Hao Xu

Xuan Yang, Hao Xu, Tingfeng Hui et al.

Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world scenarios. Such benchmarks mostly rely on simulated idealized user assumptions and lacks experience-oriented evaluation. These limitations fail to account for the ambiguity, uncooperative behaviors, and shifting intentions characteristic of real-world users. To fill this gap, we propose RUT-Bench, a dedicated benchmark designed to assess LLMs under diverse Real-world User Tool calling scenarios. RUT-Bench supports high-fidelity simulations covering both ideal rational patterns and heterogeneous non-ideal behaviors across single-turn and multi-turn dialogues. We conduct comprehensive evaluations on 19 widely adopted open-source and proprietary LLMs using our benchmark. Experimental results reveal that no tested LLMs achieve an overall success rate above 40%, and nearly all of them experience noticeable performance drops when facing more complicated non-ideal user inputs. Our code and data is available at https://github.com/Miaow-Lab/RUT-Bench.

Xueting Yang, Yihao Luo, Yuliang Xiu et al.

Realistic virtual humans play a crucial role in numerous industries, such as metaverse, intelligent healthcare, and self-driving simulation. But creating them on a large scale with high levels of realism remains a challenge. The utilization of deep implicit function sparks a new era of image-based 3D clothed human reconstruction, enabling pixel-aligned shape recovery with fine details. Subsequently, the vast majority of works locate the surface by regressing the deterministic implicit value for each point. However, should all points be treated equally regardless of their proximity to the surface? In this paper, we propose replacing the implicit value with an adaptive uncertainty distribution, to differentiate between points based on their distance to the surface. This simple ``value to distribution'' transition yields significant improvements on nearly all the baselines. Furthermore, qualitative results demonstrate that the models trained using our uncertainty distribution loss, can capture more intricate wrinkles, and realistic limbs. Code and models are available for research purposes at https://github.com/psyai-net/D-IF_release.

Hao Xu, Tengfei Xue, Dongnan Liu et al.

White matter (WM) tract segmentation based on diffusion magnetic resonance imaging (dMRI) plays an important role in the analysis of human health and brain diseases. However, the annotation of WM tracts is time-consuming and needs experienced neuroanatomists. In this study, to explore tract segmentation in the challenging setting of minimal annotations, we propose a novel framework utilizing only one annotated subject (subject-level one-shot) for tract segmentation. Our method is constructed by proposed registration-based peak augmentation (RPA) and uncertainty-based refining (URe) modules. RPA module synthesizes pseudo subjects and their corresponding labels to improve the tract segmentation performance. The proposed URe module alleviates the negative influence of the low-confidence voxels on pseudo subjects. Experimental results show that our method outperforms other state-of-the-art methods by a large margin, and our proposed modules are effective. Overall, our method achieves accurate whole-brain tract segmentation with only one annotated subject. Our code is available at https://github.com/HaoXu0507/ISBI2023-One-Shot-WM-Tract-Segmentation.

Hongyu Ding, Sizhuo Zhang, Ziming Xu et al.

Embodied navigation requires an agent to map language and visual observations to a stream of spatial actions that drive a real robot through environments it has never seen. The dominant approach has been to scale vision-language-action (VLA) foundation models on ever-larger collections of robot trajectories. This paper argues that, for navigation specifically, generality can be obtained structurally, not only through data scale. The underlying decision structure of navigation reduces to a single Language-Vision-Robot Actions Translation. The language action emits semantic-level directional command and the vision action emits a pixel-level visual target. Both outputs lie inside the natural output manifold of pretrained multimodal large language models (MLLMs), so the task can be reasoned about by an agent rather than learned from robot data. Therefore, we present Uni-LaViRA, a unified agentic architecture that extends the same insight to four task families (VLN-CE, ObjectNav, EQA, and Aerial-VLN) and to four heterogeneous real robots (Wheeled, Quadruped, Humanoid robot, and a self-built UAV) in a zero-shot manner. Two agent-loop mechanisms make this unification practical. TODO List Memory (TDM) rewrites a structured checklist of pending sub-goals at every step, reciting the unfinished items back into the agent's most recent attention window. Second Chance Backtrack (SCB) rolls the robot back to the pre-error state and conditions the agent's next plan on the failed sub-trajectory, turning single-pass navigation into a self-correcting process. With zero training effort, Uni-LaViRA reaches 60.7% SR on VLN-CE R2R, 51.3% on VLN-CE RxR, 77.7% on HM3D-v2, 60.0% on HM3D-OVON, 54.7% on MP3D-EQA, and 40.0% on OpenUAV, matching or even surpassing recent training navigation foundation models that consume millions of samples and thousands of GPU-hours.

Simon Dahan, Hao Xu, Logan Z. J. Williams et al.

Recent state-of-the-art performances of Vision Transformers (ViT) in computer vision tasks demonstrate that a general-purpose architecture, which implements long-range self-attention, could replace the local feature learning operations of convolutional neural networks. In this paper, we extend ViTs to surfaces by reformulating the task of surface learning as a sequence-to-sequence learning problem, by proposing patching mechanisms for general surface meshes. Sequences of patches are then processed by a transformer encoder and used for classification or regression. We validate our method on a range of different biomedical surface domains and tasks: brain age prediction in the developing Human Connectome Project (dHCP), fluid intelligence prediction in the Human Connectome Project (HCP), and coronary artery calcium score classification using surfaces from the Scottish Computed Tomography of the Heart (SCOT-HEART) dataset, and investigate the impact of pretraining and data augmentation on model performance. Results suggest that Surface Vision Transformers (SiT) demonstrate consistent improvement over geometric deep learning methods for brain age and fluid intelligence prediction and achieve comparable performance on calcium score classification to standard metrics used in clinical practice. Furthermore, analysis of transformer attention maps offers clear and individualised predictions of the features driving each task. Code is available on Github: https://github.com/metrics-lab/surface-vision-transformers

Xiaoyu Zhu, Hao Zhou, Pengfei Xing et al. · deepmind

In this paper, we investigate the use of diffusion models which are pre-trained on large-scale image-caption pairs for open-vocabulary 3D semantic understanding. We propose a novel method, namely Diff2Scene, which leverages frozen representations from text-image generative models, along with salient-aware and geometric-aware masks, for open-vocabulary 3D semantic segmentation and visual grounding tasks. Diff2Scene gets rid of any labeled 3D data and effectively identifies objects, appearances, materials, locations and their compositions in 3D scenes. We show that it outperforms competitive baselines and achieves significant improvements over state-of-the-art methods. In particular, Diff2Scene improves the state-of-the-art method on ScanNet200 by 12%.

Huadeng Wang, Hao Xu, Bingbing Li et al.

