Ruiqi Wu

Yuming Chen, Xinbin Yuan, Jiabao Wang et al.

We aim at providing the object detection community with an efficient and performant object detector, termed YOLO-MS. The core design is based on a series of investigations on how multi-branch features of the basic block and convolutions with different kernel sizes affect the detection performance of objects at different scales. The outcome is a new strategy that can significantly enhance multi-scale feature representations of real-time object detectors. To verify the effectiveness of our work, we train our YOLO-MS on the MS COCO dataset from scratch without relying on any other large-scale datasets, like ImageNet or pre-trained weights. Without bells and whistles, our YOLO-MS outperforms the recent state-of-the-art real-time object detectors, including YOLO-v7, RTMDet, and YOLO-v8. Taking the XS version of YOLO-MS as an example, it can achieve an AP score of 42+% on MS COCO, which is about 2% higher than RTMDet with the same model size. Furthermore, our work can also serve as a plug-and-play module for other YOLO models. Typically, our method significantly advances the APs, APl, and AP of YOLOv8-N from 18%+, 52%+, and 37%+ to 20%+, 55%+, and 40%+, respectively, with even fewer parameters and MACs. Code and trained models are publicly available at https://github.com/FishAndWasabi/YOLO-MS. We also provide the Jittor version at https://github.com/NK-JittorCV/nk-yolo.

Chunle Guo, Ruiqi Wu, Xin Jin et al.

In this paper, we present a ranking-based underwater image quality assessment (UIQA) method, abbreviated as URanker. The URanker is built on the efficient conv-attentional image Transformer. In terms of underwater images, we specially devise (1) the histogram prior that embeds the color distribution of an underwater image as histogram token to attend global degradation and (2) the dynamic cross-scale correspondence to model local degradation. The final prediction depends on the class tokens from different scales, which comprehensively considers multi-scale dependencies. With the margin ranking loss, our URanker can accurately rank the order of underwater images of the same scene enhanced by different underwater image enhancement (UIE) algorithms according to their visual quality. To achieve that, we also contribute a dataset, URankerSet, containing sufficient results enhanced by different UIE algorithms and the corresponding perceptual rankings, to train our URanker. Apart from the good performance of URanker, we found that a simple U-shape UIE network can obtain promising performance when it is coupled with our pre-trained URanker as additional supervision. In addition, we also propose a normalization tail that can significantly improve the performance of UIE networks. Extensive experiments demonstrate the state-of-the-art performance of our method. The key designs of our method are discussed. We will release our dataset and code.

Ruiqi Wu, Liangyu Chen, Tong Yang et al.

With the impressive progress in diffusion-based text-to-image generation, extending such powerful generative ability to text-to-video raises enormous attention. Existing methods either require large-scale text-video pairs and a large number of training resources or learn motions that are precisely aligned with template videos. It is non-trivial to balance a trade-off between the degree of generation freedom and the resource costs for video generation. In our study, we present a few-shot-based tuning framework, LAMP, which enables text-to-image diffusion model Learn A specific Motion Pattern with 8~16 videos on a single GPU. Specifically, we design a first-frame-conditioned pipeline that uses an off-the-shelf text-to-image model for content generation so that our tuned video diffusion model mainly focuses on motion learning. The well-developed text-to-image techniques can provide visually pleasing and diverse content as generation conditions, which highly improves video quality and generation freedom. To capture the features of temporal dimension, we expand the pretrained 2D convolution layers of the T2I model to our novel temporal-spatial motion learning layers and modify the attention blocks to the temporal level. Additionally, we develop an effective inference trick, shared-noise sampling, which can improve the stability of videos with computational costs. Our method can also be flexibly applied to other tasks, e.g. real-world image animation and video editing. Extensive experiments demonstrate that LAMP can effectively learn the motion pattern on limited data and generate high-quality videos. The code and models are available at https://rq-wu.github.io/projects/LAMP.

Bingliang Jiao, Lingqiao Liu, Liying Gao et al.

