Lin Ma

Dingfeng Shi, Yujie Zhong, Qiong Cao et al.

This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries, similar to DETR, which has shown great success in object detection. However, the framework suffers from several problems if directly applied to TAD: the insufficient exploration of inter-query relation in the decoder, the inadequate classification training due to a limited number of training samples, and the unreliable classification scores at inference. To this end, we first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations. Moreover, we propose two losses to facilitate and stabilize the training of action classification. Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries. The proposed method, named ReAct, achieves the state-of-the-art performance on THUMOS14, with much lower computational costs than previous methods. Besides, extensive ablation studies are conducted to verify the effectiveness of each proposed component. The code is available at https://github.com/sssste/React.

Yang Jiao, Zequn Jie, Shaoxiang Chen et al.

Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features from two drastically different modalities. Recent approaches aim at exploring the semantic densities of camera features through lifting points in 2D camera images (referred to as seeds) into 3D space, and then incorporate 2D semantics via cross-modal interaction or fusion techniques. However, depth information is under-investigated in these approaches when lifting points into 3D space, thus 2D semantics can not be reliably fused with 3D points. Moreover, their multi-modal fusion strategy, which is implemented as concatenation or attention, either can not effectively fuse 2D and 3D information or is unable to perform fine-grained interactions in the voxel space. To this end, we propose a novel framework with better utilization of the depth information and fine-grained cross-modal interaction between LiDAR and camera, which consists of two important components. First, a Multi-Depth Unprojection (MDU) method with depth-aware designs is used to enhance the depth quality of the lifted points at each interaction level. Second, a Gated Modality-Aware Convolution (GMA-Conv) block is applied to modulate voxels involved with the camera modality in a fine-grained manner and then aggregate multi-modal features into a unified space. Together they provide the detection head with more comprehensive features from LiDAR and camera. On the nuScenes test benchmark, our proposed method, abbreviated as MSMDFusion, achieves state-of-the-art 3D object detection results with 71.5% mAP and 74.0% NDS, and strong tracking results with 74.0% AMOTA without using test-time-augmentation and ensemble techniques. The code is available at https://github.com/SxJyJay/MSMDFusion.

Jinlong Li, Zequn Jie, Xu Wang et al.

Generating precise class-aware pseudo ground-truths, a.k.a, class activation maps (CAMs), is essential for weakly-supervised semantic segmentation. The original CAM method usually produces incomplete and inaccurate localization maps. To tackle with this issue, this paper proposes an Expansion and Shrinkage scheme based on the offset learning in the deformable convolution, to sequentially improve the recall and precision of the located object in the two respective stages. In the Expansion stage, an offset learning branch in a deformable convolution layer, referred as "expansion sampler" seeks for sampling increasingly less discriminative object regions, driven by an inverse supervision signal that maximizes image-level classification loss. The located more complete object in the Expansion stage is then gradually narrowed down to the final object region during the Shrinkage stage. In the Shrinkage stage, the offset learning branch of another deformable convolution layer, referred as "shrinkage sampler", is introduced to exclude the false positive background regions attended in the Expansion stage to improve the precision of the localization maps. We conduct various experiments on PASCAL VOC 2012 and MS COCO 2014 to well demonstrate the superiority of our method over other state-of-the-art methods for weakly-supervised semantic segmentation. Code will be made publicly available here https://github.com/TyroneLi/ESOL_WSSS.

Sifan Zhou, Zhi Tian, Xiangxiang Chu et al.

The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios. Existing BEV-based (i.e., Bird Eye View) detectors favor sparse convolutions (known as SPConv) to speed up training and inference, which puts a hard barrier for deployment, especially for on-device applications. In this paper, to tackle the challenge of efficient 3D object detection from an industry perspective, we devise a deployment-friendly pillar-based 3D detector, termed FastPillars. First, we introduce a novel lightweight Max-and-Attention Pillar Encoding (MAPE) module specially for enhancing small 3D objects. Second, we propose a simple yet effective principle for designing a backbone in pillar-based 3D detection. We construct FastPillars based on these designs, achieving high performance and low latency without SPConv. Extensive experiments on two large-scale datasets demonstrate the effectiveness and efficiency of FastPillars for on-device 3D detection regarding both performance and speed. Specifically, FastPillars delivers state-of-the-art accuracy on Waymo Open Dataset with 1.8X speed up and 3.8 mAPH/L2 improvement over CenterPoint (SPConv-based). Our code is publicly available at: https://github.com/StiphyJay/FastPillars.

Yang Jiao, Shaoxiang Chen, Zequn Jie et al.

3D dense captioning is a recently-proposed novel task, where point clouds contain more geometric information than the 2D counterpart. However, it is also more challenging due to the higher complexity and wider variety of inter-object relations contained in point clouds. Existing methods only treat such relations as by-products of object feature learning in graphs without specifically encoding them, which leads to sub-optimal results. In this paper, aiming at improving 3D dense captioning via capturing and utilizing the complex relations in the 3D scene, we propose MORE, a Multi-Order RElation mining model, to support generating more descriptive and comprehensive captions. Technically, our MORE encodes object relations in a progressive manner since complex relations can be deduced from a limited number of basic ones. We first devise a novel Spatial Layout Graph Convolution (SLGC), which semantically encodes several first-order relations as edges of a graph constructed over 3D object proposals. Next, from the resulting graph, we further extract multiple triplets which encapsulate basic first-order relations as the basic unit, and construct several Object-centric Triplet Attention Graphs (OTAG) to infer multi-order relations for every target object. The updated node features from OTAG are aggregated and fed into the caption decoder to provide abundant relational cues, so that captions including diverse relations with context objects can be generated. Extensive experiments on the Scan2Cap dataset prove the effectiveness of our proposed MORE and its components, and we also outperform the current state-of-the-art method. Our code is available at https://github.com/SxJyJay/MORE.

Dingfeng Shi, Yujie Zhong, Qiong Cao et al.

In this paper, we present a one-stage framework TriDet for temporal action detection. Existing methods often suffer from imprecise boundary predictions due to the ambiguous action boundaries in videos. To alleviate this problem, we propose a novel Trident-head to model the action boundary via an estimated relative probability distribution around the boundary. In the feature pyramid of TriDet, we propose an efficient Scalable-Granularity Perception (SGP) layer to mitigate the rank loss problem of self-attention that takes place in the video features and aggregate information across different temporal granularities. Benefiting from the Trident-head and the SGP-based feature pyramid, TriDet achieves state-of-the-art performance on three challenging benchmarks: THUMOS14, HACS and EPIC-KITCHEN 100, with lower computational costs, compared to previous methods. For example, TriDet hits an average mAP of $69.3\%$ on THUMOS14, outperforming the previous best by $2.5\%$, but with only $74.6\%$ of its latency. The code is released to https://github.com/sssste/TriDet.

Cong Han, Yujie Zhong, Dengjie Li et al.