Mitosis detection is one of the challenging problems in computational pathology, and mitotic count is an important index of cancer grading for pathologists. However, current counts of mitotic nuclei rely on pathologists looking microscopically at the number of mitotic nuclei in hot spots, which is subjective and time-consuming. In this paper, we propose a two-stage cascaded network, named FoCasNet, for mitosis detection. In the first stage, a detection network named M_det is proposed to detect as many mitoses as possible. In the second stage, a classification network M_class is proposed to refine the results of the first stage. In addition, the attention mechanism, normalization method, and hybrid anchor branch classification subnet are introduced to improve the overall detection performance. Our method achieves the current highest F1-score of 0.888 on the public dataset ICPR 2012. We also evaluated our method on the GZMH dataset released by our research team for the first time and reached the highest F1-score of 0.563, which is also better than multiple classic detection networks widely used at present. It confirmed the effectiveness and generalization of our method. The code will be available at: https://github.com/antifen/mitosis-nuclei-detection.

Yiyang Xu, Hao Xu, Matthew Sinclair et al.

Cardiac magnetic resonance (CMR) imaging and computed tomography (CT) are two common non-invasive imaging methods for assessing patients with cardiovascular disease. CMR typically acquires multiple sparse 2D slices, with unavoidable respiratory motion artefacts between slices, whereas CT acquires isotropic dense data but uses ionising radiation. In this study, we explore the combination of Slice Shifting Algorithm (SSA), Spatial Transformer Network (STN), and Label Transformer Network (LTN) to: 1) correct respiratory motion between segmented slices, and 2) transform sparse segmentation data into dense segmentation. All combinations were validated using synthetic motion-corrupted CMR slice segmentation generated from CT in 1699 cases, where the dense CT serves as the ground truth. In 199 testing cases, SSA-LTN achieved the best results for Dice score and Huasdorff distance (94.0% and 4.7 mm respectively, average over 5 labels) but gave topological errors in 8 cases. STN was effective as a plug-in tool for correcting all topological errors with minimal impact on overall performance (93.5% and 5.0 mm respectively). SSA also proves to be a valuable plug-in tool, enhancing performance over both STN-based and LTN-based models. The code for these different combinations is available at https://github.com/XESchong/STACOM2024.

Lin Ma, Jiangtao Gong, Hao Xu et al.

Assembly sequence planning (ASP) is the essential process for modern manufacturing, proven to be NP-complete thus its effective and efficient solution has been a challenge for researchers in the field. In this paper, we present a graph-transformer based framework for the ASP problem which is trained and demonstrated on a self-collected ASP database. The ASP database contains a self-collected set of LEGO models. The LEGO model is abstracted to a heterogeneous graph structure after a thorough analysis of the original structure and feature extraction. The ground truth assembly sequence is first generated by brute-force search and then adjusted manually to in line with human rational habits. Based on this self-collected ASP dataset, we propose a heterogeneous graph-transformer framework to learn the latent rules for assembly planning. We evaluated the proposed framework in a series of experiment. The results show that the similarity of the predicted and ground truth sequences can reach 0.44, a medium correlation measured by Kendall's $τ$. Meanwhile, we compared the different effects of node features and edge features and generated a feasible and reasonable assembly sequence as a benchmark for further research. Our data set and code is available on https://github.com/AIR-DISCOVER/ICRA\_ASP.

Hao Yang, Hao Xu, Kai Wan et al.

This paper investigates a cooperative jamming (CJ)-aided secure wireless communication system. Conventional CJ schemes transmit Gaussian noise (GN) to improve security, which inherently degrades the legitimate receiver's performance. While encoded jamming (EJ) mitigates this interference, its superiority over GN is highly channel-dependent. To overcome this limitation, we introduce a joint optimization framework integrating a reconfigurable intelligent surface (RIS) with EJ to maximize the secrecy rate. \RED{We first establish the information-theoretic relationship between the EJ and GN schemes, identifying the spatial channel conditions that limit EJ performance. For the multiple-input single-output (MISO) scenario, we analytically derive the ergodic secrecy gap as the number of RIS elements grows large and obtain a positive EJ-over-GN gap under explicit power and channel conditions.} Furthermore, for the general multiple-input multiple-output (MIMO) setup, we develop a low-complexity algorithm based on the weighted minimum mean-square-error (WMMSE) framework to handle the resulting non-smooth max-min structure through a WMMSE-based mode-selection framework. By introducing a parameterized function abstraction, the transmit precoding matrices and the RIS phase shift matrix are jointly optimized via block coordinate descent (BCD). Simulation results support the analysis and show that, under the evaluated settings, RIS-assisted EJ can overcome the identified spatial bottlenecks and outperform the optimized GN baseline.

Hao Xu, Bo Li, Fei Zhong

Fire-detection technology is of great importance for successful fire-prevention measures. Image-based fire detection is one effective method. At present, object-detection algorithms are deficient in performing detection speed and accuracy tasks when they are applied in complex fire scenarios. In this study, a lightweight fire-detection algorithm, Light-YOLOv5 (You Only Look Once version five), is presented. First, a separable vision transformer (SepViT) block is used to replace several C3 modules in the final layer of a backbone network to enhance both the contact of the backbone network to global in-formation and the extraction of flame and smoke features; second, a light bidirectional feature pyramid network (Light-BiFPN) is designed to lighten the model while improving the feature extraction and balancing speed and accuracy features during a fire-detection procedure; third, a global attention mechanism (GAM) is fused into the network to cause the model to focus more on the global dimensional features and further improve the detection accuracy of the model; and finally, the Mish activation function and SIoU loss are utilized to simultaneously increase the convergence speed and enhance the accuracy. The experimental results show that compared to the original algorithm, the mean average accuracy (mAP) of Light-YOLOv5 increases by 3.3%, the number of parameters decreases by 27.1%, and the floating point operations (FLOPs) decrease by 19.1%. The detection speed reaches 91.1 FPS, which can detect targets in complex fire scenarios in real time.

Chao Li, Zijie Guo, Qiuting He et al.

Utilizing long-range dependency, a concept extensively studied in homogeneous graphs, remains underexplored in heterogeneous graphs, especially on large ones, posing two significant challenges: Reducing computational costs while maximizing effective information utilization in the presence of heterogeneity, and overcoming the over-smoothing issue in graph neural networks. To address this gap, we investigate the importance of different meta-paths and introduce an automatic framework for utilizing long-range dependency on heterogeneous graphs, denoted as Long-range Meta-path Search through Progressive Sampling (LMSPS). Specifically, we develop a search space with all meta-paths related to the target node type. By employing a progressive sampling algorithm, LMSPS dynamically shrinks the search space with hop-independent time complexity. Through a sampling evaluation strategy, LMSPS conducts a specialized and effective meta-path selection, leading to retraining with only effective meta-paths, thus mitigating costs and over-smoothing. Extensive experiments across diverse heterogeneous datasets validate LMSPS's capability in discovering effective long-range meta-paths, surpassing state-of-the-art methods. Our code is available at https://github.com/JHL-HUST/LMSPS.