In the current person Re-identification (ReID) methods, most domain generalization works focus on dealing with style differences between domains while largely ignoring unpredictable camera view change, which we identify as another major factor leading to a poor generalization of ReID methods. To tackle the viewpoint change, this work proposes to use a 3D dense pose estimation model and a texture mapping module to map the pedestrian images to canonical view images. Due to the imperfection of the texture mapping module, the canonical view images may lose the discriminative detail clues from the original images, and thus directly using them for ReID will inevitably result in poor performance. To handle this issue, we propose to fuse the original image and canonical view image via a transformer-based module. The key insight of this design is that the cross-attention mechanism in the transformer could be an ideal solution to align the discriminative texture clues from the original image with the canonical view image, which could compensate for the low-quality texture information of the canonical view image. Through extensive experiments, we show that our method can lead to superior performance over the existing approaches in various evaluation settings.

Hua Li, Junyan Liang, Ruiqi Wu et al.

Stereo superpixel segmentation aims at grouping the discretizing pixels into perceptual regions through left and right views more collaboratively and efficiently. Existing superpixel segmentation algorithms mostly utilize color and spatial features as input, which may impose strong constraints on spatial information while utilizing the disparity information in terms of stereo image pairs. To alleviate this issue, we propose a stereo superpixel segmentation method with a decoupling mechanism of spatial information in this work. To decouple stereo disparity information and spatial information, the spatial information is temporarily removed before fusing the features of stereo image pairs, and a decoupled stereo fusion module (DSFM) is proposed to handle the stereo features alignment as well as occlusion problems. Moreover, since the spatial information is vital to superpixel segmentation, we further design a dynamic spatiality embedding module (DSEM) to re-add spatial information, and the weights of spatial information will be adaptively adjusted through the dynamic fusion (DF) mechanism in DSEM for achieving a finer segmentation. Comprehensive experimental results demonstrate that our method can achieve the state-of-the-art performance on the KITTI2015 and Cityscapes datasets, and also verify the efficiency when applied in salient object detection on NJU2K dataset. The source code will be available publicly after paper is accepted.

Chenran Zhang, Ruiqi Wu, Tao Zhou et al.

Medical vision-language pretraining (VLP) models have recently been investigated for their generalization to diverse downstream tasks. However, current medical VLP methods typically force the model to learn simple and complex concepts simultaneously. This anti-cognitive process leads to suboptimal feature representations, especially under distribution shift. To address this limitation, we propose a Knowledge-driven Cognitive Orchestration for Medical VLP (MedKCO) that involves both the ordering of the pretraining data and the learning objective of vision-language contrast. Specifically, we design a two level curriculum by incorporating diagnostic sensitivity and intra-class sample representativeness for the ordering of the pretraining data. Moreover, considering the inter-class similarity of medical images, we introduce a self-paced asymmetric contrastive loss to dynamically adjust the participation of the pretraining objective. We evaluate the proposed pretraining method on three medical imaging scenarios in multiple vision-language downstream tasks, and compare it with several curriculum learning methods. Extensive experiments show that our method significantly surpasses all baselines. https://github.com/Mr-Talon/MedKCO.

Ziyue Zhu, Zhao Zhang, Zheng Lin et al.

To achieve visual consistency in composite images, recent image harmonization methods typically summarize the appearance pattern of global background and apply it to the global foreground without location discrepancy. However, for a real image, the appearances (illumination, color temperature, saturation, hue, texture, etc) of different regions can vary significantly. So previous methods, which transfer the appearance globally, are not optimal. Trying to solve this issue, we firstly match the contents between the foreground and background and then adaptively adjust every foreground location according to the appearance of its content-related background regions. Further, we design a residual reconstruction strategy, that uses the predicted residual to adjust the appearance, and the composite foreground to reserve the image details. Extensive experiments demonstrate the effectiveness of our method. The source code will be available publicly.

Sheng Luo, Wei Chen, Wanxin Tian et al.

