Xu Tang

Haochen Wang, Cilin Yan, Shuai Wang et al.

Video Instance Segmentation (VIS) aims at segmenting and categorizing objects in videos from a closed set of training categories, lacking the generalization ability to handle novel categories in real-world videos. To address this limitation, we make the following three contributions. First, we introduce the novel task of Open-Vocabulary Video Instance Segmentation, which aims to simultaneously segment, track, and classify objects in videos from open-set categories, including novel categories unseen during training. Second, to benchmark Open-Vocabulary VIS, we collect a Large-Vocabulary Video Instance Segmentation dataset (LV-VIS), that contains well-annotated objects from 1,196 diverse categories, significantly surpassing the category size of existing datasets by more than one order of magnitude. Third, we propose an efficient Memory-Induced Transformer architecture, OV2Seg, to first achieve Open-Vocabulary VIS in an end-to-end manner with near real-time inference speed. Extensive experiments on LV-VIS and four existing VIS datasets demonstrate the strong zero-shot generalization ability of OV2Seg on novel categories. The dataset and code are released here https://github.com/haochenheheda/LVVIS.

Liang Pan, Jingbo Wang, Buzhen Huang et al.

We present a physics-based character control framework for synthesizing human-scene interactions. Recent advances adopt physics simulation to mitigate artifacts produced by data-driven kinematic approaches. However, existing physics-based methods mainly focus on single-object environments, resulting in limited applicability in realistic 3D scenes with multi-objects. To address such challenges, we propose a framework that enables physically simulated characters to perform long-term interaction tasks in diverse, cluttered, and unseen 3D scenes. The key idea is to decouple human-scene interactions into two fundamental processes, Interacting and Navigating, which motivates us to construct two reusable Controllers, namely InterCon and NavCon. Specifically, InterCon uses two complementary policies to enable characters to enter or leave the interacting state with a particular object (e.g., sitting on a chair or getting up). To realize navigation in cluttered environments, we introduce NavCon, where a trajectory following policy enables characters to track pre-planned collision-free paths. Benefiting from the divide and conquer strategy, we can train all policies in simple environments and directly apply them in complex multi-object scenes through coordination from a rule-based scheduler. Video and code are available at https://github.com/liangpan99/InterScene.

Cilin Yan, Haochen Wang, Jie Liu et al.

Click-based interactive segmentation aims to generate target masks via human clicking, which facilitates efficient pixel-level annotation and image editing. In such a task, target ambiguity remains a problem hindering the accuracy and efficiency of segmentation. That is, in scenes with rich context, one click may correspond to multiple potential targets, while most previous interactive segmentors only generate a single mask and fail to deal with target ambiguity. In this paper, we propose a novel interactive segmentation network named PiClick, to yield all potentially reasonable masks and suggest the most plausible one for the user. Specifically, PiClick utilizes a Transformer-based architecture to generate all potential target masks by mutually interactive mask queries. Moreover, a Target Reasoning module(TRM) is designed in PiClick to automatically suggest the user-desired mask from all candidates, relieving target ambiguity and extra-human efforts. Extensive experiments on 9 interactive segmentation datasets demonstrate PiClick performs favorably against previous state-of-the-arts considering the segmentation results. Moreover, we show that PiClick effectively reduces human efforts in annotating and picking the desired masks. To ease the usage and inspire future research, we release the source code of PiClick together with a plug-and-play annotation tool at https://github.com/cilinyan/PiClick.

Xiangrong Zhang, Tianyang Zhang, Guanchun Wang et al.

Remote sensing object detection (RSOD), one of the most fundamental and challenging tasks in the remote sensing field, has received longstanding attention. In recent years, deep learning techniques have demonstrated robust feature representation capabilities and led to a big leap in the development of RSOD techniques. In this era of rapid technical evolution, this review aims to present a comprehensive review of the recent achievements in deep learning based RSOD methods. More than 300 papers are covered in this review. We identify five main challenges in RSOD, including multi-scale object detection, rotated object detection, weak object detection, tiny object detection, and object detection with limited supervision, and systematically review the corresponding methods developed in a hierarchical division manner. We also review the widely used benchmark datasets and evaluation metrics within the field of RSOD, as well as the application scenarios for RSOD. Future research directions are provided for further promoting the research in RSOD.

Yuting Yang, Licheng Jiao, Xu Liu et al.

Dynamic attention mechanism and global modeling ability make Transformer show strong feature learning ability. In recent years, Transformer has become comparable to CNNs methods in computer vision. This review mainly investigates the current research progress of Transformer in image and video applications, which makes a comprehensive overview of Transformer in visual learning understanding. First, the attention mechanism is reviewed, which plays an essential part in Transformer. And then, the visual Transformer model and the principle of each module are introduced. Thirdly, the existing Transformer-based models are investigated, and their performance is compared in visual learning understanding applications. Three image tasks and two video tasks of computer vision are investigated. The former mainly includes image classification, object detection, and image segmentation. The latter contains object tracking and video classification. It is significant for comparing different models' performance in various tasks on several public benchmark data sets. Finally, ten general problems are summarized, and the developing prospects of the visual Transformer are given in this review.

Keyan Chen, Xiaolong Jiang, Yao Hu et al.

In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training stage, resembling an open-vocabulary scenario. To achieve this goal, we make the following contributions: (i) we start with a naive two-stage approach for open-vocabulary object detection and attribute classification, termed CLIP-Attr. The candidate objects are first proposed with an offline RPN and later classified for semantic category and attributes; (ii) we combine all available datasets and train with a federated strategy to finetune the CLIP model, aligning the visual representation with attributes, additionally, we investigate the efficacy of leveraging freely available online image-caption pairs under weakly supervised learning; (iii) in pursuit of efficiency, we train a Faster-RCNN type model end-to-end with knowledge distillation, that performs class-agnostic object proposals and classification on semantic categories and attributes with classifiers generated from a text encoder; Finally, (iv) we conduct extensive experiments on VAW, MS-COCO, LSA, and OVAD datasets, and show that recognition of semantic category and attributes is complementary for visual scene understanding, i.e., jointly training object detection and attributes prediction largely outperform existing approaches that treat the two tasks independently, demonstrating strong generalization ability to novel attributes and categories.

Zhengguang Zhou, Jing Li, Huaxia Li et al.

Tuning-free personalized image generation methods have achieved significant success in maintaining facial consistency, i.e., identities, even with multiple characters. However, the lack of holistic consistency in scenes with multiple characters hampers these methods' ability to create a cohesive narrative. In this paper, we introduce StoryMaker, a personalization solution that preserves not only facial consistency but also clothing, hairstyles, and body consistency, thus facilitating the creation of a story through a series of images. StoryMaker incorporates conditions based on face identities and cropped character images, which include clothing, hairstyles, and bodies. Specifically, we integrate the facial identity information with the cropped character images using the Positional-aware Perceiver Resampler (PPR) to obtain distinct character features. To prevent intermingling of multiple characters and the background, we separately constrain the cross-attention impact regions of different characters and the background using MSE loss with segmentation masks. Additionally, we train the generation network conditioned on poses to promote decoupling from poses. A LoRA is also employed to enhance fidelity and quality. Experiments underscore the effectiveness of our approach. StoryMaker supports numerous applications and is compatible with other societal plug-ins. Our source codes and model weights are available at https://github.com/RedAIGC/StoryMaker.