Hao Xu, Junsheng Zeng, Dongxiao Zhang

Data-driven discovery of PDEs has made tremendous progress recently, and many canonical PDEs have been discovered successfully for proof-of-concept. However, determining the most proper PDE without prior references remains challenging in terms of practical applications. In this work, a physics-informed information criterion (PIC) is proposed to measure the parsimony and precision of the discovered PDE synthetically. The proposed PIC achieves state-of-the-art robustness to highly noisy and sparse data on seven canonical PDEs from different physical scenes, which confirms its ability to handle difficult situations. The PIC is also employed to discover unrevealed macroscale governing equations from microscopic simulation data in an actual physical scene. The results show that the discovered macroscale PDE is precise and parsimonious, and satisfies underlying symmetries, which facilitates understanding and simulation of the physical process. The proposition of PIC enables practical applications of PDE discovery in discovering unrevealed governing equations in broader physical scenes.

Ziqiao Peng, Haoyu Wu, Zhenbo Song et al.

Speech-driven 3D face animation aims to generate realistic facial expressions that match the speech content and emotion. However, existing methods often neglect emotional facial expressions or fail to disentangle them from speech content. To address this issue, this paper proposes an end-to-end neural network to disentangle different emotions in speech so as to generate rich 3D facial expressions. Specifically, we introduce the emotion disentangling encoder (EDE) to disentangle the emotion and content in the speech by cross-reconstructed speech signals with different emotion labels. Then an emotion-guided feature fusion decoder is employed to generate a 3D talking face with enhanced emotion. The decoder is driven by the disentangled identity, emotional, and content embeddings so as to generate controllable personal and emotional styles. Finally, considering the scarcity of the 3D emotional talking face data, we resort to the supervision of facial blendshapes, which enables the reconstruction of plausible 3D faces from 2D emotional data, and contribute a large-scale 3D emotional talking face dataset (3D-ETF) to train the network. Our experiments and user studies demonstrate that our approach outperforms state-of-the-art methods and exhibits more diverse facial movements. We recommend watching the supplementary video: https://ziqiaopeng.github.io/emotalk

Yuchao Zheng, Chen Li, Xiaomin Zhou et al.

Background: Breast cancer has the highest prevalence in women globally. The classification and diagnosis of breast cancer and its histopathological images have always been a hot spot of clinical concern. In Computer-Aided Diagnosis (CAD), traditional classification models mostly use a single network to extract features, which has significant limitations. On the other hand, many networks are trained and optimized on patient-level datasets, ignoring the application of lower-level data labels. Method: This paper proposes a deep ensemble model based on image-level labels for the binary classification of benign and malignant lesions of breast histopathological images. First, the BreaKHis dataset is randomly divided into a training, validation and test set. Then, data augmentation techniques are used to balance the number of benign and malignant samples. Thirdly, considering the performance of transfer learning and the complementarity between each network, VGG16, Xception, ResNet50, DenseNet201 are selected as the base classifiers. Result: In the ensemble network model with accuracy as the weight, the image-level binary classification achieves an accuracy of $98.90\%$. In order to verify the capabilities of our method, the latest Transformer and Multilayer Perception (MLP) models have been experimentally compared on the same dataset. Our model wins with a $5\%-20\%$ advantage, emphasizing the ensemble model's far-reaching significance in classification tasks. Conclusion: This research focuses on improving the model's classification performance with an ensemble algorithm. Transfer learning plays an essential role in small datasets, improving training speed and accuracy. Our model has outperformed many existing approaches in accuracy, providing a method for the field of auxiliary medical diagnosis.

Binzhu Xie, Shi Qiu, Sicheng Zhang et al.

Robust 3D hand reconstruction in egocentric vision is challenging due to depth ambiguity, self-occlusion, and complex hand-object interactions. Prior methods mitigate these issues by scaling training data or adding auxiliary cues, but they often struggle in unseen contexts. We present EgoHandICL, the first in-context learning (ICL) framework for 3D hand reconstruction that improves semantic alignment, visual consistency, and robustness under challenging egocentric conditions. EgoHandICL introduces complementary exemplar retrieval guided by vision-language models (VLMs), an ICL-tailored tokenizer for multimodal context, and a masked autoencoder (MAE)-based architecture trained with hand-guided geometric and perceptual objectives. Experiments on ARCTIC and EgoExo4D show consistent gains over state-of-the-art methods. We also demonstrate real-world generalization and improve EgoVLM hand-object interaction reasoning by using reconstructed hands as visual prompts. Code and data: https://github.com/Nicous20/EgoHandICL

Zebin Ma, Yonglin Zou, Xiaobin Huang et al.

Functional peptides have the potential to treat a variety of diseases. Their good therapeutic efficacy and low toxicity make them ideal therapeutic agents. Artificial intelligence-based computational strategies can help quickly identify new functional peptides from collections of protein sequences and discover their different functions.Using protein language model-based embeddings (ESM-2), we developed a tool called pLMFPPred (Protein Language Model-based Functional Peptide Predictor) for predicting functional peptides and identifying toxic peptides. We also introduced SMOTE-TOMEK data synthesis sampling and Shapley value-based feature selection techniques to relieve data imbalance issues and reduce computational costs. On a validated independent test set, pLMFPPred achieved accuracy, Area under the curve - Receiver Operating Characteristics, and F1-Score values of 0.974, 0.99, and 0.974, respectively. Comparative experiments show that pLMFPPred outperforms current methods for predicting functional peptides.The experimental results suggest that the proposed method (pLMFPPred) can provide better performance in terms of Accuracy, Area under the curve - Receiver Operating Characteristics, and F1-Score than existing methods. pLMFPPred has achieved good performance in predicting functional peptides and represents a new computational method for predicting functional peptides.

Suyi Chen, Hao Xu, Haipeng Li et al.

Data plays a crucial role in training learning-based methods for 3D point cloud registration. However, the real-world dataset is expensive to build, while rendering-based synthetic data suffers from domain gaps. In this work, we present PointRegGPT, boosting 3D point cloud registration using generative point-cloud pairs for training. Given a single depth map, we first apply a random camera motion to re-project it into a target depth map. Converting them to point clouds gives a training pair. To enhance the data realism, we formulate a generative model as a depth inpainting diffusion to process the target depth map with the re-projected source depth map as the condition. Also, we design a depth correction module to alleviate artifacts caused by point penetration during the re-projection. To our knowledge, this is the first generative approach that explores realistic data generation for indoor point cloud registration. When equipped with our approach, several recent algorithms can improve their performance significantly and achieve SOTA consistently on two common benchmarks. The code and dataset will be released on https://github.com/Chen-Suyi/PointRegGPT.

