Hong Zhang

Huaqi Tao, Bingxi Liu, Jinqiang Cui et al.

Cracks play a crucial role in assessing the safety and durability of manufactured buildings. However, the long and sharp topological features and complex background of cracks make the task of crack segmentation extremely challenging. In this paper, we propose a novel convolutional-transformer network based on encoder-decoder architecture to solve this challenge. Particularly, we designed a Dilated Residual Block (DRB) and a Boundary Awareness Module (BAM). The DRB pays attention to the local detail of cracks and adjusts the feature dimension for other blocks as needed. And the BAM learns the boundary features from the dilated crack label. Furthermore, the DRB is combined with a lightweight transformer that captures global information to serve as an effective encoder. Experimental results show that the proposed network performs better than state-of-the-art algorithms on two typical datasets. Datasets, code, and trained models are available for research at https://github.com/HqiTao/CT-crackseg.

Tianle Zeng, Yanci Wen, Xueang Yu et al.

Recent aerial vision-language-action (VLA) models show promising single-UAV capabilities, such as tracking moving objects and navigating to language-specified landmarks. However, it remains unclear whether these capabilities can transfer to air-ground cooperation, where a UAV and a UGV must act jointly in a shared, closed-loop physical world. We study this question with CARLA-Air, a single-process air-ground evaluation environment that unifies CARLA and AirSim inside one Unreal Engine runtime. By sharing the same world state, physics tick, and sensing pipeline, CARLA-Air enables physically consistent UAV--UGV interaction and precise measurement of simulation-timestamp alignment and effective coordination latency. Using CARLA-Air, we evaluate representative aerial VLA and planning baselines on two complementary diagnostic tasks: moving-platform landing and occlusion-recovery escort. The results show that current aerial VLA models can often track or follow a ground partner, but struggle to convert this single-agent competence into stable cooperative behavior. State prompting provides limited benefit, and naive bidirectional interaction fails to consistently improve performance and can amplify errors for most baselines. These findings suggest that, under the tested text-based cue interfaces, zero-shot cooperative air-ground VLA requires three components beyond the current paradigm: explicit partner-state grounding, low-latency action coordination, and team-level objective alignment. Our code is available at https://github.com/louiszengCN/CarlaAir.

Yuze Zhao, Jintao Huang, Jinghan Hu et al.

Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have leverage Attention-based Transformer architectures and achieved superior performance and generalization capabilities. They have since covered extensive areas of traditional learning tasks. For instance, text-based tasks such as text-classification and sequence-labeling, as well as multi-modal tasks like Visual Question Answering (VQA) and Optical Character Recognition (OCR), which were previously addressed using different models, can now be tackled based on one foundation model. Consequently, the training and lightweight fine-tuning of LLMs and MLLMs, especially those based on Transformer architecture, has become particularly important. In recognition of these overwhelming needs, we develop SWIFT, a customizable one-stop infrastructure for large models. With support of over $300+$ LLMs and $50+$ MLLMs, SWIFT stands as the open-source framework that provide the most comprehensive support for fine-tuning large models. In particular, it is the first training framework that provides systematic support for MLLMs. In addition to the core functionalities of fine-tuning, SWIFT also integrates post-training processes such as inference, evaluation, and model quantization, to facilitate fast adoptions of large models in various application scenarios. With a systematic integration of various training techniques, SWIFT offers helpful utilities such as benchmark comparisons among different training techniques for large models. For fine-tuning models specialized in agent framework, we show that notable improvements on the ToolBench leader-board can be achieved by training with customized dataset on SWIFT, with an increase of 5.2%-21.8% in the Act.EM metric over various baseline models, a reduction in hallucination by 1.6%-14.1%, and an average performance improvement of 8%-17%.

Shrirang Abhyankar, Jed Brown, Emil M. Constantinescu et al.

High-quality ordinary differential equation (ODE) solver libraries have a long history, going back to the 1970s. Over the past several years we have implemented, on top of the PETSc linear and nonlinear solver package, a new general-purpose, extensive, extensible library for solving ODEs and differential algebraic equations (DAEs). Package includes support for both forward and adjoint sensitivities that can be easily utilized by the TAO optimization package, which is also part of PETSc. The ODE/DAE integrator library strives to be highly scalable but also to deliver high efficiency for modest-sized problems. The library includes explicit solvers, implicit solvers, and a collection of implicit-explicit solvers, all with a common user interface and runtime selection of solver types, adaptive error control, and monitoring of solution progress. The library also offers enormous flexibility in selection of nonlinear and linear solvers, including the entire suite of PETSc iterative solvers, as well as several parallel direct solvers.

Yuan Cheng, Songtao Feng, Jing Yang et al.

As representation learning becomes a powerful technique to reduce sample complexity in reinforcement learning (RL) in practice, theoretical understanding of its advantage is still limited. In this paper, we theoretically characterize the benefit of representation learning under the low-rank Markov decision process (MDP) model. We first study multitask low-rank RL (as upstream training), where all tasks share a common representation, and propose a new multitask reward-free algorithm called REFUEL. REFUEL learns both the transition kernel and the near-optimal policy for each task, and outputs a well-learned representation for downstream tasks. Our result demonstrates that multitask representation learning is provably more sample-efficient than learning each task individually, as long as the total number of tasks is above a certain threshold. We then study the downstream RL in both online and offline settings, where the agent is assigned with a new task sharing the same representation as the upstream tasks. For both online and offline settings, we develop a sample-efficient algorithm, and show that it finds a near-optimal policy with the suboptimality gap bounded by the sum of the estimation error of the learned representation in upstream and a vanishing term as the number of downstream samples becomes large. Our downstream results of online and offline RL further capture the benefit of employing the learned representation from upstream as opposed to learning the representation of the low-rank model directly. To the best of our knowledge, this is the first theoretical study that characterizes the benefit of representation learning in exploration-based reward-free multitask RL for both upstream and downstream tasks.

Hong Zhang, Ji Liu, Juncheng Jia et al.

Despite achieving remarkable performance, Federated Learning (FL) suffers from two critical challenges, i.e., limited computational resources and low training efficiency. In this paper, we propose a novel FL framework, i.e., FedDUAP, with two original contributions, to exploit the insensitive data on the server and the decentralized data in edge devices to further improve the training efficiency. First, a dynamic server update algorithm is designed to exploit the insensitive data on the server, in order to dynamically determine the optimal steps of the server update for improving the convergence and accuracy of the global model. Second, a layer-adaptive model pruning method is developed to perform unique pruning operations adapted to the different dimensions and importance of multiple layers, to achieve a good balance between efficiency and effectiveness. By integrating the two original techniques together, our proposed FL model, FedDUAP, significantly outperforms baseline approaches in terms of accuracy (up to 4.8% higher), efficiency (up to 2.8 times faster), and computational cost (up to 61.9% smaller).