Foundation models have indeed made a profound impact on various fields, emerging as pivotal components that significantly shape the capabilities of intelligent systems. In the context of intelligent vehicles, leveraging the power of foundation models has proven to be transformative, offering notable advancements in visual understanding. Equipped with multi-modal and multi-task learning capabilities, multi-modal multi-task visual understanding foundation models (MM-VUFMs) effectively process and fuse data from diverse modalities and simultaneously handle various driving-related tasks with powerful adaptability, contributing to a more holistic understanding of the surrounding scene. In this survey, we present a systematic analysis of MM-VUFMs specifically designed for road scenes. Our objective is not only to provide a comprehensive overview of common practices, referring to task-specific models, unified multi-modal models, unified multi-task models, and foundation model prompting techniques, but also to highlight their advanced capabilities in diverse learning paradigms. These paradigms include open-world understanding, efficient transfer for road scenes, continual learning, interactive and generative capability. Moreover, we provide insights into key challenges and future trends, such as closed-loop driving systems, interpretability, embodied driving agents, and world models. To facilitate researchers in staying abreast of the latest developments in MM-VUFMs for road scenes, we have established a continuously updated repository at https://github.com/rolsheng/MM-VUFM4DS

Ruiqi Wu, Chenran Zhang, Jianle Zhang et al.

Current fundus image analysis models are predominantly built for specific tasks relying on individual datasets. The learning process is usually based on data-driven paradigm without prior knowledge, resulting in poor transferability and generalizability. To address this issue, we propose MM-Retinal, a multi-modal dataset that encompasses high-quality image-text pairs collected from professional fundus diagram books. Moreover, enabled by MM-Retinal, we present a novel Knowledge-enhanced foundational pretraining model which incorporates Fundus Image-Text expertise, called KeepFIT. It is designed with image similarity-guided text revision and mixed training strategy to infuse expert knowledge. Our proposed fundus foundation model achieves state-of-the-art performance across six unseen downstream tasks and holds excellent generalization ability in zero-shot and few-shot scenarios. MM-Retinal and KeepFIT are available at https://github.com/lxirich/MM-Retinal.

Ziwei Li, Liujun Zhu, Yuchen Liu et al.

Process-based simulation models encode decades of scientific understanding across the Earth sciences, yet the communities most exposed to climate risk and resource scarcity are the least able to use them. Here, we introduce knowledge infrastructure (KI), an agent-actionable scaffold that externalizes expertise into validated modelling operators, staged domain protocols, and diagnostic recovery mechanisms. Across a 3,000-trial coupled-hydrology benchmark, agents equipped with KI produced physically plausible, verifiable end-to-end simulations in up to 84% of trials, while agents without KI plateaued below 40%. KI generalizes across disciplines. We packaged its construction into a Knowledge Dissection Toolkit (KDT) that autonomously produced KI enabling end-to-end agent execution of 117 additional process-based models across 14 Earth-science domains. Across all 119 KIs, modelling decisions and failure remedies converged despite different underlying physics, showing that operational expertise is structured and extractable rather than ad hoc. Demonstrations show KI-equipped agents lowering both the access barrier between non-specialist users and process-based simulation, and the integration barrier between modelling communities. Through this scaffold, process-based science can then evolve as a living scientific commons, answerable to whoever needs to know and extendable by whoever can contribute.

Ruiqi Wu, Xuanhua He, Meng Cheng et al.

We propose Infinite-World, a robust interactive world model capable of maintaining coherent visual memory over 1000+ frames in complex real-world environments. While existing world models can be efficiently optimized on synthetic data with perfect ground-truth, they lack an effective training paradigm for real-world videos due to noisy pose estimations and the scarcity of viewpoint revisits. To bridge this gap, we first introduce a Hierarchical Pose-free Memory Compressor (HPMC) that recursively distills historical latents into a fixed-budget representation. By jointly optimizing the compressor with the generative backbone, HPMC enables the model to autonomously anchor generations in the distant past with bounded computational cost, eliminating the need for explicit geometric priors. Second, we propose an Uncertainty-aware Action Labeling module that discretizes continuous motion into a tri-state logic. This strategy maximizes the utilization of raw video data while shielding the deterministic action space from being corrupted by noisy trajectories, ensuring robust action-response learning. Furthermore, guided by insights from a pilot toy study, we employ a Revisit-Dense Finetuning Strategy using a compact, 30-minute dataset to efficiently activate the model's long-range loop-closure capabilities. Extensive experiments, including objective metrics and user studies, demonstrate that Infinite-World achieves superior performance in visual quality, action controllability, and spatial consistency.