Fausto Giunchiglia, Gabor Bella, Nandu Chandran Nair et al.

In today's multilingual lexical databases, the majority of the world's languages are under-represented. Beyond a mere issue of resource incompleteness, we show that existing lexical databases have structural limitations that result in a reduced expressivity on culturally-specific words and in mapping them across languages. In particular, the lexical meaning space of dominant languages, such as English, is represented more accurately while linguistically or culturally diverse languages are mapped in an approximate manner. Our paper assesses state-of-the-art multilingual lexical databases and evaluates their strengths and limitations with respect to their expressivity on lexical phenomena of linguistic diversity.

Bo Li, YiHua Chen, Hao Xu et al.

The swift and precise detection of vehicles plays a significant role in intelligent transportation systems. Current vehicle detection algorithms encounter challenges of high computational complexity, low detection rate, and limited feasibility on mobile devices. To address these issues, this paper proposes a lightweight vehicle detection algorithm based on YOLOv7-tiny (You Only Look Once version seven) called Ghost-YOLOv7. The width of model is scaled to 0.5 and the standard convolution of the backbone network is replaced with Ghost convolution to achieve a lighter network and improve the detection speed; then a self-designed Ghost bi-directional feature pyramid network (Ghost-BiFPN) is embedded into the neck network to enhance feature extraction capability of the algorithm and enriches semantic information; and a Ghost Decouoled Head (GDH) is employed for accurate prediction of vehicle location and species; finally, a coordinate attention mechanism is introduced into the output layer to suppress environmental interference. The WIoU loss function is employed to further enhance the detection accuracy. Ablation experiments results on the PASCAL VOC dataset demonstrate that Ghost-YOLOv7 outperforms the original YOLOv7-tiny model. It achieving a 29.8% reduction in computation, 37.3% reduction in the number of parameters, 35.1% reduction in model weights, 1.1% higher mean average precision (mAP), the detection speed is higher 27FPS compared with the original algorithm. Ghost-YOLOv7 was also compared on KITTI and BIT-vehicle datasets as well, and the results show that this algorithm has the overall best performance.

Ziqiao Peng, Yihao Luo, Yue Shi et al.

Speech-driven 3D face animation technique, extending its applications to various multimedia fields. Previous research has generated promising realistic lip movements and facial expressions from audio signals. However, traditional regression models solely driven by data face several essential problems, such as difficulties in accessing precise labels and domain gaps between different modalities, leading to unsatisfactory results lacking precision and coherence. To enhance the visual accuracy of generated lip movement while reducing the dependence on labeled data, we propose a novel framework SelfTalk, by involving self-supervision in a cross-modals network system to learn 3D talking faces. The framework constructs a network system consisting of three modules: facial animator, speech recognizer, and lip-reading interpreter. The core of SelfTalk is a commutative training diagram that facilitates compatible features exchange among audio, text, and lip shape, enabling our models to learn the intricate connection between these factors. The proposed framework leverages the knowledge learned from the lip-reading interpreter to generate more plausible lip shapes. Extensive experiments and user studies demonstrate that our proposed approach achieves state-of-the-art performance both qualitatively and quantitatively. We recommend watching the supplementary video.

Hao Xu, Jinglong Lin, Dongxiao Zhang et al.

A new research framework is proposed to incorporate machine learning techniques into the field of experimental chemistry to facilitate chromatographic enantioseparation. A documentary dataset of chiral molecular retention times (CMRT dataset) in high-performance liquid chromatography is established to handle the challenge of data acquisition. Based on the CMRT dataset, a quantile geometry-enhanced graph neural network is proposed to learn the molecular structure-retention time relationship, which shows a satisfactory predictive ability for enantiomers. The domain knowledge of chromatography is incorporated into the machine learning model to achieve multi-column prediction, which paves the way for chromatographic enantioseparation prediction by calculating the separation probability. Experiments confirm that the proposed research framework works well in retention time prediction and chromatographic enantioseparation facilitation, which sheds light on the application of machine learning techniques to the experimental scene and improves the efficiency of experimenters to speed up scientific discovery.

Xiaolei Diao, Daqian Shi, Jian Li et al.

Optical character recognition (OCR) methods have been applied to diverse tasks, e.g., street view text recognition and document analysis. Recently, zero-shot OCR has piqued the interest of the research community because it considers a practical OCR scenario with unbalanced data distribution. However, there is a lack of benchmarks for evaluating such zero-shot methods that apply a divide-and-conquer recognition strategy by decomposing characters into radicals. Meanwhile, radical recognition, as another important OCR task, also lacks radical-level annotation for model training. In this paper, we construct an ancient Chinese character image dataset that contains both radical-level and character-level annotations to satisfy the requirements of the above-mentioned methods, namely, ACCID, where radical-level annotations include radical categories, radical locations, and structural relations. To increase the adaptability of ACCID, we propose a splicing-based synthetic character algorithm to augment the training samples and apply an image denoising method to improve the image quality. By introducing character decomposition and recombination, we propose a baseline method for zero-shot OCR. The experimental results demonstrate the validity of ACCID and the baseline model quantitatively and qualitatively.

Haoming Chen, Runyang Feng, Sifan Wu et al.

Human pose estimation aims at localizing human anatomical keypoints or body parts in the input data (e.g., images, videos, or signals). It forms a crucial component in enabling machines to have an insightful understanding of the behaviors of humans, and has become a salient problem in computer vision and related fields. Deep learning techniques allow learning feature representations directly from the data, significantly pushing the performance boundary of human pose estimation. In this paper, we reap the recent achievements of 2D human pose estimation methods and present a comprehensive survey. Briefly, existing approaches put their efforts in three directions, namely network architecture design, network training refinement, and post processing. Network architecture design looks at the architecture of human pose estimation models, extracting more robust features for keypoint recognition and localization. Network training refinement tap into the training of neural networks and aims to improve the representational ability of models. Post processing further incorporates model-agnostic polishing strategies to improve the performance of keypoint detection. More than 200 research contributions are involved in this survey, covering methodological frameworks, common benchmark datasets, evaluation metrics, and performance comparisons. We seek to provide researchers with a more comprehensive and systematic review on human pose estimation, allowing them to acquire a grand panorama and better identify future directions.

Yiqian Wu, Hao Xu, Xiangjun Tang et al.