Recently, the open-vocabulary semantic segmentation problem has attracted increasing attention and the best performing methods are based on two-stream networks: one stream for proposal mask generation and the other for segment classification using a pretrained visual-language model. However, existing two-stream methods require passing a great number of (up to a hundred) image crops into the visual-language model, which is highly inefficient. To address the problem, we propose a network that only needs a single pass through the visual-language model for each input image. Specifically, we first propose a novel network adaptation approach, termed patch severance, to restrict the harmful interference between the patch embeddings in the pre-trained visual encoder. We then propose classification anchor learning to encourage the network to spatially focus on more discriminative features for classification. Extensive experiments demonstrate that the proposed method achieves outstanding performance, surpassing state-of-the-art methods while being 4 to 7 times faster at inference. Code: https://github.com/CongHan0808/DeOP.git

Jinlong Li, Zequn Jie, Xu Wang et al.

Most of the existing semantic segmentation approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel "Progressive Patch Learning" approach is proposed to improve the local details extraction of the classification, producing the CAM better covering the whole object rather than only the most discriminative regions as in CAMs obtained in conventional classification models. "Patch Learning" destructs the feature maps into patches and independently processes each local patch in parallel before the final aggregation. Such a mechanism enforces the network to find weak information from the scattered discriminative local parts, achieving enhanced local details sensitivity. "Progressive Patch Learning" further extends the feature destruction and patch learning to multi-level granularities in a progressive manner. Cooperating with a multi-stage optimization strategy, such a "Progressive Patch Learning" mechanism implicitly provides the model with the feature extraction ability across different locality-granularities. As an alternative to the implicit multi-granularity progressive fusion approach, we additionally propose an explicit method to simultaneously fuse features from different granularities in a single model, further enhancing the CAM quality on the full object coverage. Our proposed method achieves outstanding performance on the PASCAL VOC 2012 dataset e.g., with 69.6$% mIoU on the test set), which surpasses most existing weakly supervised semantic segmentation methods. Code will be made publicly available here https://github.com/TyroneLi/PPL_WSSS.

Anthony Cioppa, Silvio Giancola, Vladimir Somers et al. · pku

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.

Hao Wang, Pengzhen Ren, Zequn Jie et al.

Open-vocabulary detection is a challenging task due to the requirement of detecting objects based on class names, including those not encountered during training. Existing methods have shown strong zero-shot detection capabilities through pre-training and pseudo-labeling on diverse large-scale datasets. However, these approaches encounter two main challenges: (i) how to effectively eliminate data noise from pseudo-labeling, and (ii) how to efficiently leverage the language-aware capability for region-level cross-modality fusion and alignment. To address these challenges, we propose a novel unified open-vocabulary detection method called OV-DINO, which is pre-trained on diverse large-scale datasets with language-aware selective fusion in a unified framework. Specifically, we introduce a Unified Data Integration (UniDI) pipeline to enable end-to-end training and eliminate noise from pseudo-label generation by unifying different data sources into detection-centric data format. In addition, we propose a Language-Aware Selective Fusion (LASF) module to enhance the cross-modality alignment through a language-aware query selection and fusion process. We evaluate the performance of the proposed OV-DINO on popular open-vocabulary detection benchmarks, achieving state-of-the-art results with an AP of 50.6% on the COCO benchmark and 40.1% on the LVIS benchmark in a zero-shot manner, demonstrating its strong generalization ability. Furthermore, the fine-tuned OV-DINO on COCO achieves 58.4% AP, outperforming many existing methods with the same backbone. The code for OV-DINO is available at https://github.com/wanghao9610/OV-DINO.

Xiao Zhou, Yujie Zhong, Zhen Cheng et al.

Object re-identification (ReID) aims to find instances with the same identity as the given probe from a large gallery. Pairwise losses play an important role in training a strong ReID network. Existing pairwise losses densely exploit each instance as an anchor and sample its triplets in a mini-batch. This dense sampling mechanism inevitably introduces positive pairs that share few visual similarities, which can be harmful to the training. To address this problem, we propose a novel loss paradigm termed Sparse Pairwise (SP) loss that only leverages few appropriate pairs for each class in a mini-batch, and empirically demonstrate that it is sufficient for the ReID tasks. Based on the proposed loss framework, we propose an adaptive positive mining strategy that can dynamically adapt to diverse intra-class variations. Extensive experiments show that SP loss and its adaptive variant AdaSP loss outperform other pairwise losses, and achieve state-of-the-art performance across several ReID benchmarks. Code is available at https://github.com/Astaxanthin/AdaSP.

Jiaming Chen, Weixin Luo, Ran Song et al.

This paper presents a novel hierarchical alignment model (HAM) that learns multi-granularity visual and linguistic representations in an end-to-end manner. We extract key points and proposal points to model 3D contexts and instances, and propose point-language alignment with context modulation (PLACM) mechanism, which learns to gradually align word-level and sentence-level linguistic embeddings with visual representations, while the modulation with the visual context captures latent informative relationships. To further capture both global and local relationships, we propose a spatially multi-granular modeling scheme that applies PLACM to both global and local fields. Experimental results demonstrate the superiority of HAM, with visualized results showing that it can dynamically model fine-grained visual and linguistic representations. HAM outperforms existing methods by a significant margin and achieves state-of-the-art performance on two publicly available datasets, and won the championship in ECCV 2022 ScanRefer challenge. Code is available at~\url{https://github.com/PPjmchen/HAM}.

Lin Ma, Jiangtao Gong, Hao Xu et al.

Assembly sequence planning (ASP) is the essential process for modern manufacturing, proven to be NP-complete thus its effective and efficient solution has been a challenge for researchers in the field. In this paper, we present a graph-transformer based framework for the ASP problem which is trained and demonstrated on a self-collected ASP database. The ASP database contains a self-collected set of LEGO models. The LEGO model is abstracted to a heterogeneous graph structure after a thorough analysis of the original structure and feature extraction. The ground truth assembly sequence is first generated by brute-force search and then adjusted manually to in line with human rational habits. Based on this self-collected ASP dataset, we propose a heterogeneous graph-transformer framework to learn the latent rules for assembly planning. We evaluated the proposed framework in a series of experiment. The results show that the similarity of the predicted and ground truth sequences can reach 0.44, a medium correlation measured by Kendall's $τ$. Meanwhile, we compared the different effects of node features and edge features and generated a feasible and reasonable assembly sequence as a benchmark for further research. Our data set and code is available on https://github.com/AIR-DISCOVER/ICRA\_ASP.

Silvio Giancola, Anthony Cioppa, Adrien Deliège et al.

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on detecting line and goal part elements, (4) camera calibration, dedicated to retrieving the intrinsic and extrinsic camera parameters, (5) player re-identification, focusing on retrieving the same players across multiple views, and (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams. Compared to last year's challenges, tasks (1-2) had their evaluation metrics redefined to consider tighter temporal accuracies, and tasks (3-6) were novel, including their underlying data and annotations. More information on the tasks, challenges and leaderboards are available on https://www.soccer-net.org. Baselines and development kits are available on https://github.com/SoccerNet.