Xuanhua He, Tianyu Yang, Ke Cao et al.

Current video avatar generation methods excel at identity preservation and motion alignment but lack genuine agency, they cannot autonomously pursue long-term goals through adaptive environmental interaction. We address this by introducing L-IVA (Long-horizon Interactive Visual Avatar), a task and benchmark for evaluating goal-directed planning in stochastic generative environments, and ORCA (Online Reasoning and Cognitive Architecture), the first framework enabling active intelligence in video avatars. ORCA embodies Internal World Model (IWM) capabilities through two key innovations: (1) a closed-loop OTAR cycle (Observe-Think-Act-Reflect) that maintains robust state tracking under generative uncertainty by continuously verifying predicted outcomes against actual generations, and (2) a hierarchical dual-system architecture where System 2 performs strategic reasoning with state prediction while System 1 translates abstract plans into precise, model-specific action captions. By formulating avatar control as a POMDP and implementing continuous belief updating with outcome verification, ORCA enables autonomous multi-step task completion in open-domain scenarios. Extensive experiments demonstrate that ORCA significantly outperforms open-loop and non-reflective baselines in task success rate and behavioral coherence, validating our IWM-inspired design for advancing video avatar intelligence from passive animation to active, goal-oriented behavior.

Shining Wang, Yunlong Wang, Ruiqi Wu et al.

When discussing the Aerial-Ground Person Re-identification (AGPReID) task, we face the main challenge of the significant appearance variations caused by different viewpoints, making identity matching difficult. To address this issue, previous methods attempt to reduce the differences between viewpoints by critical attributes and decoupling the viewpoints. While these methods can mitigate viewpoint differences to some extent, they still face two main issues: (1) difficulty in handling viewpoint diversity and (2) neglect of the contribution of local features. To effectively address these challenges, we design and implement the Self-Calibrating and Adaptive Prompt (SeCap) method for the AGPReID task. The core of this framework relies on the Prompt Re-calibration Module (PRM), which adaptively re-calibrates prompts based on the input. Combined with the Local Feature Refinement Module (LFRM), SeCap can extract view-invariant features from local features for AGPReID. Meanwhile, given the current scarcity of datasets in the AGPReID field, we further contribute two real-world Large-scale Aerial-Ground Person Re-Identification datasets, LAGPeR and G2APS-ReID. The former is collected and annotated by us independently, covering $4,231$ unique identities and containing $63,841$ high-quality images; the latter is reconstructed from the person search dataset G2APS. Through extensive experiments on AGPReID datasets, we demonstrate that SeCap is a feasible and effective solution for the AGPReID task. The datasets and source code available on https://github.com/wangshining681/SeCap-AGPReID.

Ruiqi Wu, Na Su, Chenran Zhang et al.

Vision-language pretraining (VLP) has been investigated to generalize across diverse downstream tasks for fundus image analysis. Although recent methods showcase promising achievements, they significantly rely on large-scale private image-text data but pay less attention to the pretraining manner, which limits their further advancements. In this work, we introduce MM-Retinal V2, a high-quality image-text paired dataset comprising CFP, FFA, and OCT image modalities. Then, we propose a novel fundus vision-language pretraining model, namely KeepFIT V2, which is pretrained by integrating knowledge from the elite data spark into categorical public datasets. Specifically, a preliminary textual pretraining is adopted to equip the text encoder with primarily ophthalmic textual knowledge. Moreover, a hybrid image-text knowledge injection module is designed for knowledge transfer, which is essentially based on a combination of global semantic concepts from contrastive learning and local appearance details from generative learning. Extensive experiments across zero-shot, few-shot, and linear probing settings highlight the generalization and transferability of KeepFIT V2, delivering performance competitive to state-of-the-art fundus VLP models trained on large-scale private image-text datasets. Our dataset and model are publicly available via https://github.com/lxirich/MM-Retinal.

Xinjie Wang, Liu Liu, Yu Cao et al.