3D-aware face generators are typically trained on 2D real-life face image datasets that primarily consist of near-frontal face data, and as such, they are unable to construct one-quarter headshot 3D portraits with complete head, neck, and shoulder geometry. Two reasons account for this issue: First, existing facial recognition methods struggle with extracting facial data captured from large camera angles or back views. Second, it is challenging to learn a distribution of 3D portraits covering the one-quarter headshot region from single-view data due to significant geometric deformation caused by diverse body poses. To this end, we first create the dataset 360°-Portrait-HQ (360°PHQ for short) which consists of high-quality single-view real portraits annotated with a variety of camera parameters (the yaw angles span the entire 360° range) and body poses. We then propose 3DPortraitGAN, the first 3D-aware one-quarter headshot portrait generator that learns a canonical 3D avatar distribution from the 360°PHQ dataset with body pose self-learning. Our model can generate view-consistent portrait images from all camera angles with a canonical one-quarter headshot 3D representation. Our experiments show that the proposed framework can accurately predict portrait body poses and generate view-consistent, realistic portrait images with complete geometry from all camera angles.

Zheng Yuan, Aldo Pastore, Dorina de Jong et al.

Phonetic convergence describes the automatic and unconscious speech adaptation of two interlocutors in a conversation. This paper proposes a Siamese recurrent neural network (RNN) architecture to measure the convergence of the holistic spectral characteristics of speech sounds in an L2-L2 interaction. We extend an alternating reading task (the ART) dataset by adding 20 native Slovak L2 English speakers. We train and test the Siamese RNN model to measure phonetic convergence of L2 English speech from three different native language groups: Italian (9 dyads), French (10 dyads) and Slovak (10 dyads). Our results indicate that the Siamese RNN model effectively captures the dynamics of phonetic convergence and the speaker's imitation ability. Moreover, this text-independent model is scalable and capable of handling L1-induced speaker variability.

Yuling Wang, Hao Xu, Yanhua Yu et al.

It is well established that graph neural networks (GNNs) can be interpreted and designed from the perspective of optimization objective. With this clear optimization objective, the deduced GNNs architecture has sound theoretical foundation, which is able to flexibly remedy the weakness of GNNs. However, this optimization objective is only proved for GNNs with single-relational graph. Can we infer a new type of GNNs for multi-relational graphs by extending this optimization objective, so as to simultaneously solve the issues in previous multi-relational GNNs, e.g., over-parameterization? In this paper, we propose a novel ensemble multi-relational GNNs by designing an ensemble multi-relational (EMR) optimization objective. This EMR optimization objective is able to derive an iterative updating rule, which can be formalized as an ensemble message passing (EnMP) layer with multi-relations. We further analyze the nice properties of EnMP layer, e.g., the relationship with multi-relational personalized PageRank. Finally, a new multi-relational GNNs which well alleviate the over-smoothing and over-parameterization issues are proposed. Extensive experiments conducted on four benchmark datasets well demonstrate the effectiveness of the proposed model.

Daqian Shi, Xiaolei Diao, Lida Shi et al.

Degraded images commonly exist in the general sources of character images, leading to unsatisfactory character recognition results. Existing methods have dedicated efforts to restoring degraded character images. However, the denoising results obtained by these methods do not appear to improve character recognition performance. This is mainly because current methods only focus on pixel-level information and ignore critical features of a character, such as its glyph, resulting in character-glyph damage during the denoising process. In this paper, we introduce a novel generic framework based on glyph fusion and attention mechanisms, i.e., CharFormer, for precisely recovering character images without changing their inherent glyphs. Unlike existing frameworks, CharFormer introduces a parallel target task for capturing additional information and injecting it into the image denoising backbone, which will maintain the consistency of character glyphs during character image denoising. Moreover, we utilize attention-based networks for global-local feature interaction, which will help to deal with blind denoising and enhance denoising performance. We compare CharFormer with state-of-the-art methods on multiple datasets. The experimental results show the superiority of CharFormer quantitatively and qualitatively.

Huixuan Chi, Hao Xu, Hao Fu et al.

Modeling the evolution of user preference is essential in recommender systems. Recently, dynamic graph-based methods have been studied and achieved SOTA for recommendation, majority of which focus on user's stable long-term preference. However, in real-world scenario, user's short-term preference evolves over time dynamically. Although there exists sequential methods that attempt to capture it, how to model the evolution of short-term preference with dynamic graph-based methods has not been well-addressed yet. In particular: 1) existing methods do not explicitly encode and capture the evolution of short-term preference as sequential methods do; 2) simply using last few interactions is not enough for modeling the changing trend. In this paper, we propose Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation (LSTSR) to capture the evolution of short-term preference under dynamic graph. Specifically, we explicitly encode short-term preference and optimize it via memory mechanism, which has three key operations: Message, Aggregate and Update. Our memory mechanism can not only store one-hop information, but also trigger with new interactions online. Extensive experiments conducted on five public datasets show that LSTSR consistently outperforms many state-of-the-art recommendation methods across various lines.

Daqian Shi, Xiaolei Diao, Hao Tang et al.

Constructing high-quality character image datasets is challenging because real-world images are often affected by image degradation. There are limitations when applying current image restoration methods to such real-world character images, since (i) the categories of noise in character images are different from those in general images; (ii) real-world character images usually contain more complex image degradation, e.g., mixed noise at different noise levels. To address these problems, we propose a real-world character restoration network (RCRN) to effectively restore degraded character images, where character skeleton information and scale-ensemble feature extraction are utilized to obtain better restoration performance. The proposed method consists of a skeleton extractor (SENet) and a character image restorer (CiRNet). SENet aims to preserve the structural consistency of the character and normalize complex noise. Then, CiRNet reconstructs clean images from degraded character images and their skeletons. Due to the lack of benchmarks for real-world character image restoration, we constructed a dataset containing 1,606 character images with real-world degradation to evaluate the validity of the proposed method. The experimental results demonstrate that RCRN outperforms state-of-the-art methods quantitatively and qualitatively.

Hao Xu, Rite Bo, Fausto Giunchiglia et al.

Although studies have demonstrated that Large Language Models (LLMs) can perform well on Out-of-Distribution (OOD) tasks, their advantage tends to diminish as the distribution shift becomes more severe. Consequently, researchers aim to retrieve distributionally similar and informative demonstrations from the available source domain to boost the inference capabilities of LLMs. However, in practical scenarios where the target domain is inaccessible, evaluating the unknown distribution is challenging, which indirectly impacts the quality of the selected demonstrations. To address this problem, we propose \textbf{DOPA}, a demonstration search framework that incorporates an OOD proxy to approximate the inaccessible target domain and guide the retrieval process. Building on proxy-based evaluation, DOPA further introduces a Mahalanobis distance-based global diversity constraint to ensure sufficient diversity among the retrieved demonstrations. Experimental results on multiple LLMs and tasks demonstrate that DOPA effectively enhances robustness in OOD settings\footnote{https://github.com/bort64/ood\_code}.