Zhangkai Ni, Wenhan Yang, Hanli Wang et al.

Getting rid of the fundamental limitations in fitting to the paired training data, recent unsupervised low-light enhancement methods excel in adjusting illumination and contrast of images. However, for unsupervised low light enhancement, the remaining noise suppression issue due to the lacking of supervision of detailed signal largely impedes the wide deployment of these methods in real-world applications. Herein, we propose a novel Cycle-Interactive Generative Adversarial Network (CIGAN) for unsupervised low-light image enhancement, which is capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals between two domains, e.g., suppressing/synthesizing realistic noise in the cyclic enhancement/degradation process. In particular, the proposed low-light guided transformation feed-forwards the features of low-light images from the generator of enhancement GAN (eGAN) into the generator of degradation GAN (dGAN). With the learned information of real low-light images, dGAN can synthesize more realistic diverse illumination and contrast in low-light images. Moreover, the feature randomized perturbation module in dGAN learns to increase the feature randomness to produce diverse feature distributions, persuading the synthesized low-light images to contain realistic noise. Extensive experiments demonstrate both the superiority of the proposed method and the effectiveness of each module in CIGAN.

Qian Yang, Yunxin Li, Baotian Hu et al. · mila

Visual Entailment with natural language explanations aims to infer the relationship between a text-image pair and generate a sentence to explain the decision-making process. Previous methods rely mainly on a pre-trained vision-language model to perform the relation inference and a language model to generate the corresponding explanation. However, the pre-trained vision-language models mainly build token-level alignment between text and image yet ignore the high-level semantic alignment between the phrases (chunks) and visual contents, which is critical for vision-language reasoning. Moreover, the explanation generator based only on the encoded joint representation does not explicitly consider the critical decision-making points of relation inference. Thus the generated explanations are less faithful to visual-language reasoning. To mitigate these problems, we propose a unified Chunk-aware Alignment and Lexical Constraint based method, dubbed as CALeC. It contains a Chunk-aware Semantic Interactor (arr. CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr. LeCG). Specifically, CSI exploits the sentence structure inherent in language and various image regions to build chunk-aware semantic alignment. Relation inferrer uses an attention-based reasoning network to incorporate the token-level and chunk-level vision-language representations. LeCG utilizes lexical constraints to expressly incorporate the words or chunks focused by the relation inferrer into explanation generation, improving the faithfulness and informativeness of the explanations. We conduct extensive experiments on three datasets, and experimental results indicate that CALeC significantly outperforms other competitor models on inference accuracy and quality of generated explanations.

Chengjian Feng, Zequn Jie, Yujie Zhong et al.

Recent LSS-based multi-view 3D object detection has made tremendous progress, by processing the features in Brid-Eye-View (BEV) via the convolutional detector. However, the typical convolution ignores the radial symmetry of the BEV features and increases the difficulty of the detector optimization. To preserve the inherent property of the BEV features and ease the optimization, we propose an azimuth-equivariant convolution (AeConv) and an azimuth-equivariant anchor. The sampling grid of AeConv is always in the radial direction, thus it can learn azimuth-invariant BEV features. The proposed anchor enables the detection head to learn predicting azimuth-irrelevant targets. In addition, we introduce a camera-decoupled virtual depth to unify the depth prediction for the images with different camera intrinsic parameters. The resultant detector is dubbed Azimuth-equivariant Detector (AeDet). Extensive experiments are conducted on nuScenes, and AeDet achieves a 62.0% NDS, surpassing the recent multi-view 3D object detectors such as PETRv2 and BEVDepth by a large margin. Project page: https://fcjian.github.io/aedet.

Liming Zheng, Feng Yan, Fanfan Liu et al.

Foundation models hold significant potential for enabling robots to perform long-horizon general manipulation tasks. However, the simplicity of tasks and the uniformity of environments in existing benchmarks restrict their effective deployment in complex scenarios. To address this limitation, this paper introduces the \textit{RoboCAS} benchmark, the first benchmark specifically designed for complex object arrangement scenarios in robotic manipulation. This benchmark employs flexible and concise scripted policies to efficiently collect a diverse array of demonstrations, showcasing scattered, orderly, and stacked object arrangements within a highly realistic physical simulation environment. It includes complex processes such as target retrieval, obstacle clearance, and robot manipulation, testing agents' abilities to perform long-horizon planning for spatial reasoning and predicting chain reactions under ambiguous instructions. Extensive experiments on multiple baseline models reveal their limitations in managing complex object arrangement scenarios, underscoring the urgent need for intelligent agents capable of performing long-horizon operations in practical deployments and providing valuable insights for future research directions. Project website: \url{https://github.com/notFoundThisPerson/RoboCAS-v0}.

Jiaming Li, Zhijia Liang, Weikai Chen et al.

Fine-grained open-vocabulary object detection (FG-OVD) aims to detect novel object categories described by attribute-rich texts. While existing open-vocabulary detectors show promise at the base-category level, they underperform in fine-grained settings due to the semantic entanglement of subjects and attributes in pretrained vision-language model (VLM) embeddings -- leading to over-representation of attributes, mislocalization, and semantic drift in embedding space. We propose GUIDED, a decomposition framework specifically designed to address the semantic entanglement between subjects and attributes in fine-grained prompts. By separating object localization and fine-grained recognition into distinct pathways, HUIDED aligns each subtask with the module best suited for its respective roles. Specifically, given a fine-grained class name, we first use a language model to extract a coarse-grained subject and its descriptive attributes. Then the detector is guided solely by the subject embedding, ensuring stable localization unaffected by irrelevant or overrepresented attributes. To selectively retain helpful attributes, we introduce an attribute embedding fusion module that incorporates attribute information into detection queries in an attention-based manner. This mitigates over-representation while preserving discriminative power. Finally, a region-level attribute discrimination module compares each detected region against full fine-grained class names using a refined vision-language model with a projection head for improved alignment. Extensive experiments on FG-OVD and 3F-OVD benchmarks show that GUIDED achieves new state-of-the-art results, demonstrating the benefits of disentangled modeling and modular optimization. Our code will be released at https://github.com/lijm48/GUIDED.

Xiaohan Lan, Yitian Yuan, Xin Wang et al.