Kaituo Xu, Yan Jia, Kai Huang et al.

We present FireRedASR2S, a state-of-the-art industrial-grade all-in-one automatic speech recognition (ASR) system. It integrates four modules in a unified pipeline: ASR, Voice Activity Detection (VAD), Spoken Language Identification (LID), and Punctuation Prediction (Punc). All modules achieve SOTA performance on the evaluated benchmarks: FireRedASR2: An ASR module with two variants, FireRedASR2-LLM (8B+ parameters) and FireRedASR2-AED (1B+ parameters), supporting speech and singing transcription for Mandarin, Chinese dialects and accents, English, and code-switching. Compared to FireRedASR, FireRedASR2 delivers improved recognition accuracy and broader dialect and accent coverage. FireRedASR2-LLM achieves 2.89% average CER on 4 public Mandarin benchmarks and 11.55% on 19 public Chinese dialects and accents benchmarks, outperforming competitive baselines including Doubao-ASR, Qwen3-ASR, and Fun-ASR. FireRedVAD: An ultra-lightweight module (0.6M parameters) based on the Deep Feedforward Sequential Memory Network (DFSMN), supporting streaming VAD, non-streaming VAD, and multi-label VAD (mVAD). On the FLEURS-VAD-102 benchmark, it achieves 97.57% frame-level F1 and 99.60% AUC-ROC, outperforming Silero-VAD, TEN-VAD, FunASR-VAD, and WebRTC-VAD. FireRedLID: An Encoder-Decoder LID module supporting 100+ languages and 20+ Chinese dialects and accents. On FLEURS (82 languages), it achieves 97.18% utterance-level accuracy, outperforming Whisper and SpeechBrain. FireRedPunc: A BERT-style punctuation prediction module for Chinese and English. On multi-domain benchmarks, it achieves 78.90% average F1, outperforming FunASR-Punc (62.77%). To advance research in speech processing, we release model weights and code at https://github.com/FireRedTeam/FireRedASR2S.

Jinpeng Yu, Binbin Huang, Yuxuan Zhang et al.

Point cloud completion aims to recover accurate global geometry and preserve fine-grained local details from partial point clouds. Conventional methods typically predict unseen points directly from 3D point cloud coordinates or use self-projected multi-view depth maps to ease this task. However, these gray-scale depth maps cannot reach multi-view consistency, consequently restricting the performance. In this paper, we introduce a GeoFormer that simultaneously enhances the global geometric structure of the points and improves the local details. Specifically, we design a CCM Feature Enhanced Point Generator to integrate image features from multi-view consistent canonical coordinate maps (CCMs) and align them with pure point features, thereby enhancing the global geometry feature. Additionally, we employ the Multi-scale Geometry-aware Upsampler module to progressively enhance local details. This is achieved through cross attention between the multi-scale features extracted from the partial input and the features derived from previously estimated points. Extensive experiments on the PCN, ShapeNet-55/34, and KITTI benchmarks demonstrate that our GeoFormer outperforms recent methods, achieving the state-of-the-art performance. Our code is available at \href{https://github.com/Jinpeng-Yu/GeoFormer}{https://github.com/Jinpeng-Yu/GeoFormer}.

Guanchun Wang, Xiangrong Zhang, Zelin Peng et al.

Weakly supervised object detection (WSOD) is a challenging task, in which image-level labels (e.g., categories of the instances in the whole image) are used to train an object detector. Many existing methods follow the standard multiple instance learning (MIL) paradigm and have achieved promising performance. However, the lack of deterministic information leads to part domination and missing instances. To address these issues, this paper focuses on identifying and fully exploiting the deterministic information in WSOD. We discover that negative instances (i.e. absolutely wrong instances), ignored in most of the previous studies, normally contain valuable deterministic information. Based on this observation, we here propose a negative deterministic information (NDI) based method for improving WSOD, namely NDI-WSOD. Specifically, our method consists of two stages: NDI collecting and exploiting. In the collecting stage, we design several processes to identify and distill the NDI from negative instances online. In the exploiting stage, we utilize the extracted NDI to construct a novel negative contrastive learning mechanism and a negative guided instance selection strategy for dealing with the issues of part domination and missing instances, respectively. Experimental results on several public benchmarks including VOC 2007, VOC 2012 and MS COCO show that our method achieves satisfactory performance.

Jie Guo, Qimeng Wang, Yan Gao et al.

CLIP (Contrastive Language-Image Pretraining) is well-developed for open-vocabulary zero-shot image-level recognition, while its applications in pixel-level tasks are less investigated, where most efforts directly adopt CLIP features without deliberative adaptations. In this work, we first demonstrate the necessity of image-pixel CLIP feature adaption, then provide Multi-View Prompt learning (MVP-SEG) as an effective solution to achieve image-pixel adaptation and to solve open-vocabulary semantic segmentation. Concretely, MVP-SEG deliberately learns multiple prompts trained by our Orthogonal Constraint Loss (OCLoss), by which each prompt is supervised to exploit CLIP feature on different object parts, and collaborative segmentation masks generated by all prompts promote better segmentation. Moreover, MVP-SEG introduces Global Prompt Refining (GPR) to further eliminate class-wise segmentation noise. Experiments show that the multi-view prompts learned from seen categories have strong generalization to unseen categories, and MVP-SEG+ which combines the knowledge transfer stage significantly outperforms previous methods on several benchmarks. Moreover, qualitative results justify that MVP-SEG does lead to better focus on different local parts.

Wenxuan Huang, Yu Zeng, Qiuchen Wang et al.

Multimodal large language models (MLLMs) have achieved remarkable success across a broad range of vision tasks. However, constrained by the capacity of their internal world knowledge, prior work has proposed augmenting MLLMs by ``reasoning-then-tool-call'' for visual and textual search engines to obtain substantial gains on tasks requiring extensive factual information. However, these approaches typically define multimodal search in a naive setting, assuming that a single full-level or entity-level image query and few text query suffices to retrieve the key evidence needed to answer the question, which is unrealistic in real-world scenarios with substantial visual noise. Moreover, they are often limited in the reasoning depth and search breadth, making it difficult to solve complex questions that require aggregating evidence from diverse visual and textual sources. Building on this, we propose Vision-DeepResearch, which proposes one new multimodal deep-research paradigm, i.e., performs multi-turn, multi-entity and multi-scale visual and textual search to robustly hit real-world search engines under heavy noise. Our Vision-DeepResearch supports dozens of reasoning steps and hundreds of engine interactions, while internalizing deep-research capabilities into the MLLM via cold-start supervision and RL training, resulting in a strong end-to-end multimodal deep-research MLLM. It substantially outperforming existing multimodal deep-research MLLMs, and workflows built on strong closed-source foundation model such as GPT-5, Gemini-2.5-pro and Claude-4-Sonnet. The code will be released in https://github.com/Osilly/Vision-DeepResearch.

Yuqun Yang, Xu Tang, Xiangrong Zhang et al.