Jian Li, Haojing Huang, Yujia Zhang et al.

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These approaches commonly use a binary cross-entropy mechanism on pairwise samples, i.e., minimizing and maximizing the loss based on preferred or dis-preferred responses, respectively. However, while this training strategy omits the reward model, it also overlooks the varying preference degrees within different responses. We hypothesize that this is a key factor hindering LLMs from sufficiently understanding human preferences. To address this problem, we propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss, thereby helping LLMs improve their ability to understand the degree of preference. Extensive experiments are conducted on two widely used datasets of different tasks. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods and significantly boost their performance to achieve state-of-the-art performance. We also conduct detailed analyses to offer comprehensive insights into SPO, which verifies its effectiveness. The code is available at https://github.com/lijian16/SPO.

Berkin Akin, Suyog Gupta, Yun Long et al.

On-device ML accelerators are becoming a standard in modern mobile system-on-chips (SoC). Neural architecture search (NAS) comes to the rescue for efficiently utilizing the high compute throughput offered by these accelerators. However, existing NAS frameworks have several practical limitations in scaling to multiple tasks and different target platforms. In this work, we provide a two-pronged approach to this challenge: (i) a NAS-enabling infrastructure that decouples model cost evaluation, search space design, and the NAS algorithm to rapidly target various on-device ML tasks, and (ii) search spaces crafted from group convolution based inverted bottleneck (IBN) variants that provide flexible quality/performance trade-offs on ML accelerators, complementing the existing full and depthwise convolution based IBNs. Using this approach we target a state-of-the-art mobile platform, Google Tensor SoC, and demonstrate neural architectures that improve the quality-performance pareto frontier for various computer vision (classification, detection, segmentation) as well as natural language processing tasks.

Xuan Yang, Jiayu Liu, Yuhang Lai et al.

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as a powerful tool for interpretability, existing approaches predominantly operate at the token level, creating a granularity mismatch when capturing more critical step-level information, such as reasoning direction and semantic transitions. In this work, we propose step-level sparse autoencoder (SSAE), which serves as an analytical tool to disentangle different aspects of LLMs' reasoning steps into sparse features. Specifically, by precisely controlling the sparsity of a step feature conditioned on its context, we form an information bottleneck in step reconstruction, which splits incremental information from background information and disentangles it into several sparsely activated dimensions. Experiments on multiple base models and reasoning tasks show the effectiveness of the extracted features. By linear probing, we can easily predict surface-level information, such as generation length and first token distribution, as well as more complicated properties, such as the correctness and logicality of the step. These observations indicate that LLMs should already at least partly know about these properties during generation, which provides the foundation for the self-verification ability of LLMs. The code is available at https://github.com/Miaow-Lab/SSAE

Rui Song, Lida Shi, Ruihua Qi et al.

In recent years, rapid advances in Multimodal Large Language Models (MLLMs) have increasingly stimulated research on ancient Chinese scripts. As the evolution of written characters constitutes a fundamental pathway for understanding cultural transformation and historical continuity, how MLLMs can be systematically leveraged to support and advance text evolution analysis remains an open and largely underexplored problem. To bridge this gap, we construct a comprehensive benchmark comprising 11 tasks and over 130,000 instances, specifically designed to evaluate the capability of MLLMs in analyzing the evolution of ancient Chinese scripts. We conduct extensive evaluations across multiple widely used MLLMs and observe that, while existing models demonstrate a limited ability in glyph-level comparison, their performance on core tasks-such as character recognition and evolutionary reasoning-remains substantially constrained. Motivated by these findings, we propose a glyph-driven fine-tuning framework (GEVO) that explicitly encourages models to capture evolutionary consistency in glyph transformations and enhances their understanding of text evolution. Experimental results show that even models at the 2B scale achieve consistent and comprehensive performance improvements across all evaluated tasks. To facilitate future research, we publicly release both the benchmark and the trained models\footnote{https://github.com/songruiecho/GEVO}.

Hui Xiao, Li Dong, Kangkang Song et al.

Convolutional neural networks can achieve remarkable performance in semantic segmentation tasks. However, such neural network approaches heavily rely on costly pixel-level annotation. Semi-supervised learning is a promising resolution to tackle this issue, but its performance still far falls behind the fully supervised counterpart. This work proposes a cross-teacher training framework with three modules that significantly improves traditional semi-supervised learning approaches. The core is a cross-teacher module, which could simultaneously reduce the coupling among peer networks and the error accumulation between teacher and student networks. In addition, we propose two complementary contrastive learning modules. The high-level module can transfer high-quality knowledge from labeled data to unlabeled ones and promote separation between classes in feature space. The low-level module can encourage low-quality features learning from the high-quality features among peer networks. In experiments, the cross-teacher module significantly improves the performance of traditional student-teacher approaches, and our framework outperforms stateof-the-art methods on benchmark datasets. Our source code of CTT will be released.

Rui Song, Fausto Giunchiglia, Yingji Li et al.

Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning. In general, a keyword is regarded as a shortcut if it creates a superficial association with the label, resulting in a false prediction. Conversely, shortcut learning can be mitigated if the model relies on robust causal features that help produce sound predictions. To this end, many studies have explored post-hoc interpretable methods to mine shortcuts and causal features for robustness and generalization. However, most existing methods focus only on single word in a sentence and lack consideration of word-group, leading to wrong causal features. To solve this problem, we propose a new Word-Group mining approach, which captures the causal effect of any keyword combination and orders the combinations that most affect the prediction. Our approach bases on effective post-hoc analysis and beam search, which ensures the mining effect and reduces the complexity. Then, we build a counterfactual augmentation method based on the multiple word-groups, and use an adaptive voting mechanism to learn the influence of different augmentated samples on the prediction results, so as to force the model to pay attention to effective causal features. We demonstrate the effectiveness of the proposed method by several tasks on 8 affective review datasets and 4 toxic language datasets, including cross-domain text classificaion, text attack and gender fairness test.

Yuwei Ren, Jiuyuan Lu, Andrian Beletchi et al.