Temporal Sentence Grounding in Videos (TSGV), which aims to ground a natural language sentence in an untrimmed video, has drawn widespread attention over the past few years. However, recent studies have found that current benchmark datasets may have obvious moment annotation biases, enabling several simple baselines even without training to achieve SOTA performance. In this paper, we take a closer look at existing evaluation protocols, and find both the prevailing dataset and evaluation metrics are the devils that lead to untrustworthy benchmarking. Therefore, we propose to re-organize the two widely-used datasets, making the ground-truth moment distributions different in the training and test splits, i.e., out-of-distribution (OOD) test. Meanwhile, we introduce a new evaluation metric "dR@n,IoU@m" that discounts the basic recall scores to alleviate the inflating evaluation caused by biased datasets. New benchmarking results indicate that our proposed evaluation protocols can better monitor the research progress. Furthermore, we propose a novel causality-based Multi-branch Deconfounding Debiasing (MDD) framework for unbiased moment prediction. Specifically, we design a multi-branch deconfounder to eliminate the effects caused by multiple confounders with causal intervention. In order to help the model better align the semantics between sentence queries and video moments, we enhance the representations during feature encoding. Specifically, for textual information, the query is parsed into several verb-centered phrases to obtain a more fine-grained textual feature. For visual information, the positional information has been decomposed from moment features to enhance representations of moments with diverse locations. Extensive experiments demonstrate that our proposed approach can achieve competitive results among existing SOTA approaches and outperform the base model with great gains.

Wenbo Hu, Yuling Wang, Lin Ma et al.

Despite the tremendous progress in neural radiance fields (NeRF), we still face a dilemma of the trade-off between quality and efficiency, e.g., MipNeRF presents fine-detailed and anti-aliased renderings but takes days for training, while Instant-ngp can accomplish the reconstruction in a few minutes but suffers from blurring or aliasing when rendering at various distances or resolutions due to ignoring the sampling area. To this end, we propose a novel Tri-Mip encoding that enables both instant reconstruction and anti-aliased high-fidelity rendering for neural radiance fields. The key is to factorize the pre-filtered 3D feature spaces in three orthogonal mipmaps. In this way, we can efficiently perform 3D area sampling by taking advantage of 2D pre-filtered feature maps, which significantly elevates the rendering quality without sacrificing efficiency. To cope with the novel Tri-Mip representation, we propose a cone-casting rendering technique to efficiently sample anti-aliased 3D features with the Tri-Mip encoding considering both pixel imaging and observing distance. Extensive experiments on both synthetic and real-world datasets demonstrate our method achieves state-of-the-art rendering quality and reconstruction speed while maintaining a compact representation that reduces 25% model size compared against Instant-ngp.

Shuqiang Cao, Weixin Luo, Bairui Wang et al.

Recently, there has been a growing trend toward feature-based approaches for Online Action Detection (OAD). However, these approaches have limitations due to their fixed backbone design, which ignores the potential capability of a trainable backbone. In this paper, we propose the first end-to-end OAD model, termed E2E-LOAD, designed to address the major challenge of OAD, namely, long-term understanding and efficient online reasoning. Specifically, our proposed approach adopts an initial spatial model that is shared by all frames and maintains a long sequence cache for inference at a low computational cost. We also advocate an asymmetric spatial-temporal model for long-form and short-form modeling effectively. Furthermore, we propose a novel and efficient inference mechanism that accelerates heavy spatial-temporal exploration. Extensive ablation studies and experiments demonstrate the effectiveness and efficiency of our proposed method. Notably, we achieve 17.3 (+12.6) FPS for end-to-end OAD with 72.4%~(+1.2%), 90.3%~(+0.7%), and 48.1%~(+26.0%) mAP on THMOUS14, TVSeries, and HDD, respectively, which is 3x faster than previous approaches. The source code will be made publicly available.

Yang Jiao, Zequn Jie, Jingjing Chen et al.

Recently, one-stage visual grounders attract high attention due to their comparable accuracy but significantly higher efficiency than two-stage grounders. However, inter-object relation modeling has not been well studied for one-stage grounders. Inter-object relationship modeling, though important, is not necessarily performed among all objects, as only part of them are related to the text query and may confuse the model. We call these objects suspected objects. However, exploring their relationships in the one-stage paradigm is non-trivial because: First, no object proposals are available as the basis on which to select suspected objects and perform relationship modeling. Second, suspected objects are more confusing than others, as they may share similar semantics, be entangled with certain relationships, etc, and thereby more easily mislead the model prediction. Toward this end, we propose a Suspected Object Transformation mechanism (SOT), which can be seamlessly integrated into existing CNN and Transformer-based one-stage visual grounders to encourage the target object selection among the suspected ones. Suspected objects are dynamically discovered from a learned activation map adapted to the model current discrimination ability during training. Afterward, on top of suspected objects, a Keyword-Aware Discrimination module (KAD) and an Exploration by Random Connection strategy (ERC) are concurrently proposed to help the model rethink its initial prediction. On the one hand, KAD leverages keywords contributing high to suspected object discrimination. On the other hand, ERC allows the model to seek the correct object instead of being trapped in a situation that always exploits the current false prediction. Extensive experiments demonstrate the effectiveness of our proposed method.

Xiaoxu Xu, Yitian Yuan, Jinlong Li et al.

In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3D Semantic Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model predicts dense-embedding for each point which is co-embedded with both the aligned image and text spaces from the 2D vision-language model. Specifically, our method exploits the superior generalization ability of the 2D vision-language models and proposes the Embeddings Soft-Guidance Stage to utilize it to implicitly align 3D embeddings and text embeddings. Moreover, we introduce the Embeddings Specialization Stage to purify the feature representation with the help of a given scene-level label, specifying a better feature supervised by the corresponding text embedding. Thus, the 3D model is able to gain informative supervisions both from the image embedding and text embedding, leading to competitive segmentation performances. To the best of our knowledge, this is the first work to investigate 3D weakly supervised semantic segmentation by using the textual semantic information of text category labels. Moreover, with extensive quantitative and qualitative experiments, we present that our 3DSS-VLG is able not only to achieve the state-of-the-art performance on both S3DIS and ScanNet datasets, but also to maintain strong generalization capability.

Shaoxiang Chen, Zequn Jie, Xiaolin Wei et al.

In this technical report, we introduce our submission to the Waymo 3D Detection leaderboard. Our network is based on the Centerpoint architecture, but with significant improvements. We design a 2D backbone to utilize multi-scale features for better detecting objects with various sizes, together with an optimal transport-based target assignment strategy, which dynamically assigns richer supervision signals to the detection candidates. We also apply test-time augmentation and model-ensemble for further improvements. Our submission currently ranks 4th place with 78.45 mAPH on the Waymo 3D Detection leaderboard.

Yufeng Zhong, Lei Chen, Xuanle Zhao et al.

