Xiaopeng Zhang

Yuhui Xu, Lingxi Xie, Xiaotao Gu et al. · salesforce, tsinghua

Recently years have witnessed a rapid development of large language models (LLMs). Despite the strong ability in many language-understanding tasks, the heavy computational burden largely restricts the application of LLMs especially when one needs to deploy them onto edge devices. In this paper, we propose a quantization-aware low-rank adaptation (QA-LoRA) algorithm. The motivation lies in the imbalanced degrees of freedom of quantization and adaptation, and the solution is to use group-wise operators which increase the degree of freedom of quantization meanwhile decreasing that of adaptation. QA-LoRA is easily implemented with a few lines of code, and it equips the original LoRA with two-fold abilities: (i) during fine-tuning, the LLM's weights are quantized (e.g., into INT4) to reduce time and memory usage; (ii) after fine-tuning, the LLM and auxiliary weights are naturally integrated into a quantized model without loss of accuracy. We apply QA-LoRA to the LLaMA and LLaMA2 model families and validate its effectiveness in different fine-tuning datasets and downstream scenarios. Code will be made available at https://github.com/yuhuixu1993/qa-lora.

Jiazhong Cen, Jiemin Fang, Zanwei Zhou et al.

The Segment Anything Model (SAM) emerges as a powerful vision foundation model to generate high-quality 2D segmentation results. This paper aims to generalize SAM to segment 3D objects. Rather than replicating the data acquisition and annotation procedure which is costly in 3D, we design an efficient solution, leveraging the radiance field as a cheap and off-the-shelf prior that connects multi-view 2D images to the 3D space. We refer to the proposed solution as SA3D, short for Segment Anything in 3D. With SA3D, the user is only required to provide a 2D segmentation prompt (e.g., rough points) for the target object in a single view, which is used to generate its corresponding 2D mask with SAM. Next, SA3D alternately performs mask inverse rendering and cross-view self-prompting across various views to iteratively refine the 3D mask of the target object. For one view, mask inverse rendering projects the 2D mask obtained by SAM into the 3D space with guidance of the density distribution learned by the radiance field for 3D mask refinement; Then, cross-view self-prompting extracts reliable prompts automatically as the input to SAM from the rendered 2D mask of the inaccurate 3D mask for a new view. We show in experiments that SA3D adapts to various scenes and achieves 3D segmentation within seconds. Our research reveals a potential methodology to lift the ability of a 2D segmentation model to 3D. Our code is available at https://github.com/Jumpat/SegmentAnythingin3D.

Yabo Chen, Yuchen Liu, Dongsheng Jiang et al.

With the development of generative-based self-supervised learning (SSL) approaches like BeiT and MAE, how to learn good representations by masking random patches of the input image and reconstructing the missing information has grown in concern. However, BeiT and PeCo need a "pre-pretraining" stage to produce discrete codebooks for masked patches representing. MAE does not require a pre-training codebook process, but setting pixels as reconstruction targets may introduce an optimization gap between pre-training and downstream tasks that good reconstruction quality may not always lead to the high descriptive capability for the model. Considering the above issues, in this paper, we propose a simple Self-distillated masked AutoEncoder network, namely SdAE. SdAE consists of a student branch using an encoder-decoder structure to reconstruct the missing information, and a teacher branch producing latent representation of masked tokens. We also analyze how to build good views for the teacher branch to produce latent representation from the perspective of information bottleneck. After that, we propose a multi-fold masking strategy to provide multiple masked views with balanced information for boosting the performance, which can also reduce the computational complexity. Our approach generalizes well: with only 300 epochs pre-training, a vanilla ViT-Base model achieves an 84.1% fine-tuning accuracy on ImageNet-1k classification, 48.6 mIOU on ADE20K segmentation, and 48.9 mAP on COCO detection, which surpasses other methods by a considerable margin. Code is available at https://github.com/AbrahamYabo/SdAE.

Yunjie Tian, Lingxi Xie, Jiemin Fang et al.

The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual representations can be done by masking input image parts while requiring the target model to recover the missing contents. MIM has demonstrated promising results on downstream tasks, yet we are interested in whether there exist other effective ways to `learn by recovering missing contents'. In this paper, we investigate this topic by designing five other learning objectives that follow the same procedure as MIM but degrade the input image in different ways. With extensive experiments, we manage to summarize a few design principles for token-based pre-training of vision transformers. In particular, the best practice is obtained by keeping the original image style and enriching spatial masking with spatial misalignment -- this design achieves superior performance over MIM in a series of downstream recognition tasks without extra computational cost. The code is available at https://github.com/sunsmarterjie/beyond_masking.

Guanjun Wu, Taoran Yi, Jiemin Fang et al.

Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to guarantee. To achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency, we propose 4D Gaussian Splatting (4D-GS) as a holistic representation for dynamic scenes rather than applying 3D-GS for each individual frame. In 4D-GS, a novel explicit representation containing both 3D Gaussians and 4D neural voxels is proposed. A decomposed neural voxel encoding algorithm inspired by HexPlane is proposed to efficiently build Gaussian features from 4D neural voxels and then a lightweight MLP is applied to predict Gaussian deformations at novel timestamps. Our 4D-GS method achieves real-time rendering under high resolutions, 82 FPS at an 800$\times$800 resolution on an RTX 3090 GPU while maintaining comparable or better quality than previous state-of-the-art methods. More demos and code are available at https://guanjunwu.github.io/4dgs/.

Jiemin Fang, Taoran Yi, Xinggang Wang et al.

Neural radiance fields (NeRF) have shown great success in modeling 3D scenes and synthesizing novel-view images. However, most previous NeRF methods take much time to optimize one single scene. Explicit data structures, e.g. voxel features, show great potential to accelerate the training process. However, voxel features face two big challenges to be applied to dynamic scenes, i.e. modeling temporal information and capturing different scales of point motions. We propose a radiance field framework by representing scenes with time-aware voxel features, named as TiNeuVox. A tiny coordinate deformation network is introduced to model coarse motion trajectories and temporal information is further enhanced in the radiance network. A multi-distance interpolation method is proposed and applied on voxel features to model both small and large motions. Our framework significantly accelerates the optimization of dynamic radiance fields while maintaining high rendering quality. Empirical evaluation is performed on both synthetic and real scenes. Our TiNeuVox completes training with only 8 minutes and 8-MB storage cost while showing similar or even better rendering performance than previous dynamic NeRF methods.

Shuangrui Ding, Peisen Zhao, Xiaopeng Zhang et al.

