Hong Li

Zhi-Qi Cheng, Qi Dai, Hong Li et al. · cmu, uw

Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting networks, we surprisingly found too strict pixel-level spatial invariance would cause overfit noise in the density map generation. In this paper, we try to use locally connected Gaussian kernels to replace the original convolution filter to estimate the spatial position in the density map. The purpose of this is to allow the feature extraction process to potentially stimulate the density map generation process to overcome the annotation noise. Inspired by previous work, we propose a low-rank approximation accompanied with translation invariance to favorably implement the approximation of massive Gaussian convolution. Our work points a new direction for follow-up research, which should investigate how to properly relax the overly strict pixel-level spatial invariance for object counting. We evaluate our methods on 4 mainstream object counting networks (i.e., MCNN, CSRNet, SANet, and ResNet-50). Extensive experiments were conducted on 7 popular benchmarks for 3 applications (i.e., crowd, vehicle, and plant counting). Experimental results show that our methods significantly outperform other state-of-the-art methods and achieve promising learning of the spatial position of objects.

Hong Li, Xingyu Li, Pengbo Hu et al.

While the field of multi-modal learning keeps growing fast, the deficiency of the standard joint training paradigm has become clear through recent studies. They attribute the sub-optimal performance of the jointly trained model to the modality competition phenomenon. Existing works attempt to improve the jointly trained model by modulating the training process. Despite their effectiveness, those methods can only apply to late fusion models. More importantly, the mechanism of the modality competition remains unexplored. In this paper, we first propose an adaptive gradient modulation method that can boost the performance of multi-modal models with various fusion strategies. Extensive experiments show that our method surpasses all existing modulation methods. Furthermore, to have a quantitative understanding of the modality competition and the mechanism behind the effectiveness of our modulation method, we introduce a novel metric to measure the competition strength. This metric is built on the mono-modal concept, a function that is designed to represent the competition-less state of a modality. Through systematic investigation, our results confirm the intuition that the modulation encourages the model to rely on the more informative modality. In addition, we find that the jointly trained model typically has a preferred modality on which the competition is weaker than other modalities. However, this preferred modality need not dominate others. Our code will be available at https://github.com/lihong2303/AGM_ICCV2023.

Peipei Liu, Gaosheng Wang, Hong Li et al.

Named Entity Recognition (NER) on social media refers to discovering and classifying entities from unstructured free-form content, and it plays an important role for various applications such as intention understanding and user recommendation. With social media posts tending to be multimodal, Multimodal Named Entity Recognition (MNER) for the text with its accompanying image is attracting more and more attention since some textual components can only be understood in combination with visual information. However, there are two drawbacks in existing approaches: 1) Meanings of the text and its accompanying image do not match always, so the text information still plays a major role. However, social media posts are usually shorter and more informal compared with other normal contents, which easily causes incomplete semantic description and the data sparsity problem. 2) Although the visual representations of whole images or objects are already used, existing methods ignore either fine-grained semantic correspondence between objects in images and words in text or the objective fact that there are misleading objects or no objects in some images. In this work, we solve the above two problems by introducing the multi-granularity cross-modality representation learning. To resolve the first problem, we enhance the representation by semantic augmentation for each word in text. As for the second issue, we perform the cross-modality semantic interaction between text and vision at the different vision granularity to get the most effective multimodal guidance representation for every word. Experiments show that our proposed approach can achieve the SOTA or approximate SOTA performance on two benchmark datasets of tweets. The code, data and the best performing models are available at https://github.com/LiuPeiP-CS/IIE4MNER

Bohan Zeng, Xuhui Liu, Sicheng Gao et al.

Face animation has achieved much progress in computer vision. However, prevailing GAN-based methods suffer from unnatural distortions and artifacts due to sophisticated motion deformation. In this paper, we propose a Face Animation framework with an attribute-guided Diffusion Model (FADM), which is the first work to exploit the superior modeling capacity of diffusion models for photo-realistic talking-head generation. To mitigate the uncontrollable synthesis effect of the diffusion model, we design an Attribute-Guided Conditioning Network (AGCN) to adaptively combine the coarse animation features and 3D face reconstruction results, which can incorporate appearance and motion conditions into the diffusion process. These specific designs help FADM rectify unnatural artifacts and distortions, and also enrich high-fidelity facial details through iterative diffusion refinements with accurate animation attributes. FADM can flexibly and effectively improve existing animation videos. Extensive experiments on widely used talking-head benchmarks validate the effectiveness of FADM over prior arts.

Bohan Zeng, Boyu Liu, Hong Li et al.

Face animation, one of the hottest topics in computer vision, has achieved a promising performance with the help of generative models. However, it remains a critical challenge to generate identity preserving and photo-realistic images due to the sophisticated motion deformation and complex facial detail modeling. To address these problems, we propose a Face Neural Volume Rendering (FNeVR) network to fully explore the potential of 2D motion warping and 3D volume rendering in a unified framework. In FNeVR, we design a 3D Face Volume Rendering (FVR) module to enhance the facial details for image rendering. Specifically, we first extract 3D information with a well-designed architecture, and then introduce an orthogonal adaptive ray-sampling module for efficient rendering. We also design a lightweight pose editor, enabling FNeVR to edit the facial pose in a simple yet effective way. Extensive experiments show that our FNeVR obtains the best overall quality and performance on widely used talking-head benchmarks.

Yang Liu, Yanwei Du, Hong Li et al.

In this article, a nonlinear fractional Cable equation is solved by a two-grid algorithm combined with finite element (FE) method. A temporal second-order fully discrete two-grid FE scheme, in which the spatial direction is approximated by two-grid FE method and the integer and fractional derivatives in time are discretized by second-order two-step backward difference method and second-order weighted and shifted Grünwald difference (WSGD) scheme, is presented to solve nonlinear fractional Cable equation. The studied algorithm in this paper mainly covers two steps: First, the numerical solution of nonlinear FE scheme on the coarse grid is solved, Second, based on the solution of initial iteration on the coarse grid, the linearized FE system on the fine grid is solved by using Newton iteration. Here, the stability based on fully discrete two-grid method is derived. Moreover, the a priori estimates with second-order convergence rate in time is proved in detail, which is higher than the L1-approximation result with $O(τ^{2-α}+τ^{2-β})$. Finally, the numerical results by using the two-grid method and FE method are calculated, respectively, and the CPU-time is compared to verify our theoretical results.

Bohan Zeng, Shanglin Li, Yutang Feng et al.

Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to guide 3D object generation. These methods enable the synthesis of detailed and photorealistic textured objects. However, the appearance of 3D objects produced by such text-to-3D models is often unpredictable, and it is hard for single-image-to-3D methods to deal with images lacking a clear subject, complicating the generation of appearance-controllable 3D objects from complex images. To address these challenges, we present IPDreamer, a novel method that captures intricate appearance features from complex $\textbf{I}$mage $\textbf{P}$rompts and aligns the synthesized 3D object with these extracted features, enabling high-fidelity, appearance-controllable 3D object generation. Our experiments demonstrate that IPDreamer consistently generates high-quality 3D objects that align with both the textual and complex image prompts, highlighting its promising capability in appearance-controlled, complex 3D object generation. Our code is available at https://github.com/zengbohan0217/IPDreamer.

Baoli Yin, Yang Liu, Hong Li et al.

In this article, a fast algorithm based on time two-mesh (TT-M) finite element (FE) scheme, which aims at solving nonlinear problems quickly, is considered to numerically solve the nonlinear space fractional Allen-Cahn equations with smooth and non-smooth solutions. The implicit second-order $θ$ scheme containing both implicit Crank-Nicolson scheme and second-order backward difference method is applied to time direction, a fast TT-M method is used to increase the speed of calculation, and the FE method is developed to approximate the spacial direction. The TT-M FE algorithm includes the following main computing steps: firstly, a nonlinear implicit second-order $θ$ FE scheme on the time coarse mesh $τ_c$ is solved by a nonlinear iterative method; secondly, based on the chosen initial iterative value, a linearized FE system on time fine mesh $τ<τ_c$ is solved, where some useful coarse numerical solutions are found by the Lagrange's interpolation formula. The analysis for both stability and a priori error estimates are made in detail. Finally, three numerical examples with smooth and non-smooth solutions are provided to illustrate the computational efficiency in solving nonlinear partial differential equations, from which it is easy to find that the computing time can be saved.

Baoli Yin, Yang Liu, Hong Li et al.

In this article, a two-grid mixed finite element (TGMFE) method with some second-order time discrete schemes is developed for numerically solving nonlinear fourth-order reaction diffusion equation. The two-grid MFE method is used to approximate spatial direction, and some second-order $θ$ schemes formulated at time $t_{k-θ}$ are considered to discretize the time direction. TGMFE method covers two main steps: a nonlinear MFE system based on the space coarse grid is solved by the iterative algorithm and a coarse solution is arrived at, then a linearized MFE system with fine grid is considered and a TGMFE solution is obtained. Here, the stability and a priori error estimates in $L^2$-norm for both nonlinear Galerkin MFE system and TGMFE scheme are derived. Finally, some convergence results are computed for both nonlinear Galerkin MFE system and TGMFE scheme to verify our theoretical analysis, which show that the convergence rate of the time second-order $θ$ scheme including Crank-Nicolson scheme and second-order backward difference scheme is close to $2$, and that with the comparison to the computing time of nonlinear Galerkin MFE method, the CPU-time by using TGMFE method can be saved.

Yunhao Liang, Ruixuan Ying, Bo Li et al.

DeepSeek-OCR utilizes an optical 2D mapping approach to achieve high-ratio vision-text compression, claiming to decode text tokens exceeding ten times the input visual tokens. While this suggests a promising solution for the LLM long-context bottleneck, we investigate a critical question: "Visual merit or linguistic crutch - which drives DeepSeek-OCR's performance?" By employing sentence-level and word-level semantic corruption, we isolate the model's intrinsic OCR capabilities from its language priors. Results demonstrate that without linguistic support, DeepSeek-OCR's performance plummets from approximately 90% to 20%. Comparative benchmarking against 13 baseline models reveals that traditional pipeline OCR methods exhibit significantly higher robustness to such semantic perturbations than end-to-end methods. Furthermore, we find that lower visual token counts correlate with increased reliance on priors, exacerbating hallucination risks. Context stress testing also reveals a total model collapse around 10,000 text tokens, suggesting that current optical compression techniques may paradoxically aggravate the long-context bottleneck. This study empirically defines DeepSeek-OCR's capability boundaries and offers essential insights for future optimizations of the vision-text compression paradigm. We release all data, results and scripts used in this study at https://github.com/dududuck00/DeepSeekOCR.

Peipei Liu, Hong Li, Zuoguang Wang et al.

Extracting cybersecurity entities such as attackers and vulnerabilities from unstructured network texts is an important part of security analysis. However, the sparsity of intelligence data resulted from the higher frequency variations and the randomness of cybersecurity entity names makes it difficult for current methods to perform well in extracting security-related concepts and entities. To this end, we propose a semantic augmentation method which incorporates different linguistic features to enrich the representation of input tokens to detect and classify the cybersecurity names over unstructured text. In particular, we encode and aggregate the constituent feature, morphological feature and part of speech feature for each input token to improve the robustness of the method. More than that, a token gets augmented semantic information from its most similar K words in cybersecurity domain corpus where an attentive module is leveraged to weigh differences of the words, and from contextual clues based on a large-scale general field corpus. We have conducted experiments on the cybersecurity datasets DNRTI and MalwareTextDB, and the results demonstrate the effectiveness of the proposed method.

Pengbo Hu, Ji Qi, Xingyu Li et al.

There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-based planning, provides flexibility in problem solving and endows better interpretability. However, current research is mostly limited to basic scenarios of simple questions that can be straightforward answered in a few inference steps. Planning for the more challenging multi-hop visual reasoning tasks remains under-explored. Specifically, under multi-hop reasoning situations, the trade-off between accuracy and the complexity of plan-searching becomes prominent. The prevailing algorithms either address the efficiency issue by employing the fast one-stop generation or adopt a complex iterative generation method to improve accuracy. Both fail to balance the need for efficiency and performance. Drawing inspiration from the dual system of cognition in the human brain, the fast and the slow think processes, we propose a hierarchical plan-searching algorithm that integrates the one-stop reasoning (fast) and the Tree-of-thought (slow). Our approach succeeds in performance while significantly saving inference steps. Moreover, we repurpose the PTR and the CLEVER datasets, developing a systematic framework for evaluating the performance and efficiency of LLMs-based plan-search algorithms under reasoning tasks at different levels of difficulty. Extensive experiments demonstrate the superiority of our proposed algorithm in terms of performance and efficiency. The dataset and code will be release soon.

Peipei Liu, Xin Zheng, Hong Li et al.

Modality representation learning is an important problem for multimodal sentiment analysis (MSA), since the highly distinguishable representations can contribute to improving the analysis effect. Previous works of MSA have usually focused on multimodal fusion strategies, and the deep study of modal representation learning was given less attention. Recently, contrastive learning has been confirmed effective at endowing the learned representation with stronger discriminate ability. Inspired by this, we explore the improvement approaches of modality representation with contrastive learning in this study. To this end, we devise a three-stages framework with multi-view contrastive learning to refine representations for the specific objectives. At the first stage, for the improvement of unimodal representations, we employ the supervised contrastive learning to pull samples within the same class together while the other samples are pushed apart. At the second stage, a self-supervised contrastive learning is designed for the improvement of the distilled unimodal representations after cross-modal interaction. At last, we leverage again the supervised contrastive learning to enhance the fused multimodal representation. After all the contrast trainings, we next achieve the classification task based on frozen representations. We conduct experiments on three open datasets, and results show the advance of our model.