The development of large vision language models drives the demand for managing, and applying massive amounts of multimodal data, making OCR technology, which extracts information from visual images, increasingly popular. However, existing OCR methods primarily focus on recognizing text elements from images or scanned documents (Text-centric OCR), neglecting the identification of visual elements from visually information-dense image sources (Vision-centric OCR), such as charts, web pages and science plots. In reality, these visually information-dense images are widespread on the internet and have significant real-world application value, such as data visualization and web page analysis. In this technical report, we propose OCRVerse, the first holistic OCR method in end-to-end manner that enables unified text-centric OCR and vision-centric OCR. To this end, we constructe comprehensive data engineering to cover a wide range of text-centric documents, such as newspapers, magazines and books, as well as vision-centric rendered composites, including charts, web pages and scientific plots. Moreover, we propose a two-stage SFT-RL multi-domain training method for OCRVerse. SFT directly mixes cross-domain data to train and establish initial domain knowledge, while RL focuses on designing personalized reward strategies for the characteristics of each domain. Specifically, since different domains require various output formats and expected outputs, we provide sufficient flexibility in the RL stage to customize flexible reward signals for each domain, thereby improving cross-domain fusion and avoiding data conflicts. Experimental results demonstrate the effectiveness of OCRVerse, achieving competitive results across text-centric and vision-centric data types, even comparable to large-scale open-source and closed-source models.

Xuexun Liu, Xiaoxu Xu, Qiudan Zhang et al.

Weakly supervised 3D instance segmentation is essential for 3D scene understanding, especially as the growing scale of data and high annotation costs associated with fully supervised approaches. Existing methods primarily rely on two forms of weak supervision: one-thing-one-click annotations and bounding box annotations, both of which aim to reduce labeling efforts. However, these approaches still encounter limitations, including labor-intensive annotation processes, high complexity, and reliance on expert annotators. To address these challenges, we propose \textbf{DBGroup}, a two-stage weakly supervised 3D instance segmentation framework that leverages scene-level annotations as a more efficient and scalable alternative. In the first stage, we introduce a Dual-Branch Point Grouping module to generate pseudo labels guided by semantic and mask cues extracted from multi-view images. To further improve label quality, we develop two refinement strategies: Granularity-Aware Instance Merging and Semantic Selection and Propagation. The second stage involves multi-round self-training on an end-to-end instance segmentation network using the refined pseudo-labels. Additionally, we introduce an Instance Mask Filter strategy to address inconsistencies within the pseudo labels. Extensive experiments demonstrate that DBGroup achieves competitive performance compared to sparse-point-level supervised 3D instance segmentation methods, while surpassing state-of-the-art scene-level supervised 3D semantic segmentation approaches. Code is available at https://github.com/liuxuexun/DBGroup.

Jiaqi Chen, Bingqian Lin, Xinmin Liu et al.

LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) task. However, existing LLM-based methods often focus only on solving high-level task planning by selecting nodes in predefined navigation graphs for movements, overlooking low-level control in navigation scenarios. To bridge this gap, we propose AO-Planner, a novel Affordances-Oriented Planner for continuous VLN task. Our AO-Planner integrates various foundation models to achieve affordances-oriented low-level motion planning and high-level decision-making, both performed in a zero-shot setting. Specifically, we employ a Visual Affordances Prompting (VAP) approach, where the visible ground is segmented by SAM to provide navigational affordances, based on which the LLM selects potential candidate waypoints and plans low-level paths towards selected waypoints. We further propose a high-level PathAgent which marks planned paths into the image input and reasons the most probable path by comprehending all environmental information. Finally, we convert the selected path into 3D coordinates using camera intrinsic parameters and depth information, avoiding challenging 3D predictions for LLMs. Experiments on the challenging R2R-CE and RxR-CE datasets show that AO-Planner achieves state-of-the-art zero-shot performance (8.8% improvement on SPL). Our method can also serve as a data annotator to obtain pseudo-labels, distilling its waypoint prediction ability into a learning-based predictor. This new predictor does not require any waypoint data from the simulator and achieves 47% SR competing with supervised methods. We establish an effective connection between LLM and 3D world, presenting novel prospects for employing foundation models in low-level motion control.

Xuanle Zhao, Deyang Jiang, Zhixiong Zeng et al.

Multimodal code generation has garnered significant interest within the research community. Despite the notable success of recent vision-language models (VLMs) on specialized tasks like Chart-to-code generation, their reliance on single-task training regimens fosters a narrow paradigm that hinders the development of generalized \textbf{VI}sio\textbf{N} \textbf{C}ode \textbf{I}ntelligence. In this work, we introduce \textbf{VinciCoder}, a unified multimodal code generation model that addresses this limitation via a two-stage training framework. We begin by constructing a large-scale Supervised Finetuning (SFT) corpus comprising 1.6M image-code pairs for tasks involving direct code generation and visual-based code refinement. Subsequently, we introduce a Visual Reinforcement Learning (ViRL) strategy, which employs a coarse-to-fine reward mechanism to improve visual fidelity by calculating visual similarity across local and global image patches. Extensive experiments on various multimodal code generation benchmarks demonstrate that VinciCoder achieves state-of-the-art performance, underscoring the effectiveness of our coarse-to-fine ViRL strategy. The code and model will be available at https://github.com/DocTron-hub/VinciCoder.

Feng Yan, Zhiheng Li, Weixin Luo et al.

This is a brief technical report of our proposed method for Multiple-Object Tracking (MOT) Challenge in Complex Environments. In this paper, we treat the MOT task as a two-stage task including human detection and trajectory matching. Specifically, we designed an improved human detector and associated most of detection to guarantee the integrity of the motion trajectory. We also propose a location-wise matching matrix to obtain more accurate trace matching. Without any model merging, our method achieves 66.672 HOTA and 93.971 MOTA on the DanceTrack challenge dataset.

Shuqiang Cao, Weixin Luo, Bairui Wang et al.

Online action detection aims at the accurate action prediction of the current frame based on long historical observations. Meanwhile, it demands real-time inference on online streaming videos. In this paper, we advocate a novel and efficient principle for online action detection. It merely updates the latest and oldest historical representations in one window but reuses the intermediate ones, which have been already computed. Based on this principle, we introduce a window-based cascade Transformer with a circular historical queue, where it conducts multi-stage attentions and cascade refinement on each window. We also explore the association between online action detection and its counterpart offline action segmentation as an auxiliary task. We find that such an extra supervision helps discriminative history clustering and acts as feature augmentation for better training the classifier and cascade refinement. Our proposed method achieves the state-of-the-art performances on three challenging datasets THUMOS'14, TVSeries, and HDD. Codes will be available after acceptance.

Mahdieh Kazemimoghadam, Zi Yang, Lin Ma et al.