Yuzhe Zhang, Hong Zhang

Financial named entity recognition (FinNER) from literature is a challenging task in the field of financial text information extraction, which aims to extract a large amount of financial knowledge from unstructured texts. It is widely accepted to use sequence tagging frameworks to implement FinNER tasks. However, such sequence tagging models cannot fully take advantage of the semantic information in the texts. Instead, we formulate the FinNER task as a machine reading comprehension (MRC) problem and propose a new model termed FinBERT-MRC. This formulation introduces significant prior information by utilizing well-designed queries, and extracts start index and end index of target entities without decoding modules such as conditional random fields (CRF). We conduct experiments on a publicly available Chinese financial dataset ChFinAnn and a real-word bussiness dataset AdminPunish. FinBERT-MRC model achieves average F1 scores of 92.78% and 96.80% on the two datasets, respectively, with average F1 gains +3.94% and +0.89% over some sequence tagging models including BiLSTM-CRF, BERT-Tagger, and BERT-CRF. The source code is available at https://github.com/zyz0000/FinBERT-MRC.

Guangcheng Chen, Li He, Yisheng Guan et al.

Current polarimetric 3D reconstruction methods, including those in the well-established shape from polarization literature, are all developed under the orthographic projection assumption. In the case of a large field of view, however, this assumption does not hold and may result in significant reconstruction errors in methods that make this assumption. To address this problem, we present the perspective phase angle (PPA) model that is applicable to perspective cameras. Compared with the orthographic model, the proposed PPA model accurately describes the relationship between polarization phase angle and surface normal under perspective projection. In addition, the PPA model makes it possible to estimate surface normals from only one single-view phase angle map and does not suffer from the so-called $π$-ambiguity problem. Experiments on real data show that the PPA model is more accurate for surface normal estimation with a perspective camera than the orthographic model.

YuPeng Huang, Hong Zhang, Siyuan Jiang et al.

Virtual screening, including molecular docking, plays an essential role in drug discovery. Many traditional and machine-learning based methods are available to fulfil the docking task. The traditional docking methods are normally extensively time-consuming, and their performance in blind docking remains to be improved. Although the runtime of docking based on machine learning is significantly decreased, their accuracy is still limited. In this study, we take the advantage of both traditional and machine-learning based methods, and present a method Deep Site and Docking Pose (DSDP) to improve the performance of blind docking. For the traditional blind docking, the entire protein is covered by a cube, and the initial positions of ligands are randomly generated in the cube. In contract, DSDP can predict the binding site of proteins and provide an accurate searching space and initial positions for the further conformational sampling. The docking task of DSDP makes use of the score function and a similar but modified searching strategy of AutoDock Vina, accelerated by implementation in GPUs. We systematically compare its performance with the state-of-the-art methods, including Autodock Vina, GNINA, QuickVina, SMINA, and DiffDock. DSDP reaches a 29.8% top-1 success rate (RMSD < 2 Å) on an unbiased and challenging test dataset with 1.2 s wall-clock computational time per system. Its performances on DUD-E dataset and the time-split PDBBind dataset used in EquiBind, TankBind, and DiffDock are also effective, presenting a 57.2% and 41.8% top-1 success rate with 0.8 s and 1.0 s per system, respectively.

Hong Zhang, Haewoon Kwak, Wei Gao et al.

People who share similar opinions towards controversial topics could form an echo chamber and may share similar political views toward other topics as well. The existence of such connections, which we call connected behavior, gives researchers a unique opportunity to predict how one would behave for a future event given their past behaviors. In this work, we propose a framework to conduct connected behavior analysis. Neural stance detection models are trained on Twitter data collected on three seemingly independent topics, i.e., wearing a mask, racial equality, and Trump, to detect people's stance, which we consider as their online behavior in each topic-related event. Our results reveal a strong connection between the stances toward the three topical events and demonstrate the power of past behaviors in predicting one's future behavior.

Ling Ge, Chunming Hu, Guanghui Ma et al.

For named entity recognition (NER) in zero-resource languages, utilizing knowledge distillation methods to transfer language-independent knowledge from the rich-resource source languages to zero-resource languages is an effective means. Typically, these approaches adopt a teacher-student architecture, where the teacher network is trained in the source language, and the student network seeks to learn knowledge from the teacher network and is expected to perform well in the target language. Despite the impressive performance achieved by these methods, we argue that they have two limitations. Firstly, the teacher network fails to effectively learn language-independent knowledge shared across languages due to the differences in the feature distribution between the source and target languages. Secondly, the student network acquires all of its knowledge from the teacher network and ignores the learning of target language-specific knowledge. Undesirably, these limitations would hinder the model's performance in the target language. This paper proposes an unsupervised prototype knowledge distillation network (ProKD) to address these issues. Specifically, ProKD presents a contrastive learning-based prototype alignment method to achieve class feature alignment by adjusting the distance among prototypes in the source and target languages, boosting the teacher network's capacity to acquire language-independent knowledge. In addition, ProKD introduces a prototypical self-training method to learn the intrinsic structure of the language by retraining the student network on the target data using samples' distance information from prototypes, thereby enhancing the student network's ability to acquire language-specific knowledge. Extensive experiments on three benchmark cross-lingual NER datasets demonstrate the effectiveness of our approach.

Tianle Zeng, Hanjing Ye, Jianwei Peng et al.

Outdoor vision-language navigation (VLN) in long-range, open-world environments is frequently disrupted by semantic-cue interruptions, where informative goal cues become sparse, occluded, or leave the field of view. Once such cues disappear, agents enter a cue-free phase and often degrade into backtracking, oscillatory headings, or aimless exploration. While memory-based methods attempt to bridge these gaps, they often fail under traversability-driven detours: the remembered cue direction may be infeasible, forcing detours that prolong cue-free phases and gradually render robot-centric cues stale and implicit histories blurred. This makes traversability a stability condition for maintaining goal-directed guidance, rather than merely a local safety concern. We propose a unified outdoor VLN framework that survives semantic-cue interruptions by maintaining traversability-consistent executable guidance throughout prolonged cue-free phases. Specifically, our method extracts semantic bearings from visibility-gated goal or exploration cues and grounds them into executable headings using a real-time near-field traversability profile, providing goal-consistent feasible guidance beyond reject-only safety filtering. To prevent guidance degradation during detours, we lift intermittent 2D evidence into a world-aligned 3D cue memory with an uncertainty-aware readout mechanism, ensuring guidance remains continuously reachable and stable as the robot moves. We evaluate the framework on quadrupedal and wheeled platforms over 600--1000 m routes. Our method improves simulation success rate by over 10 percentage points over the strongest baseline and achieves a real-world success rate of 40%, compared to 17.5% for the strongest baseline, with substantially higher robustness during prolonged cue-free intervals.