Constructing a physically realistic and accurately scaled simulated 3D world is crucial for the training and evaluation of embodied intelligence tasks. The diversity, realism, low cost accessibility and affordability of 3D data assets are critical for achieving generalization and scalability in embodied AI. However, most current embodied intelligence tasks still rely heavily on traditional 3D computer graphics assets manually created and annotated, which suffer from high production costs and limited realism. These limitations significantly hinder the scalability of data driven approaches. We present EmbodiedGen, a foundational platform for interactive 3D world generation. It enables the scalable generation of high-quality, controllable and photorealistic 3D assets with accurate physical properties and real-world scale in the Unified Robotics Description Format (URDF) at low cost. These assets can be directly imported into various physics simulation engines for fine-grained physical control, supporting downstream tasks in training and evaluation. EmbodiedGen is an easy-to-use, full-featured toolkit composed of six key modules: Image-to-3D, Text-to-3D, Texture Generation, Articulated Object Generation, Scene Generation and Layout Generation. EmbodiedGen generates diverse and interactive 3D worlds composed of generative 3D assets, leveraging generative AI to address the challenges of generalization and evaluation to the needs of embodied intelligence related research. Code is available at https://horizonrobotics.github.io/robot_lab/embodied_gen/index.html.

Yuang Yao, Ruiqi Wu, Yi Zhou et al.

Traditional fundus image analysis models focus on single-modal tasks, ignoring fundus modality complementarity, which limits their versatility. Recently, retinal foundation models have emerged, but most still remain modality-specific. Integrating multiple fundus imaging modalities into a single foundation model is valuable. However, in dynamic environments, data from different modalities often arrive incrementally, necessitating continual pre-training. To address this, we propose RetCoP, the first continual vision-language pre-training framework in the fundus domain, which incrementally integrates image and text features from different imaging modalities into a single unified foundation model. To mitigate catastrophic forgetting in continual pre-training, we introduce a rehearsal strategy utilizing representative image-text pairs and an off-diagonal information distillation approach. The former allows the model to revisit knowledge from previous stages, while the latter explicitly preserves the alignment between image and text representations. Experiments show that RetCoP outperforms all the compared methods, achieving the best generalization and lowest forgetting rate. The code can be found at https://github.com/Yuang-Yao/RetCoP.

Ruiqi Wu, Yuang Yao, Tengfei Ma et al.

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities with reinforcement learning paradigm. Although several multimodal reasoning models have been explored in the medical domain, most of them focus exclusively on basic reasoning, which refers to shallow inference based on visual feature matching. However, real-world clinical diagnosis extends beyond basic reasoning, demanding reasoning processes that integrate heterogeneous clinical information (such as chief complaints and medical history) with multimodal medical imaging data. To bridge this gap, we introduce MM-Retinal-Reason, the first ophthalmic multimodal dataset with the full spectrum of perception and reasoning. It encompasses both basic reasoning tasks and complex reasoning tasks, aiming to enhance visual-centric fundamental reasoning capabilities and emulate realistic clinical thinking patterns. Building upon MM-Retinal-Reason, we propose OphthaReason, the first ophthalmology-specific multimodal reasoning model with step-by-step reasoning traces. To enable flexible adaptation to both basic and complex reasoning tasks, we specifically design a novel method called Uncertainty-Aware Dynamic Thinking (UADT), which estimates sample-level uncertainty via entropy and dynamically modulates the model's exploration depth using a shaped advantage mechanism. Comprehensive experiments demonstrate that our model achieves state-of-the-art performance on both basic and complex reasoning tasks, outperforming general-purpose MLLMs, medical MLLMs, RL-based medical MLLMs, and ophthalmic MLLMs by at least 24.92\%, 15.00\%, 21.20\%, and 17.66\%. Project Page: \href{https://github.com/lxirich/OphthaReason}{link}.

Hongqiu Ni, Jiabao Zhang, Guopeng Li et al.