Deep learning (DL) models for medical image segmentation are highly influenced by intensity variations of input images and lack generalization due to primarily utilizing pixels' intensity information for inference. Acquiring sufficient training data is another challenge limiting models' applications. We proposed to leverage the consistency of organs' anatomical shape and position information in medical images. We introduced a framework leveraging recurring anatomical patterns through global binary masks for organ segmentation. Two scenarios were studied.1) Global binary masks were the only model's (i.e. U-Net) input, forcing exclusively encoding organs' position and shape information for segmentation/localization.2) Global binary masks were incorporated as an additional channel functioning as position/shape clues to mitigate training data scarcity. Two datasets of the brain and heart CT images with their ground-truth were split into (26:10:10) and (12:3:5) for training, validation, and test respectively. Training exclusively on global binary masks led to Dice scores of 0.77(0.06) and 0.85(0.04), with the average Euclidian distance of 3.12(1.43)mm and 2.5(0.93)mm relative to the center of mass of the ground truth for the brain and heart structures respectively. The outcomes indicate that a surprising degree of position and shape information is encoded through global binary masks. Incorporating global binary masks led to significantly higher accuracy relative to the model trained on only CT images in small subsets of training data; the performance improved by 4.3-125.3% and 1.3-48.1% for 1-8 training cases of the brain and heart datasets respectively. The findings imply the advantages of utilizing global binary masks for building generalizable models and to compensate for training data scarcity.

Zixu Wang, Yujie Zhong, Yishu Miao et al.

Despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck in the area. Most video-language models are trained via pair-level loss to predict whether a pair of video and text is aligned. However, even in paired video-text segments, only a subset of the frames are semantically relevant to the corresponding text, with the remainder representing noise; where the ratio of noisy frames is higher for longer videos. We propose FineCo (Fine-grained Contrastive Loss for Frame Sampling), an approach to better learn video and language representations with a fine-grained contrastive objective operating on video frames. It helps distil a video by selecting the frames that are semantically equivalent to the text, improving cross-modal correspondence. Building on the well established VideoCLIP model as a starting point, FineCo achieves state-of-the-art performance on YouCookII, a text-video retrieval benchmark with long videos. FineCo also achieves competitive results on text-video retrieval (MSR-VTT), and video question answering datasets (MSR-VTT QA and MSR-VTT MC) with shorter videos.

Zhijian Huang, Tao Tang, Shaoxiang Chen et al.

Data-driven approaches for autonomous driving (AD) have been widely adopted in the past decade but are confronted with dataset bias and uninterpretability. Inspired by the knowledge-driven nature of human driving, recent approaches explore the potential of large language models (LLMs) to improve understanding and decision-making in traffic scenarios. They find that the pretrain-finetune paradigm of LLMs on downstream data with the Chain-of-Thought (CoT) reasoning process can enhance explainability and scene understanding. However, such a popular strategy proves to suffer from the notorious problems of misalignment between the crafted CoTs against the consequent decision-making, which remains untouched by previous LLM-based AD methods. To address this problem, we motivate an end-to-end decision-making model based on multimodality-augmented LLM, which simultaneously executes CoT reasoning and carries out planning results. Furthermore, we propose a reasoning-decision alignment constraint between the paired CoTs and planning results, imposing the correspondence between reasoning and decision-making. Moreover, we redesign the CoTs to enable the model to comprehend complex scenarios and enhance decision-making performance. We dub our proposed large language planners with reasoning-decision alignment as RDA-Driver. Experimental evaluations on the nuScenes and DriveLM-nuScenes benchmarks demonstrate the effectiveness of our RDA-Driver in enhancing the performance of end-to-end AD systems. Specifically, our RDA-Driver achieves state-of-the-art planning performance on the nuScenes dataset with 0.80 L2 error and 0.32 collision rate, and also achieves leading results on challenging DriveLM-nuScenes benchmarks with 0.82 L2 error and 0.38 collision rate.

Dengjie Li, Siyu Chen, Yujie Zhong et al.

In person re-identification (ReID) tasks, many works explore the learning of part features to improve the performance over global image features. Existing methods explicitly extract part features by either using a hand-designed image division or keypoints obtained with external visual systems. In this work, we propose to learn Discriminative implicit Parts (DiPs) which are decoupled from explicit body parts. Therefore, DiPs can learn to extract any discriminative features that can benefit in distinguishing identities, which is beyond predefined body parts (such as accessories). Moreover, we propose a novel implicit position to give a geometric interpretation for each DiP. The implicit position can also serve as a learning signal to encourage DiPs to be more position-equivariant with the identity in the image. Lastly, an additional DiP weighting is introduced to handle the invisible or occluded situation and further improve the feature representation of DiPs. Extensive experiments show that the proposed method achieves state-of-the-art performance on multiple person ReID benchmarks.

Bangbang Yang, Wenqi Dong, Lin Ma et al.

Diffusion-based methods have achieved prominent success in generating 2D media. However, accomplishing similar proficiencies for scene-level mesh texturing in 3D spatial applications, e.g., XR/VR, remains constrained, primarily due to the intricate nature of 3D geometry and the necessity for immersive free-viewpoint rendering. In this paper, we propose a novel indoor scene texturing framework, which delivers text-driven texture generation with enchanting details and authentic spatial coherence. The key insight is to first imagine a stylized 360° panoramic texture from the central viewpoint of the scene, and then propagate it to the rest areas with inpainting and imitating techniques. To ensure meaningful and aligned textures to the scene, we develop a novel coarse-to-fine panoramic texture generation approach with dual texture alignment, which both considers the geometry and texture cues of the captured scenes. To survive from cluttered geometries during texture propagation, we design a separated strategy, which conducts texture inpainting in confidential regions and then learns an implicit imitating network to synthesize textures in occluded and tiny structural areas. Extensive experiments and the immersive VR application on real-world indoor scenes demonstrate the high quality of the generated textures and the engaging experience on VR headsets. Project webpage: https://ybbbbt.com/publication/dreamspace

Yufeng Zhong, Long Xu, Jiebo Luo et al.

3D dense captioning, as an emerging vision-language task, aims to identify and locate each object from a set of point clouds and generate a distinctive natural language sentence for describing each located object. However, the existing methods mainly focus on mining inter-object relationship, while ignoring contextual information, especially the non-object details and background environment within the point clouds, thus leading to low-quality descriptions, such as inaccurate relative position information. In this paper, we make the first attempt to utilize the point clouds clustering features as the contextual information to supply the non-object details and background environment of the point clouds and incorporate them into the 3D dense captioning task. We propose two separate modules, namely the Global Context Modeling (GCM) and Local Context Modeling (LCM), in a coarse-to-fine manner to perform the contextual modeling of the point clouds. Specifically, the GCM module captures the inter-object relationship among all objects with global contextual information to obtain more complete scene information of the whole point clouds. The LCM module exploits the influence of the neighboring objects of the target object and local contextual information to enrich the object representations. With such global and local contextual modeling strategies, our proposed model can effectively characterize the object representations and contextual information and thereby generate comprehensive and detailed descriptions of the located objects. Extensive experiments on the ScanRefer and Nr3D datasets demonstrate that our proposed method sets a new record on the 3D dense captioning task, and verify the effectiveness of our raised contextual modeling of point clouds.

Lin Ma, Longrui Chen, Yan Zhang et al.