Transformers have become the primary backbone of the computer vision community due to their impressive performance. However, the unfriendly computation cost impedes their potential in the video recognition domain. To optimize the speed-accuracy trade-off, we propose Semantic-aware Temporal Accumulation score (STA) to prune spatio-temporal tokens integrally. STA score considers two critical factors: temporal redundancy and semantic importance. The former depicts a specific region based on whether it is a new occurrence or a seen entity by aggregating token-to-token similarity in consecutive frames while the latter evaluates each token based on its contribution to the overall prediction. As a result, tokens with higher scores of STA carry more temporal redundancy as well as lower semantics thus being pruned. Based on the STA score, we are able to progressively prune the tokens without introducing any additional parameters or requiring further re-training. We directly apply the STA module to off-the-shelf ViT and VideoSwin backbones, and the empirical results on Kinetics-400 and Something-Something V2 achieve over 30% computation reduction with a negligible ~0.2% accuracy drop. The code is released at https://github.com/Mark12Ding/STA.

Rongtao Xu, Changwei Wang, Jiaxi Sun et al.

Efficiently training accurate deep models for weakly supervised semantic segmentation (WSSS) with image-level labels is challenging and important. Recently, end-to-end WSSS methods have become the focus of research due to their high training efficiency. However, current methods suffer from insufficient extraction of comprehensive semantic information, resulting in low-quality pseudo-labels and sub-optimal solutions for end-to-end WSSS. To this end, we propose a simple and novel Self Correspondence Distillation (SCD) method to refine pseudo-labels without introducing external supervision. Our SCD enables the network to utilize feature correspondence derived from itself as a distillation target, which can enhance the network's feature learning process by complementing semantic information. In addition, to further improve the segmentation accuracy, we design a Variation-aware Refine Module to enhance the local consistency of pseudo-labels by computing pixel-level variation. Finally, we present an efficient end-to-end Transformer-based framework (TSCD) via SCD and Variation-aware Refine Module for the accurate WSSS task. Extensive experiments on the PASCAL VOC 2012 and MS COCO 2014 datasets demonstrate that our method significantly outperforms other state-of-the-art methods. Our code is available at {https://github.com/Rongtao-Xu/RepresentationLearning/tree/main/SCD-AAAI2023}.

Pu Li, Jianwei Guo, Xiaopeng Zhang et al.

Reverse engineering CAD models from raw geometry is a classic but strenuous research problem. Previous learning-based methods rely heavily on labels due to the supervised design patterns or reconstruct CAD shapes that are not easily editable. In this work, we introduce SECAD-Net, an end-to-end neural network aimed at reconstructing compact and easy-to-edit CAD models in a self-supervised manner. Drawing inspiration from the modeling language that is most commonly used in modern CAD software, we propose to learn 2D sketches and 3D extrusion parameters from raw shapes, from which a set of extrusion cylinders can be generated by extruding each sketch from a 2D plane into a 3D body. By incorporating the Boolean operation (i.e., union), these cylinders can be combined to closely approximate the target geometry. We advocate the use of implicit fields for sketch representation, which allows for creating CAD variations by interpolating latent codes in the sketch latent space. Extensive experiments on both ABC and Fusion 360 datasets demonstrate the effectiveness of our method, and show superiority over state-of-the-art alternatives including the closely related method for supervised CAD reconstruction. We further apply our approach to CAD editing and single-view CAD reconstruction. The code is released at https://github.com/BunnySoCrazy/SECAD-Net.

Taoran Yi, Jiemin Fang, Junjie Wang et al.

In recent times, the generation of 3D assets from text prompts has shown impressive results. Both 2D and 3D diffusion models can help generate decent 3D objects based on prompts. 3D diffusion models have good 3D consistency, but their quality and generalization are limited as trainable 3D data is expensive and hard to obtain. 2D diffusion models enjoy strong abilities of generalization and fine generation, but 3D consistency is hard to guarantee. This paper attempts to bridge the power from the two types of diffusion models via the recent explicit and efficient 3D Gaussian splatting representation. A fast 3D object generation framework, named as GaussianDreamer, is proposed, where the 3D diffusion model provides priors for initialization and the 2D diffusion model enriches the geometry and appearance. Operations of noisy point growing and color perturbation are introduced to enhance the initialized Gaussians. Our GaussianDreamer can generate a high-quality 3D instance or 3D avatar within 15 minutes on one GPU, much faster than previous methods, while the generated instances can be directly rendered in real time. Demos and code are available at https://taoranyi.com/gaussiandreamer/.

Jin Li, Yaoming Wang, Xiaopeng Zhang et al.

Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. However, when it comes to handling long token sequences, especially in dense prediction tasks that require high-resolution input, the complexity of ViTs increases significantly. Notably, dense prediction tasks, such as semantic segmentation or object detection, emphasize more on the contours or shapes of objects, while the texture inside objects is less informative. Motivated by this observation, we propose to apply adaptive resolution for different regions in the image according to their importance. Specifically, at the intermediate layer of the ViT, we utilize a spatial-aware density-based clustering algorithm to select representative tokens from the token sequence. Once the representative tokens are determined, we proceed to merge other tokens into their closest representative token. Consequently, semantic similar tokens are merged together to form low-resolution regions, while semantic irrelevant tokens are preserved independently as high-resolution regions. This strategy effectively reduces the number of tokens, allowing subsequent layers to handle a reduced token sequence and achieve acceleration. We evaluate our proposed method on three different datasets and observe promising performance. For example, the "Segmenter ViT-L" model can be accelerated by 48% FPS without fine-tuning, while maintaining the performance. Additionally, our method can be applied to accelerate fine-tuning as well. Experimental results demonstrate that we can save 52% training time while accelerating 2.46 times FPS with only a 0.09% performance drop. The code is available at https://github.com/caddyless/ailurus/tree/main.

Junjie Wang, Jiemin Fang, Xiaopeng Zhang et al.

Recently, impressive results have been achieved in 3D scene editing with text instructions based on a 2D diffusion model. However, current diffusion models primarily generate images by predicting noise in the latent space, and the editing is usually applied to the whole image, which makes it challenging to perform delicate, especially localized, editing for 3D scenes. Inspired by recent 3D Gaussian splatting, we propose a systematic framework, named GaussianEditor, to edit 3D scenes delicately via 3D Gaussians with text instructions. Benefiting from the explicit property of 3D Gaussians, we design a series of techniques to achieve delicate editing. Specifically, we first extract the region of interest (RoI) corresponding to the text instruction, aligning it to 3D Gaussians. The Gaussian RoI is further used to control the editing process. Our framework can achieve more delicate and precise editing of 3D scenes than previous methods while enjoying much faster training speed, i.e. within 20 minutes on a single V100 GPU, more than twice as fast as Instruct-NeRF2NeRF (45 minutes -- 2 hours).

Rongtao Xu, Changwei Wang, Jiguang Zhang et al.