Peipei Liu, Hong Li, Zhiyu Wang et al.

Enterprise relation extraction aims to detect pairs of enterprise entities and identify the business relations between them from unstructured or semi-structured text data, and it is crucial for several real-world applications such as risk analysis, rating research and supply chain security. However, previous work mainly focuses on getting attribute information about enterprises like personnel and corporate business, and pays little attention to enterprise relation extraction. To encourage further progress in the research, we introduce the CEntRE, a new dataset constructed from publicly available business news data with careful human annotation and intelligent data processing. Extensive experiments on CEntRE with six excellent models demonstrate the challenges of our proposed dataset.

Hong Li, Jianping Li, Wei Li et al.

In this paper, we study the prize-collecting rural postman problem (PCRPP), a variant of the rural postman problem. Given a PCRPP instance consisting of an undirected graph whose edges have nonnegative lengths and nonnegative profits, together with a root vertex, the goal is to find a closed walk that starts and ends at the root vertex and minimizes the sum of its length and the profits of all edges that the walk does not traverse. A natural way to design an approximation algorithm for the PCRPP is to construct a prize-collecting traveling salesman problem (PCTSP) instance from the given PCRPP instance, apply an approximation algorithm to the PCTSP instance, and then convert the resulting PCTSP solution into a PCRPP solution. We show that this approach has an inherent factor-two barrier: even if the constructed PCTSP instance is solved exactly, the resulting PCRPP solution can have objective value arbitrarily close to twice the optimum value of the original PCRPP instance. Our main result is a polynomial-time approximation algorithm with approximation ratio strictly smaller than 1.6 for the PCRPP. On a public 118-instance benchmark set, the proposed algorithm has average and maximum optimality gaps of 3.39\% and 12.12\%, respectively.

Peng Ren, Haoyang Ge, Chuan Qi et al.

Robots are increasingly expected to execute open ended natural language requests in human environments, which demands reliable long horizon execution under partial observability. This is especially challenging for humanoids because locomotion and manipulation are tightly coupled through stance, reachability, and balance. We present a humanoid agent framework that turns VLM plans into verifiable task programs and closes the loop with multi object 3D geometric supervision. A VLM planner compiles each instruction into a typed JSON sequence of subtasks with explicit predicate based preconditions and success conditions. Using SAM3 and RGB-D, we ground all task relevant entities in 3D, estimate object centroids and extents, and evaluate predicates over stable frames to obtain condition level diagnostics. The supervisor uses these diagnostics to verify subtask completion and to provide condition-level feedback for progression and replanning. We execute each subtask by coordinating humanoid locomotion and whole-body manipulation, selecting feasible motion primitives under reachability and balance constraints. Experiments on tabletop manipulation and long horizon humanoid loco manipulation tasks show improved robustness from multi object grounding, temporal stability, and recovery driven replanning.

Weiqing Xiao, Hong Li, Xiuyu Yang et al.

Recent advances have shown that large-scale video diffusion models can be repurposed as neural renderers by first decomposing videos into intrinsic scene representations and then performing forward rendering under novel illumination. While promising, this paradigm fundamentally relies on accurate intrinsic decomposition, which remains highly unreliable for real-world videos and often leads to distorted appearances, broken materials, and accumulated temporal artifacts during relighting. In this work, we present Relit-LiVE, a novel video relighting framework that produces physically consistent, temporally stable results without requiring prior knowledge of camera pose. Our key insight is to explicitly introduce raw reference images into the rendering process, enabling the model to recover critical scene cues that are inevitably lost or corrupted in intrinsic representations. Furthermore, we propose a novel environment video prediction formulation that simultaneously generates relit videos and per-frame environment maps aligned with each camera viewpoint in a single diffusion process. This joint prediction enforces strong geometric-illumination alignment and naturally supports dynamic lighting and camera motion, significantly improving physical consistency in video relighting while easing the requirement of known per-frame camera pose. Extensive experiments demonstrate that Relit-LiVE consistently outperforms state-of-the-art video relighting and neural rendering methods across synthetic and real-world benchmarks. Beyond relighting, our framework naturally supports a wide range of downstream applications, including scene-level rendering, material editing, object insertion, and streaming video relighting. The Project is available at https://github.com/zhuxing0/Relit-LiVE.

Ruizhong Qiu, Hanqing Zeng, Yinglong Xia et al.

Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRAs models expand neural networks efficiently by routing each layer input to a small subset of specialized LoRAs of the layer. Existing Mixture-of-LoRAs routers assign a learned routing weight to each LoRA to enable end-to-end training of the router. Despite their empirical promise, we observe that the routing weights are typically extremely imbalanced across LoRAs in practice, where only one or two LoRAs often dominate the routing weights. This essentially limits the number of effective LoRAs and thus severely hinders the expressive power of existing Mixture-of-LoRAs models. In this work, we attribute this weakness to the nature of learnable routing weights and rethink the fundamental design of the router. To address this critical issue, we propose a new router designed that we call Reinforcement Routing for Mixture-of-LoRAs (ReMix). Our key idea is using non-learnable routing weights to ensure all active LoRAs to be equally effective, with no LoRA dominating the routing weights. However, our routers cannot be trained directly via gradient descent due to our non-learnable routing weights. Hence, we further propose an unbiased gradient estimator for the router by employing the reinforce leave-one-out (RLOO) technique, where we regard the supervision loss as the reward and the router as the policy in reinforcement learning. Our gradient estimator also enables to scale up training compute to boost the predictive performance of our ReMix. Extensive experiments demonstrate that our proposed ReMix significantly outperform state-of-the-art parameter-efficient finetuning methods under a comparable number of activated parameters.

Ling Yang, Bohan Zeng, Jiaming Liu et al.

Diffusion models have significantly improved the performance of image editing. Existing methods realize various approaches to achieve high-quality image editing, including but not limited to text control, dragging operation, and mask-and-inpainting. Among these, instruction-based editing stands out for its convenience and effectiveness in following human instructions across diverse scenarios. However, it still focuses on simple editing operations like adding, replacing, or deleting, and falls short of understanding aspects of world dynamics that convey the realistic dynamic nature in the physical world. Therefore, this work, EditWorld, introduces a new editing task, namely world-instructed image editing, which defines and categorizes the instructions grounded by various world scenarios. We curate a new image editing dataset with world instructions using a set of large pretrained models (e.g., GPT-3.5, Video-LLava and SDXL). To enable sufficient simulation of world dynamics for image editing, our EditWorld trains model in the curated dataset, and improves instruction-following ability with designed post-edit strategy. Extensive experiments demonstrate our method significantly outperforms existing editing methods in this new task. Our dataset and code will be available at https://github.com/YangLing0818/EditWorld

Xuying Ning, Katherine Tieu, Dongqi Fu et al.

