Yu Zhang

Xinyu Shi, Dong Wei, Yu Zhang et al.

Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into a few class-wise prototypes, or used partial support information (e.g., only foreground) at the pixel level, causing non-negligible information loss. In this paper, we propose Dense pixel-wise Cross-query-and-support Attention weighted Mask Aggregation (DCAMA), where both foreground and background support information are fully exploited via multi-level pixel-wise correlations between paired query and support features. Implemented with the scaled dot-product attention in the Transformer architecture, DCAMA treats every query pixel as a token, computes its similarities with all support pixels, and predicts its segmentation label as an additive aggregation of all the support pixels' labels -- weighted by the similarities. Based on the unique formulation of DCAMA, we further propose efficient and effective one-pass inference for n-shot segmentation, where pixels of all support images are collected for the mask aggregation at once. Experiments show that our DCAMA significantly advances the state of the art on standard FSS benchmarks of PASCAL-5i, COCO-20i, and FSS-1000, e.g., with 3.1%, 9.7%, and 3.6% absolute improvements in 1-shot mIoU over previous best records. Ablative studies also verify the design DCAMA.

Xiaomeng Chu, Jiajun Deng, Jianmin Ji et al.

The recent advance in multi-camera 3D object detection is featured by bird's-eye view (BEV) representation or object queries. However, the ill-posed transformation from image-plane view to 3D space inevitably causes feature clutter and distortion, making the objects blur into the background. To this end, we explore how to incorporate supplementary cues for differentiating objects in the transformed feature representation. Formally, we introduce OA-DET3D, a general plug-in module that improves 3D object detection by bringing object awareness into a variety of existing 3D object detection pipelines. Specifically, OA-DET3D boosts the representation of objects by leveraging object-centric depth information and foreground pseudo points. First, we use object-level supervision from the properties of each 3D bounding box to guide the network in learning the depth distribution. Next, we select foreground pixels using a 2D object detector and project them into 3D space for pseudo-voxel feature encoding. Finally, the object-aware depth features and pseudo-voxel features are incorporated into the BEV representation or query feature from the baseline model with a deformable attention mechanism. We conduct extensive experiments on the nuScenes dataset and Argoverse 2 dataset to validate the merits of OA-DET3D. Our method achieves consistent improvements over the BEV-based baselines in terms of both average precision and comprehensive detection score.

Yi Zhai, Yu Zhang, Shuo Liu et al.

Tensor program tuning is a non-convex objective optimization problem, to which search-based approaches have proven to be effective. At the core of the search-based approaches lies the design of the cost model. Though deep learning-based cost models perform significantly better than other methods, they still fall short and suffer from the following problems. First, their feature extraction heavily relies on expert-level domain knowledge in hardware architectures. Even so, the extracted features are often unsatisfactory and require separate considerations for CPUs and GPUs. Second, a cost model trained on one hardware platform usually performs poorly on another, a problem we call cross-hardware unavailability. In order to address these problems, we propose TLP and MTLTLP. TLP is a deep learning-based cost model that facilitates tensor program tuning. Instead of extracting features from the tensor program itself, TLP extracts features from the schedule primitives. We treat schedule primitives as tensor languages. TLP is thus a Tensor Language Processing task. In this way, the task of predicting the tensor program latency through the cost model is transformed into a natural language processing (NLP) regression task. MTL-TLP combines Multi-Task Learning and TLP to cope with the cross-hardware unavailability problem. We incorporate these techniques into the Ansor framework and conduct detailed experiments. Results show that TLP can speed up the average search time by 9.1X and 3.0X on CPU and GPU workloads, respectively, compared to the state-of-the-art implementation. MTL-TLP can achieve a speed-up of 4.7X and 2.9X on CPU and GPU workloads, respectively, using only 7% of the target hardware data.

Yu Zhang, Yue Zhang, Leyang Cui et al.

Recent work has witnessed a paradigm shift from Seq2Seq to Seq2Edit in the field of text editing, with the aim of addressing the slow autoregressive inference problem posed by the former. Despite promising results, Seq2Edit approaches still face several challenges such as inflexibility in generation and difficulty in generalizing to other languages. In this work, we propose a novel non-autoregressive text editing method to circumvent the above issues, by modeling the edit process with latent CTC alignments. We make a crucial extension to CTC by introducing the copy operation into the edit space, thus enabling more efficient management of textual overlap in editing. We conduct extensive experiments on GEC and sentence fusion tasks, showing that our proposed method significantly outperforms existing Seq2Edit models and achieves similar or even better results than Seq2Seq with over $4\times$ speedup. Moreover, it demonstrates good generalizability on German and Russian. In-depth analyses reveal the strengths of our method in terms of the robustness under various scenarios and generating fluent and flexible outputs.