General change detection (GCD) and semantic change detection (SCD) are common methods for identifying changes and distinguishing object categories involved in those changes, respectively. However, the binary changes provided by GCD is often not practical enough, while annotating semantic labels for training SCD models is very expensive. Therefore, there is a novel solution that intuitively dividing changes into three trends (``appear'', ``disappear'' and ``transform'') instead of semantic categories, named it trend change detection (TCD) in this paper. It offers more detailed change information than GCD, while requiring less manual annotation cost than SCD. However, there are limited public data sets with specific trend labels to support TCD application. To address this issue, we propose a softmatch distance which is used to construct a weakly-supervised TCD branch in a simple GCD model, using GCD labels instead of TCD label for training. Furthermore, a strategic approach is presented to successfully explore and extract background information, which is crucial for the weakly-supervised TCD task. The experiment results on four public data sets are highly encouraging, which demonstrates the effectiveness of our proposed model.

Hao Wu, Haoran Lou, Xinyue Li et al.

We present FireRed-OCR, a systematic framework to specialize general VLMs into high-performance OCR models. Large Vision-Language Models (VLMs) have demonstrated impressive general capabilities but frequently suffer from ``structural hallucination'' when processing complex documents, limiting their utility in industrial OCR applications. In this paper, we introduce FireRed-OCR, a novel framework designed to transform general-purpose VLMs (based on Qwen3-VL) into pixel-precise structural document parsing experts. To address the scarcity of high-quality structured data, we construct a ``Geometry + Semantics'' Data Factory. Unlike traditional random sampling, our pipeline leverages geometric feature clustering and multi-dimensional tagging to synthesize and curate a highly balanced dataset, effectively handling long-tail layouts and rare document types. Furthermore, we propose a Three-Stage Progressive Training strategy that guides the model from pixel-level perception to logical structure generation. This curriculum includes: (1) Multi-task Pre-alignment to ground the model's understanding of document structure; (2) Specialized SFT for standardizing full-image Markdown output; and (3) Format-Constrained Group Relative Policy Optimization (GRPO), which utilizes reinforcement learning to enforce strict syntactic validity and structural integrity (e.g., table closure, formula syntax). Extensive evaluations on OmniDocBench v1.5 demonstrate that FireRed-OCR achieves state-of-the-art performance with an overall score of 92.94\%, significantly outperforming strong baselines such as DeepSeek-OCR 2 and OCRVerse across text, formula, table, and reading order metrics. We open-source our code and model weights to facilitate the ``General VLM to Specialized Structural Expert'' paradigm.

Qixun Wang, Xu Bai, Haofan Wang et al.

There has been significant progress in personalized image synthesis with methods such as Textual Inversion, DreamBooth, and LoRA. Yet, their real-world applicability is hindered by high storage demands, lengthy fine-tuning processes, and the need for multiple reference images. Conversely, existing ID embedding-based methods, while requiring only a single forward inference, face challenges: they either necessitate extensive fine-tuning across numerous model parameters, lack compatibility with community pre-trained models, or fail to maintain high face fidelity. Addressing these limitations, we introduce InstantID, a powerful diffusion model-based solution. Our plug-and-play module adeptly handles image personalization in various styles using just a single facial image, while ensuring high fidelity. To achieve this, we design a novel IdentityNet by imposing strong semantic and weak spatial conditions, integrating facial and landmark images with textual prompts to steer the image generation. InstantID demonstrates exceptional performance and efficiency, proving highly beneficial in real-world applications where identity preservation is paramount. Moreover, our work seamlessly integrates with popular pre-trained text-to-image diffusion models like SD1.5 and SDXL, serving as an adaptable plugin. Our codes and pre-trained checkpoints will be available at https://github.com/InstantID/InstantID.

Zhichao Sun, Yidong Ma, Gang Liu et al.

Large Vision-Language Models (LVLMs) achieve impressive performance across multiple tasks. A significant challenge, however, is their prohibitive inference cost when processing high-resolution visual inputs. While visual token pruning has emerged as a promising solution, existing methods that primarily focus on semantic relevance often discard tokens that are crucial for spatial reasoning. We address this gap through a novel insight into \emph{how LVLMs process spatial reasoning}. Specifically, we reveal that LVLMs implicitly establish visual coordinate systems through Rotary Position Embeddings (RoPE), where specific token positions serve as \textbf{implicit visual coordinates} (IVC tokens) that are essential for spatial reasoning. Based on this insight, we propose \textbf{IVC-Prune}, a training-free, prompt-aware pruning strategy that retains both IVC tokens and semantically relevant foreground tokens. IVC tokens are identified by theoretically analyzing the mathematical properties of RoPE, targeting positions at which its rotation matrices approximate identity matrix or the $90^\circ$ rotation matrix. Foreground tokens are identified through a robust two-stage process: semantic seed discovery followed by contextual refinement via value-vector similarity. Extensive evaluations across four representative LVLMs and twenty diverse benchmarks show that IVC-Prune reduces visual tokens by approximately 50\% while maintaining $\geq$ 99\% of the original performance and even achieving improvements on several benchmarks. Source codes are available at https://github.com/FireRedTeam/IVC-Prune.

Super Intelligence Team, Changhao Qiao, Chao Hui et al.

We present FireRed-Image-Edit, a diffusion transformer for instruction-based image editing that achieves state-of-the-art performance through systematic optimization of data curation, training methodology, and evaluation design. We construct a 1.6B-sample training corpus, comprising 900M text-to-image and 700M image editing pairs from diverse sources. After rigorous cleaning, stratification, auto-labeling, and two-stage filtering, we retain over 100M high-quality samples balanced between generation and editing, ensuring strong semantic coverage and instruction alignment. Our multi-stage training pipeline progressively builds editing capability via pre-training, supervised fine-tuning, and reinforcement learning. To improve data efficiency, we introduce a Multi-Condition Aware Bucket Sampler for variable-resolution batching and Stochastic Instruction Alignment with dynamic prompt re-indexing. To stabilize optimization and enhance controllability, we propose Asymmetric Gradient Optimization for DPO, DiffusionNFT with layout-aware OCR rewards for text editing, and a differentiable Consistency Loss for identity preservation. We further establish REDEdit-Bench, a comprehensive benchmark spanning 15 editing categories, including newly introduced beautification and low-level enhancement tasks. Extensive experiments on REDEdit-Bench and public benchmarks (ImgEdit and GEdit) demonstrate competitive or superior performance against both open-source and proprietary systems. We release code, models, and the benchmark suite to support future research.

Shanglin Li, Bohan Zeng, Yutang Feng et al.

Recent advances in vision-language models like Stable Diffusion have shown remarkable power in creative image synthesis and editing.However, most existing text-to-image editing methods encounter two obstacles: First, the text prompt needs to be carefully crafted to achieve good results, which is not intuitive or user-friendly. Second, they are insensitive to local edits and can irreversibly affect non-edited regions, leaving obvious editing traces. To tackle these problems, we propose a Zero-shot instructiON-guided local image Editing approach, termed ZONE. We first convert the editing intent from the user-provided instruction (e.g., "make his tie blue") into specific image editing regions through InstructPix2Pix. We then propose a Region-IoU scheme for precise image layer extraction from an off-the-shelf segment model. We further develop an edge smoother based on FFT for seamless blending between the layer and the image.Our method allows for arbitrary manipulation of a specific region with a single instruction while preserving the rest. Extensive experiments demonstrate that our ZONE achieves remarkable local editing results and user-friendliness, outperforming state-of-the-art methods. Code is available at https://github.com/lsl001006/ZONE.

Cunzheng Wang, Ziyuan Guo, Yuxuan Duan et al.