Accurate skin lesion segmentation from dermoscopic images is of great importance for skin cancer diagnosis. However, automatic segmentation of melanoma remains a challenging task because it is difficult to incorporate useful texture representations into the learning process. Texture representations are not only related to the local structural information learned by CNN, but also include the global statistical texture information of the input image. In this paper, we propose a trans\textbf{Former} network (\textbf{SkinFormer}) that efficiently extracts and fuses statistical texture representation for \textbf{Skin} lesion segmentation. Specifically, to quantify the statistical texture of input features, a Kurtosis-guided Statistical Counting Operator is designed. We propose Statistical Texture Fusion Transformer and Statistical Texture Enhance Transformer with the help of Kurtosis-guided Statistical Counting Operator by utilizing the transformer's global attention mechanism. The former fuses structural texture information and statistical texture information, and the latter enhances the statistical texture of multi-scale features. {Extensive experiments on three publicly available skin lesion datasets validate that our SkinFormer outperforms other SOAT methods, and our method achieves 93.2\% Dice score on ISIC 2018. It can be easy to extend SkinFormer to segment 3D images in the future.} Our code is available at https://github.com/Rongtao-Xu/SkinFormer.

Lin Liu, Lingxi Xie, Xiaopeng Zhang et al.

Learning a generalized prior for natural image restoration is an important yet challenging task. Early methods mostly involved handcrafted priors including normalized sparsity, l_0 gradients, dark channel priors, etc. Recently, deep neural networks have been used to learn various image priors but do not guarantee to generalize. In this paper, we propose a novel approach that embeds a task-agnostic prior into a transformer. Our approach, named Task-Agnostic Prior Embedding (TAPE), consists of two stages, namely, task-agnostic pre-training and task-specific fine-tuning, where the first stage embeds prior knowledge about natural images into the transformer and the second stage extracts the knowledge to assist downstream image restoration. Experiments on various types of degradation validate the effectiveness of TAPE. The image restoration performance in terms of PSNR is improved by as much as 1.45dB and even outperforms task-specific algorithms. More importantly, TAPE shows the ability of disentangling generalized image priors from degraded images, which enjoys favorable transfer ability to unknown downstream tasks.

Chao Liu, Jianwei Guo, Dong-Ming Yan et al.

Registering urban point clouds is a quite challenging task due to the large-scale, noise and data incompleteness of LiDAR scanning data. In this paper, we propose SARNet, a novel semantic augmented registration network aimed at achieving efficient registration of urban point clouds at city scale. Different from previous methods that construct correspondences only in the point-level space, our approach fully exploits semantic features as assistance to improve registration accuracy. Specifically, we extract per-point semantic labels with advanced semantic segmentation networks and build a prior semantic part-to-part correspondence. Then we incorporate the semantic information into a learning-based registration pipeline, consisting of three core modules: a semantic-based farthest point sampling module to efficiently filter out outliers and dynamic objects; a semantic-augmented feature extraction module for learning more discriminative point descriptors; a semantic-refined transformation estimation module that utilizes prior semantic matching as a mask to refine point correspondences by reducing false matching for better convergence. We evaluate the proposed SARNet extensively by using real-world data from large regions of urban scenes and comparing it with alternative methods. The code is available at https://github.com/WinterCodeForEverything/SARNet.

Yueyang Weng, Xiaopeng Zhang, Yongjin Mu et al.

Action chunking is a widely adopted approach in Learning from Demonstration (LfD). By modeling multi-step action chunks rather than single-step actions, action chunking significantly enhances modeling capabilities for human expert policies. However, because action chunking makes a single decision only after a complete action block has been executed, the resulting reduction in decision frequency restricts the utilization of real-time observations, impairing reactivity in dynamic or noisy environments. Existing efforts to address this issue have primarily resorted to trading off reactivity against decision consistency, without achieving both. To address this limitation, we propose a novel algorithm, Temporal Action Selection (TAS), which caches predicted action chunks from multiple timesteps and dynamically selects the optimal action through a lightweight selector network. TAS achieves balanced optimization across both reactivity and decision consistency. Experiments across multiple tasks with diverse base policy architectures show that TAS significantly improves success rates. Furthermore, integrating TAS as a base policy with residual reinforcement learning (RL) improves both training efficiency and the performance ceiling. Experiments in both simulation and physical robots confirm the method's efficacy.

Tianliang Zhang, Qixiang Ye, Baochang Zhang et al.

Pedestrian detection in the wild remains a challenging problem especially for scenes containing serious occlusion. In this paper, we propose a novel feature learning method in the deep learning framework, referred to as Feature Calibration Network (FC-Net), to adaptively detect pedestrians under various occlusions. FC-Net is based on the observation that the visible parts of pedestrians are selective and decisive for detection, and is implemented as a self-paced feature learning framework with a self-activation (SA) module and a feature calibration (FC) module. In a new self-activated manner, FC-Net learns features which highlight the visible parts and suppress the occluded parts of pedestrians. The SA module estimates pedestrian activation maps by reusing classifier weights, without any additional parameter involved, therefore resulting in an extremely parsimony model to reinforce the semantics of features, while the FC module calibrates the convolutional features for adaptive pedestrian representation in both pixel-wise and region-based ways. Experiments on CityPersons and Caltech datasets demonstrate that FC-Net improves detection performance on occluded pedestrians up to 10% while maintaining excellent performance on non-occluded instances.

Chufeng Tang, Lingxi Xie, Gang Zhang et al.

The requirement of expensive annotations is a major burden for training a well-performed instance segmentation model. In this paper, we present an economic active learning setting, named active pointly-supervised instance segmentation (APIS), which starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object. The key of APIS is to find the most desirable points to maximize the segmentation accuracy with limited annotation budgets. We formulate this setting and propose several uncertainty-based sampling strategies. The model developed with these strategies yields consistent performance gain on the challenging MS-COCO dataset, compared against other learning strategies. The results suggest that APIS, integrating the advantages of active learning and point-based supervision, is an effective learning paradigm for label-efficient instance segmentation.

Chufeng Tang, Lingxi Xie, Xiaopeng Zhang et al.

Humans have the ability of recognizing visual semantics in an unlimited granularity, but existing visual recognition algorithms cannot achieve this goal. In this paper, we establish a new paradigm named visual recognition by request (ViRReq) to bridge the gap. The key lies in decomposing visual recognition into atomic tasks named requests and leveraging a knowledge base, a hierarchical and text-based dictionary, to assist task definition. ViRReq allows for (i) learning complicated whole-part hierarchies from highly incomplete annotations and (ii) inserting new concepts with minimal efforts. We also establish a solid baseline by integrating language-driven recognition into recent semantic and instance segmentation methods, and demonstrate its flexible recognition ability on CPP and ADE20K, two datasets with hierarchical whole-part annotations.

Chen Ju, Zeqian Li, Peisen Zhao et al.

In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instances from arbitrary categories within some untrimmed videos, even not seen at training time. We adopt a Transformer-based two-stage action localization architecture with class-agnostic action proposal, followed by open-vocabulary classification. We make the following contributions. First, to compensate image-text foundation models with temporal motions, we improve category-agnostic action proposal by explicitly aligning embeddings of optical flows, RGB and texts, which has largely been ignored in existing low-shot methods. Second, to improve open-vocabulary action classification, we construct classifiers with strong discriminative power, i.e., avoid lexical ambiguities. To be specific, we propose to prompt the pre-trained CLIP text encoder either with detailed action descriptions (acquired from large-scale language models), or visually-conditioned instance-specific prompt vectors. Third, we conduct thorough experiments and ablation studies on THUMOS14 and ActivityNet1.3, demonstrating the superior performance of our proposed model, outperforming existing state-of-the-art approaches by one significant margin.