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control and optimization that make harness reliable and adaptive. Third, we discuss scaling the harness from single-agent systems to multi-agent settings, where shared code artifacts support multi-agent coordination, review, and verification. Across these layers, we summarize representative methods and practical applications of code as agent harness, spanning coding assistants, GUI/OS automation, embodied agents, scientific discovery, personalization and recommendation, DevOps, and enterprise workflows. We further outline open challenges for harness engineering, including evaluation beyond final task success, verification under incomplete feedback, regression-free harness improvement, consistent shared state across multiple agents, human oversight for safety-critical actions, and extensions to multimodal environments. By centering code as the harness of agentic AI, this survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.

Rengan Xu, Junjie Yang, Yifan Xu et al.

The integration of hardware accelerators has significantly advanced the capabilities of modern recommendation systems, enabling the exploration of complex ranking paradigms previously deemed impractical. However, the GPU-based computational costs present substantial challenges. In this paper, we demonstrate our development of an efficiency-driven approach to explore these paradigms, moving beyond traditional reliance on native PyTorch modules. We address the specific challenges posed by ranking models' dependence on categorical features, which vary in length and complicate GPU utilization. We introduce Jagged Feature Interaction Kernels, a novel method designed to extract fine-grained insights from long categorical features through efficient handling of dynamically sized tensors. We further enhance the performance of attention mechanisms by integrating Jagged tensors with Flash Attention. Our novel Jagged Flash Attention achieves up to 9x speedup and 22x memory reduction compared to dense attention. Notably, it also outperforms dense flash attention, with up to 3x speedup and 53% more memory efficiency. In production models, we observe 10% QPS improvement and 18% memory savings, enabling us to scale our recommendation systems with longer features and more complex architectures.

Xuhui Liu, Zhi Qiao, Runkun Liu et al.

Computed tomography (CT) is widely utilized in clinical settings because it delivers detailed 3D images of the human body. However, performing CT scans is not always feasible due to radiation exposure and limitations in certain surgical environments. As an alternative, reconstructing CT images from ultra-sparse X-rays offers a valuable solution and has gained significant interest in scientific research and medical applications. However, it presents great challenges as it is inherently an ill-posed problem, often compromised by artifacts resulting from overlapping structures in X-ray images. In this paper, we propose DiffuX2CT, which models CT reconstruction from orthogonal biplanar X-rays as a conditional diffusion process. DiffuX2CT is established with a 3D global coherence denoising model with a new, implicit conditioning mechanism. We realize the conditioning mechanism by a newly designed tri-plane decoupling generator and an implicit neural decoder. By doing so, DiffuX2CT achieves structure-controllable reconstruction, which enables 3D structural information to be recovered from 2D X-rays, therefore producing faithful textures in CT images. As an extra contribution, we collect a real-world lumbar CT dataset, called LumbarV, as a new benchmark to verify the clinical significance and performance of CT reconstruction from X-rays. Extensive experiments on this dataset and three more publicly available datasets demonstrate the effectiveness of our proposal.

Hong Li, Yutang Feng, Minqi Meng et al.

Generating high-fidelity 3D avatars from text or image prompts is highly sought after in virtual reality and human-computer interaction. However, existing text-driven methods often rely on iterative Score Distillation Sampling (SDS) or CLIP optimization, which struggle with fine-grained semantic control and suffer from excessively slow inference. Meanwhile, image-driven approaches are severely bottlenecked by the scarcity and high acquisition cost of high-quality 3D facial scans, limiting model generalization. To address these challenges, we first construct a novel, large-scale dataset comprising over 100,000 pairs across four modalities: fine-grained textual descriptions, in-the-wild face images, high-quality light-normalized texture UV maps, and 3D geometric shapes. Leveraging this comprehensive dataset, we propose PromptAvatar, a framework featuring dual diffusion models. Specifically, it integrates a Texture Diffusion Model (TDM) that supports flexible multi-condition guidance from text and/or image prompts, alongside a Geometry Diffusion Model (GDM) guided by text prompts. By learning the direct mapping from multi-modal prompts to 3D representations, PromptAvatar eliminates the need for time-consuming iterative optimization, successfully generating high-fidelity, shading-free 3D avatars in under 10 seconds. Extensive quantitative and qualitative experiments demonstrate that our method significantly outperforms existing state-of-the-art approaches in generation quality, fine-grained detail alignment, and computational efficiency.

Hong Li, Boyu Liu, Xuhui Liu et al.

Face animation deals with controlling and generating facial features with a wide range of applications. The methods based on unsupervised keypoint positioning can produce realistic and detailed virtual portraits. However, they cannot achieve controllable face generation since the existing keypoint decomposition pipelines fail to fully decouple identity semantics and intertwined motion information (e.g., rotation, translation, and expression). To address these issues, we present a new method, Motion Manipulation via unsupervised keypoint positioning in Face Animation (MMFA). We first introduce self-supervised representation learning to encode and decode expressions in the latent feature space and decouple them from other motion information. Secondly, we propose a new way to compute keypoints aiming to achieve arbitrary motion control. Moreover, we design a variational autoencoder to map expression features to a continuous Gaussian distribution, allowing us for the first time to interpolate facial expressions in an unsupervised framework. We have conducted extensive experiments on publicly available datasets to validate the effectiveness of MMFA, which show that MMFA offers pronounced advantages over prior arts in creating realistic animation and manipulating face motion.

Hong Li, Zhiquan Tan, Xingyu Li et al.

While vision-and-language models significantly advance in many fields, the challenge of continual learning is unsolved. Parameter-efficient modules like adapters and prompts present a promising way to alleviate catastrophic forgetting. However, existing works usually learn individual adapters for each task, which may result in redundant knowledge among adapters. Moreover, they continue to use the original pre-trained model to initialize the downstream model, leading to negligible changes in the model's generalization compared to the original model. In addition, there is still a lack of research investigating the consequences of integrating a multi-modal model into the updating procedure for both uni-modal and multi-modal tasks and the subsequent impacts it has on downstream tasks. In this paper, we propose an adapter-based two-stage learning paradigm, a multi-modal continual learning scheme that consists of experience-based learning and novel knowledge expansion, which helps the model fully use experience knowledge and compensate for novel knowledge. Extensive experiments demonstrate that our method is proficient for continual learning. It expands the distribution of representation upstream while also minimizing the negative impact of forgetting previous tasks. Additionally, it enhances the generalization capability for downstream tasks. Furthermore, we incorporate both multi-modal and uni-modal tasks into upstream continual learning. We observe that learning from upstream tasks can help with downstream tasks. Our code will be available at: https://github.com/lihong2303/ATLAS.