Hong Zhang, Yixuan Lyu, Qian Yu et al.

In the domain of Camouflaged Object Segmentation (COS), despite continuous improvements in segmentation performance, the underlying mechanisms of effective camouflage remain poorly understood, akin to a black box. To address this gap, we present the first comprehensive study to examine the impact of camouflage attributes on the effectiveness of camouflage patterns, offering a quantitative framework for the evaluation of camouflage designs. To support this analysis, we have compiled the first dataset comprising descriptions of camouflaged objects and their attribute contributions, termed COD-Text And X-attributions (COD-TAX). Moreover, drawing inspiration from the hierarchical process by which humans process information: from high-level textual descriptions of overarching scenarios, through mid-level summaries of local areas, to low-level pixel data for detailed analysis. We have developed a robust framework that combines textual and visual information for the task of COS, named Attribution CUe Modeling with Eye-fixation Network (ACUMEN). ACUMEN demonstrates superior performance, outperforming nine leading methods across three widely-used datasets. We conclude by highlighting key insights derived from the attributes identified in our study. Code: https://github.com/lyu-yx/ACUMEN.

Bangwei Guo, Xingyu Li, Jitendra Jonnagaddala et al.

Artificial intelligence (AI) models have been developed for predicting clinically relevant biomarkers, including microsatellite instability (MSI), for colorectal cancers (CRC). However, the current deep-learning networks are data-hungry and require large training datasets, which are often lacking in the medical domain. In this study, based on the latest Hierarchical Vision Transformer using Shifted Windows (Swin-T), we developed an efficient workflow for biomarkers in CRC (MSI, hypermutation, chromosomal instability, CpG island methylator phenotype, BRAF, and TP53 mutation) that only required relatively small datasets, but achieved the state-of-the-art (SOTA) predictive performance. Our Swin-T workflow not only substantially outperformed published models in an intra-study cross-validation experiment using TCGA-CRC-DX dataset (N = 462), but also showed excellent generalizability in cross-study external validation and delivered a SOTA AUROC of 0.90 for MSI using the MCO dataset for training (N = 1065) and the same TCGA-CRC-DX for testing. Similar performance (AUROC=0.91) was achieved by Echle and colleagues using approximately 8000 training samples (ResNet18) on the same testing dataset. Swin-T was extremely efficient using small training datasets and exhibits robust predictive performance with only 200-500 training samples. These data indicate that Swin-T may be 5-10 times more efficient than the current state-of-the-art algorithms for MSI based on ResNet18 and ShuffleNet. Furthermore, the Swin-T models showed promise as pre-screening tests for MSI status and BRAF mutation status, which could exclude and reduce the samples before the subsequent standard testing in a cascading diagnostic workflow to allow turnaround time reduction and cost saving.

Qiang Fu, Hongshan Yu, Islam Ali et al.

In this paper we propose a novel sparse optical flow (SOF)-based line feature tracking method for the camera pose estimation problem. This method is inspired by the point-based SOF algorithm and developed based on an observation that two adjacent images in time-varying image sequences satisfy brightness invariant. Based on this observation, we re-define the goal of line feature tracking: track two endpoints of a line feature instead of the entire line based on gray value matching instead of descriptor matching. To achieve this goal, an efficient two endpoint tracking (TET) method is presented: first, describe a given line feature with its two endpoints; next, track the two endpoints based on SOF to obtain two new tracked endpoints by minimizing a pixel-level grayscale residual function; finally, connect the two tracked endpoints to generate a new line feature. The correspondence is established between the given and the new line feature. Compared with current descriptor-based methods, our TET method needs not to compute descriptors and detect line features repeatedly. Naturally, it has an obvious advantage over computation. Experiments in several public benchmark datasets show our method yields highly competitive accuracy with an obvious advantage over speed.

Dehao Huang, Aoxiang Gu, Chengjie Zhang et al.

Confidence estimation for Vision-Language-Action (VLA) models is essential for robots to perform manipulation tasks in the open world, providing crucial signals for risk-sensitive decision-making and failure anticipation. Existing confidence estimation methods typically rely on ensemble-based paradigms or action-token probabilities to predict the likelihood of task success. However, they still encounter challenges in computational efficiency and cross-architecture generalizability. These methods usually require repeated sampling, leading to inference inefficiency, and are restricted to VLA models with discrete action outputs, making them difficult to apply to continuous action spaces. To address this issue, we propose VLAConf, a one-class discriminative confidence framework. By leveraging frozen pretrained VLA internal representations, VLAConf directly estimates step-wise anomaly scores in a single forward pass using a lightweight confidence head, thereby eliminating the overhead of exhaustive resampling. We additionally use step-conditioned modeling to encode rollout-phase information along the manipulation trajectory. Experiments on the LIBERO benchmark demonstrate that VLAConf significantly improves the quality of the confidence signal constructed for post-hoc calibration, outperforming existing baselines by a large margin in inference efficiency. The effectiveness of VLAConf is further validated in real-robot experiments. To access the source code and supplementary videos, visit https://sites.google.com/view/vlaconf.

Hong Zhang, Wenjun Zhao

Neural ordinary differential equations (neural ODEs) have emerged as a novel network architecture that bridges dynamical systems and deep learning. However, the gradient obtained with the continuous adjoint method in the vanilla neural ODE is not reverse-accurate. Other approaches suffer either from an excessive memory requirement due to deep computational graphs or from limited choices for the time integration scheme, hampering their application to large-scale complex dynamical systems. To achieve accurate gradients without compromising memory efficiency and flexibility, we present a new neural ODE framework, PNODE, based on high-level discrete adjoint algorithmic differentiation. By leveraging discrete adjoint time integrators and advanced checkpointing strategies tailored for these integrators, PNODE can provide a balance between memory and computational costs, while computing the gradients consistently and accurately. We provide an open-source implementation based on PyTorch and PETSc, one of the most commonly used portable, scalable scientific computing libraries. We demonstrate the performance through extensive numerical experiments on image classification and continuous normalizing flow problems. We show that PNODE achieves the highest memory efficiency when compared with other reverse-accurate methods. On the image classification problems, PNODE is up to two times faster than the vanilla neural ODE and up to 2.3 times faster than the best existing reverse-accurate method. We also show that PNODE enables the use of the implicit time integration methods that are needed for stiff dynamical systems.

Tianle Zeng, Hanxuan Chen, Yanci Wen et al.