Dongsheng Jiang, Yuchen Liu, Songlin Liu et al.

Multi-modal Large Language Models (MLLMs) have made significant strides in expanding the capabilities of Large Language Models (LLMs) through the incorporation of visual perception interfaces. Despite the emergence of exciting applications and the availability of diverse instruction tuning data, existing approaches often rely on CLIP or its variants as the visual branch, and merely extract features from the deep layers. However, these methods lack a comprehensive analysis of the visual encoders in MLLMs. In this paper, we conduct an extensive investigation into the effectiveness of different vision encoders within MLLMs. Our findings reveal that the shallow layer features of CLIP offer particular advantages for fine-grained tasks such as grounding and region understanding. Surprisingly, the vision-only model DINO, which is not pretrained with text-image alignment, demonstrates promising performance as a visual branch within MLLMs. By simply equipping it with an MLP layer for alignment, DINO surpasses CLIP in fine-grained related perception tasks. Building upon these observations, we propose a simple yet effective feature merging strategy, named COMM, that integrates CLIP and DINO with Multi-level features Merging, to enhance the visual capabilities of MLLMs. We evaluate COMM through comprehensive experiments on a wide range of benchmarks, including image captioning, visual question answering, visual grounding, and object hallucination. Experimental results demonstrate the superior performance of COMM compared to existing methods, showcasing its enhanced visual capabilities within MLLMs.

Shuangrui Ding, Weidi Xie, Yabo Chen et al.

In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However, taking flow as input brings about two drawbacks. First, flow cannot capture sufficient cues when objects remain static or partially occluded. Second, it is challenging to establish temporal coherency from flow-only input, due to the missing texture information. To tackle these limitations, we propose a model for directly processing consecutive RGB frames, and infer the optical flow between any pair of frames using a layered representation, with the opacity channels being treated as the segmentation. Additionally, to enforce object permanence, we apply temporal consistency loss on the inferred masks from randomly-paired frames, which refer to the motions at different paces, and encourage the model to segment the objects even if they may not move at the current time point. Experimentally, we demonstrate superior performance over previous state-of-the-art methods on three public video segmentation datasets (DAVIS2016, SegTrackv2, and FBMS-59), while being computationally efficient by avoiding the overhead of computing optical flow as input.

Ning Liao, Bowen Shi, Xiaopeng Zhang et al.

Prompt learning has achieved great success in efficiently exploiting large-scale pre-trained models in natural language processing (NLP). It reformulates the downstream tasks as the generative pre-training ones to achieve consistency, thus improving the performance stably. However, when transferring it to the vision area, current visual prompt learning methods are almost designed on discriminative pre-trained models, and there is also a lack of careful design to unify the forms of pre-training and downstream tasks. To explore prompt learning on the generative pre-trained visual model, as well as keeping the task consistency, we propose Visual Prompt learning as masked visual Token Modeling (VPTM) to transform the downstream visual classification into the pre-trained masked visual token prediction. In addition, we develop the prototypical verbalizer for mapping the predicted visual token with implicit semantics to explicit downstream labels. To our best knowledge, VPTM is the first visual prompt method on the generative pre-trained visual model, which achieves consistency between pre-training and downstream visual classification by task reformulation. Experiments show that VPTM outperforms other visual prompt methods and achieves excellent efficiency. Moreover, the task consistency of VPTM contributes to the robustness against prompt location, prompt length and prototype dimension, and could be deployed uniformly.

Lingxi Xie, Longhui Wei, Xiaopeng Zhang et al.

The AI community has been pursuing algorithms known as artificial general intelligence (AGI) that apply to any kind of real-world problem. Recently, chat systems powered by large language models (LLMs) emerge and rapidly become a promising direction to achieve AGI in natural language processing (NLP), but the path towards AGI in computer vision (CV) remains unclear. One may owe the dilemma to the fact that visual signals are more complex than language signals, yet we are interested in finding concrete reasons, as well as absorbing experiences from GPT and LLMs to solve the problem. In this paper, we start with a conceptual definition of AGI and briefly review how NLP solves a wide range of tasks via a chat system. The analysis inspires us that unification is the next important goal of CV. But, despite various efforts in this direction, CV is still far from a system like GPT that naturally integrates all tasks. We point out that the essential weakness of CV lies in lacking a paradigm to learn from environments, yet NLP has accomplished the task in the text world. We then imagine a pipeline that puts a CV algorithm (i.e., an agent) in world-scale, interactable environments, pre-trains it to predict future frames with respect to its action, and then fine-tunes it with instruction to accomplish various tasks. We expect substantial research and engineering efforts to push the idea forward and scale it up, for which we share our perspectives on future research directions.

Fangzhou Wang, Qijing Wang, Bangqi Fu et al.

Due to cost benefits, supply chains of integrated circuits (ICs) are largely outsourced nowadays. However, passing ICs through various third-party providers gives rise to many threats, like piracy of IC intellectual property or insertion of hardware Trojans, i.e., malicious circuit modifications. In this work, we proactively and systematically harden the physical layouts of ICs against post-design insertion of Trojans. Toward that end, we propose a multiplexer-based logic-locking scheme that is (i) devised for layout-level Trojan prevention, (ii) resilient against state-of-the-art, oracle-less machine learning attacks, and (iii) fully integrated into a tailored, yet generic, commercial-grade design flow. Our work provides in-depth security and layout analysis on a challenging benchmark suite. We show that ours can render layouts resilient, with reasonable overheads, against Trojan insertion in general and also against second-order attacks (i.e., adversaries seeking to bypass the locking defense in an oracle-less setting). We release our layout artifacts for independent verification [29] and we will release our methodology's source code.

Pengfei Chen, Lingxi Xie, Xinyue Huo et al.

The Segment Anything model (SAM) has shown a generalized ability to group image pixels into patches, but applying it to semantic-aware segmentation still faces major challenges. This paper presents SAM-CP, a simple approach that establishes two types of composable prompts beyond SAM and composes them for versatile segmentation. Specifically, given a set of classes (in texts) and a set of SAM patches, the Type-I prompt judges whether a SAM patch aligns with a text label, and the Type-II prompt judges whether two SAM patches with the same text label also belong to the same instance. To decrease the complexity in dealing with a large number of semantic classes and patches, we establish a unified framework that calculates the affinity between (semantic and instance) queries and SAM patches and merges patches with high affinity to the query. Experiments show that SAM-CP achieves semantic, instance, and panoptic segmentation in both open and closed domains. In particular, it achieves state-of-the-art performance in open-vocabulary segmentation. Our research offers a novel and generalized methodology for equipping vision foundation models like SAM with multi-grained semantic perception abilities.