Shaocong Xu, Songlin Wei, Qizhe Wei et al.

Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monocular depth, causing holes and temporally unstable estimates. Our key observation is that modern video diffusion models already synthesize convincing transparent phenomena, suggesting they have internalized the optical rules. We build TransPhy3D, a synthetic video corpus of transparent/reflective scenes: 11k sequences rendered with Blender/Cycles. Scenes are assembled from a curated bank of category-rich static assets and shape-rich procedural assets paired with glass/plastic/metal materials. We render RGB + depth + normals with physically based ray tracing and OptiX denoising. Starting from a large video diffusion model, we learn a video-to-video translator for depth (and normals) via lightweight LoRA adapters. During training we concatenate RGB and (noisy) depth latents in the DiT backbone and co-train on TransPhy3D and existing frame-wise synthetic datasets, yielding temporally consistent predictions for arbitrary-length input videos. The resulting model, DKT, achieves zero-shot SOTA on real and synthetic video benchmarks involving transparency: ClearPose, DREDS (CatKnown/CatNovel), and TransPhy3D-Test. It improves accuracy and temporal consistency over strong image/video baselines, and a normal variant sets the best video normal estimation results on ClearPose. A compact 1.3B version runs at ~0.17 s/frame. Integrated into a grasping stack, DKT's depth boosts success rates across translucent, reflective and diffuse surfaces, outperforming prior estimators. Together, these results support a broader claim: "Diffusion knows transparency." Generative video priors can be repurposed, efficiently and label-free, into robust, temporally coherent perception for challenging real-world manipulation.

Hong Li, Zhen Zhou, Honggang Zhang et al.

Data-parallel (DP) training with synchronous all-reduce is a dominant paradigm for full-parameter fine-tuning of large language models (LLMs). While parameter synchronization guarantees numerical equivalence of model weights after each iteration, it does not necessarily imply alignment of worker-level optimization dynamics before gradient aggregation. This paper identifies and studies this latent mismatch, termed \emph{silent inconsistency}, where cross-worker divergence in losses and gradients can remain invisible under conventional aggregated monitoring signals. We propose a lightweight, model-agnostic diagnostic framework that quantifies worker-level consistency using training signals readily available in standard pipelines. Specifically, we introduce three complementary metrics: loss dispersion, gradient-norm dispersion, and gradient-direction consistency measured by inter-worker cosine similarity. The proposed metrics incur negligible overhead and require no modification to model architecture, synchronization mechanisms, or optimization algorithms. We validate the framework by fully fine-tuning the 1B-parameter \texttt{openPangu-Embedded-1B-V1.1} model on the \texttt{tatsu-lab/alpaca} dataset using an 8-NPU DP setup, under controlled perturbations of cross-rank stochasticity. Experimental results show that progressively desynchronized data shuffling and random seeds lead to substantial increases in loss/gradient dispersion and reduced directional alignment, despite smooth globally averaged loss curves. These findings demonstrate that the proposed indicators provide actionable visibility into hidden instability modes in large-scale DP fine-tuning, enabling more reliable diagnosis and configuration assessment.

Yonghao Zhao, Changtao Li, Chi Shu et al.

Survival prognosis is crucial for medical informatics. Practitioners often confront small-sized clinical data, especially cancer patient cases, which can be insufficient to induce useful patterns for survival predictions. This study deals with small sample survival analysis by leveraging transfer learning, a useful machine learning technique that can enhance the target analysis with related knowledge pre-learned from other data. We propose and develop various transfer learning methods designed for common survival models. For parametric models such as DeepSurv, Cox-CC (Cox-based neural networks), and DeepHit (end-to-end deep learning model), we apply standard transfer learning techniques like pretraining and fine-tuning. For non-parametric models such as Random Survival Forest, we propose a new transfer survival forest (TSF) model that transfers tree structures from source tasks and fine-tunes them with target data. We evaluated the transfer learning methods on colorectal cancer (CRC) prognosis. The source data are 27,379 SEER CRC stage I patients, and the target data are 728 CRC stage I patients from the West China Hospital. When enhanced by transfer learning, Cox-CC's $C^{td}$ value was boosted from 0.7868 to 0.8111, DeepHit's from 0.8085 to 0.8135, DeepSurv's from 0.7722 to 0.8043, and RSF's from 0.7940 to 0.8297 (the highest performance). All models trained with data as small as 50 demonstrated even more significant improvement. Conclusions: Therefore, the current survival models used for cancer prognosis can be enhanced and improved by properly designed transfer learning techniques. The source code used in this study is available at https://github.com/YonghaoZhao722/TSF.

Nanxi Li, Xiang Wang, Yuanjie Chen et al.

While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in image and video understanding, their ability to comprehend the physical world has become an increasingly important research focus. Despite their improvements, current MLLMs struggle significantly with high-level physics reasoning. In this work, we investigate the first step of physical reasoning, i.e., intuitive physics understanding, revealing substantial limitations in understanding the dynamics of continuum objects. To isolate and evaluate this specific capability, we introduce two fundamental benchmark tasks: Next Frame Selection (NFS) and Temporal Coherence Verification (TCV). Our experiments demonstrate that even state-of-the-art MLLMs perform poorly on these foundational tasks. To address this limitation, we propose Scene Dynamic Field (SDF), a concise approach that leverages physics simulators within a multi-task fine-tuning framework. SDF substantially improves performance, achieving up to 20.7% gains on fluid tasks while showing strong generalization to unseen physical domains. This work not only highlights a critical gap in current MLLMs but also presents a promising cost-efficient approach for developing more physically grounded MLLMs. Our code and data are available at https://github.com/andylinx/Scene-Dynamic-Field.

Kun Xiao, Guohui Wang, Yi Chen et al.

Event cameras are a new type of sensors that are different from traditional cameras. Each pixel is triggered asynchronously by event. The trigger event is the change of the brightness irradiated on the pixel. If the increment or decrement of brightness is higher than a certain threshold, an event is output. Compared with traditional cameras, event cameras have the advantages of high dynamic range and no motion blur. Accumulating events to frames and using traditional SLAM algorithm is a direct and efficient way for event-based SLAM. Different event accumulator settings, such as slice method of event stream, processing method for no motion, using polarity or not, decay function and event contribution, can cause quite different accumulating results. We conducted the research on how to accumulate event frames to achieve a better event-based SLAM performance. For experiment verification, accumulated event frames are fed to the traditional SLAM system to construct an event-based SLAM system. Our strategy of setting event accumulator has been evaluated on the public dataset. The experiment results show that our method can achieve better performance in most sequences compared with the state-of-the-art event frame based SLAM algorithm. In addition, the proposed approach has been tested on a quadrotor UAV to show the potential of applications in real scenario. Code and results are open sourced to benefit the research community of event cameras.