The convergence of low-altitude economies, embodied intelligence, and air-ground cooperative systems creates growing demand for simulation infrastructure capable of jointly modeling aerial and ground agents within a single physically coherent environment. Existing open-source platforms remain domain-segregated: driving simulators lack aerial dynamics, while multirotor simulators lack realistic ground scenes. Bridge-based co-simulation introduces synchronization overhead and cannot guarantee strict spatial-temporal consistency. We present CARLA-Air, an open-source infrastructure that unifies high-fidelity urban driving and physics-accurate multirotor flight within a single Unreal Engine process. The platform preserves both CARLA and AirSim native Python APIs and ROS 2 interfaces, enabling zero-modification code reuse. Within a shared physics tick and rendering pipeline, CARLA-Air delivers photorealistic environments with rule-compliant traffic, socially-aware pedestrians, and aerodynamically consistent UAV dynamics, synchronously capturing up to 18 sensor modalities across all platforms at each tick. The platform supports representative air-ground embodied intelligence workloads spanning cooperation, embodied navigation and vision-language action, multi-modal perception and dataset construction, and reinforcement-learning-based policy training. An extensible asset pipeline allows integration of custom robot platforms into the shared world. By inheriting AirSim's aerial capabilities -- whose upstream development has been archived -- CARLA-Air ensures this widely adopted flight stack continues to evolve within a modern infrastructure. Released with prebuilt binaries and full source: https://github.com/louiszengCN/CarlaAir

Jiamin Zheng, Jingwen Yu, Guangcheng Chen et al.

Indoor robot navigation is often compromised by glass surfaces, which severely corrupt depth sensor measurements. While foundation models like Depth Anything 3 provide excellent geometric priors, they lack an absolute metric scale. We propose a training-free framework that leverages depth foundation models as a structural prior, employing a robust local RANSAC-based alignment to fuse it with raw sensor depth. This naturally avoids contamination from erroneous glass measurements and recovers an accurate metric scale. Furthermore, we introduce \ti{GlassRecon}, a novel RGB-D dataset with geometrically derived ground truth for glass regions. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art baselines, especially under severe sensor depth corruption. The dataset and related code will be released at https://github.com/jarvisyjw/GlassRecon.

Enze Ye, Yuhang Wang, Hong Zhang et al.

The dynamics of biomolecules are crucial for our understanding of their functioning in living systems. However, current 3D imaging techniques, such as cryogenic electron microscopy (cryo-EM), require freezing the sample, which limits the observation of their conformational changes in real time. The innovative liquid-phase electron microscopy (liquid-phase EM) technique allows molecules to be placed in the native liquid environment, providing a unique opportunity to observe their dynamics. In this paper, we propose TEMPOR, a Temporal Electron MicroscoPy Object Reconstruction algorithm for liquid-phase EM that leverages an implicit neural representation (INR) and a dynamical variational auto-encoder (DVAE) to recover time series of molecular structures. We demonstrate its advantages in recovering different motion dynamics from two simulated datasets, 7bcq and Cas9. To our knowledge, our work is the first attempt to directly recover 3D structures of a temporally-varying particle from liquid-phase EM movies. It provides a promising new approach for studying molecules' 3D dynamics in structural biology.

Xingyu Li, Jitendra Jonnagaddala, Min Cen et al.

Several deep learning algorithms have been developed to predict survival of cancer patients using whole slide images (WSIs).However, identification of image phenotypes within the WSIs that are relevant to patient survival and disease progression is difficult for both clinicians, and deep learning algorithms. Most deep learning based Multiple Instance Learning (MIL) algorithms for survival prediction use either top instances (e.g., maxpooling) or top/bottom instances (e.g., MesoNet) to identify image phenotypes. In this study, we hypothesize that wholistic information of the distribution of the patch scores within a WSI can predict the cancer survival better. We developed a distribution based multiple-instance survival learning algorithm (DeepDisMISL) to validate this hypothesis. We designed and executed experiments using two large international colorectal cancer WSIs datasets - MCO CRC and TCGA COAD-READ. Our results suggest that the more information about the distribution of the patch scores for a WSI, the better is the prediction performance. Including multiple neighborhood instances around each selected distribution location (e.g., percentiles) could further improve the prediction. DeepDisMISL demonstrated superior predictive ability compared to other recently published, state-of-the-art algorithms. Furthermore, our algorithm is interpretable and could assist in understanding the relationship between cancer morphological phenotypes and patients cancer survival risk.

Guotian Zeng, Bi Zeng, Hong Zhang et al.

Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the tracked targets, the genuine bounding box fails to capture the appearance information explicitly and introduces cluttered background. This paper proposes RTrack, a novel object representation baseline tracker that utilizes a set of sample points to get a pseudo bounding box. RTrack automatically arranges these points to define the spatial extents and highlight local areas. Building upon the baseline, we conducted an in-depth exploration of the training potential and introduced a one-to-many leading assignment strategy. It is worth noting that our approach achieves competitive performance to the state-of-the-art trackers on the GOT-10k dataset while reducing training time to just 10% of the previous state-of-the-art (SOTA) trackers' training costs. The substantial reduction in training costs brings single-object tracking (SOT) closer to the object detection (OD) task. Extensive experiments demonstrate that our proposed RTrack achieves SOTA results with faster convergence.

Yuzhe Zhang, Min Cen, Tongzhou Wu et al.

Few-shot relation extraction (FSRE) aims at recognizing unseen relations by learning with merely a handful of annotated instances. To generalize to new relations more effectively, this paper proposes a novel pipeline for the FSRE task based on queRy-information guided Attention and adaptive Prototype fuSion, namely RAPS. Specifically, RAPS first derives the relation prototype by the query-information guided attention module, which exploits rich interactive information between the support instances and the query instances, in order to obtain more accurate initial prototype representations. Then RAPS elaborately combines the derived initial prototype with the relation information by the adaptive prototype fusion mechanism to get the integrated prototype for both train and prediction. Experiments on the benchmark dataset FewRel 1.0 show a significant improvement of our method against state-of-the-art methods.

Hanjing Ye, Weixi Situ, Jianwei Peng et al.

Robot person following (RPF) -- mobile robots that follow and assist a specific person -- has emerging applications in personal assistance, security patrols, eldercare, and logistics. To be effective, such robots must follow the target while ensuring safety and comfort for both the target and surrounding people. In this work, we present the first comprehensive study of RPF, which (i) surveys representative scenarios, motion-planning methods, and evaluation metrics with a focus on safety and comfort; (ii) introduces Follow-Bench, a unified benchmark simulating diverse scenarios, including various target trajectory patterns, crowd dynamics, and environmental layouts; and (iii) re-implements eight representative RPF planners, ensuring that both safety and comfort are systematically considered. Moreover, we evaluate the two best-performing planners from our benchmark on a differential-drive robot to provide insights into real-world deployment of RPF planners. Extensive simulation and real-world experiments provide quantitative study of the safety-comfort trade-offs of existing planners, while revealing open challenges and future research directions.