Haohang Xu, Lin Liu, Zhibo Zhang et al.

Diffusion-based image editing models have achieved significant progress in real world applications. However, conventional models typically rely on natural language prompts, which often lack the precision required to localize target objects. Consequently, these models struggle to maintain background consistency due to their global image regeneration paradigm. Recognizing that visual cues provide an intuitive means for users to highlight specific areas of interest, we utilize bounding boxes as guidance to explicitly define the editing target. This approach ensures that the diffusion model can accurately localize the target while preserving background consistency. To achieve this, we propose FineEdit, a multi-level bounding box injection method that enables the model to utilize spatial conditions more effectively. To support this high precision guidance, we present FineEdit-1.2M, a large scale, fine-grained dataset comprising 1.2 million image editing pairs with precise bounding box annotations. Furthermore, we construct a comprehensive benchmark, termed FineEdit-Bench, which includes 1,000 images across 10 subjects to effectively evaluate region based editing capabilities. Evaluations on FineEdit-Bench demonstrate that our model significantly outperforms state-of-the-art open-source models (e.g., Qwen-Image-Edit and LongCat-Image-Edit) in instruction compliance and background preservation. Further assessments on open benchmarks (GEdit and ImgEdit Bench) confirm its superior generalization and robustness.

Changwei Wang, Rongtao Xu, Yuyang Zhang et al.

Limited by the locality of convolutional neural networks, most existing local features description methods only learn local descriptors with local information and lack awareness of global and surrounding spatial context. In this work, we focus on making local descriptors "look wider to describe better" by learning local Descriptors with More Than just Local information (MTLDesc). Specifically, we resort to context augmentation and spatial attention mechanisms to make our MTLDesc obtain non-local awareness. First, Adaptive Global Context Augmented Module and Diverse Local Context Augmented Module are proposed to construct robust local descriptors with context information from global to local. Second, Consistent Attention Weighted Triplet Loss is designed to integrate spatial attention awareness into both optimization and matching stages of local descriptors learning. Third, Local Features Detection with Feature Pyramid is given to obtain more stable and accurate keypoints localization. With the above innovations, the performance of our MTLDesc significantly surpasses the prior state-of-the-art local descriptors on HPatches, Aachen Day-Night localization and InLoc indoor localization benchmarks.

Bowen Shi, Xiaopeng Zhang, Yaoming Wang et al.

Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised pre-training excel at capturing longer-range global patterns and enabling better feature discrimination, while MIM can introduce more local and diverse attention across all transformer layers. In this paper, we explore how to obtain a model that combines their strengths. We start by examining previous feature distillation and mask feature reconstruction methods and identify their limitations. We find that their increasing diversity mainly derives from the asymmetric designs, but these designs may in turn compromise the discrimination ability. In order to better obtain both discrimination and diversity, we propose a simple but effective Hybrid Distillation strategy, which utilizes both the supervised/CL teacher and the MIM teacher to jointly guide the student model. Hybrid Distill imitates the token relations of the MIM teacher to alleviate attention collapse, as well as distills the feature maps of the supervised/CL teacher to enable discrimination. Furthermore, a progressive redundant token masking strategy is also utilized to reduce the distilling costs and avoid falling into local optima. Experiment results prove that Hybrid Distill can achieve superior performance on different benchmarks.

Ning Liao, Xiaopeng Zhang, Min Cao et al.

In realistic open-set scenarios where labels of a part of testing data are totally unknown, when vision-language (VL) prompt learning methods encounter inputs related to unknown classes (i.e., not seen during training), they always predict them as one of the training classes. The exhibited label bias causes difficulty in open set recognition (OSR), in which an image should be correctly predicted as one of the known classes or the unknown one. To achieve this goal, we propose a vision-language prompt tuning method with mitigated label bias (M-Tuning). It introduces open words from the WordNet to extend the range of words forming the prompt texts from only closed-set label words to more, and thus prompts are tuned in a simulated open-set scenario. Besides, inspired by the observation that classifying directly on large datasets causes a much higher false positive rate than on small datasets, we propose a Combinatorial Tuning and Testing (CTT) strategy for improving performance. CTT decomposes M-Tuning on large datasets as multiple independent group-wise tuning on fewer classes, then makes accurate and comprehensive predictions by selecting the optimal sub-prompt. Finally, given the lack of VL-based OSR baselines in the literature, especially for prompt methods, we contribute new baselines for fair comparisons. Our method achieves the best performance on datasets with various scales, and extensive ablation studies also validate its effectiveness.

Yuqing Chen, Lin Liu, Haisu Wu et al.

Video object removal frequently struggles to simultaneously eliminate target objects and their associated physical effects (e.g., smoke, reflections, light, and ripples) in out-of-domain scenarios due to complex spatiotemporal ambiguities. While existing methods primarily rely on spatial masks, they often fail to capture weakly correlated effects, and the potential of explicit textual guidance remains underexplored. Furthermore, a fundamental optimization conflict exists in removal models between high-level semantic generalization and precise pixel-level background preservation. To address these challenges, we propose GenEraser, a novel framework for generalized and high-fidelity video object and effect removal. First, we introduce a Multi-Conditional Mixture-of-Experts (MC-MoE) paired with Bipartite Text guidance to fully exploit the multimodal priors of Diffusion Transformers, significantly enhancing the identification of complex effects. Second, a Learnable Deep ``CFG'' Fusion mechanism (LD-CFG) is developed to adaptively balance the relative dominance of mask and textual conditions across diverse scenarios. Finally, we propose a Decoupled Expert Architecture, comprising a Locator and a Preserver, to mitigate the inherent trade-off between semantic generalization and pixel alignment. Extensive experiments demonstrate that our GenEraser surpasses recent state-of-the-art approaches, achieving significant quantitative improvements (e.g., $2.16$ dB and $1.44$ dB on the ROSE Benchmark and VOR-Eval, respectively) while maintaining exceptionally robust generalization in open-world scenarios. https://cyqii.github.io/GenEraser.github.io/

Sen Pei, Jiaxi Sun, Xiaopeng Zhang et al.

Recent studies show that the deep neural networks (DNNs) have achieved great success in various tasks. However, even the \emph{state-of-the-art} deep learning based classifiers are extremely vulnerable to adversarial examples, resulting in sharp decay of discrimination accuracy in the presence of enormous unknown attacks. Given the fact that neural networks are widely used in the open world scenario which can be safety-critical situations, mitigating the adversarial effects of deep learning methods has become an urgent need. Generally, conventional DNNs can be attacked with a dramatically high success rate since their gradient is exposed thoroughly in the white-box scenario, making it effortless to ruin a well trained classifier with only imperceptible perturbations in the raw data space. For tackling this problem, we propose a plug-and-play layer that is training-free, termed as \textbf{G}radient \textbf{C}oncealment \textbf{M}odule (GCM), concealing the vulnerable direction of gradient while guaranteeing the classification accuracy during the inference time. GCM reports superior defense results on the ImageNet classification benchmark, improving up to 63.41\% top-1 attack robustness (AR) when faced with adversarial inputs compared to the vanilla DNNs. Moreover, we use GCM in the CVPR 2022 Robust Classification Challenge, currently achieving \textbf{2nd} place in Phase II with only a tiny version of ConvNext. The code will be made available.