We explore the feasibility of AI assisted hand-gesture recognition using 802.11ad 60GHz (mmWave) technology in smartphones. Range-Doppler information (RDI) is obtained by using pulse Doppler radar for gesture recognition. We built a prototype system, where radar sensing and WLAN communication waveform can coexist by time-division duplex (TDD), to demonstrate the real-time hand-gesture inference. It can gather sensing data and predict gestures within 100 milliseconds. First, we build the pipeline for the real-time feature processing, which is robust to occasional frame drops in the data stream. RDI sequence restoration is implemented to handle the frame dropping in the continuous data stream, and also applied to data augmentation. Second, different gestures RDI are analyzed, where finger and hand motions can clearly show distinctive features. Third, five typical gestures (swipe, palm-holding, pull-push, finger-sliding and noise) are experimented with, and a classification framework is explored to segment the different gestures in the continuous gesture sequence with arbitrary inputs. We evaluate our architecture on a large multi-person dataset and report > 95% accuracy with one CNN + LSTM model. Further, a pure CNN model is developed to fit to on-device implementation, which minimizes the inference latency, power consumption and computation cost. And the accuracy of this CNN model is more than 93% with only 2.29K parameters.

Hao Xu, Wei Fan, Ambrose C. Taylor et al.

Computational solid mechanics has become an indispensable approach in engineering, and numerical investigation of fracture in composites is essential as composites are widely used in structural applications. Crack evolution in composites is the bridge to elucidate the relationship between the microstructure and fracture performance, but crack-based finite element methods are computationally expensive and time-consuming, limiting their application in computation-intensive scenarios. Here we propose a deep learning framework called Crack-Net, which incorporates the relationship between crack evolution and stress response to predict the fracture process in composites. Trained on a high-precision fracture development dataset generated using the phase field method, Crack-Net demonstrates a remarkable capability to accurately forecast the long-term evolution of crack growth patterns and the stress-strain curve for a given composite design. The Crack-Net captures the essential principle of crack growth, which enables it to handle more complex microstructures such as binary co-continuous structures. Moreover, transfer learning is adopted to further improve the generalization ability of Crack-Net for composite materials with reinforcements of different strengths. The proposed Crack-Net holds great promise for practical applications in engineering and materials science, in which accurate and efficient fracture prediction is crucial for optimizing material performance and microstructural design.

YukTungSamuel Fang, Zhikang Shi, Jiabin Qiu et al.

Driven by recent advancements in foundation models, semantic scene graphs have emerged as a promising paradigm for high-level 3D environmental abstraction in robot navigation. However, existing frameworks struggle to successfully handle complex embodied queries while ensuring continuous semantic graph construction. To address these limitations, we present INHerit-SG, an asynchronous dual-stream architecture that systematically structures the 3D environment into a RAG-ready knowledge base. Specifically, our framework integrates comprehensive node representations, an event-triggered asynchronous update scheme, and a structured retrieval mechanism. While geometric segmentation is decoupled from semantic reasoning to maintain mapping efficiency, the semantic nodes also store natural language summaries to support text-based retrieval. Furthermore, we propose an interpretable retrieval pipeline that couples the reasoning capabilities of multi-role LLMs with the topological structure of the scene graph, followed by a visual verification process to mitigate false positives. We evaluate INHerit-SG on a newly constructed benchmark for complex embodied semantic query retrieval, HM3DSem-SQR, and in real-world environments. Experiments demonstrate that our system achieves state-of-the-art performance on complex queries, especially for those involving negations and chained spatial constraints. Project Page: https://fangyuktung.github.io/INHeritSG.github.io/

Hao Xu, Jia Liu, Yang Shen et al.

Graph Pooling technology plays an important role in graph node classification tasks. Sorting pooling technologies maintain large-value units for pooling graphs of varying sizes. However, by analyzing the statistical characteristic of activated units after pooling, we found that a large number of units dropped by sorting pooling are negative-value units that contain useful information and can contribute considerably to the final decision. To maintain more useful information, a novel pooling technology, called Geometric Pooling (GP), was proposed to contain the unique node features with negative values by measuring the similarity of all node features. We reveal the effectiveness of GP from the entropy reduction view. The experiments were conducted on TUdatasets to show the effectiveness of GP. The results showed that the proposed GP outperforms the SOTA graph pooling technologies by 1%\sim5% with fewer parameters.

Chao Li, Hao Xu, Kun He

Meta-structures are widely used to define which subset of neighbors to aggregate information in heterogeneous information networks (HINs). In this work, we investigate existing meta-structures, including meta-path and meta-graph, and observe that they are initially designed manually with fixed patterns and hence are insufficient to encode various rich semantic information on diverse HINs. Through reflection on their limitation, we define a new concept called meta-multigraph as a more expressive and flexible generalization of meta-graph, and propose a stable differentiable search method to automatically optimize the meta-multigraph for specific HINs and tasks. As the flexibility of meta-multigraphs may propagate redundant messages, we further introduce a complex-to-concise (C2C) meta-multigraph that propagates messages from complex to concise along the depth of meta-multigraph. Moreover, we observe that the differentiable search typically suffers from unstable search and a significant gap between the meta-structures in search and evaluation. To this end, we propose a progressive search algorithm by implicitly narrowing the search space to improve search stability and reduce inconsistency. Extensive experiments are conducted on six medium-scale benchmark datasets and one large-scale benchmark dataset over two representative tasks, i.e., node classification and recommendation. Empirical results demonstrate that our search methods can automatically find expressive meta-multigraphs and C2C meta-multigraphs, enabling our model to outperform state-of-the-art heterogeneous graph neural networks.

Yuanchen Bei, Hao Xu, Sheng Zhou et al.

Dynamic graph data mining has gained popularity in recent years due to the rich information contained in dynamic graphs and their widespread use in the real world. Despite the advances in dynamic graph neural networks (DGNNs), the rich information and diverse downstream tasks have posed significant difficulties for the practical application of DGNNs in industrial scenarios. To this end, in this paper, we propose to address them by pre-training and present the Contrastive Pre-Training Method for Dynamic Graph Neural Networks (CPDG). CPDG tackles the challenges of pre-training for DGNNs, including generalization capability and long-short term modeling capability, through a flexible structural-temporal subgraph sampler along with structural-temporal contrastive pre-training schemes. Extensive experiments conducted on both large-scale research and industrial dynamic graph datasets show that CPDG outperforms existing methods in dynamic graph pre-training for various downstream tasks under three transfer settings.

Xiaolei Diao, Daqian Shi, Hao Tang et al.

The long-tail effect is a common issue that limits the performance of deep learning models on real-world datasets. Character image datasets are also affected by such unbalanced data distribution due to differences in character usage frequency. Thus, current character recognition methods are limited when applied in the real world, especially for the categories in the tail that lack training samples, e.g., uncommon characters. In this paper, we propose a zero-shot character recognition framework via radical-based reasoning, called RZCR, to improve the recognition performance of few-sample character categories in the tail. Specifically, we exploit radicals, the graphical units of characters, by decomposing and reconstructing characters according to orthography. RZCR consists of a visual semantic fusion-based radical information extractor (RIE) and a knowledge graph character reasoner (KGR). RIE aims to recognize candidate radicals and their possible structural relations from character images in parallel. The results are then fed into KGR to recognize the target character by reasoning with a knowledge graph. We validate our method on multiple datasets, and RZCR shows promising experimental results, especially on few-sample character datasets.