Shimian Zhang, Skanda Bharadwaj, Keaton Kraiger et al.

We demonstrate the utility of recurring pattern discovery from a single image for spatial understanding of a 3D scene in terms of (1) vanishing point detection, (2) hypothesizing 3D translation symmetry and (3) counting the number of RP instances in the image. Furthermore, we illustrate the feasibility of leveraging RP discovery output to form a more precise, quantitative text description of the scene. Our quantitative evaluations on a new 1K+ Recurring Pattern (RP) benchmark with diverse variations show that visual perception of recurrence from one single view leads to scene understanding outcomes that are as good as or better than existing supervised methods and/or unsupervised methods that use millions of images.

Jiaxu Wan, Xu Wang, Mengwei Xie et al.

Recent spatial intelligence approaches typically attach 3D cues to 2D reasoning pipelines or couple MLLMs with black-box reconstruction modules, leading to weak spatial consistency, limited viewpoint diversity, and evidence chains that cannot be traced back to supporting views. Frameworks for "thinking with images" (e.g., ChatGPT-o3 and DeepEyes) show that stepwise multimodal reasoning can emerge by interleaving hypothesis formation with active acquisition of visual evidence, but they do not address three key challenges in spatial Chain-of-Thought (CoT): building global space perception under strict token budgets, explicitly associating 3D hypotheses with video frames for verification, and designing spatially grounded rewards for reinforcement learning. To address these issues, we present EagleVision, a dual-stage framework for progressive spatial cognition through macro perception and micro verification. In the macro perception stage, EagleVision employs a semantics-perspective-fusion determinantal point process (SPF-DPP) to select a compact set of geometry- and semantics-aware keyframes from long videos under a fixed token budget. In the micro verification stage, we formalize spatial CoT as BEV-grounded pose querying: the agent iteratively predicts poses on a BEV plane, retrieves the nearest real frames, and is trained purely by reinforcement learning with a spatial grounding reward that scores the consistency between predicted poses and observed views. On VSI-Bench, EagleVision achieves state-of-the-art performance among open-source vision-language models, demonstrating strong and generalizable spatial understanding.

Paul Tranquilli, Adrian Sandu, Hong Zhang

This paper develops a new class of linearly implicit time integration schemes called Linearly-Implicit Runge-Kutta-W (LIRK-W) methods. These schemes are based on an implicit-explicit approach which does not require a splitting of the right hand side and allow for arbitrary, time dependent, and stage varying approximations of the linear systems appearing in the method. Several formulations of LIRK-W schemes, each designed for specific approximation types, and their associated order condition theories are presented.

Ji Liu, Juncheng Jia, Hong Zhang et al.

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this paper, we propose a new FL framework, i.e., FedDUMAP, with three original contributions, to leverage the shared insensitive data on the server in addition to the distributed data in edge devices so as to efficiently train a global model. First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy. Second, we propose an adaptive optimization method with the dynamic server update algorithm to exploit the global momentum on the server and each local device for superior accuracy. Third, we develop a layer-adaptive model pruning method to carry out specific pruning operations, which is adapted to the diverse features of each layer so as to attain an excellent trade-off between effectiveness and efficiency. Our proposed FL model, FedDUMAP, combines the three original techniques and has a significantly better performance compared with baseline approaches in terms of efficiency (up to 16.9 times faster), accuracy (up to 20.4% higher), and computational cost (up to 62.6% smaller).

Bingxi Liu, Yujie Fu, Feng Lu et al.

Visual Place Recognition (VPR) is the task of retrieving database images similar to a query photo by comparing it to a large database of known images. In real-world applications, extreme illumination changes caused by query images taken at night pose a significant obstacle that VPR needs to overcome. However, a training set with day-night correspondence for city-scale, street-level VPR does not exist. To address this challenge, we propose a novel pipeline that divides VPR and conquers Nocturnal Place Recognition (NPR). Specifically, we first established a street-level day-night dataset, NightStreet, and used it to train an unpaired image-to-image translation model. Then we used this model to process existing large-scale VPR datasets to generate the VPR-Night datasets and demonstrated how to combine them with two popular VPR pipelines. Finally, we proposed a divide-and-conquer VPR framework and provided explanations at the theoretical, experimental, and application levels. Under our framework, previous methods can significantly improve performance on two public datasets, including the top-ranked method.

Hanjing Ye, Weinan Chen, Jingwen Yu et al.

Visual place recognition (VPR) in condition-varying environments is still an open problem. Popular solutions are CNN-based image descriptors, which have been shown to outperform traditional image descriptors based on hand-crafted visual features. However, there are two drawbacks of current CNN-based descriptors: a) their high dimension and b) lack of generalization, leading to low efficiency and poor performance in applications. In this paper, we propose to use a convolutional autoencoder (CAE) to tackle this problem. We employ a high-level layer of a pre-trained CNN to generate features, and train a CAE to map the features to a low-dimensional space to improve the condition invariance property of the descriptor and reduce its dimension at the same time. We verify our method in three challenging datasets involving significant illumination changes, and our method is shown to be superior to the state-of-the-art. For the benefit of the community, we make public the source code.

Jiaru Jia, Mingzhe Liu, Jiake Xie et al.

Generating semantic segmentation datasets has consistently been laborious and time-consuming, particularly in the context of large models or specialized domains(i.e. Medical Imaging or Remote Sensing). Specifically, large models necessitate a substantial volume of data, while datasets in professional domains frequently require the involvement of domain experts. Both scenarios are susceptible to inaccurate data labeling, which can significantly affect the ultimate performance of the trained model. This paper proposes a simple and effective label pixel-level completion method, \textbf{Label Mask AutoEncoder} (L-MAE), which fully uses the existing information in the label to generate the complete label. The proposed model are the first to apply the Mask Auto-Encoder to downstream tasks. In detail, L-MAE adopts the fusion strategy that stacks the label and the corresponding image, namely fuse map. Moreover, since some of the image information is lost when masking the fuse map, direct reconstruction may lead to poor performance. We proposed Image Patch Supplement algorithm to supplement the missing information during the mask-reconstruct process, and empirically found that an average of 4.1\% mIoU can be improved. We conducted a experiment to evaluate the efficacy of L-MAE to complete the dataset. We employed a degraded Pascal VOC dataset and the degraded dataset enhanced by L-MAE to train an identical conventional semantic segmentation model for the initial set of experiments. The results of these experiments demonstrate a performance enhancement of 13.5\% in the model trained with the L-MAE-enhanced dataset compared to the unenhanced dataset.