Yuanqi Li, Jianwei Guo, Xinran Yang et al.

The growing size of point clouds enlarges consumptions of storage, transmission, and computation of 3D scenes. Raw data is redundant, noisy, and non-uniform. Therefore, simplifying point clouds for achieving compact, clean, and uniform points is becoming increasingly important for 3D vision and graphics tasks. Previous learning based methods aim to generate fewer points for scene understanding, regardless of the quality of surface reconstruction, leading to results with low reconstruction accuracy and bad point distribution. In this paper, we propose a novel point cloud simplification network (PCS-Net) dedicated to high-quality surface mesh reconstruction while maintaining geometric fidelity. We first learn a sampling matrix in a feature-aware simplification module to reduce the number of points. Then we propose a novel double-scale resampling module to refine the positions of the sampled points, to achieve a uniform distribution. To further retain important shape features, an adaptive sampling strategy with a novel saliency loss is designed. With our PCS-Net, the input non-uniform and noisy point cloud can be simplified in a feature-aware manner, i.e., points near salient features are consolidated but still with uniform distribution locally. Experiments demonstrate the effectiveness of our method and show that we outperform previous simplification or reconstruction-oriented upsampling methods.

Zhe Feng, Sen Lian, Changwei Wang et al.

The quadratic complexity of softmax attention presents a major obstacle for scaling Transformers to high-resolution vision tasks. Existing linear attention variants often replace the softmax with Gaussian kernels to reduce complexity, but such approximations lack theoretical grounding and tend to oversuppress mid-range token interactions. We propose LaplacianFormer, a Transformer variant that employs a Laplacian kernel as a principled alternative to softmax, motivated by empirical observations and theoretical analysis. To address expressiveness degradation under low-rank approximations, we introduce a provably injective feature map that retains fine-grained token information. For efficient computation, we adopt a Nyström approximation of the kernel matrix and solve the resulting system using Newton--Schulz iteration, avoiding costly matrix inversion and SVD. We further develop custom CUDA implementations for both the kernel and solver, enabling high-throughput forward and backward passes suitable for edge deployment. Experiments on ImageNet show that LaplacianFormer achieves strong performance-efficiency trade-offs while improving attention expressiveness.

Peisen Zhao, Xiaopeng Zhang, Mingxing Xu et al.

While Multimodal Large Language Models (MLLMs) have experienced rapid advancements, their visual encoders frequently remain a performance bottleneck. Conventional CLIP-based encoders struggle with dense spatial tasks due to the loss of visual details caused by low-resolution pretraining and the reliance on noisy, coarse web-crawled image-text pairs. To overcome these limitations, we introduce FineViT, a novel vision encoder specifically designed to unlock fine-grained perception. By replacing coarse web data with dense recaptions, we systematically mitigate information loss through a progressive training paradigm.: first, the encoder is trained from scratch at a high native resolution on billions of global recaptioned image-text pairs, establishing a robust, detail rich semantic foundation. Subsequently, we further enhance its local perception through LLM alignment, utilizing our curated FineCap-450M dataset that comprises over $450$ million high quality local captions. Extensive experiments validate the effectiveness of the progressive strategy. FineViT achieves state-of-the-art zero-shot recognition and retrieval performance, especially in long-context retrieval, and consistently outperforms multimodal visual encoders such as SigLIP2 and Qwen-ViT when integrated into MLLMs. We hope FineViT could serve as a powerful new baseline for fine-grained visual perception.

Chen Yang, Sikuang Li, Jiemin Fang et al.

Reconstructing and rendering 3D objects from highly sparse views is of critical importance for promoting applications of 3D vision techniques and improving user experience. However, images from sparse views only contain very limited 3D information, leading to two significant challenges: 1) Difficulty in building multi-view consistency as images for matching are too few; 2) Partially omitted or highly compressed object information as view coverage is insufficient. To tackle these challenges, we propose GaussianObject, a framework to represent and render the 3D object with Gaussian splatting that achieves high rendering quality with only 4 input images. We first introduce techniques of visual hull and floater elimination, which explicitly inject structure priors into the initial optimization process to help build multi-view consistency, yielding a coarse 3D Gaussian representation. Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined. We design a self-generating strategy to obtain image pairs for training the repair model. We further design a COLMAP-free variant, where pre-given accurate camera poses are not required, which achieves competitive quality and facilitates wider applications. GaussianObject is evaluated on several challenging datasets, including MipNeRF360, OmniObject3D, OpenIllumination, and our-collected unposed images, achieving superior performance from only four views and significantly outperforming previous SOTA methods. Our demo is available at https://gaussianobject.github.io/, and the code has been released at https://github.com/GaussianObject/GaussianObject.

Yan Li, Lin Liu, Xiaopeng Zhang et al.

Instruction-based video editing requires transforming a source video according to a natural-language instruction while preserving irrelevant content and remaining temporally coherent. We argue that existing Diffusion Transformer (DiT) editors struggle with this task for two structural reasons. First, conditioning signals are fed undifferentiated into all transformer blocks, forcing a single token stream to encode both global editing intent and fine-grained visual evidence. Second, the cross-attention patterns that govern the edit are supervised only indirectly through pixel-level reconstruction, leaving the model's internal reasoning process under-constrained. To address both limitations, we propose RVEDiT, an implicit Reasoning Video Editing DiT framework built around two complementary components. The first, Granularity-Routed Token Conditioning, introduces learnable editing tokens distilled from a multimodal LLM and routes them to shallow blocks, while reserving native visual and textual tokens for deeper blocks, thereby inducing a coarse-to-fine editing process inside the backbone. The second, Reference-Anchored Attention Alignment, employs a parameter-sharing reference branch during training and maximizes the mutual information between the attention features of the editing and reference branches, regularizing the model's internal reasoning without incurring any additional inference cost. Experiments on standard instruction-based video editing benchmarks show that RVEDiT consistently outperforms state-of-the-art baselines, with particularly strong gains on localized and compositional edits.

Lin Liu, Zhihan Xiao, Haohang Xu et al.