Pedestrians' safety is a crucial factor in assessing autonomous driving scenarios. However, pedestrian safety evaluation is rarely considered by existing autonomous driving simulation platforms. This paper proposes a pedestrian safety evaluation method for autonomous driving, in which not only the collision events but also the conflict events together with the characteristics of pedestrians are fully considered. Moreover, to apply the pedestrian safety evaluation system, we construct a high-fidelity simulation framework embedded with pedestrian safety-critical characteristics. We demonstrate our simulation framework and pedestrian safety evaluation with a comparative experiment with two kinds of autonomous driving perception algorithms -- single-vehicle perception and vehicle-to-infrastructure (V2I) cooperative perception. The results show that our framework can evaluate different autonomous driving algorithms with detailed and quantitative pedestrian safety indexes. To this end, the proposed simulation method and framework can be used to access different autonomous driving algorithms and evaluate pedestrians' safety performance in future autonomous driving simulations, which can inspire more pedestrian-friendly autonomous driving algorithms.

Siqi Yang, Zilve Gao, Haibo Qiu et al.

Multimodal Large Language Models (MLLMs) demonstrate significant potential but remain brittle in complex, long-chain visual reasoning tasks. A critical failure mode is "visual forgetting", where models progressively lose visual grounding as reasoning extends, a phenomenon aptly described as "think longer, see less". We posit this failure stems from current training paradigms prematurely entangling two distinct cognitive skills: (1) abstract logical reasoning "how-to-think") and (2) strategic visual perception ("when-to-look"). This creates a foundational cold-start deficiency -- weakening abstract reasoning -- and a strategic perception deficit, as models lack a policy for when to perceive. In this paper, we propose a novel curriculum-based framework to disentangle these skills. First, we introduce a disentangled Supervised Fine-Tuning (SFT) curriculum that builds a robust abstract reasoning backbone on text-only data before anchoring it to vision with a novel Perception-Grounded Chain-of-Thought (PG-CoT) paradigm. Second, we resolve the strategic perception deficit by formulating timing as a reinforcement learning problem. We design a Pivotal Perception Reward that teaches the model when to look by coupling perceptual actions to linguistic markers of cognitive uncertainty (e.g., "wait", "verify"), thereby learning an autonomous grounding policy. Our contributions include the formalization of these two deficiencies and the development of a principled, two-stage framework to address them, transforming the model from a heuristic-driven observer to a strategic, grounded reasoner. \textbf{Code}: \url{https://github.com/gaozilve-max/learning-when-to-look}.

Jinwu Chen, Qidie Wu, Bin Li et al.

Optimizing CUDA kernels is a challenging and labor-intensive task, given the need for hardware-software co-design expertise and the proprietary nature of high-performance kernel libraries. While recent large language models (LLMs) combined with evolutionary algorithms show promise in automatic kernel optimization, existing approaches often fall short in performance due to their suboptimal agent designs and mismatched evolution representations. This work identifies these mismatches and proposes cuPilot, a strategy-coordinated multi-agent framework that introduces strategy as an intermediate semantic representation for kernel evolution. Key contributions include a strategy-coordinated evolution algorithm, roofline-guided prompting, and strategy-level population initialization. Experimental results show that the generated kernels by cuPilot achieve an average speed up of 3.09$\times$ over PyTorch on a benchmark of 100 kernels. On the GEMM tasks, cuPilot showcases sophisticated optimizations and achieves high utilization of critical hardware units. The generated kernels are open-sourced at https://github.com/champloo2878/cuPilot-Kernels.git.

Lin Ma, Conan Liu, Tiefeng Ma et al.

Clustering methods are being applied to a wider range of scenarios involving more complex datasets, where the shapes of clusters tend to be arbitrary. In this paper, we propose a novel Path-based Valley-seeking clustering algorithm for arbitrarily shaped clusters. This work aims to seek the valleys among clusters and then individually extract clusters. Three vital techniques are used in this algorithm. First, path distance (minmax distance) is employed to transform the irregular boundaries among clusters, that is density valleys, into perfect spherical shells. Second, a suitable density measurement, $k$-distance, is employed to make adjustment on Minimum Spanning Tree, by which a robust minmax distance is calculated. Third, we seek the transformed density valleys by determining their centers and radius. First, the clusters are wrapped in spherical shells after the distance transformation, making the extraction process efficient even with clusters of arbitrary shape. Second, adjusted Minimum Spanning Tree enhances the robustness of minmax distance under different kinds of noise. Last, the number of clusters does not need to be inputted or decided manually due to the individual extraction process. After applying the proposed algorithm to several commonly used synthetic datasets, the results indicate that the Path-based Valley-seeking algorithm is accurate and efficient. The algorithm is based on the dissimilarity of objects, so it can be applied to a wide range of fields. Its performance on real-world datasets illustrates its versatility.

Yunxin Li, Shenyuan Jiang, Baotian Hu et al.

Recent advancements in Multimodal Large Language Models (MLLMs) underscore the significance of scalable models and data to boost performance, yet this often incurs substantial computational costs. Although the Mixture of Experts (MoE) architecture has been employed to efficiently scale large language and image-text models, these efforts typically involve fewer experts and limited modalities. To address this, our work presents the pioneering attempt to develop a unified MLLM with the MoE architecture, named Uni-MoE that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We also implement a sparse MoE architecture within the LLMs to enable efficient training and inference through modality-level data parallelism and expert-level model parallelism. To enhance the multi-expert collaboration and generalization, we present a progressive training strategy: 1) Cross-modality alignment using various connectors with different cross-modality data, 2) Training modality-specific experts with cross-modality instruction data to activate experts' preferences, and 3) Tuning the Uni-MoE framework utilizing Low-Rank Adaptation (LoRA) on mixed multimodal instruction data. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets. The extensive experimental results demonstrate Uni-MoE's principal advantage of significantly reducing performance bias in handling mixed multimodal datasets, alongside improved multi-expert collaboration and generalization. Our findings highlight the substantial potential of MoE frameworks in advancing MLLMs and the code is available at https://github.com/HITsz-TMG/UMOE-Scaling-Unified-Multimodal-LLMs.

Bin Liu, Xiaohong Liu, Qin Luo et al.

Pairwise learning underpins implicit collaborative filtering, yet its effectiveness is often hindered by sparse supervision, noisy interactions, and popularity-driven exposure bias. In this paper, we propose Variational Bayesian Personalized Ranking (VarBPR), a tractable variational framework for implicit-feedback pairwise learning that offers principled exposure controllability and theoretical interpretability. VarBPR reformulates pairwise learning as variational inference over discrete latent indexing variables, explicitly modeling noise and indexing uncertainty, and divides training into two stages: variational inference and variational learning. In the variational inference stage, we develop a variational formulation that integrates preference alignment, denoising, and popularity debiasing under a unified ELBO/regularization objective, deriving closed-form posteriors with clear control semantics: the prior encodes a target exposure pattern, while temperature/regularization strength controls posterior-prior adherence. As a result, exposure controllability becomes an endogenous and interpretable outcome of variational inference. In the variational learning stage, we propose a posterior-compression objective that reduces the ideal ELBO's computational complexity from polynomial to linear, with the approximation justified by an explicit Jensen-gap upper bound. Theoretically, we provide interpretable generalization guarantees by identifying a structural error component and revealing the opportunity cost of prioritizing certain exposure patterns (e.g., long-tail), offering a concrete analytical lens for designing controllable recommender systems. Empirically, We validate VarBPR across popular backbones; it demonstrates consistent gains in ranking accuracy, enables controlled long-tail exposure, and preserves the linear-time complexity of BPR.