Hong Zhang, Paul Andries Zegeling

Motivated by observations of saturation overshoot, this paper investigates numerical modeling of two-phase flow incorporating dynamic capillary pressure. The effects of the dynamic capillary coefficient, the infiltrating flux rate and the initial and boundary values are systematically studied using a travelling wave ansatz and efficient numerical methods. The travelling wave solutions may exhibit monotonic, non-monotonic or plateau-shaped behaviour. Special attention is paid to the non-monotonic profiles. The travelling wave results are confirmed by numerically solving the partial differential equation using an accurate adaptive moving mesh solver. Comparisons between the computed solutions using the Brooks-Corey model and the laboratory measurements of saturation overshoot verify the effectiveness of our approach.

Cheng Ge, Yi Lu, Jia Qu et al.

De novo peptide sequencing from mass spectrometry data is an important method for protein identification. Recently, various deep learning approaches were applied for de novo peptide sequencing and DeepNovoV2 is one of the represetative models. In this study, we proposed an enhanced model, DePS, which can improve the accuracy of de novo peptide sequencing even with missing signal peaks or large number of noisy peaks in tandem mass spectrometry data. It is showed that, for the same test set of DeepNovoV2, the DePS model achieved excellent results of 74.22%, 74.21% and 41.68% for amino acid recall, amino acid precision and peptide recall respectively. Furthermore, the results suggested that DePS outperforms DeepNovoV2 on the cross species dataset.

Jingwen Yu, Hanjing Ye, Jianhao Jiao et al.

Visual loop closure detection is an important module in visual simultaneous localization and mapping (SLAM), which associates current camera observation with previously visited places. Loop closures correct drifts in trajectory estimation to build a globally consistent map. However, a false loop closure can be fatal, so verification is required as an additional step to ensure robustness by rejecting the false positive loops. Geometric verification has been a well-acknowledged solution that leverages spatial clues provided by local feature matching to find true positives. Existing feature matching methods focus on homography and pose estimation in long-term visual localization, lacking references for geometric verification. To fill the gap, this paper proposes a unified benchmark targeting geometric verification of loop closure detection under long-term conditional variations. Furthermore, we evaluate six representative local feature matching methods (handcrafted and learning-based) under the benchmark, with in-depth analysis for limitations and future directions.

Guangcheng Chen, Yicheng He, Li He et al.

Neural implicit surface reconstruction has achieved remarkable progress recently. Despite resorting to complex radiance modeling, state-of-the-art methods still struggle with textureless and specular surfaces. Different from RGB images, polarization images can provide direct constraints on the azimuth angles of the surface normals. In this paper, we present PISR, a novel method that utilizes a geometrically accurate polarimetric loss to refine shape independently of appearance. In addition, PISR smooths surface normals in image space to eliminate severe shape distortions and leverages the hash-grid-based neural signed distance function to accelerate the reconstruction. Experimental results demonstrate that PISR achieves higher accuracy and robustness, with an L1 Chamfer distance of 0.5 mm and an F-score of 99.5% at 1 mm, while converging 4~30 times faster than previous polarimetric surface reconstruction methods.

JiaXu Wan, Hong Zhang, Jin Zhang et al.

Many multi-object tracking (MOT) methods follow the framework of "tracking by detection", which associates the target objects-of-interest based on the detection results. However, due to the separate models for detection and association, the tracking results are not optimal.Moreover, the speed is limited by some cumbersome association methods to achieve high tracking performance. In this work, we propose an end-to-end MOT method, with a Gaussian filter-inspired dynamic search region refinement module to dynamically filter and refine the search region by considering both the template information from the past frames and the detection results from the current frame with little computational burden, and a lightweight attention-based tracking head to achieve the effective fine-grained instance association. Extensive experiments and ablation study on MOT17 and MOT20 datasets demonstrate that our method can achieve the state-of-the-art performance with reasonable speed.

Zhongzhan Huang, Senwei Liang, Hong Zhang et al.

The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines. However, traditional numerical solvers are limited by the choice of step sizes when estimating integration, resulting in a trade-off between accuracy and computational efficiency. To address this challenge, we introduce a deep learning-based corrector called Neural Vector (NeurVec), which can compensate for integration errors and enable larger time step sizes in simulations. Our extensive experiments on a variety of complex dynamical system benchmarks demonstrate that NeurVec exhibits remarkable generalization capability on a continuous phase space, even when trained using limited and discrete data. NeurVec significantly accelerates traditional solvers, achieving speeds tens to hundreds of times faster while maintaining high levels of accuracy and stability. Moreover, NeurVec's simple-yet-effective design, combined with its ease of implementation, has the potential to establish a new paradigm for fast-solving differential equations based on deep learning.

Bangwei Guo, Xingyu Li, Miaomiao Yang et al.

Deep-learning models based on whole-slide digital pathology images (WSIs) become increasingly popular for predicting molecular biomarkers. Instance-based models has been the mainstream strategy for predicting genetic alterations using WSIs although bag-based models along with self-attention mechanism-based algorithms have been proposed for other digital pathology applications. In this paper, we proposed a novel Attention-based Multiple Instance Mutation Learning (AMIML) model for predicting gene mutations. AMIML was comprised of successive 1-D convolutional layers, a decoder, and a residual weight connection to facilitate further integration of a lightweight attention mechanism to detect the most predictive image patches. Using data for 24 clinically relevant genes from four cancer cohorts in The Cancer Genome Atlas (TCGA) studies (UCEC, BRCA, GBM and KIRC), we compared AMIML with one popular instance-based model and four recently published bag-based models (e.g., CHOWDER, HE2RNA, etc.). AMIML demonstrated excellent robustness, not only outperforming all the five baseline algorithms in the vast majority of the tested genes (17 out of 24), but also providing near-best-performance for the other seven genes. Conversely, the performance of the baseline published algorithms varied across different cancers/genes. In addition, compared to the published models for genetic alterations, AMIML provided a significant improvement for predicting a wide range of genes (e.g., KMT2C, TP53, and SETD2 for KIRC; ERBB2, BRCA1, and BRCA2 for BRCA; JAK1, POLE, and MTOR for UCEC) as well as produced outstanding predictive models for other clinically relevant gene mutations, which have not been reported in the current literature. Furthermore, with the flexible and interpretable attention-based MIL pooling mechanism, AMIML could further zero-in and detect predictive image patches.

Chen Hu, Qianxi Zhao, Xiaochen Yuan et al.

The Newton-Schulz (NS) iteration has become a key technique for orthogonalization in optimizers such as Muon and for optimization on the Stiefel manifold. Despite its effectiveness, the conventional NS iteration incurs significant computational overhead due to repeated high-dimensional matrix multiplications. To overcome these limitations, we propose Iteration-Free Newton-Schulz Orthogonalization (IFNSO), a novel framework that consolidates the traditional iterative structure into a unified and Iteration-Free formulation. By analyzing the contribution of individual matrix powers, we streamline the process by removing insignificant terms and introducing a polynomial with learnable coefficients. These coefficients are optimized to ensure both superior computational efficiency and stable convergence. Extensive experiments demonstrate that IFNSO achieves superior performance compared to existing methods. Our code is available at: https://github.com/greekinRoma/Unified_Newton_Schulz_Orthogonalization.