Bo Li, Duyuan Zheng, Xinyang Liu et al.

Person re-identification (ReID) in surveillance is challenged by occlusion, viewpoint distortion, and poor image quality. Most existing methods rely on complex modules or perform well only on clear frontal images. We propose Sh-ViT (Shuffling Vision Transformer), a lightweight and robust model for occluded person ReID. Built on ViT-Base, Sh-ViT introduces three components: First, a Shuffle module in the final Transformer layer to break spatial correlations and enhance robustness to occlusion and blur; Second, scenario-adapted augmentation (geometric transforms, erasing, blur, and color adjustment) to simulate surveillance conditions; Third, DeiT-based knowledge distillation to improve learning with limited labels.To support real-world evaluation, we construct the MyTT dataset, containing over 10,000 pedestrians and 30,000+ images from base station inspections, with frequent equipment occlusion and camera variations. Experiments show that Sh-ViT achieves 83.2% Rank-1 and 80.1% mAP on MyTT, outperforming CNN and ViT baselines, and 94.6% Rank-1 and 87.5% mAP on Market1501, surpassing state-of-the-art methods.In summary, Sh-ViT improves robustness to occlusion and blur without external modules, offering a practical solution for surveillance-based personnel monitoring.

Wenjie Wang, Wei Wu, Ying Liu et al.

Medical document OCR is challenging due to complex layouts, domain-specific terminology, and noisy annotations, while requiring strict field-level exact matching. Existing OCR systems and general-purpose vision-language models often fail to reliably parse such documents. We propose MeDocVL, a post-trained vision-language model for query-driven medical document parsing. Our framework combines Training-driven Label Refinement to construct high-quality supervision from noisy annotations, with a Noise-aware Hybrid Post-training strategy that integrates reinforcement learning and supervised fine-tuning to achieve robust and precise extraction. Experiments on medical invoice benchmarks show that MeDocVL consistently outperforms conventional OCR systems and strong VLM baselines, achieving state-of-the-art performance under noisy supervision.

Guojun Lei, Chi Wang, Hong Li et al.

We present a unified controllable video generation approach AnimateAnything that facilitates precise and consistent video manipulation across various conditions, including camera trajectories, text prompts, and user motion annotations. Specifically, we carefully design a multi-scale control feature fusion network to construct a common motion representation for different conditions. It explicitly converts all control information into frame-by-frame optical flows. Then we incorporate the optical flows as motion priors to guide final video generation. In addition, to reduce the flickering issues caused by large-scale motion, we propose a frequency-based stabilization module. It can enhance temporal coherence by ensuring the video's frequency domain consistency. Experiments demonstrate that our method outperforms the state-of-the-art approaches. For more details and videos, please refer to the webpage: https://yu-shaonian.github.io/Animate_Anything/.

Houyuan Chen, Hong Li, Xianghao Kong et al.

Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and limits the modeling of correlations across modalities. We present UniVidX, a unified multimodal framework that leverages VDM priors for versatile video generation. UniVidX formulates pixel-aligned tasks as conditional generation in a shared multimodal space, adapts to modality-specific distributions while preserving the backbone's native priors, and promotes cross-modal consistency during synthesis. It is built on three key designs. Stochastic Condition Masking (SCM) randomly partitions modalities into clean conditions and noisy targets during training, enabling omni-directional conditional generation instead of fixed mappings. Decoupled Gated LoRA (DGL) introduces per-modality LoRAs that are activated when a modality serves as the generation target, preserving the strong priors of the VDM. Cross-Modal Self-Attention (CMSA) shares keys and values across modalities while keeping modality-specific queries, facilitating information exchange and inter-modal alignment. We instantiate UniVidX in two domains: UniVid-Intrinsic, for RGB videos and intrinsic maps including albedo, irradiance, and normal; and UniVid-Alpha, for blended RGB videos and their constituent RGBA layers. Experiments show that both models achieve performance competitive with state-of-the-art methods across distinct tasks and generalize robustly to in-the-wild scenarios, even when trained on fewer than 1,000 videos. Project page: https://houyuanchen111.github.io/UniVidX.github.io/

Qingyu Zheng, Guijun Han, Wei Li et al.

Advances in data assimilation (DA) methods have greatly improved the accuracy of Earth system predictions. To fuse multi-source data and reconstruct the nonlinear evolution missing from observations, geoscientists are developing future-oriented DA methods. In this paper, we redesign a purely data-driven latent space DA framework (DeepDA) that employs a generative artificial intelligence model to capture the nonlinear evolution in sea surface temperature. Under variational constraints, DeepDA embedded with nonlinear features can effectively fuse heterogeneous data. The results show that DeepDA remains highly stable in capturing and generating nonlinear evolutions even when a large amount of observational information is missing. It can be found that when only 10% of the observation information is available, the error increase of DeepDA does not exceed 40%. Furthermore, DeepDA has been shown to be robust in the fusion of real observations and ensemble simulations. In particular, this paper provides a mechanism analysis of the nonlinear evolution generated by DeepDA from the perspective of physical patterns, which reveals the inherent explainability of our DL model in capturing multi-scale ocean signals.

Hong Li, Houyuan Chen, Chongjie Ye et al.

Universal photometric stereo (PS) is defined by two factors: it must (i) operate under arbitrary, unknown lighting conditions and (ii) avoid reliance on specific illumination models. Despite progress (e.g., SDM UniPS), two challenges remain. First, current encoders cannot guarantee that illumination and normal information are decoupled. To enforce decoupling, we introduce LINO UniPS with two key components: (i) Light Register Tokens with light alignment supervision to aggregate point, direction, and environment lights; (ii) Interleaved Attention Block featuring global cross-image attention that takes all lighting conditions together so the encoder can factor out lighting while retaining normal-related evidence. Second, high-frequency geometric details are easily lost. We address this with (i) a Wavelet-based Dual-branch Architecture and (ii) a Normal-gradient Perception Loss. These techniques yield a unified feature space in which lighting is explicitly represented by register tokens, while normal details are preserved via wavelet branch. We further introduce PS-Verse, a large-scale synthetic dataset graded by geometric complexity and lighting diversity, and adopt curriculum training from simple to complex scenes. Extensive experiments show new state-of-the-art results on public benchmarks (e.g., DiLiGenT, Luces), stronger generalization to real materials, and improved efficiency; ablations confirm that Light Register Tokens + Interleaved Attention Block drive better feature decoupling, while Wavelet-based Dual-branch Architecture + Normal-gradient Perception Loss recover finer details.

Jialin Zheng, Haoyu Wang, Yangbin Zeng et al.