Yuqian Fu, Xingyu Qiu, Bin Ren et al.

Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains. In conjunction with NTIRE 2025, we organized the 1st CD-FSOD Challenge, aiming to advance the performance of current object detectors on entirely novel target domains with only limited labeled data. The challenge attracted 152 registered participants, received submissions from 42 teams, and concluded with 13 teams making valid final submissions. Participants approached the task from diverse perspectives, proposing novel models that achieved new state-of-the-art (SOTA) results under both open-source and closed-source settings. In this report, we present an overview of the 1st NTIRE 2025 CD-FSOD Challenge, highlighting the proposed solutions and summarizing the results submitted by the participants.

Kaizhen Zhu, Mokai Pan, Zhechuan Yu et al.

Diffusion Bridge and Flow Matching have both demonstrated compelling empirical performance in transformation between arbitrary distributions. However, there remains confusion about which approach is generally preferable, and the substantial discrepancies in their modeling assumptions and practical implementations have hindered a unified theoretical account of their relative merits. We have, for the first time, provided a unified theoretical and experimental validation of these two models. We recast their frameworks through the lens of Stochastic Optimal Control and prove that the cost function of the Diffusion Bridge is lower, guiding the system toward more stable and natural trajectories. Simultaneously, from the perspective of Optimal Transport, interpolation coefficients $t$ and $1-t$ of Flow Matching become increasingly ineffective when the training data size is reduced. To corroborate these theoretical claims, we propose a novel, powerful architecture for Diffusion Bridge built on a latent Transformer, and implement a Flow Matching model with the same structure to enable a fair performance comparison in various experiments. Comprehensive experiments are conducted across Image Inpainting, Super-Resolution, Deblurring, Denoising, Translation, and Style Transfer tasks, systematically varying both the distributional discrepancy (different difficulty) and the training data size. Extensive empirical results align perfectly with our theoretical predictions and allow us to delineate the respective advantages and disadvantages of these two models. Our code is available at https://anonymous.4open.science/r/DBFM-3E8E/.

Zhongkai Yu, Yue Guan, Zihao Yu et al.

Large Language Models (LLMs) with Mixture of Experts (MoE) architectures achieve remarkable performance improvements, but their random expert selection mechanism introduces significant data movement overhead that becomes the dominant bottleneck in multi-unit serving systems. To forecast the patterns underlying this data movement, we conduct comprehensive data-movement-centric profiling across three state-of-the-art large-scale MoE models (200B- 671B) using over 24,000 requests spanning diverse workloads. With the resulting 150GB+ trace files, we perform systematic analysis from both temporal and spatial perspectives and distill six key insights to guide the design of diverse future serving systems. Taking wafer-scale GPUs as a case study, we demonstrate that minor architectural modifications leveraging our insights achieve substantial performance gains, delivering 6.3X and 4.0X average speedups on DeepSeek V3 and Qwen3, respectively. Our work provides the first comprehensive data-centric analysis of MoE models at scale. Our profiling traces and analysis results are publicly available at {https://huggingface.co/datasets/core12345/MoE_expert_selection_trace. We will also release our simulation framework shortly to facilitate future research in this area.

Xinran Zhang, Hanqi Zhu, Yifan Duan et al.

Constructing precise 3D maps is crucial for the development of future map-based systems such as self-driving and navigation. However, generating these maps in complex environments, such as multi-level parking garages or shopping malls, remains a formidable challenge. In this paper, we introduce a participatory sensing approach that delegates map-building tasks to map users, thereby enabling cost-effective and continuous data collection. The proposed method harnesses the collective efforts of users, facilitating the expansion and ongoing update of the maps as the environment evolves. We realized this approach by developing Map++, an efficient system that functions as a plug-and-play extension, supporting participatory map-building based on existing SLAM algorithms. Map++ addresses a plethora of scalability issues in this participatory map-building system by proposing a set of lightweight, application-layer protocols. We evaluated Map++ in four representative settings: an indoor garage, an outdoor plaza, a public SLAM benchmark, and a simulated environment. The results demonstrate that Map++ can reduce traffic volume by approximately 46% with negligible degradation in mapping accuracy, i.e., less than 0.03m compared to the baseline system. It can support approximately $2 \times$ as many concurrent users as the baseline under the same network bandwidth. Additionally, for users who travel on already-mapped trajectories, they can directly utilize the existing maps for localization and save 47% of the CPU usage.