Hong Zhang, Barry Smith, Satish Balay et al.

While large language models have significantly accelerated scientific code generation, comprehensively evaluating the generated code remains a major challenge. Traditional benchmarks reduce evaluation to test-case matching, an approach insufficient for library code in HPC where solver selection, API conventions, memory management, and performance are just as critical as functional correctness. To address this gap, we introduce petscagent-bench, an agentic framework built on an agents-evaluating-agents paradigm. Instead of relying on static scripts, petscagent-bench deploys a tool-augmented evaluator agent that compiles, executes, and measures code produced by a separate model-under-test agent, orchestrating a 14-evaluator pipeline across five scoring categories: correctness, performance, code quality, algorithmic appropriateness, and library-specific conventions. Because the agents communicate through standardized protocols (A2A and MCP), the framework enables black-box evaluation of any coding agent without requiring access to its source code. We demonstrate the framework on a benchmark suite of realistic problems using the PETSc library for HPC. Our empirical analysis of frontier models reveals that while current models generate readable, well-structured code, they consistently struggle with library-specific conventions that traditional pass/fail metrics completely miss.

Yicheng He, Jingwen Yu, Guangcheng Chen et al.

Maintaining an up-to-date map that accurately reflects recent changes in the environment is crucial, especially for robots that repeatedly traverse the same space. Failing to promptly update the changed regions can degrade map quality, resulting in poor localization, inefficient operations, and even lost robots. 3D Gaussian Splatting (3DGS) has recently seen widespread adoption in online map reconstruction due to its dense, differentiable, and photorealistic properties, yet accurately and efficiently updating the regions of change remains a challenge. In this paper, we propose VG-Mapping, a novel online 3DGS-based mapping system tailored for such semi-static scenes. Our approach introduces a variation-aware density control strategy that decouples Gaussian density regulation from optimization. Specifically, we identify regions with variation to guide initialization and pruning, which avoids the use of stale information in defining the starting point for the subsequent optimization. Furthermore, to address the absence of public benchmarks for this task, we construct a RGB-D dataset comprising both synthetic and real-world semi-static environments. Experimental results demonstrate that our method substantially improves the rendering quality and map update efficiency in semi-static scenes. The code and dataset are available at https://github.com/heyicheng-never/VG-Mapping.

Min Cen, Xingyu Li, Bangwei Guo et al.

NLP-based computer vision models, particularly vision transformers, have been shown to outperform CNN models in many imaging tasks. However, most digital pathology artificial-intelligence models are based on CNN architectures, probably owing to a lack of data regarding NLP models for pathology images. In this study, we developed digital pathology pipelines to benchmark the five most recently proposed NLP models (vision transformer (ViT), Swin Transformer, MobileViT, CMT, and Sequencer2D) and four popular CNN models (ResNet18, ResNet50, MobileNetV2, and EfficientNet) to predict biomarkers in colorectal cancer (microsatellite instability, CpG island methylator phenotype, and BRAF mutation). Hematoxylin and eosin-stained whole-slide images from Molecular and Cellular Oncology and The Cancer Genome Atlas were used as training and external validation datasets, respectively. Cross-study external validations revealed that the NLP-based models significantly outperformed the CNN-based models in biomarker prediction tasks, improving the overall prediction and precision up to approximately 10% and 26%, respectively. Notably, compared with existing models in the current literature using large training datasets, our NLP models achieved state-of-the-art predictions for all three biomarkers using a relatively small training dataset, suggesting that large training datasets are not a prerequisite for NLP models or transformers, and NLP may be more suitable for clinical studies in which small training datasets are commonly collected. The superior performance of Sequencer2D suggests that further research and innovation on both transformer and bidirectional long short-term memory architectures are warranted in the field of digital pathology. NLP models can replace classic CNN architectures and become the new workhorse backbone in the field of digital pathology.

Hong Zhang, Yunrui Guo, Weibin Li et al.

We present a robust and accurate numerical method to solve the modified Buckley-Leverett equation in two-phase porous media flow with dynamic capillary pressure effect. A symmetric interior penalty discontinuous Galerkin method is used to discretize the equation in the space direction. For accuracy and stability issues, the third-order strong stability preserving implicit-explicit Runge-Kutta method is adopted to solve the nonlinear semi-discrete system: the linear diffusion term is discretized implicitly while the nonlinear flux term is discretized explicitly. The spatial accuracy of the discontinuous Galerkin method depends on the limiters applied to the solution: we test a minmod-TVB limiter, a simple WENO limiter and a high-order shock-capturing moment limiter to demonstrate that a suitable shock capturing moment limiter leads to more accurate approximation of solution. A set of representative numerical experiments are presented to show the accuracy and efficiency of the proposed approach. The results indicate that the moment limiter proposed by Moe et al. [Arxiv:1507.03024, 2015] is the most suitable one to be used in solving the modified Buckley- Leverett equation, and high order schemes perform much better than lower order schemes. Our simulation results are consistent with the previous results in Kao et al.[J. Sci. Comput., 64(3) (2015), 837-857], Zhang and Zegeling [J. Comput. Phys., 345 (2017), 510-527 and Commun. Comput. Phys., 22(4) (2017), 935-964].

Xin Liu, Shuhuan Wen, Jing Zhao et al.

The integration of cloud computing and edge computing is an effective way to achieve global consistent and real-time multi-robot Simultaneous Localization and Mapping (SLAM). Cloud computing effectively solves the problem of limited computing, communication and storage capacity of terminal equipment. However, limited bandwidth and extremely long communication links between terminal devices and the cloud result in serious performance degradation of multi-robot SLAM systems. To reduce the computational cost of feature tracking and improve the real-time performance of the robot, a lightweight SLAM method of optical flow tracking based on pyramid IMU prediction is proposed. On this basis, a centralized multi-robot SLAM system based on a robot-edge-cloud layered architecture is proposed to realize real-time collaborative SLAM. It avoids the problems of limited on-board computing resources and low execution efficiency of single robot. In this framework, only the feature points and keyframe descriptors are transmitted and lossless encoding and compression are carried out to realize real-time remote information transmission with limited bandwidth resources. This design reduces the actual bandwidth occupied in the process of data transmission, and does not cause the loss of SLAM accuracy caused by data compression. Through experimental verification on the EuRoC dataset, compared with the current most advanced local feature compression method, our method can achieve lower data volume feature transmission, and compared with the current advanced centralized multi-robot SLAM scheme, it can achieve the same or better positioning accuracy under low computational load.

Islam Ali, Bingqing, Wan et al.