Consistency distillation methods have demonstrated significant success in accelerating generative tasks of diffusion models. However, since previous consistency distillation methods use simple and straightforward strategies in selecting target timesteps, they usually struggle with blurs and detail losses in generated images. To address these limitations, we introduce Target-Driven Distillation (TDD), which (1) adopts a delicate selection strategy of target timesteps, increasing the training efficiency; (2) utilizes decoupled guidances during training, making TDD open to post-tuning on guidance scale during inference periods; (3) can be optionally equipped with non-equidistant sampling and x0 clipping, enabling a more flexible and accurate way for image sampling. Experiments verify that TDD achieves state-of-the-art performance in few-step generation, offering a better choice among consistency distillation models.

Weiquan Lin, Yaoqing Hu, Liangchen Dai et al.

Monocular 3D hand reconstruction is intrinsically a geometric problem, yet RGB appearance features alone often struggle to resolve severe ambiguities caused by self-occlusions and hand-object interactions. While introducing depth can explicitly provide spatial cues, raw sensor-captured depth maps are extensively noisy and incomplete, limiting their usefulness for fine-grained hand reconstruction. To bridge this gap, we propose GeoHand, a novel framework that unlocks high-quality geometric priors from a frozen foundational monocular geometry estimator (MoGe2). Recognizing that these priors are oriented toward general scenes, we introduce a map-level GeoAdapter to recalibrate the spatial features, specifically adapting them for detailed hand reconstruction. Furthermore, to systematically integrate these adapted priors without overwhelming intrinsic RGB appearance cues, we employ a gated cross-modal token fusion strategy. Finally, to secure precise local articulation, we design a Keypoint-Queried Iterative Refiner (KQIR) that uses projected joint locations to query geometry-aware image features for spatial correction. By combining global geometric disambiguation with local refinement in a unified pipeline, GeoHand achieves state-of-the-art performance on FreiHAND, DexYCB, and HO3Dv3, especially under severe occlusions and hand-object interactions.

Runqi Wang, Yang Chen, Sijie Xu et al.

Face swapping transfers the identity of a source face to a target face while retaining the attributes like expression, pose, hair, and background of the target face. Advanced face swapping methods have achieved attractive results. However, these methods often inadvertently transfer identity information from the target face, compromising expression-related details and accurate identity. We propose a novel method DynamicFace that leverages the power of diffusion models and plug-and-play adaptive attention layers for image and video face swapping. First, we introduce four fine-grained facial conditions using 3D facial priors. All conditions are designed to be disentangled from each other for precise and unique control. Then, we adopt Face Former and ReferenceNet for high-level and detailed identity injection. Through experiments on the FF++ dataset, we demonstrate that our method achieves state-of-the-art results in face swapping, showcasing superior image quality, identity preservation, and expression accuracy. Our framework seamlessly adapts to both image and video domains. Our code and results will be available on the project page: https://dynamic-face.github.io/

Xiangyuan Wang, Honghao Cai, Yunhao Bai et al.

High-quality training triplets (source-target image pairs with precise editing instructions) are a critical bottleneck for scaling instruction-guided image editing models. Vision-language models (VLMs) are widely used for automated instruction synthesis, but we identify three systematic failure modes in image-pair settings: orientation inconsistency (e.g., left/right confusion), viewpoint ambiguity, and insufficient fine-grained attribute description. Human evaluation shows that over 47% of instructions from strong baseline VLMs contain critical errors unusable for downstream training. We propose EditCaption, a scalable two-stage post-training pipeline for VLM-based instruction synthesis. Stage 1 builds a 100K supervised fine-tuning (SFT) dataset by combining GLM automatic annotation, EditScore-based filtering, and human refinement for spatial, directional, and attribute-level accuracy. Stage 2 collects 10K human preference pairs targeting the three failure modes and applies direct preference optimization (DPO) for alignment beyond SFT alone. On Eval-400, ByteMorph-Bench, and HQ-Edit, fine-tuned Qwen3-VL models outperform open-source baselines; the 235B model reaches 4.712 on Eval-400 (vs. Gemini-3-Pro 4.706, GPT-4.1 4.220, Kimi-K2.5 4.111) and 4.588 on ByteMorph-Bench (vs. Gemini-3-Pro 4.522, GPT-4.1 3.412). Human evaluation shows critical errors falling from 47.75% to 23% and correctness rising from 41.75% to 66%. The work offers a practical path to scalable, human-aligned instruction synthesis for image editing data.

Haohua Chen, Tianze Zhou, Wei Zhu et al.

Virtual Try-on (VTON) has become a core capability for online retail, where realistic try-on results provide reliable fit guidance, reduce returns, and benefit both consumers and merchants. Diffusion-based VTON methods achieve photorealistic synthesis, yet often rely on intricate architectures such as auxiliary reference networks and suffer from slow sampling, making the trade-off between fidelity and efficiency a persistent challenge. We approach VTON as a structured image editing problem that demands strong conditional generation under three key requirements: subject preservation, faithful texture transfer, and seamless harmonization. Under this perspective, our training framework is generic and transfers to broader image editing tasks. Moreover, the paired data produced by VTON constitutes a rich supervisory resource for training general-purpose editors. We present PROMO, a promptable virtual try-on framework built upon a Flow Matching DiT backbone with latent multi-modal conditional concatenation. By leveraging conditioning efficiency and self-reference mechanisms, our approach substantially reduces inference overhead. On standard benchmarks, PROMO surpasses both prior VTON methods and general image editing models in visual fidelity while delivering a competitive balance between quality and speed. These results demonstrate that flow-matching transformers, coupled with latent multi-modal conditioning and self-reference acceleration, offer an effective and training-efficient solution for high-quality virtual try-on.

Sijie Xu, Runqi Wang, Wei Zhu et al.

Diffusion-based stylization methods typically denoise from a specific partial noise state for image-to-image and video-to-video tasks. This multi-step diffusion process is computationally expensive and hinders real-world application. A promising solution to speed up the process is to obtain few-step consistency models through trajectory distillation. However, current consistency models only force the initial-step alignment between the probability flow ODE (PF-ODE) trajectories of the student and the imperfect teacher models. This training strategy can not ensure the consistency of whole trajectories. To address this issue, we propose single trajectory distillation (STD) starting from a specific partial noise state. We introduce a trajectory bank to store the teacher model's trajectory states, mitigating the time cost during training. Besides, we use an asymmetric adversarial loss to enhance the style and quality of the generated images. Extensive experiments on image and video stylization demonstrate that our method surpasses existing acceleration models in terms of style similarity and aesthetic evaluations. Our code and results will be available on the project page: https://single-trajectory-distillation.github.io.

Kangjie Zhang, Wenxuan Huang, Xin Zhou et al.

Contrastive Language-Image Pre-training (CLIP) has achieved widely applications in various computer vision tasks, e.g., text-to-image generation, Image-Text retrieval and Image captioning. However, CLIP suffers from high memory and computation cost, which prohibits its usage to the resource-limited application scenarios. Existing CLIP compression methods typically reduce the size of pre-trained CLIP weights by selecting their subset as weight inheritance for further retraining via mask optimization or important weight measurement. However, these select-based weight inheritance often compromises the feature presentation ability, especially on the extreme compression. In this paper, we propose a novel mapping-based CLIP compression framework, CLIP-Map. It leverages learnable matrices to map and combine pretrained weights by Full-Mapping with Kronecker Factorization, aiming to preserve as much information from the original weights as possible. To mitigate the optimization challenges introduced by the learnable mapping, we propose Diagonal Inheritance Initialization to reduce the distribution shifting problem for efficient and effective mapping learning. Extensive experimental results demonstrate that the proposed CLIP-Map outperforms select-based frameworks across various compression ratios, with particularly significant gains observed under high compression settings.