Qing Xiao, Siyeop Yoon, Hui Ren et al.

Alzheimer's Disease (AD) is a neurodegenerative condition characterized by diverse progression rates among individuals, with changes in cortical thickness (CTh) closely linked to its progression. Accurately forecasting CTh trajectories can significantly enhance early diagnosis and intervention strategies, providing timely care. However, the longitudinal data essential for these studies often suffer from temporal sparsity and incompleteness, presenting substantial challenges in modeling the disease's progression accurately. Existing methods are limited, focusing primarily on datasets without missing entries or requiring predefined assumptions about CTh progression. To overcome these obstacles, we propose a conditional score-based diffusion model specifically designed to generate CTh trajectories with the given baseline information, such as age, sex, and initial diagnosis. Our conditional diffusion model utilizes all available data during the training phase to make predictions based solely on baseline information during inference without needing prior history about CTh progression. The prediction accuracy of the proposed CTh prediction pipeline using a conditional score-based model was compared for sub-groups consisting of cognitively normal, mild cognitive impairment, and AD subjects. The Bland-Altman analysis shows our diffusion-based prediction model has a near-zero bias with narrow 95% confidential interval compared to the ground-truth CTh in 6-36 months. In addition, our conditional diffusion model has a stochastic generative nature, therefore, we demonstrated an uncertainty analysis of patient-specific CTh prediction through multiple realizations.

Yueqi Zhang, Peiwen Yuan, Shaoxiong Feng et al.

Human-AI conversation frequently relies on quoting earlier text-"check it with the formula I just highlighted"-yet today's large language models (LLMs) lack an explicit mechanism for locating and exploiting such spans. We formalise the challenge as span-conditioned generation, decomposing each turn into the dialogue history, a set of token-offset quotation spans, and an intent utterance. Building on this abstraction, we introduce a quotation-centric data pipeline that automatically synthesises task-specific dialogues, verifies answer correctness through multi-stage consistency checks, and yields both a heterogeneous training corpus and the first benchmark covering five representative scenarios. To meet the benchmark's zero-overhead and parameter-efficiency requirements, we propose QuAda, a lightweight training-based method that attaches two bottleneck projections to every attention head, dynamically amplifying or suppressing attention to quoted spans at inference time while leaving the prompt unchanged and updating < 2.8% of backbone weights. Experiments across models show that QuAda is suitable for all scenarios and generalises to unseen topics, offering an effective, plug-and-play solution for quotation-aware dialogue.

Xinrui Lin, Yangfan Wu, Huanyu Yang et al.

Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planning in open-world scenarios. However, it is challenging to ground a LLM-generated plan to be executable for the specified robot with certain restrictions. This paper introduces CLMASP, an approach that couples LLMs with Answer Set Programming (ASP) to overcome the limitations, where ASP is a non-monotonic logic programming formalism renowned for its capacity to represent and reason about a robot's action knowledge. CLMASP initiates with a LLM generating a basic skeleton plan, which is subsequently tailored to the specific scenario using a vector database. This plan is then refined by an ASP program with a robot's action knowledge, which integrates implementation details into the skeleton, grounding the LLM's abstract outputs in practical robot contexts. Our experiments conducted on the VirtualHome platform demonstrate CLMASP's efficacy. Compared to the baseline executable rate of under 2% with LLM approaches, CLMASP significantly improves this to over 90%.

Hanqi Zhu, Jiajun Deng, Yu Zhang et al.