Large Language Models (LLMs) are increasingly being deployed as intelligent agents. Their multi-stage workflows, which alternate between local computation and calls to external network services like Web APIs, introduce a mismatch in their execution pattern and the scheduling granularity of existing inference systems such as vLLM. Existing systems typically focus on per-segment optimization which prevents them from minimizing the end-to-end latency of the complete agentic workflow, i.e., the global Job Completion Time (JCT) over the entire request lifecycle. To address this limitation, we propose Astraea, a service engine designed to shift the optimization from local segments to the global request lifecycle. Astraea employs a state-aware, hierarchical scheduling algorithm that integrates a request's historical state with future predictions. It dynamically classifies requests by their I/O and compute intensive nature and uses an enhanced HRRN policy to balance efficiency and fairness. Astraea also implements an adaptive KV cache manager that intelligently handles the agent state during I/O waits based on the system memory pressure. Extensive experiments show that Astraea reduces average JCT by up to 25.5\% compared to baseline methods. Moreover, our approach demonstrates strong robustness and stability under high load across various model scales.

Jie Ou, Jinyu Guo, Shiyao Guo et al.

Many-Shot In-Context Learning (ICL) has emerged as a promising paradigm, leveraging extensive examples to unlock the reasoning potential of Large Language Models (LLMs). However, existing methods typically rely on a predetermined, fixed number of shots. This static approach often fails to adapt to the varying difficulty of different queries, leading to either insufficient context or interference from noise. Furthermore, the prohibitive computational and memory costs of long contexts severely limit Many-Shot's feasibility. To address the above limitations, we propose AdapShot, which dynamically optimizes shot counts and leverages KV cache reuse for efficient inference. Specifically, we design a probe-based evaluation mechanism that utilizes output entropy to determine the optimal number of shots. To bypass the redundant prefilling computation during both the probing and inference phases, we incorporate a semantics-aware KV cache reuse strategy. Within this reuse strategy, to address positional encoding incompatibilities, we introduce a decoupling and re-encoding method that enables the flexible reordering of cached key-value pairs. Extensive experiments demonstrate that AdapShot achieves an average performance gain of around 10% and a 4.64x speedup compared to state-of-the-art DBSA.

Jiayi Fu, Siyu Liu, Zikun Liu et al.

We propose a novel Iterative Predictor-Critic Code Decoding framework for real-world image dehazing, abbreviated as IPC-Dehaze, which leverages the high-quality codebook prior encapsulated in a pre-trained VQGAN. Apart from previous codebook-based methods that rely on one-shot decoding, our method utilizes high-quality codes obtained in the previous iteration to guide the prediction of the Code-Predictor in the subsequent iteration, improving code prediction accuracy and ensuring stable dehazing performance. Our idea stems from the observations that 1) the degradation of hazy images varies with haze density and scene depth, and 2) clear regions play crucial cues in restoring dense haze regions. However, it is non-trivial to progressively refine the obtained codes in subsequent iterations, owing to the difficulty in determining which codes should be retained or replaced at each iteration. Another key insight of our study is to propose Code-Critic to capture interrelations among codes. The Code-Critic is used to evaluate code correlations and then resample a set of codes with the highest mask scores, i.e., a higher score indicates that the code is more likely to be rejected, which helps retain more accurate codes and predict difficult ones. Extensive experiments demonstrate the superiority of our method over state-of-the-art methods in real-world dehazing.

Ruiqi Wu, Bingliang Jiao, Wenxuan Wang et al.

The Visible-Infrared Person Re-identification (VI ReID) aims to match visible and infrared images of the same pedestrians across non-overlapped camera views. These two input modalities contain both invariant information, such as shape, and modality-specific details, such as color. An ideal model should utilize valuable information from both modalities during training for enhanced representational capability. However, the gap caused by modality-specific information poses substantial challenges for the VI ReID model to handle distinct modality inputs simultaneously. To address this, we introduce the Modality-aware and Instance-aware Visual Prompts (MIP) network in our work, designed to effectively utilize both invariant and specific information for identification. Specifically, our MIP model is built on the transformer architecture. In this model, we have designed a series of modality-specific prompts, which could enable our model to adapt to and make use of the specific information inherent in different modality inputs, thereby reducing the interference caused by the modality gap and achieving better identification. Besides, we also employ each pedestrian feature to construct a group of instance-specific prompts. These customized prompts are responsible for guiding our model to adapt to each pedestrian instance dynamically, thereby capturing identity-level discriminative clues for identification. Through extensive experiments on SYSU-MM01 and RegDB datasets, the effectiveness of both our designed modules is evaluated. Additionally, our proposed MIP performs better than most state-of-the-art methods.