Edge Digital Twins (EDTs) are crucial for monitoring and control of Power Electronics Systems (PES). However, existing modeling approaches struggle to consistently capture continuously evolving hybrid dynamics that are inherent in PES, degrading Sim-to-Real generalization on resource-constrained edge devices. To address these challenges, this paper proposes a Physics-Embedded Neural ODEs (PENODE) that (i) embeds the hybrid operating mechanism as an event automaton to explicitly govern discrete switching and (ii) injects known governing ODE components directly into the neural parameterization of unmodeled dynamics. This unified design yields a differentiable end-to-end trainable architecture that preserves physical interpretability while reducing redundancy, and it supports a cloud-to-edge toolchain for efficient FPGA deployment. Experimental results demonstrate that PENODE achieves significantly higher accuracy in benchmarks in white-box, gray-box, and black-box scenarios, with a 75% reduction in neuron count, validating that the proposed PENODE maintains physical interpretability, efficient edge deployment, and real-time control enhancement.

Haodong Zhu, Wenhao Dong, Linlin Yang et al.

Leveraging the complementary characteristics of visible (RGB) and infrared (IR) imagery offers significant potential for improving object detection. In this paper, we propose WaveMamba, a cross-modality fusion method that efficiently integrates the unique and complementary frequency features of RGB and IR decomposed by Discrete Wavelet Transform (DWT). An improved detection head incorporating the Inverse Discrete Wavelet Transform (IDWT) is also proposed to reduce information loss and produce the final detection results. The core of our approach is the introduction of WaveMamba Fusion Block (WMFB), which facilitates comprehensive fusion across low-/high-frequency sub-bands. Within WMFB, the Low-frequency Mamba Fusion Block (LMFB), built upon the Mamba framework, first performs initial low-frequency feature fusion with channel swapping, followed by deep fusion with an advanced gated attention mechanism for enhanced integration. High-frequency features are enhanced using a strategy that applies an ``absolute maximum" fusion approach. These advancements lead to significant performance gains, with our method surpassing state-of-the-art approaches and achieving average mAP improvements of 4.5% on four benchmarks.

Jialin Zheng, Haoyu Wang, Yangbin Zeng et al.

Advancing the dynamics inference of power electronic systems (PES) to the real-time edge-side holds transform-ative potential for testing, control, and monitoring. How-ever, efficiently inferring the inherent hybrid continu-ous-discrete dynamics on resource-constrained edge hardware remains a significant challenge. This letter pro-poses a neural substitute solver (NSS) approach, which is a neural-network-based framework aimed at rapid accurate inference with significantly reduced computational costs. Specifically, NSS leverages lightweight neural networks to substitute time-consuming matrix operation and high-order numerical integration steps in traditional solvers, which transforms sequential bottlenecks into highly parallel operation suitable for edge hardware. Experimental vali-dation on a multi-stage DC-DC converter demonstrates that NSS achieves 23x speedup and 60% hardware resource reduction compared to traditional solvers, paving the way for deploying edge inference of high-fidelity PES dynamics.

Yichen Yang, Hong Li, Haodong Zhu et al.

Existing autoregressive (AR) methods for generating artist-designed meshes struggle to balance global structural consistency with high-fidelity local details, and are susceptible to error accumulation. To address this, we propose PartDiffuser, a novel semi-autoregressive diffusion framework for point-cloud-to-mesh generation. The method first performs semantic segmentation on the mesh and then operates in a "part-wise" manner: it employs autoregression between parts to ensure global topology, while utilizing a parallel discrete diffusion process within each semantic part to precisely reconstruct high-frequency geometric features. PartDiffuser is based on the DiT architecture and introduces a part-aware cross-attention mechanism, using point clouds as hierarchical geometric conditioning to dynamically control the generation process, thereby effectively decoupling the global and local generation tasks. Experiments demonstrate that this method significantly outperforms state-of-the-art (SOTA) models in generating 3D meshes with rich detail, exhibiting exceptional detail representation suitable for real-world applications.

Hong Li, Chongjie Ye, Houyuan Chen et al.

Neural asset authoring and neural rendering have traditionally evolved as disjoint paradigms: one generates digital assets for fixed graphics pipelines, while the other maps conventional assets to images. However, treating them as independent entities limits the potential for end-to-end optimization in fidelity and consistency. In this paper, we bridge this gap with NeAR, a Coupled Neural Asset--Renderer Stack. We argue that co-designing the asset representation and the renderer creates a robust "contract" for superior generation. On the asset side, we introduce the Lighting-Homogenized SLAT (LH-SLAT). Leveraging a rectified-flow model, NeAR lifts casually lit single images into a canonical, illumination-invariant latent space, effectively suppressing baked-in shadows and highlights. On the renderer side, we design a lighting-aware neural decoder tailored to interpret these homogenized latents. Conditioned on HDR environment maps and camera views, it synthesizes relightable 3D Gaussian splats in real-time without per-object optimization. We validate NeAR on four tasks: (1) G-buffer-based forward rendering, (2) random-lit reconstruction, (3) unknown-lit relighting, and (4) novel-view relighting. Extensive experiments demonstrate that our coupled stack outperforms state-of-the-art baselines in both quantitative metrics and perceptual quality. We hope this coupled asset-renderer perspective inspires future graphics stacks that view neural assets and renderers as co-designed components instead of independent entities.

Guojun Lei, Chi Wang, Yikai Wang et al.

Generating videos guided by camera trajectories poses significant challenges in achieving consistency and generalizability, particularly when both camera and object motions are present. Existing approaches often attempt to learn these motions separately, which may lead to confusion regarding the relative motion between the camera and the objects. To address this challenge, we propose a novel approach that integrates both camera and object motions by converting them into the motion of corresponding pixels. Utilizing a stable diffusion network, we effectively learn reference motion maps in relation to the specified camera trajectory. These maps, along with an extracted semantic object prior, are then fed into an image-to-video network to generate the desired video that can accurately follow the designated camera trajectory while maintaining consistent object motions. Extensive experiments verify that our model outperforms SOTA methods by a large margin.

Guojun Lei, Rong Zhang, Chi Wang et al.

We propose a novel architecture UniTransfer, which introduces both spatial and diffusion timestep decomposition in a progressive paradigm, achieving precise and controllable video concept transfer. Specifically, in terms of spatial decomposition, we decouple videos into three key components: the foreground subject, the background, and the motion flow. Building upon this decomposed formulation, we further introduce a dual-to-single-stream DiT-based architecture for supporting fine-grained control over different components in the videos. We also introduce a self-supervised pretraining strategy based on random masking to enhance the decomposed representation learning from large-scale unlabeled video data. Inspired by the Chain-of-Thought reasoning paradigm, we further revisit the denoising diffusion process and propose a Chain-of-Prompt (CoP) mechanism to achieve the timestep decomposition. We decompose the denoising process into three stages of different granularity and leverage large language models (LLMs) for stage-specific instructions to guide the generation progressively. We also curate an animal-centric video dataset called OpenAnimal to facilitate the advancement and benchmarking of research in video concept transfer. Extensive experiments demonstrate that our method achieves high-quality and controllable video concept transfer across diverse reference images and scenes, surpassing existing baselines in both visual fidelity and editability. Web Page: https://yu-shaonian.github.io/UniTransfer-Web/

Renzhi Wu, Junjie Yang, Li Chen et al.