Hao Xu, Yuntian Chen, Zhenzhong Zeng et al.

Despite the remarkable strides made by AI-driven models in modern precipitation forecasting, these black-box models cannot inherently deepen the comprehension of underlying mechanisms. To address this limitation, we propose an AI-driven knowledge discovery framework known as genetic algorithm-geographic weighted regression (GA-GWR). Our approach seeks to unveil the explicit equations that govern the intricate relationship between precipitation patterns and terrain characteristics in regions marked by complex terrain. Through this AI-driven knowledge discovery, we uncover previously undisclosed explicit equations that shed light on the connection between terrain features and precipitation patterns. These equations demonstrate remarkable accuracy when applied to precipitation data, outperforming conventional empirical models. Notably, our research reveals that the parameters within these equations are dynamic, adapting to evolving climate patterns. Ultimately, the unveiled equations have practical applications, particularly in fine-scale downscaling for precipitation predictions using low-resolution future climate data. This capability offers invaluable insights into the anticipated changes in precipitation patterns across diverse terrains under future climate scenarios, which enhances our ability to address the challenges posed by contemporary climate science.

Hao Xu, Hui Xiao, Huazheng Hao et al.

Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually used to filter out a large number of low-confidence predictions for unlabeled data. However, such filtering can not fully exploit unlabeled data with low prediction confidence. To overcome this problem, in this work, we propose a mutual learning framework based on pseudo-negative labels. Negative labels are those that a corresponding data item does not belong. In each iteration, one submodel generates pseudo-negative labels for each data item, and the other submodel learns from these labels. The role of the two submodels exchanges after each iteration until convergence. By reducing the prediction probability on pseudo-negative labels, the dual model can improve its prediction ability. We also propose a mechanism to select a few pseudo-negative labels to feed into submodels. In the experiments, our framework achieves state-of-the-art results on several main benchmarks. Specifically, with our framework, the error rates of the 13-layer CNN model are 9.35% and 7.94% for CIFAR-10 with 1000 and 4000 labels, respectively. In addition, for the non-augmented MNIST with only 20 labels, the error rate is 0.81% by our framework, which is much smaller than that of other approaches. Our approach also demonstrates a significant performance improvement in domain adaptation.

Bin Ji, Shasha Li, Hao Xu et al.

Span-based joint extraction simultaneously conducts named entity recognition (NER) and relation extraction (RE) in text span form. However, since previous span-based models rely on span-level classifications, they cannot benefit from token-level label information, which has been proven advantageous for the task. In this paper, we propose a Sequence Tagging augmented Span-based Network (STSN), a span-based joint model that can make use of token-level label information. In STSN, we construct a core neural architecture by deep stacking multiple attention layers, each of which consists of three basic attention units. On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE. Experimental results on three benchmark datasets show that STSN consistently outperforms the strongest baselines in terms of F1, creating new state-of-the-art results.

Zhaoxin Fan, Yuqing Pan, Hao Xu et al.

In the field of full-body reconstruction, the scarcity of annotated data often impedes the efficacy of prevailing methods. To address this issue, we introduce FuRPE, a novel framework that employs part-experts and an ingenious pseudo ground-truth selection scheme to derive high-quality pseudo labels. These labels, central to our approach, equip our network with the capability to efficiently learn from the available data. Integral to FuRPE is a unique exponential moving average training strategy and expert-derived feature distillation strategy. These novel elements of FuRPE not only serve to further refine the model but also to reduce potential biases that may arise from inaccuracies in pseudo labels, thereby optimizing the network's training process and enhancing the robustness of the model. We apply FuRPE to train both two-stage and fully convolutional single-stage full-body reconstruction networks. Our exhaustive experiments on numerous benchmark datasets illustrate a substantial performance boost over existing methods, underscoring FuRPE's potential to reshape the state-of-the-art in full-body reconstruction.

Bin Ren, Yawei Li, Nancy Mehta et al.

This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes. The task of this challenge is to super-resolve an input image with a magnification factor of x4 based on pairs of low and corresponding high-resolution images. The primary objective is to develop networks that optimize various aspects such as runtime, parameters, and FLOPs, while still maintaining a peak signal-to-noise ratio (PSNR) of approximately 26.90 dB on the DIV2K_LSDIR_valid dataset and 26.99 dB on the DIV2K_LSDIR_test dataset. In addition, this challenge has 4 tracks including the main track (overall performance), sub-track 1 (runtime), sub-track 2 (FLOPs), and sub-track 3 (parameters). In the main track, all three metrics (ie runtime, FLOPs, and parameter count) were considered. The ranking of the main track is calculated based on a weighted sum-up of the scores of all other sub-tracks. In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking. In sub-track 2, the number of FLOPs was considered. The score calculated based on the corresponding FLOPs was used to determine the ranking. In sub-track 3, the number of parameters was considered. The score calculated based on the corresponding parameters was used to determine the ranking. RLFN is set as the baseline for efficiency measurement. The challenge had 262 registered participants, and 34 teams made valid submissions. They gauge the state-of-the-art in efficient single-image super-resolution. To facilitate the reproducibility of the challenge and enable other researchers to build upon these findings, the code and the pre-trained model of validated solutions are made publicly available at https://github.com/Amazingren/NTIRE2024_ESR/.

Tianle Wang, Zhongyuan Wu, Shenghao Jin et al.

Reinforcement learning with verifiable rewards (RLVR) has become a central component of large language model (LLM) post-training. Unlike supervised fine-tuning (SFT), RLVR lets an LLM generate multiple candidate solutions and reinforces those that lead to a verifiably correct final answer. However, in practice, RLVR often requires thousands of training steps to reach strong performance, incurring substantial computation largely attributed to prolonged exploration. In this work, we make a surprising observation: during RLVR, LLMs evolve in a strongly linear manner. Specifically, both model weights and model output log-probabilities exhibit strong linear correlations with RL training steps. This suggests that RLVR predominantly amplifies trends that emerge early in training, rather than continuously discovering new behaviors throughout the entire optimization trajectory. Motivated by this linearity, we investigate whether future model states can be predicted from intermediate checkpoints via extrapolation, avoiding continued expensive training. We show that Weight Extrapolation produces models with performance comparable to standard RL training while requiring significantly less computation. Moreover, Logits Extrapolation consistently outperforms continued RL training on mathematics and code benchmarks by extrapolating beyond the step range where RL training remains stable. Our code is available at https://github.com/Miaow-Lab/RLVR-Linearity