Robustness and resilience of simultaneous localization and mapping (SLAM) are critical requirements for modern autonomous robotic systems. One of the essential steps to achieve robustness and resilience is the ability of SLAM to have an integrity measure for its localization estimates, and thus, have internal fault tolerance mechanisms to deal with performance degradation. In this work, we introduce a novel method for predicting SLAM localization error based on the characterization of raw sensor inputs. The proposed method relies on using a random forest regression model trained on 1-D global pooled features that are generated from characterized raw sensor data. The model is validated by using it to predict the performance of ORB-SLAM3 on three different datasets running on four different operating modes, resulting in an average prediction accuracy of up to 94.7\%. The paper also studies the impact of 12 different 1-D global pooling functions on regression quality, and the superiority of 1-D global averaging is quantitatively proven. Finally, the paper studies the quality of prediction with limited training data, and proves that we are able to maintain proper prediction quality when only 20 \% of the training examples are used for training, which highlights how the proposed model can optimize the evaluation footprint of SLAM systems.

Zhongjie Duan, Hong Zhang, Yingda Chen

Controllable diffusion methods have substantially expanded the practical utility of diffusion models, but they are typically developed as isolated, backbone-specific systems with incompatible training pipelines, parameter formats, and runtime hooks. This fragmentation makes it difficult to reuse infrastructure across tasks, transfer capabilities across backbones, or compose multiple controls within a single generation pipeline. We present Diffusion Templates, a unified and open plugin framework that decouples base-model inference from controllable capability injection. The framework is organized around three components: Template models that map arbitrary task-specific inputs to an intermediate capability representation, a Template cache that functions as a standardized interface for capability injection, and a Template pipeline that loads, merges, and injects one or more Template caches into the base diffusion runtime. Because the interface is defined at the systems level rather than tied to a specific control architecture, heterogeneous capability carriers such as KV-Cache and LoRA can be supported under the same abstraction. Based on this design, we build a diverse model zoo spanning structural control, brightness adjustment, color adjustment, image editing, super-resolution, sharpness enhancement, aesthetic alignment, content reference, local inpainting, and age control. These case studies show that Diffusion Templates can unify a broad range of controllable generation tasks while preserving modularity, composability, and practical extensibility across rapidly evolving diffusion backbones. All resources will be open sourced, including code, models, and datasets.

Shuhua Yang, Hui Yuan, Xiaoying Zhang et al.

Conversational recommendation systems elicit user preferences by interacting with users to obtain their feedback on recommended commodities. Such systems utilize a multi-armed bandit framework to learn user preferences in an online manner and have received great success in recent years. However, existing conversational bandit methods have several limitations. First, they only enable users to provide explicit binary feedback on the recommended items or categories, leading to ambiguity in interpretation. In practice, users are usually faced with more than one choice. Relative feedback, known for its informativeness, has gained increasing popularity in recommendation system design. Moreover, current contextual bandit methods mainly work under linear reward assumptions, ignoring practical non-linear reward structures in generalized linear models. Therefore, in this paper, we introduce relative feedback-based conversations into conversational recommendation systems through the integration of dueling bandits in generalized linear models (GLM) and propose a novel conversational dueling bandit algorithm called ConDuel. Theoretical analyses of regret upper bounds and empirical validations on synthetic and real-world data underscore ConDuel's efficacy. We also demonstrate the potential to extend our algorithm to multinomial logit bandits with theoretical and experimental guarantees, which further proves the applicability of the proposed framework.

Hong Zhang, Zhongjie Duan, Xingjun Wang et al.

Recent advancements in diffusion models have significantly advanced text-to-image generation, yet global text prompts alone remain insufficient for achieving fine-grained control over individual entities within an image. To address this limitation, we present EliGen, a novel framework for Entity-level controlled image Generation. Firstly, we put forward regional attention, a mechanism for diffusion transformers that requires no additional parameters, seamlessly integrating entity prompts and arbitrary-shaped spatial masks. By contributing a high-quality dataset with fine-grained spatial and semantic entity-level annotations, we train EliGen to achieve robust and accurate entity-level manipulation, surpassing existing methods in both spatial precision and image quality. Additionally, we propose an inpainting fusion pipeline, extending its capabilities to multi-entity image inpainting tasks. We further demonstrate its flexibility by integrating it with other open-source models such as IP-Adapter, In-Context LoRA and MLLM, unlocking new creative possibilities. The source code, model, and dataset are published at https://github.com/modelscope/DiffSynth-Studio.git.

Shiyao Zhang, Liwei Deng, Shuyu Zhang et al.

In future intelligent transportation systems, autonomous cooperative planning (ACP), becomes a promising technique to increase the effectiveness and security of multi-vehicle interactions. However, multiple uncertainties cannot be fully addressed for existing ACP strategies, e.g. perception, planning, and communication uncertainties. To address these, a novel deep reinforcement learning-based autonomous cooperative planning (DRLACP) framework is proposed to tackle various uncertainties on cooperative motion planning schemes. Specifically, the soft actor-critic (SAC) with the implementation of gate recurrent units (GRUs) is adopted to learn the deterministic optimal time-varying actions with imperfect state information occurred by planning, communication, and perception uncertainties. In addition, the real-time actions of autonomous vehicles (AVs) are demonstrated via the Car Learning to Act (CARLA) simulation platform. Evaluation results show that the proposed DRLACP learns and performs cooperative planning effectively, which outperforms other baseline methods under different scenarios with imperfect AV state information.

Hong Zhang, Yu Zhang

Spiking neural networks (SNNs) are potential competitors to artificial neural networks (ANNs) due to their high energy-efficiency on neuromorphic hardware. However, SNNs are unfolded over simulation time steps during the training process. Thus, SNNs require much more memory than ANNs, which impedes the training of deeper SNN models. In this paper, we propose the reversible spiking neural network to reduce the memory cost of intermediate activations and membrane potentials during training. Firstly, we extend the reversible architecture along temporal dimension and propose the reversible spiking block, which can reconstruct the computational graph and recompute all intermediate variables in forward pass with a reverse process. On this basis, we adopt the state-of-the-art SNN models to the reversible variants, namely reversible spiking ResNet (RevSResNet) and reversible spiking transformer (RevSFormer). Through experiments on static and neuromorphic datasets, we demonstrate that the memory cost per image of our reversible SNNs does not increase with the network depth. On CIFAR10 and CIFAR100 datasets, our RevSResNet37 and RevSFormer-4-384 achieve comparable accuracies and consume 3.79x and 3.00x lower GPU memory per image than their counterparts with roughly identical model complexity and parameters. We believe that this work can unleash the memory constraints in SNN training and pave the way for training extremely large and deep SNNs. The code is available at https://github.com/mi804/RevSNN.git.