Video editing has recently achieved remarkable progress with diffusion-based generative models, enabling diverse object-level manipulations from natural language instructions. However, existing methods often struggle under occlusion, viewpoint changes, and fast object motion, where unreliable visual observations lead to inaccurate localization, temporal flickering, and inconsistent edits. In this work, we identify the absence of reliable visual anchors as a fundamental bottleneck in occlusion-robust video editing. To address this issue, we propose an occlusion-aware physics-semantic keyframe selection framework that automatically identifies an optimal anchor frame for downstream editing. Specifically, our method evaluates candidate frames from three complementary perspectives: structural completeness for avoiding truncated observations, cycle-consistent tracking stability for measuring physical reliability, and vision-language-based attribute visibility for ensuring semantic clarity. The selected keyframe is then propagated through bidirectional tracking to generate dense spatiotemporal masks, which are used as auxiliary supervision for a diffusion-based video editing backbone. By transforming occlusion handling from explicit reconstruction into reliable anchor selection, our framework enables precise and temporally consistent editing without requiring manual annotations. Extensive experiments on challenging video editing benchmarks demonstrate the effectiveness and high-quality performance of our method.

Yan Li, Lin Liu, Xiaopeng Zhang et al.

Instruction-based image editing with diffusion models has achieved impressive results, yet existing methods struggle with fine-grained instructions specifying precise attributes such as colors, positions, and quantities. While recent approaches employ Group Relative Policy Optimization (GRPO) for alignment, they optimize only at individual sampling steps, providing sparse feedback that limits trajectory-level control. We propose a unified framework CogniEdit, combining multi-modal reasoning with dense reward optimization that propagates gradients across consecutive denoising steps, enabling trajectory-level gradient flow through the sampling process. Our method comprises three components: (1) Multi-modal Large Language Models for decomposing complex instructions into actionable directives, (2) Dynamic Token Focus Relocation that adaptively emphasizes fine-grained attributes, and (3) Dense GRPO-based optimization that propagates gradients across consecutive steps for trajectory-level supervision. Extensive experiments on benchmark datasets demonstrate that our CogniEdit achieves state-of-the-art performance in balancing fine-grained instruction following with visual quality and editability preservation

Xiaofeng Han, Shunpeng Chen, Zenghuang Fu et al.

Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically review the applications and advancements of multimodal fusion methods and VLMs in the field of robot vision. For semantic scene understanding tasks, we categorize fusion approaches into encoder-decoder frameworks, attention-based architectures, and graph neural networks. Meanwhile, we also analyze the architectural characteristics and practical implementations of these fusion strategies in key tasks such as simultaneous localization and mapping (SLAM), 3D object detection, navigation, and manipulation. We compare the evolutionary paths and applicability of VLMs based on large language models (LLMs) with traditional multimodal fusion methods.Additionally, we conduct an in-depth analysis of commonly used datasets, evaluating their applicability and challenges in real-world robotic scenarios. Building on this analysis, we identify key challenges in current research, including cross-modal alignment, efficient fusion, real-time deployment, and domain adaptation. We propose future directions such as self-supervised learning for robust multimodal representations, structured spatial memory and environment modeling to enhance spatial intelligence, and the integration of adversarial robustness and human feedback mechanisms to enable ethically aligned system deployment. Through a comprehensive review, comparative analysis, and forward-looking discussion, we provide a valuable reference for advancing multimodal perception and interaction in robotic vision. A comprehensive list of studies in this survey is available at https://github.com/Xiaofeng-Han-Res/MF-RV.

Mingda Jia, Weiliang Meng, Zenghuang Fu et al.

Dense video captioning jointly localizes and captions salient events in untrimmed videos. Recent methods primarily focus on leveraging additional prior knowledge and advanced multi-task architectures to achieve competitive performance. However, these pipelines rely on implicit modeling that uses frame-level or fragmented video features, failing to capture the temporal coherence across event sequences and comprehensive semantics within visual contexts. To address this, we propose an explicit temporal-semantic modeling framework called Context-Aware Cross-Modal Interaction (CACMI), which leverages both latent temporal characteristics within videos and linguistic semantics from text corpus. Specifically, our model consists of two core components: Cross-modal Frame Aggregation aggregates relevant frames to extract temporally coherent, event-aligned textual features through cross-modal retrieval; and Context-aware Feature Enhancement utilizes query-guided attention to integrate visual dynamics with pseudo-event semantics. Extensive experiments on the ActivityNet Captions and YouCook2 datasets demonstrate that CACMI achieves the state-of-the-art performance on dense video captioning task.

Wenhao Xu, Rongtao Xu, Changwei Wang et al.

Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks. The present landscape features two-stage methodologies beset by issues such as intricate pipelines and elevated computational costs. While current one-stage approaches alleviate these concerns and incorporate Visual Prompt Training (VPT) to uphold CLIP's generalization capacity, they still fall short in fully harnessing CLIP's potential for pixel-level unseen class demarcation and precise pixel predictions. To further stimulate CLIP's zero-shot dense prediction capability, we propose SPT-SEG, a one-stage approach that improves CLIP's adaptability from image to pixel. Specifically, we initially introduce Spectral Prompt Tuning (SPT), incorporating spectral prompts into the CLIP visual encoder's shallow layers to capture structural intricacies of images, thereby enhancing comprehension of unseen classes. Subsequently, we introduce the Spectral Guided Decoder (SGD), utilizing both high and low-frequency information to steer the network's spatial focus towards more prominent classification features, enabling precise pixel-level prediction outcomes. Through extensive experiments on two public datasets, we demonstrate the superiority of our method over state-of-the-art approaches, performing well across all classes and particularly excelling in handling unseen classes. Code is available at:https://github.com/clearxu/SPT.

Bowen Shi, Peisen Zhao, Zichen Wang et al.

Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual tasks. However, existing approaches primarily focus on training models to match global image representations with textual descriptions, thereby overlooking the critical alignment between local regions and corresponding text tokens. This paper extends CLIP with multi-granularity alignment. Notably, we deliberately construct a new dataset comprising pseudo annotations at various levels of granularities, encompassing image-level, region-level as well as pixel-level captions and tags. Accordingly, we develop a Unified Multi-Granularity learning framework, termed UMG-CLIP, which simultaneously empowers the model with versatile perception abilities across different levels of detail. With parameter efficient tuning, UMG-CLIP surpasses current widely used CLIP variants and achieves state-of-the-art performance on diverse image understanding benchmarks, including open-world recognition, retrieval, semantic segmentation, and panoptic segmentation tasks. We believe that UMG-CLIP represents a valuable advancement in vision-language foundation models. The code is available at https://github.com/lygsbw/UMG-CLIP.

Sida He, Lingxi Xie, Xiaopeng Zhang et al.

Historical archives contain qualitative descriptions of climate events, yet converting these into quantitative records has remained a fundamental challenge. Here we introduce a paradigm shift: a generative AI framework that inverts the logic of historical chroniclers by inferring the quantitative climate patterns associated with documented events. Applied to historical Chinese archives, it produces the sub-annual precipitation reconstruction for southeastern China over the period 1368-1911 AD. Our reconstruction not only quantifies iconic extremes like the Ming Dynasty's Great Drought but also, crucially, maps the full spatial and seasonal structure of El Ni$ñ$o influence on precipitation in this region over five centuries, revealing dynamics inaccessible in shorter modern records. Our methodology and high-resolution climate dataset are directly applicable to climate science and have broader implications for the historical and social sciences.