Yuxuan Zhang, Yiren Song, Jiaming Liu et al.

Recent advancements in subject-driven image generation have led to zero-shot generation, yet precise selection and focus on crucial subject representations remain challenging. Addressing this, we introduce the SSR-Encoder, a novel architecture designed for selectively capturing any subject from single or multiple reference images. It responds to various query modalities including text and masks, without necessitating test-time fine-tuning. The SSR-Encoder combines a Token-to-Patch Aligner that aligns query inputs with image patches and a Detail-Preserving Subject Encoder for extracting and preserving fine features of the subjects, thereby generating subject embeddings. These embeddings, used in conjunction with original text embeddings, condition the generation process. Characterized by its model generalizability and efficiency, the SSR-Encoder adapts to a range of custom models and control modules. Enhanced by the Embedding Consistency Regularization Loss for improved training, our extensive experiments demonstrate its effectiveness in versatile and high-quality image generation, indicating its broad applicability. Project page: https://ssr-encoder.github.io

Qiang Xiang, Shuang Sun, Binglei Li et al.

Diffusion models have demonstrated remarkable capabilities in generating high-quality images. Recent advancements in Layout-to-Image (L2I) generation have leveraged positional conditions and textual descriptions to facilitate precise and controllable image synthesis. Despite overall progress, current L2I methods still exhibit suboptimal performance. Therefore, we propose InstanceAssemble, a novel architecture that incorporates layout conditions via instance-assembling attention, enabling position control with bounding boxes (bbox) and multimodal content control including texts and additional visual content. Our method achieves flexible adaption to existing DiT-based T2I models through light-weighted LoRA modules. Additionally, we propose a Layout-to-Image benchmark, Denselayout, a comprehensive benchmark for layout-to-image generation, containing 5k images with 90k instances in total. We further introduce Layout Grounding Score (LGS), an interpretable evaluation metric to more precisely assess the accuracy of L2I generation. Experiments demonstrate that our InstanceAssemble method achieves state-of-the-art performance under complex layout conditions, while exhibiting strong compatibility with diverse style LoRA modules. The code and pretrained models are publicly available at https://github.com/FireRedTeam/InstanceAssemble.

Bo Wang, Mengyuan Xu, Yue Yan et al.

Precise lesion resection depends on accurately identifying fine-grained anatomical structures. While many coarse-grained segmentation (CGS) methods have been successful in large-scale segmentation (e.g., organs), they fall short in clinical scenarios requiring fine-grained segmentation (FGS), which remains challenging due to frequent individual variations in small-scale anatomical structures. Although recent Mamba-based models have advanced medical image segmentation, they often rely on fixed manually-defined scanning orders, which limit their adaptability to individual variations in FGS. To address this, we propose ASM-UNet, a novel Mamba-based architecture for FGS. It introduces adaptive scan scores to dynamically guide the scanning order, generated by combining group-level commonalities and individual-level variations. Experiments on two public datasets (ACDC and Synapse) and a newly proposed challenging biliary tract FGS dataset, namely BTMS, demonstrate that ASM-UNet achieves superior performance in both CGS and FGS tasks. Our code and dataset are available at https://github.com/YqunYang/ASM-UNet.

Zhichao Sun, Huazhang Hu, Yidong Ma et al.

With the exponential growth of data, traditional object detection methods are increasingly struggling to handle vast vocabulary object detection tasks effectively. We analyze two key limitations of classification-based detectors: positive gradient dilution, where rare positive categories receive insufficient learning signals, and hard negative gradient dilution, where discriminative gradients are overwhelmed by numerous easy negatives. To address these challenges, we propose CQ-DINO, a category query-based object detection framework that reformulates classification as a contrastive task between object queries and learnable category queries. Our method introduces image-guided query selection, which reduces the negative space by adaptively retrieving top-K relevant categories per image via cross-attention, thereby rebalancing gradient distributions and facilitating implicit hard example mining. Furthermore, CQ-DINO flexibly integrates explicit hierarchical category relationships in structured datasets (e.g., V3Det) or learns implicit category correlations via self-attention in generic datasets (e.g., COCO). Experiments demonstrate that CQ-DINO achieves superior performance on the challenging V3Det benchmark (surpassing previous methods by 2.1% AP) while maintaining competitiveness in COCO. Our work provides a scalable solution for real-world detection systems requiring wide category coverage. The code is publicly at https://github.com/FireRedTeam/CQ-DINO.

Xiaolong Liu, Qimeng Wang, Yao Hu et al.

Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this task with complicated pipelines. They often need to train multiple networks and involve hand-designed operations, such as non-maximal suppression and anchor generation, which limit the flexibility and prevent end-to-end learning. In this paper, we propose an end-to-end Transformer-based method for TAD, termed TadTR. Given a small set of learnable embeddings called action queries, TadTR adaptively extracts temporal context information from the video for each query and directly predicts action instances with the context. To adapt Transformer to TAD, we propose three improvements to enhance its locality awareness. The core is a temporal deformable attention module that selectively attends to a sparse set of key snippets in a video. A segment refinement mechanism and an actionness regression head are designed to refine the boundaries and confidence of the predicted instances, respectively. With such a simple pipeline, TadTR requires lower computation cost than previous detectors, while preserving remarkable performance. As a self-contained detector, it achieves state-of-the-art performance on THUMOS14 (56.7% mAP) and HACS Segments (32.09% mAP). Combined with an extra action classifier, it obtains 36.75% mAP on ActivityNet-1.3. Code is available at https://github.com/xlliu7/TadTR.

Xu Liu, Licheng Jiao, Xu Tang et al.

The approaches for analyzing the polarimetric scattering matrix of polarimetric synthetic aperture radar (PolSAR) data have always been the focus of PolSAR image classification. Generally, the polarization coherent matrix and the covariance matrix obtained by the polarimetric scattering matrix only show a limited number of polarimetric information. In order to solve this problem, we propose a sparse scattering coding way to deal with polarimetric scattering matrix and obtain a close complete feature. This encoding mode can also maintain polarimetric information of scattering matrix completely. At the same time, in view of this encoding way, we design a corresponding classification algorithm based on convolution network to combine this feature. Based on sparse scattering coding and convolution neural network, the polarimetric convolutional network is proposed to classify PolSAR images by making full use of polarimetric information. We perform the experiments on the PolSAR images acquired by AIRSAR and RADARSAT-2 to verify the proposed method. The experimental results demonstrate that the proposed method get better results and has huge potential for PolSAR data classification. Source code for sparse scattering coding is available at https://github.com/liuxuvip/Polarimetric-Scattering-Coding.

Xu Tang, Daniel K. Du, Zeqiang He et al.