Meituan LongCat Team, Bairui Wang, Bayan et al.

We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.

Lei Chen, Feng Yan, Yujie Zhong et al.

Multimodal Large Language Models (MLLM) have made significant progress in the field of document analysis. Despite this, existing benchmarks typically focus only on extracting text and simple layout information, neglecting the complex interactions between elements in structured documents such as mind maps and flowcharts. To address this issue, we introduce the new benchmark named MindBench, which not only includes meticulously constructed bilingual authentic or synthetic images, detailed annotations, evaluation metrics and baseline models, but also specifically designs five types of structured understanding and parsing tasks. These tasks include full parsing, partial parsing, position-related parsing, structured Visual Question Answering (VQA), and position-related VQA, covering key areas such as text recognition, spatial awareness, relationship discernment, and structured parsing. Extensive experimental results demonstrate the substantial potential and significant room for improvement in current models' ability to handle structured document information. We anticipate that the launch of MindBench will significantly advance research and application development in structured document analysis technology. MindBench is available at: https://miasanlei.github.io/MindBench.github.io/.

Benyamin Haghi, Lin Ma, Sahin Lale et al.

We present an integrated approach by combining analog computing and deep learning for electrocardiogram (ECG) arrhythmia classification. We propose EKGNet, a hardware-efficient and fully analog arrhythmia classification architecture that archives high accuracy with low power consumption. The proposed architecture leverages the energy efficiency of transistors operating in the subthreshold region, eliminating the need for analog-to-digital converters (ADC) and static random access memory (SRAM). The system design includes a novel analog sequential Multiply-Accumulate (MAC) circuit that mitigates process, supply voltage, and temperature variations. Experimental evaluations on PhysioNet's MIT-BIH and PTB Diagnostics datasets demonstrate the effectiveness of the proposed method, achieving average balanced accuracy of 95% and 94.25% for intra-patient arrhythmia classification and myocardial infarction (MI) classification, respectively. This innovative approach presents a promising avenue for developing low-power arrhythmia classification systems with enhanced accuracy and transferability in biomedical applications.

Jinlong Li, Dong Zhao, Zequn Jie et al.

Efficient fine-tuning of vision-language models (VLMs) like CLIP for specific downstream tasks is gaining significant attention. Previous works primarily focus on prompt learning to adapt the CLIP into a variety of downstream tasks, however, suffering from task overfitting when fine-tuned on a small data set. In this paper, we introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization, while a self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. Specifically, trainable orthogonal matrices are injected seamlessly into the transformer architecture and enforced with orthogonality constraint during the training, benefiting from the norm-preserving property and thus leading to stable and faster convergence, while keeping the pre-trained weights frozen. To alleviate deviation from fine-tuning, a self-regularization strategy is further employed to retain the generalization of the model during the training within a bypass manner. In addition, to enrich the sample diversity for downstream tasks under the small dataset scenario, we first explore attentive CutOut data augmentation to boost the efficient fine-tuning, leading to better model fitting capacity for specific downstream task. Then we support the theoretical analysis on how our approach improves the specific downstream performance and maintains the generalizability. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario on par with the elaborated prompt learning methods.

Tengjin Weng, Wenhao Jiang, Jingyi Wang et al.

Multimodal large language models (MLLMs) have achieved remarkable performance across a wide range of vision language tasks. However, their ability in low-level visual perception, particularly in detecting fine-grained visual discrepancies, remains underexplored and lacks systematic analysis. In this work, we introduce OddGridBench, a controllable benchmark for evaluating the visual discrepancy sensitivity of MLLMs. OddGridBench comprises over 1,400 grid-based images, where a single element differs from all others by one or multiple visual attributes such as color, size, rotation, or position. Experiments reveal that all evaluated MLLMs, including open-source families such as Qwen3-VL and InternVL3.5, and proprietary systems like Gemini-2.5-Pro and GPT-5, perform far below human levels in visual discrepancy detection. We further propose OddGrid-GRPO, a reinforcement learning framework that integrates curriculum learning and distance-aware reward. By progressively controlling the difficulty of training samples and incorporating spatial proximity constraints into the reward design, OddGrid-GRPO significantly enhances the model's fine-grained visual discrimination ability. We hope OddGridBench and OddGrid-GRPO will lay the groundwork for advancing perceptual grounding and visual discrepancy sensitivity in multimodal intelligence. Code and dataset are available at https://wwwtttjjj.github.io/OddGridBench/.

Cong Wei, Haoxian Tan, Yujie Zhong et al.

Recent advancements have empowered Large Language Models for Vision (vLLMs) to generate detailed perceptual outcomes, including bounding boxes and masks. Nonetheless, there are two constraints that restrict the further application of these vLLMs: the incapability of handling multiple targets per query and the failure to identify the absence of query objects in the image. In this study, we acknowledge that the main cause of these problems is the insufficient complexity of training queries. Consequently, we define the general sequence format for complex queries. Then we incorporate a semantic segmentation task in the current pipeline to fulfill the requirements of training data. Furthermore, we present three novel strategies to effectively handle the challenges arising from the direct integration of the proposed format. The effectiveness of our model in processing complex queries is validated by the comparable results with conventional methods on both close-set and open-set semantic segmentation datasets. Additionally, we outperform a series of vLLMs in reasoning and referring segmentation, showcasing our model's remarkable capabilities. We release the code at https://github.com/congvvc/LaSagnA.

Shimin Chen, Xiaohan Lan, Yitian Yuan et al.

Rapid development of large language models (LLMs) has significantly advanced multimodal large language models (LMMs), particularly in vision-language tasks. However, existing video-language models often overlook precise temporal localization and struggle with videos of varying lengths. We introduce TimeMarker, a versatile Video-LLM designed for high-quality dialogue based on video content, emphasizing temporal localization. TimeMarker integrates Temporal Separator Tokens to enhance temporal awareness, accurately marking specific moments within videos. It employs the AnyLength mechanism for dynamic frame sampling and adaptive token merging, enabling effective handling of both short and long videos. Additionally, TimeMarker utilizes diverse datasets, including further transformed temporal-related video QA datasets, to bolster its temporal understanding capabilities. Image and interleaved data are also employed to further enhance the model's semantic perception ability. Evaluations demonstrate that TimeMarker achieves state-of-the-art performance across multiple benchmarks, excelling in both short and long video categories. Our project page is at \url{https://github.com/TimeMarker-LLM/TimeMarker/}.