Yi Zhang, Yinda Chen, Che Liu et al.

We present Pelican-Unified 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unified 1.0 uses a single VLM as a unified understanding module, mapping scenes, instructions, visual contexts, and action histories into a shared semantic space. The same VLM also serves as a unified reasoning module, autoregressively producing task-, action-, and future-oriented chains of thought in a single forward pass and projecting the final hidden state into a dense latent variable. A Unified Future Generator (UFG) then conditions on this latent variable and jointly generates future videos and future actions through two modality-specific output heads within the same denoising process. The language, video, and action losses are all backpropagated into the shared representation, enabling the model to jointly optimize understanding, reasoning, imagination, and action during training, rather than training three isolated expert systems. Experiments demonstrate that unification does not imply compromise. With a single checkpoint, Pelican-Unified 1.0 achieves strong performance across all three capabilities: 64.7 on eight VLM benchmarks, the best among comparable-scale models; 66.03 on WorldArena, ranking first; and 93.5 on RoboTwin, the second-best average among compared action methods. These results show that the unified paradigm succeeds in preserving specialist strength while bringing understanding, reasoning, imagination, and action into one model.

Yue Chang, Liqiang Jing, Xiaopeng Zhang et al.

Hallucination is a common problem for Large Vision-Language Models (LVLMs) with long generations which is difficult to eradicate. The generation with hallucinations is partially inconsistent with the image content. To mitigate hallucination, current studies either focus on the process of model inference or the results of model generation, but the solutions they design sometimes do not deal appropriately with various types of queries and the hallucinations of the generations about these queries. To accurately deal with various hallucinations, we present a unified framework, Dentist, for hallucination mitigation. The core step is to first classify the queries, then perform different processes of hallucination mitigation based on the classification result, just like a dentist first observes the teeth and then makes a plan. In a simple deployment, Dentist can classify queries as perception or reasoning and easily mitigate potential hallucinations in answers which has been demonstrated in our experiments. On MMbench, we achieve a 13.44%/10.2%/15.8% improvement in accuracy on Image Quality, a Coarse Perception visual question answering (VQA) task, over the baseline InstructBLIP/LLaVA/VisualGLM.

Jiazhong Cen, Xudong Zhou, Jiemin Fang et al.

Recent advancements in 3D Gaussian Splatting (3D-GS) enable high-quality 3D scene reconstruction from RGB images. Many studies extend this paradigm for language-driven open-vocabulary scene understanding. However, most of them simply project 2D semantic features onto 3D Gaussians and overlook a fundamental gap between 2D and 3D understanding: a 3D object may exhibit various semantics from different viewpoints--a phenomenon we term view-dependent semantics. To address this challenge, we propose LaGa (Language Gaussians), which establishes cross-view semantic connections by decomposing the 3D scene into objects. Then, it constructs view-aggregated semantic representations by clustering semantic descriptors and reweighting them based on multi-view semantics. Extensive experiments demonstrate that LaGa effectively captures key information from view-dependent semantics, enabling a more comprehensive understanding of 3D scenes. Notably, under the same settings, LaGa achieves a significant improvement of +18.7% mIoU over the previous SOTA on the LERF-OVS dataset. Our code is available at: https://github.com/SJTU-DeepVisionLab/LaGa.

Yuchen Liu, Yaoming Wang, Bowen Shi et al.

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce prohibitive computational overhead to achieve superior performance using complementary visual representations from multiple vision encoders. To address this, we propose a progressive pruning framework, namely Multi-Encoder collaboraTivE tOken pRuning (METEOR), that eliminates redundant visual tokens across the encoding, fusion, and decoding stages for multi-encoder MLLMs. For multi-vision encoding, we discard redundant tokens within each encoder via a rank guided collaborative token assignment strategy. Subsequently, for multi-vision fusion, we combine the visual features from different encoders while reducing cross-encoder redundancy with cooperative pruning. Finally, we propose an adaptive token pruning method in the LLM decoding stage to further discard irrelevant tokens based on the text prompts with dynamically adjusting pruning ratios for specific task demands. To our best knowledge, this is the first successful attempt that achieves an efficient multi-encoder based vision language model with multi-stage pruning strategies. Extensive experiments on 11 benchmarks demonstrate the effectiveness of our proposed approach. Compared with EAGLE, a typical multi-encoder MLLMs, METEOR reduces 76% visual tokens with only 0.3% performance drop in average. The code is available at https://github.com/YuchenLiu98/METEOR.

Jiangtong Tan, Lin Liu, Jie Huanng et al.

Unified multimodal models significantly improve visual generation by combining vision-language models (VLMs) with diffusion models. However, existing methods struggle to fully balance sufficient interaction and flexible implementation due to vast representation difference. Considering abundant and hierarchical information in VLM's layers from low-level details to high-level semantics, we propose \textbf{ParaUni}. It extracts features from variants VLM's layers in a \textbf{Para}llel way for comprehensive information interaction and retains a flexible separation architecture to enhance generation in \textbf{Uni}fied multimodal model. Concretely, visual features from all VLM's layers are fed in parallel into a Layer Integration Module (LIM), which efficiently integrates fine-grained details and semantic abstractions and provides the fused representation as a condition to the diffusion model. To further enhance performance, we reveal that these hierarchical layers respond unequally to different rewards in Reinforcement Learning (RL). Crucially, we design a Layer-wise Dynamic Adjustment Mechanism (LDAM) to facilitate multiple reward improvements that aligns the hierarchical properties of these layers using RL. Extensive experiments show ParaUni leverages complementary multi-layer features to substantially improve generation quality and shows strong potential for multiple reward advances during RL stages. Code is available at https://github.com/JosephTiTan/ParaUni.

Yabo Zhang, Yuxiang Wei, Dongsheng Jiang et al.

Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling. Besides the training burden, the generated videos also suffer from appearance inconsistency and structural flickers, especially in long video synthesis. To address these challenges, we design a \emph{training-free} framework called \textbf{ControlVideo} to enable natural and efficient text-to-video generation. ControlVideo, adapted from ControlNet, leverages coarsely structural consistency from input motion sequences, and introduces three modules to improve video generation. Firstly, to ensure appearance coherence between frames, ControlVideo adds fully cross-frame interaction in self-attention modules. Secondly, to mitigate the flicker effect, it introduces an interleaved-frame smoother that employs frame interpolation on alternated frames. Finally, to produce long videos efficiently, it utilizes a hierarchical sampler that separately synthesizes each short clip with holistic coherency. Empowered with these modules, ControlVideo outperforms the state-of-the-arts on extensive motion-prompt pairs quantitatively and qualitatively. Notably, thanks to the efficient designs, it generates both short and long videos within several minutes using one NVIDIA 2080Ti. Code is available at https://github.com/YBYBZhang/ControlVideo.