Face detection has been well studied for many years and one of remaining challenges is to detect small, blurred and partially occluded faces in uncontrolled environment. This paper proposes a novel context-assisted single shot face detector, named \emph{PyramidBox} to handle the hard face detection problem. Observing the importance of the context, we improve the utilization of contextual information in the following three aspects. First, we design a novel context anchor to supervise high-level contextual feature learning by a semi-supervised method, which we call it PyramidAnchors. Second, we propose the Low-level Feature Pyramid Network to combine adequate high-level context semantic feature and Low-level facial feature together, which also allows the PyramidBox to predict faces of all scales in a single shot. Third, we introduce a context-sensitive structure to increase the capacity of prediction network to improve the final accuracy of output. In addition, we use the method of Data-anchor-sampling to augment the training samples across different scales, which increases the diversity of training data for smaller faces. By exploiting the value of context, PyramidBox achieves superior performance among the state-of-the-art over the two common face detection benchmarks, FDDB and WIDER FACE. Our code is available in PaddlePaddle: \href{https://github.com/PaddlePaddle/models/tree/develop/fluid/face_detection}{\url{https://github.com/PaddlePaddle/models/tree/develop/fluid/face_detection}}.

Fei Zhao, Chonggang Lu, Haofu Qian et al.

As a key medium for human interaction and information exchange, social networking services (SNS) pose unique challenges for large language models (LLMs): heterogeneous workloads, fast-shifting norms and slang, and multilingual, culturally diverse corpora that induce sharp distribution shift. Supervised fine-tuning (SFT) can specialize models but often triggers a ``seesaw'' between in-distribution gains and out-of-distribution robustness, especially for smaller models. To address these challenges, we introduce RedOne 2.0, an SNS-oriented LLM trained with a progressive, RL-prioritized post-training paradigm designed for rapid and stable adaptation. The pipeline consist in three stages: (1) Exploratory Learning on curated SNS corpora to establish initial alignment and identify systematic weaknesses; (2) Targeted Fine-Tuning that selectively applies SFT to the diagnosed gaps while mixing a small fraction of general data to mitigate forgetting; and (3) Refinement Learning that re-applies RL with SNS-centric signals to consolidate improvements and harmonize trade-offs across tasks. Across various tasks spanning three categories, our 4B scale model delivers an average improvements about 2.41 over the 7B sub-optimal baseline. Additionally, RedOne 2.0 achieves average performance lift about 8.74 from the base model with less than half the data required by SFT-centric method RedOne, evidencing superior data efficiency and stability at compact scales. Overall, RedOne 2.0 establishes a competitive, cost-effective baseline for domain-specific LLMs in SNS scenario, advancing capability without sacrificing robustness.

Rui Wang, Hailong Guo, Jiaming Liu et al.

In this paper, we introduce StableGarment, a unified framework to tackle garment-centric(GC) generation tasks, including GC text-to-image, controllable GC text-to-image, stylized GC text-to-image, and robust virtual try-on. The main challenge lies in retaining the intricate textures of the garment while maintaining the flexibility of pre-trained Stable Diffusion. Our solution involves the development of a garment encoder, a trainable copy of the denoising UNet equipped with additive self-attention (ASA) layers. These ASA layers are specifically devised to transfer detailed garment textures, also facilitating the integration of stylized base models for the creation of stylized images. Furthermore, the incorporation of a dedicated try-on ControlNet enables StableGarment to execute virtual try-on tasks with precision. We also build a novel data engine that produces high-quality synthesized data to preserve the model's ability to follow prompts. Extensive experiments demonstrate that our approach delivers state-of-the-art (SOTA) results among existing virtual try-on methods and exhibits high flexibility with broad potential applications in various garment-centric image generation.

Suyan Dai, Gan Sun, Fazeng Li et al.

Spectral clustering has emerged as one of the most effective clustering algorithms due to its superior performance. However, most existing models are designed for centralized settings, rendering them inapplicable in modern decentralized environments. Moreover, current federated learning approaches often suffer from poor generalization performance due to reliance on unreliable pseudo-labels, and fail to capture the latent correlations amongst heterogeneous clients. To tackle these limitations, this paper proposes a novel framework named Federated Multi-Task Clustering (i.e.,FMTC), which intends to learn personalized clustering models for heterogeneous clients while collaboratively leveraging their shared underlying structure in a privacy-preserving manner. More specifically, the FMTC framework is composed of two main components: client-side personalized clustering module, which learns a parameterized mapping model to support robust out-of-sample inference, bypassing the need for unreliable pseudo-labels; and server-side tensorial correlation module, which explicitly captures the shared knowledge across all clients. This is achieved by organizing all client models into a unified tensor and applying a low-rank regularization to discover their common subspace. To solve this joint optimization problem, we derive an efficient, privacy-preserving distributed algorithm based on the Alternating Direction Method of Multipliers, which decomposes the global problem into parallel local updates on clients and an aggregation step on the server. To the end, several extensive experiments on multiple real-world datasets demonstrate that our proposed FMTC framework significantly outperforms various baseline and state-of-the-art federated clustering algorithms.

Guanchun Wang, Chenxiao Wu, Xiangrong Zhang et al.

Open-vocabulary semantic segmentation (OVSS) in remote sensing images is a promising task that employs textual descriptions for identifying undefined land cover categories. Despite notable advances, existing methods typically employ a static inference paradigm, overlooking the distinct distribution of each scene, resulting in semantic ambiguity in diverse land covers and incomplete foreground activation. Motivated by this, we propose Seeking Consensus, termed SeeCo, a plug-and-play framework to boost the performance of training-free OVSS models in remote sensing images, which recalibrates arbitrary OVSS models on-the-fly by seeking dual consensus: geometric consensus learning (GCL) through multi-view consistent observations and semantic consensus learning (SCL) via textual description adaptive calibration, which assists collaborative recalibration of visual and textual semantics. The two consensus are injected via an online consensus injector (OCI), effectively alleviating the under-activation and semantic bias. SeeCo requires no specific training process, yet recalibrates semantic-geometric alignment for each unique scene during inference. Extensive experiments on eight remote sensing OVSS benchmarks show consistent gains, proving its effectiveness and universality.

Yansheng Li, Yuning Wu, Gong Cheng et al.

Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples. This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios. To address this limitation, we introduce the Million-scale finE-grained geospatial scEne classification dataseT (MEET), which contains over 1.03 million zoom-free remote sensing scene samples, manually annotated into 80 fine-grained categories. In MEET, each scene sample follows a scene-inscene layout, where the central scene serves as the reference, and auxiliary scenes provide crucial spatial context for finegrained classification. Moreover, to tackle the emerging challenge of scene-in-scene classification, we present the Context-Aware Transformer (CAT), a model specifically designed for this task, which adaptively fuses spatial context to accurately classify the scene samples. CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes. Based on MEET, we establish a comprehensive benchmark for fine-grained geospatial scene classification, evaluating CAT against 11 competitive baselines. The results demonstrate that CAT significantly outperforms these baselines, achieving a 1.88% higher balanced accuracy (BA) with the Swin-Large backbone, and a notable 7.87% improvement with the Swin-Huge backbone. Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping. The source code and dataset will be publicly available at https://jerrywyn.github.io/project/MEET.html.

Honghao Cai, Xiangyuan Wang, Yunhao Bai et al.

Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-attention architectures offer no explicit channel telling the network where to apply the edit. We introduce REDEdit, a co-trained, instruction- and region-aware adapter framework that retrofits a frozen DiT into a precise local editor without modifying its backbone weights. A lightweight Block Adapter at every transformer block injects a structured condition stream that factorizes what to edit (instruction semantics) from where to edit (spatial mask); a learned SpatialGate routes the adapter signal selectively into the edit region while keeping the rest of the image near-identical to the source; and a Region-Aware Loss focuses the training objective on the changing pixels. Because these components make the backbone's internal representation mask-aware end-to-end, a thin MaskPredictor head trained jointly with the editor can ground the edit region directly from the instruction and source image eliminating any user-mask requirement at deployment. We evaluate on two complementary benchmarks: MagicBrush (paired ground-truth targets) to measure pixel-level preservation and edit accuracy, and Emu-Edit Test (no ground-truth images, 9 diverse edit categories) to stress-test instruction following and generalization across edit types. On both, REDEdit achieves state-of-the-art results, simultaneously outperforming mask-free and oracle-mask baselines. A seven-variant ablation cleanly isolates the contribution of each component.

Zhenyu Lou, Qiongjie Cui, Haofan Wang et al.

Predicting future human pose is a fundamental application for machine intelligence, which drives robots to plan their behavior and paths ahead of time to seamlessly accomplish human-robot collaboration in real-world 3D scenarios. Despite encouraging results, existing approaches rarely consider the effects of the external scene on the motion sequence, leading to pronounced artifacts and physical implausibilities in the predictions. To address this limitation, this work introduces a novel multi-modal sense-informed motion prediction approach, which conditions high-fidelity generation on two modal information: external 3D scene, and internal human gaze, and is able to recognize their salience for future human activity. Furthermore, the gaze information is regarded as the human intention, and combined with both motion and scene features, we construct a ternary intention-aware attention to supervise the generation to match where the human wants to reach. Meanwhile, we introduce semantic coherence-aware attention to explicitly distinguish the salient point clouds and the underlying ones, to ensure a reasonable interaction of the generated sequence with the 3D scene. On two real-world benchmarks, the proposed method achieves state-of-the-art performance both in 3D human pose and trajectory prediction.

Kepu Zhang, Haoyue Yang, Xu Tang et al.

In legal practice, judges apply the trichotomous dogmatics of criminal law, sequentially assessing the elements of the offense, unlawfulness, and culpability to determine whether an individual's conduct constitutes a crime. Although current legal large language models (LLMs) show promising accuracy in judgment prediction, they lack trichotomous reasoning capabilities due to the absence of an appropriate benchmark dataset, preventing them from predicting innocent outcomes. As a result, every input is automatically assigned a charge, limiting their practical utility in legal contexts. To bridge this gap, we introduce LJPIV, the first benchmark dataset for Legal Judgment Prediction with Innocent Verdicts. Adhering to the trichotomous dogmatics, we extend three widely-used legal datasets through LLM-based augmentation and manual verification. Our experiments with state-of-the-art legal LLMs and novel strategies that integrate trichotomous reasoning into zero-shot prompting and fine-tuning reveal: (1) current legal LLMs have significant room for improvement, with even the best models achieving an F1 score of less than 0.3 on LJPIV; and (2) our strategies notably enhance both in-domain and cross-domain judgment prediction accuracy, especially for cases resulting in an innocent verdict.

Kepu Zhang, Guofu Xie, Weijie Yu et al.

Legal mathematical reasoning is essential for applying large language models (LLMs) in high-stakes legal contexts, where outputs must be both mathematically accurate and procedurally compliant. However, existing legal LLMs lack structured numerical reasoning, and open-domain models, though capable of calculations, often overlook mandatory legal steps. To address this, we present LexNum, the first Chinese legal mathematical reasoning benchmark, covering three representative scenarios where each instance reflects legally grounded procedural flows. We further propose LexPam, a two-stage reinforcement learning framework for efficient legal reasoning training. Leveraging curriculum learning, we use a stronger teacher model to partition data into basic and challenging subsets. A lightweight 1.5B student model is then fine-tuned with Group Relative Policy Optimization, which avoids costly value networks and enables stable training from sparse, end-of-sequence rewards. The first stage improves accuracy and format; the second introduces a novel reward to guide procedural alignment via task-specific legal elements. Experiments show that existing models perform poorly on LexNum, while LexPam enhances both mathematical accuracy and legal coherence, and generalizes effectively across tasks and domains.

Shentong Mo, Haofan Wang, Huaxia Li et al.

Video-language pre-training is a typical and challenging problem that aims at learning visual and textual representations from large-scale data in a self-supervised way. Existing pre-training approaches either captured the correspondence of image-text pairs or utilized temporal ordering of frames. However, they do not explicitly explore the natural synchronization between audio and the other two modalities. In this work, we propose an enhanced framework for Video-Language pre-training with Synchronized Audio, termed as VLSA, that can learn tri-modal representations in a unified self-supervised transformer. Specifically, our VLSA jointly aggregates embeddings of local patches and global tokens for video, text, and audio. Furthermore, we utilize local-patch masked modeling to learn modality-aware features, and leverage global audio matching to capture audio-guided features for video and text. We conduct extensive experiments on retrieval across text, video, and audio. Our simple model pre-trained on only 0.9M data achieves improving results against state-of-the-art baselines. In addition, qualitative visualizations vividly showcase the superiority of our VLSA in learning discriminative visual-textual representations.

Guanchun Wang, Xiangrong Zhang, Yifei Zhang et al.

Unsupervised anomaly detection in hyperspectral images (HSI), aiming to detect unknown targets from backgrounds, is challenging for earth surface monitoring. However, current studies are hindered by steep computational costs due to the high-dimensional property of HSI and dense sampling-based training paradigm, constraining their rapid deployment. Our key observation is that, during training, not all samples within the same homogeneous area are indispensable, whereas ingenious sampling can provide a powerful substitute for reducing costs. Motivated by this, we propose an Asymmetrical Consensus State Space Model (ACMamba) to significantly reduce computational costs without compromising accuracy. Specifically, we design an asymmetrical anomaly detection paradigm that utilizes region-level instances as an efficient alternative to dense pixel-level samples. In this paradigm, a low-cost Mamba-based module is introduced to discover global contextual attributes of regions that are essential for HSI reconstruction. Additionally, we develop a consensus learning strategy from the optimization perspective to simultaneously facilitate background reconstruction and anomaly compression, further alleviating the negative impact of anomaly reconstruction. Theoretical analysis and extensive experiments across eight benchmarks verify the superiority of ACMamba, demonstrating a faster speed and stronger performance over the state-of-the-art.

Qianying Liu, Xiao Liang, Zhiqiang Zhang et al.

We present ReMatch, a framework that leverages the generative strength of MLLMs for multimodal retrieval. Previous approaches treated an MLLM as a simple encoder, ignoring its generative nature, and under-utilising its compositional reasoning and world knowledge. We instead train the embedding MLLM end-to-end with a chat-style generative matching stage. The matching stage uses the same MLLM to autoregressively decide relevance from multi-view inputs, including both raw data and its own projected embeddings for each query and document. It provides instance-wise discrimination supervision that complements a standard contrastive loss, offering stronger gradients on hard negatives and preserving the compositional strengths of the original MLLM. To obtain semantically richer multimodal embeddings, we use multiple learnable tokens to augment each input, generating fine-grained contextual, mutually orthogonal embeddings with low inference cost. Leveraging our established high-performance baseline,we assemble the ideas mentioned above into a powerful training recipe and achieve a new state-of-the-art on the Massive Multimodal Embedding Benchmark (MMEB). Our experiments show particularly strong zero-shot generalization results on five datasets, highlighting the robustness and transferability of ReMatch.