It has been well recognized that fusing the complementary information from depth-aware LiDAR point clouds and semantic-rich stereo images would benefit 3D object detection. Nevertheless, it is not trivial to explore the inherently unnatural interaction between sparse 3D points and dense 2D pixels. To ease this difficulty, the recent proposals generally project the 3D points onto the 2D image plane to sample the image data and then aggregate the data at the points. However, this approach often suffers from the mismatch between the resolution of point clouds and RGB images, leading to sub-optimal performance. Specifically, taking the sparse points as the multi-modal data aggregation locations causes severe information loss for high-resolution images, which in turn undermines the effectiveness of multi-sensor fusion. In this paper, we present VPFNet -- a new architecture that cleverly aligns and aggregates the point cloud and image data at the `virtual' points. Particularly, with their density lying between that of the 3D points and 2D pixels, the virtual points can nicely bridge the resolution gap between the two sensors, and thus preserve more information for processing. Moreover, we also investigate the data augmentation techniques that can be applied to both point clouds and RGB images, as the data augmentation has made non-negligible contribution towards 3D object detectors to date. We have conducted extensive experiments on KITTI dataset, and have observed good performance compared to the state-of-the-art methods. Remarkably, our VPFNet achieves 83.21\% moderate 3D AP and 91.86\% moderate BEV AP on the KITTI test set, ranking the 1st since May 21th, 2021. The network design also takes computation efficiency into consideration -- we can achieve a FPS of 15 on a single NVIDIA RTX 2080Ti GPU. The code will be made available for reproduction and further investigation.

Xiaomeng Chu, Jiajun Deng, Yao Li et al.

As cameras are increasingly deployed in new application domains such as autonomous driving, performing 3D object detection on monocular images becomes an important task for visual scene understanding. Recent advances on monocular 3D object detection mainly rely on the ``pseudo-LiDAR'' generation, which performs monocular depth estimation and lifts the 2D pixels to pseudo 3D points. However, depth estimation from monocular images, due to its poor accuracy, leads to inevitable position shift of pseudo-LiDAR points within the object. Therefore, the predicted bounding boxes may suffer from inaccurate location and deformed shape. In this paper, we present a novel neighbor-voting method that incorporates neighbor predictions to ameliorate object detection from severely deformed pseudo-LiDAR point clouds. Specifically, each feature point around the object forms their own predictions, and then the ``consensus'' is achieved through voting. In this way, we can effectively combine the neighbors' predictions with local prediction and achieve more accurate 3D detection. To further enlarge the difference between the foreground region of interest (ROI) pseudo-LiDAR points and the background points, we also encode the ROI prediction scores of 2D foreground pixels into the corresponding pseudo-LiDAR points. We conduct extensive experiments on the KITTI benchmark to validate the merits of our proposed method. Our results on the bird's eye view detection outperform the state-of-the-art performance by a large margin, especially for the ``hard'' level detection.

Yang Li, Hong Zhang, Yu Zhang

The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization technique. In this paper, we explore to directly pre-training on target dataset for object detection. Under this situation, we discover that the widely adopted large resizing strategy e.g. resize image to (1333, 800) is important for fine-tuning but it's not necessary for pre-training. Specifically, we propose a new training pipeline for object detection that follows `pre-training and fine-tuning', utilizing low resolution images within target dataset to pre-training detector then load it to fine-tuning with high resolution images. With this strategy, we can use batch normalization(BN) with large bath size during pre-training, it's also memory efficient that we can apply it on machine with very limited GPU memory(11G). We call it direct detection pre-training, and also use direct pre-training for short. Experiment results show that direct pre-training accelerates the pre-training phase by more than 11x on COCO dataset while with even +1.8mAP compared to ImageNet pre-training. Besides, we found direct pre-training is also applicable to transformer based backbones e.g. Swin Transformer. Code will be available.

Yin Zhou, Pei Sun, Yu Zhang et al.

Recent work on 3D object detection advocates point cloud voxelization in birds-eye view, where objects preserve their physical dimensions and are naturally separable. When represented in this view, however, point clouds are sparse and have highly variable point density, which may cause detectors difficulties in detecting distant or small objects (pedestrians, traffic signs, etc.). On the other hand, perspective view provides dense observations, which could allow more favorable feature encoding for such cases. In this paper, we aim to synergize the birds-eye view and the perspective view and propose a novel end-to-end multi-view fusion (MVF) algorithm, which can effectively learn to utilize the complementary information from both. Specifically, we introduce dynamic voxelization, which has four merits compared to existing voxelization methods, i) removing the need of pre-allocating a tensor with fixed size; ii) overcoming the information loss due to stochastic point/voxel dropout; iii) yielding deterministic voxel embeddings and more stable detection outcomes; iv) establishing the bi-directional relationship between points and voxels, which potentially lays a natural foundation for cross-view feature fusion. By employing dynamic voxelization, the proposed feature fusion architecture enables each point to learn to fuse context information from different views. MVF operates on points and can be naturally extended to other approaches using LiDAR point clouds. We evaluate our MVF model extensively on the newly released Waymo Open Dataset and on the KITTI dataset and demonstrate that it significantly improves detection accuracy over the comparable single-view PointPillars baseline.