Cross-domain recommendation systems face the challenge of integrating fine-grained user and item relationships across various product domains. To address this, we introduce RankGraph, a scalable graph learning framework designed to serve as a core component in recommendation foundation models (FMs). By constructing and leveraging graphs composed of heterogeneous nodes and edges across multiple products, RankGraph enables the integration of complex relationships between users, posts, ads, and other entities. Our framework employs a GPU-accelerated Graph Neural Network and contrastive learning, allowing for dynamic extraction of subgraphs such as item-item and user-user graphs to support similarity-based retrieval and real-time clustering. Furthermore, RankGraph integrates graph-based pretrained representations as contextual tokens into FM sequence models, enriching them with structured relational knowledge. RankGraph has demonstrated improvements in click (+0.92%) and conversion rates (+2.82%) in online A/B tests, showcasing its effectiveness in cross-domain recommendation scenarios.

Xingyu Feng, Hebei Gao, Hong Li

We propose Cut-Once-and-LEaRn (COLER), a simple approach for unsupervised instance segmentation and object detection. COLER first uses our developed CutOnce to generate coarse pseudo labels, then enables the detector to learn from these masks. CutOnce applies Normalized Cut only once and does not rely on any clustering methods, but it can generate multiple object masks in an image. We have designed several novel yet simple modules that not only allow CutOnce to fully leverage the object discovery capabilities of self-supervised models, but also free it from reliance on mask post-processing. During training, COLER achieves strong performance without requiring specially designed loss functions for pseudo labels, and its performance is further improved through self-training. COLER is a zero-shot unsupervised model that outperforms previous state-of-the-art methods on multiple benchmarks.We believe our method can help advance the field of unsupervised object localization.

Qingyu Zheng, Qi Shao, Guijun Han et al.

Mesoscale eddies dominate the spatiotemporal multiscale variability of the ocean, and their impact on the energy cascade of the global ocean cannot be ignored. Eddy-resolving ocean forecasting is providing more reliable protection for fisheries and navigational safety, but also presents significant scientific challenges and high computational costs for traditional numerical models. Artificial intelligence (AI)-based weather and ocean forecasting systems are becoming powerful tools that balance forecast performance with computational efficiency. However, the complex multiscale features in the ocean dynamical system make AI models still face many challenges in mesoscale eddy forecasting (especially regional modelling). Here, we develop LanTu, a regional eddy-resolving ocean forecasting system based on dynamics-enhanced deep learning. We incorporate cross-scale interactions into LanTu and construct multiscale physical constraint for optimising LanTu guided by knowledge of eddy dynamics in order to improve the forecasting skill of LanTu for mesoscale evolution. The results show that LanTu outperforms the existing advanced operational numerical ocean forecasting system (NOFS) and AI-based ocean forecasting system (AI-OFS) in temperature, salinity, sea level anomaly and current prediction, with a lead time of more than 10 days. Our study highlights that dynamics-enhanced deep learning (LanTu) can be a powerful paradigm for eddy-resolving ocean forecasting.

Yuqi Li, Han Zhang, Xiaofan Gui et al.

Battery degradation is governed by complex and randomized cyclic conditions, yet existing modeling and prediction frameworks usually rely on rigid, unchanging protocols that fail to capture real-world dynamics. The stochastic electrical signals make such prediction extremely challenging, while, on the other hand, they provide abundant additional information, such as voltage fluctuations, which may probe the degradation mechanisms. Here, we present chemistry-aware battery degradation prediction under dynamic conditions with machine learning, which integrates hidden Markov processes for realistic power simulations, an automated batch-testing system that generates a large electrochemical dataset under randomized conditions, an interfacial chemistry database derived from high-throughput X-ray photoelectron spectroscopy for mechanistic probing, and a machine learning model for prediction. By automatically constructing a polynomial-scale feature space from irregular electrochemical curves, our model accurately predicts both battery life and critical knee points. This feature space also predicts the composition of the solid electrolyte interphase, revealing six distinct failure mechanisms-demonstrating a viable approach to use electrical signals to infer interfacial chemistry. This work establishes a scalable and adaptive framework for integrating chemical engineering and data science to advance noninvasive diagnostics and optimize processes for more durable and sustainable energy storage technologies.

Yulong Wang, Chang Zuo, Yin Xuan et al.

Fine-tuning large language models (LLMs) has become essential for adapting pretrained models to specific downstream tasks. In this paper, we propose Linear Chain Transformation (LinChain), a novel approach that introduces a sequence of linear transformations during fine-tuning to enrich optimization dynamics. By incorporating multiple linear transformations into the parameter update process, LinChain expands the effective rank of updates and enhances the model's ability to learn complex task-specific representations. We demonstrate that this method significantly improves the performance of LLM fine-tuning over state-of-the-art methods by providing more flexible optimization paths during training, while maintaining the inference efficiency of the resulting model. Our experiments on various benchmark tasks show that LinChain leads to better generalization, fewer learnable parameters, and improved task adaptation, making it a compelling strategy for LLM fine-tuning.

Mingwei Tang, Meng Liu, Hong Li et al.

In recommendation systems, high-quality user embeddings can capture subtle preferences, enable precise similarity calculations, and adapt to changing preferences over time to maintain relevance. The effectiveness of recommendation systems depends on the quality of user embedding. We propose to asynchronously learn high fidelity user embeddings for billions of users each day from sequence based multimodal user activities through a Transformer-like large scale feature learning module. The async learned user representations embeddings (ALURE) are further converted to user similarity graphs through graph learning and then combined with user realtime activities to retrieval highly related ads candidates for the ads delivery system. Our method shows significant gains in both offline and online experiments.

Xiaowei Chen, Hong Li, Yufan Lu et al.

This paper explores the implications of using machine learning models in the pricing of catastrophe (CAT) bonds. By integrating advanced machine learning techniques, our approach uncovers nonlinear relationships and complex interactions between key risk factors and CAT bond spreads -- dynamics that are often overlooked by traditional linear regression models. Using primary market CAT bond transaction records between January 1999 and March 2021, our findings demonstrate that machine learning models not only enhance the accuracy of CAT bond pricing but also provide a deeper understanding of how various risk factors interact and influence bond prices in a nonlinear way. These findings suggest that investors and issuers can benefit from incorporating machine learning to better capture the intricate interplay between risk factors when pricing CAT bonds. The results also highlight the potential for machine learning models to refine our understanding of asset pricing in markets characterized by complex risk structures.