Manjie Xu, Cheng Chen, Xin Jia et al.

User interests on content platforms are inherently diverse, manifesting through complex behavioral patterns across heterogeneous scenarios such as search, feed browsing, and content discovery. Traditional recommendation systems typically prioritize business metric optimization within isolated specific scenarios, neglecting cross-scenario behavioral signals and struggling to integrate advanced techniques like LLMs at billion-scale deployments, which finally limits their ability to capture holistic user interests across platform touchpoints. We propose RED-Rec, an LLM-enhanced hierarchical Recommender Engine for Diversified scenarios, tailored for industry-level content recommendation systems. RED-Rec unifies user interest representations across multiple behavioral contexts by aggregating and synthesizing actions from varied scenarios, resulting in comprehensive item and user modeling. At its core, a two-tower LLM-powered framework enables nuanced, multifaceted representations with deployment efficiency, and a scenario-aware dense mixing and querying policy effectively fuses diverse behavioral signals to capture cross-scenario user intent patterns and express fine-grained, context-specific intents during serving. We validate RED-Rec through online A/B testing on hundreds of millions of users in RedNote through online A/B testing, showing substantial performance gains in both content recommendation and advertisement targeting tasks. We further introduce a million-scale sequential recommendation dataset, RED-MMU, for comprehensive offline training and evaluation. Our work advances unified user modeling, unlocking deeper personalization and fostering more meaningful user engagement in large-scale UGC platforms.

Xu Tang, Junan Jia, Yijing Wang et al.

In the task of 3D Aerial-view Scene Semantic Segmentation (3D-AVS-SS), traditional methods struggle to address semantic ambiguity caused by scale variations and structural occlusions in aerial images. This limits their segmentation accuracy and consistency. To tackle these challenges, we propose a novel 3D-AVS-SS approach named SAD-Splat. Our method introduces a Gaussian point drop module, which integrates semantic confidence estimation with a learnable sparsity mechanism based on the Hard Concrete distribution. This module effectively eliminates redundant and semantically ambiguous Gaussian points, enhancing both segmentation performance and representation compactness. Furthermore, SAD-Splat incorporates a high-confidence pseudo-label generation pipeline. It leverages 2D foundation models to enhance supervision when ground-truth labels are limited, thereby further improving segmentation accuracy. To advance research in this domain, we introduce a challenging benchmark dataset: 3D Aerial Semantic (3D-AS), which encompasses diverse real-world aerial scenes with sparse annotations. Experimental results demonstrate that SAD-Splat achieves an excellent balance between segmentation accuracy and representation compactness. It offers an efficient and scalable solution for 3D aerial scene understanding.

Tianyao He, Runqi Wang, Yang Chen et al.

Text-driven portrait editing holds significant potential for various applications but also presents considerable challenges. An ideal text-driven portrait editing approach should achieve precise localization and appropriate content modification, yet existing methods struggle to balance reconstruction fidelity and editing flexibility. To address this issue, we propose Flux-Sculptor, a flux-based framework designed for precise text-driven portrait editing. Our framework introduces a Prompt-Aligned Spatial Locator (PASL) to accurately identify relevant editing regions and a Structure-to-Detail Edit Control (S2D-EC) strategy to spatially guide the denoising process through sequential mask-guided fusion of latent representations and attention values. Extensive experiments demonstrate that Flux-Sculptor surpasses existing methods in rich-attribute editing and facial information preservation, making it a strong candidate for practical portrait editing applications. Project page is available at https://flux-sculptor.github.io/.

Xujun Wei, Feng Zhang, Renhe Zhang et al.

In the past few years, Artificial Intelligence (AI)-based weather forecasting methods have widely demonstrated strong competitiveness among the weather forecasting systems. However, these methods are insufficient for high-spatial-resolution short-term nowcasting within 6 hours, which is crucial for warning short-duration, mesoscale and small-scale weather events. Geostationary satellite remote sensing provides detailed, high spatio-temporal and all-day observations, which can address the above limitations of existing methods. Therefore, this paper proposed an advanced data-driven thermal infrared cloud images forecasting model, "DaYu." Unlike existing data-driven weather forecasting models, DaYu is specifically designed for geostationary satellite observations, with a temporal resolution of 0.5 hours and a spatial resolution of ${0.05}^\circ$ $\times$ ${0.05}^\circ$. DaYu is based on a large-scale transformer architecture, which enables it to capture fine-grained cloud structures and learn fast-changing spatio-temporal evolution features effectively. Moreover, its attention mechanism design achieves a balance in computational complexity, making it practical for applications. DaYu not only achieves accurate forecasts up to 3 hours with a correlation coefficient higher than 0.9, 6 hours higher than 0.8, and 12 hours higher than 0.7, but also detects short-duration, mesoscale, and small-scale weather events with enhanced detail, effectively addressing the shortcomings of existing methods in providing detailed short-term nowcasting within 6 hours. Furthermore, DaYu has significant potential in short-term climate disaster prevention and mitigation.

Cilin Yan, Haochen Wang, Xiaolong Jiang et al.

Contrastive Vision-Language Pre-training(CLIP) demonstrates impressive zero-shot capability. The key to improve the adaptation of CLIP to downstream task with few exemplars lies in how to effectively model and transfer the useful knowledge embedded in CLIP. Previous work mines the knowledge typically based on the limited visual samples and close-set semantics (i.e., within target category set of downstream task). However, the aligned CLIP image/text encoders contain abundant relationships between visual features and almost infinite open semantics, which may benefit the few-shot learning but remains unexplored. In this paper, we propose to mine open semantics as anchors to perform a relation transition from image-anchor relationship to image-target relationship to make predictions. Specifically, we adopt a transformer module which takes the visual feature as "Query", the text features of the anchors as "Key" and the similarity matrix between the text features of anchor and target classes as "Value". In this way, the output of such a transformer module represents the relationship between the image and target categories, i.e., the classification predictions. To avoid manually selecting the open semantics, we make the [CLASS] token of input text embedding learnable. We conduct extensive experiments on eleven representative classification datasets. The results show that our method performs favorably against previous state-of-the-arts considering few-shot classification settings.

Bohan Zeng, Shanglin Li, Xuhui Liu et al.

Brain signal visualization has emerged as an active research area, serving as a critical interface between the human visual system and computer vision models. Although diffusion models have shown promise in analyzing functional magnetic resonance imaging (fMRI) data, including reconstructing high-quality images consistent with original visual stimuli, their accuracy in extracting semantic and silhouette information from brain signals remains limited. In this regard, we propose a novel approach, referred to as Controllable Mind Visual Diffusion Model (CMVDM). CMVDM extracts semantic and silhouette information from fMRI data using attribute alignment and assistant networks. Additionally, a residual block is incorporated to capture information beyond semantic and silhouette features. We then leverage a control model to fully exploit the extracted information for image synthesis, resulting in generated images that closely resemble the visual stimuli in terms of semantics and silhouette. Through extensive experimentation, we demonstrate that CMVDM outperforms existing state-of-the-art methods both qualitatively and quantitatively.