL) can be utilized in MDL to reduce the labeling effort by only using the most informative data. The resultant paradigm is termed multi-domain active learning (MDAL). In this work, we provide an exhaustive literature review for MDAL on the relevant fields, including AL, cross-domain information sharing schemes, and cross-domain instance evaluation approaches. It is found that the few studies which have been directly conducted on MDAL cannot serve as off-the-shelf solutions on more general MDAL tasks. To fill this gap, we construct a pipeline of MDAL and present a comprehensive comparative study of thirty different algorithms, which are established by combining six representative MDL models and five commonly used AL strategies. We evaluate the algorithms on six datasets involving textual and visual classification tasks. In most cases, AL brings notable improvements to MDL, and the naive BvSB (best vs. second best) Uncertainty strategy can perform competitively with the state-of-the-art AL strategies. Besides, BvSB with the MAN (multinomial adversarial networks) model can consistently achieve top or above-average performance on all the datasets. Furthermore, we qualitatively analyze the behaviors of the well-performed strategies and models, shedding light on their superior performance in the comparison. Finally, we recommend using BvSB with the MAN model in the application of MDAL due to their good performance in the experiments.

Bo Peng, Hongxing Fan, Wei Wang et al.

This paper presents a summary of the DFGC 2021 competition. DeepFake technology is developing fast, and realistic face-swaps are increasingly deceiving and hard to detect. At the same time, DeepFake detection methods are also improving. There is a two-party game between DeepFake creators and detectors. This competition provides a common platform for benchmarking the adversarial game between current state-of-the-art DeepFake creation and detection methods. In this paper, we present the organization, results and top solutions of this competition and also share our insights obtained during this event. We also release the DFGC-21 testing dataset collected from our participants to further benefit the research community.

Chengbin Hou, Guoji Fu, Peng Yang et al.

Dynamic Network Embedding (DNE) has recently attracted considerable attention due to the advantage of network embedding in various fields and the dynamic nature of many real-world networks. An input dynamic network to DNE is often assumed to have smooth changes over snapshots, which however would not hold for all real-world scenarios. It is natural to ask if existing DNE methods can perform well for an input dynamic network without smooth changes. To quantify it, an index called Degree of Changes (DoCs) is suggested so that the smaller DoCs indicates the smoother changes. Our comparative study shows several DNE methods are not robust enough to different DoCs even if the corresponding input dynamic networks come from the same dataset, which would make these methods unreliable and hard to use for unknown real-world applications. To propose an effective and more robust DNE method, we follow the notion of ensembles where each base learner adopts an incremental Skip-Gram embedding model. To further boost the performance, a simple yet effective strategy is designed to enhance the diversity among base learners at each timestep by capturing different levels of local-global topology. Extensive experiments demonstrate the superior effectiveness and robustness of the proposed method compared to state-of-the-art DNE methods, as well as the benefits of special designs in the proposed method and its scalability.

John Ahlgren, Maria Eugenia Berezin, Kinga Bojarczuk et al.

Software-intensive organizations rely on large numbers of software assets of different types, e.g., source-code files, tables in the data warehouse, and software configurations. Who is the most suitable owner of a given asset changes over time, e.g., due to reorganization and individual function changes. New forms of automation can help suggest more suitable owners for any given asset at a given point in time. By such efforts on ownership health, accountability of ownership is increased. The problem of finding the most suitable owners for an asset is essentially a program comprehension problem: how do we automatically determine who would be best placed to understand, maintain, evolve (and thereby assume ownership of) a given asset. This paper introduces the Facebook Ownesty system, which uses a combination of ultra large scale data mining and machine learning and has been deployed at Facebook as part of the company's ownership management approach. Ownesty processes many millions of software assets (e.g., source-code files) and it takes into account workflow and organizational aspects. The paper sets out open problems and challenges on ownership for the research community with advances expected from the fields of software engineering, programming languages, and machine learning.

Chuang Wang, Ruimin Hu, Min Hu et al.

Unlike the constraint frontal face condition, faces in the wild have various unconstrained interference factors, such as complex illumination, changing perspective and various occlusions. Facial expressions recognition (FER) in the wild is a challenging task and existing methods can't perform well. However, for occluded faces (containing occlusion caused by other objects and self-occlusion caused by head posture changes), the attention mechanism has the ability to focus on the non-occluded regions automatically. In this paper, we propose a Lossless Attention Model (LLAM) for convolutional neural networks (CNN) to extract attention-aware features from faces. Our module avoids decay information in the process of generating attention maps by using the information of the previous layer and not reducing the dimensionality. Sequentially, we adaptively refine the feature responses by fusing the attention map with the feature map. We participate in the seven basic expression classification sub-challenges of FG-2020 Affective Behavior Analysis in-the-wild Challenge. And we validate our method on the Aff-Wild2 datasets released by the Challenge. The total accuracy (Accuracy) and the unweighted mean (F1) of our method on the validation set are 0.49 and 0.38 respectively, and the final result is 0.42 (0.67 F1-Score + 0.33 Accuracy).

Chengbin Hou, Shan He, Ke Tang

Attributed networks are ubiquitous since a network often comes with auxiliary attribute information e.g. a social network with user profiles. Attributed Network Embedding (ANE) has recently attracted considerable attention, which aims to learn unified low dimensional node embeddings while preserving both structural and attribute information. The resulting node embeddings can then facilitate various network downstream tasks e.g. link prediction. Although there are several ANE methods, most of them cannot deal with incomplete attributed networks with missing links and/or missing node attributes, which often occur in real-world scenarios. To address this issue, we propose a robust ANE method, the general idea of which is to reconstruct a unified denser network by fusing two sources of information for information enhancement, and then employ a random walks based network embedding method for learning node embeddings. The experiments of link prediction, node classification, visualization, and parameter sensitivity analysis on six real-world datasets validate the effectiveness of our method to incomplete attributed networks.