arXiv subjects

Nanning Zheng

Publications and source records attributed to Nanning Zheng.

At least 37 records · Page 2Linked to original sources

arXiv2025

Riemannian Consistency Model

Consistency models are a class of generative models that enable few-step generation for diffusion and flow matching models. While consistency models have achieved promising results on Euclidean domains like images, their applications to Riemannian manifolds remain challenging due to the curved geometry. In this work, we propose the Riemannian Consistency Model (RCM), which, for the first time, enables few-step consistency modeling while respecting the intrinsic manifold constraint imposed by the Riemannian geometry. Leveraging the covariant derivative and exponential-map-based parameterization, we derive the closed-form solutions for both discrete- and continuous-time training objectives for RCM. We then demonstrate theoretical equivalence between the two variants of RCM: Riemannian consistency distillation (RCD) that relies on a teacher model to approximate the marginal vector field, and Riemannian consistency training (RCT) that utilizes the conditional vector field for training. We further propose a simplified training objective that eliminates the need for the complicated differential calculation. Finally, we provide a unique kinematics perspective for interpreting the RCM objective, offering new theoretical angles. Through extensive experiments, we manifest the superior generative quality of RCM in few-step generation on various non-Euclidean manifolds, including flat-tori, spheres, and the 3D rotation group SO(3).

cs.LG↗

arXiv2025

DAMap: Distance-aware MapNet for High Quality HD Map Construction

Predicting High-definition (HD) map elements with high quality (high classification and localization scores) is crucial to the safety of autonomous driving vehicles. However, current methods perform poorly in high quality predictions due to inherent task misalignment. Two main factors are responsible for misalignment: 1) inappropriate task labels due to one-to-many matching queries sharing the same labels, and 2) sub-optimal task features due to task-shared sampling mechanism. In this paper, we reveal two inherent defects in current methods and develop a novel HD map construction method named DAMap to address these problems. Specifically, DAMap consists of three components: Distance-aware Focal Loss (DAFL), Hybrid Loss Scheme (HLS), and Task Modulated Deformable Attention (TMDA). The DAFL is introduced to assign appropriate classification labels for one-to-many matching samples. The TMDA is proposed to obtain discriminative task-specific features. Furthermore, the HLS is proposed to better utilize the advantages of the DAFL. We perform extensive experiments and consistently achieve performance improvement on the NuScenes and Argoverse2 benchmarks under different metrics, baselines, splits, backbones, and schedules. Code will be available at https://github.com/jpdong-xjtu/DAMap.

cs.CV↗

arXiv2025

FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers

Detecting 3D objects accurately from multi-view 2D images is a challenging yet essential task in the field of autonomous driving. Current methods resort to integrating depth prediction to recover the spatial information for object query decoding, which necessitates explicit supervision from LiDAR points during the training phase. However, the predicted depth quality is still unsatisfactory such as depth discontinuity of object boundaries and indistinction of small objects, which are mainly caused by the sparse supervision of projected points and the use of high-level image features for depth prediction. Besides, cross-view consistency and scale invariance are also overlooked in previous methods. In this paper, we introduce Frequency-aware Positional Depth Embedding (FreqPDE) to equip 2D image features with spatial information for 3D detection transformer decoder, which can be obtained through three main modules. Specifically, the Frequency-aware Spatial Pyramid Encoder (FSPE) constructs a feature pyramid by combining high-frequency edge clues and low-frequency semantics from different levels respectively. Then the Cross-view Scale-invariant Depth Predictor (CSDP) estimates the pixel-level depth distribution with cross-view and efficient channel attention mechanism. Finally, the Positional Depth Encoder (PDE) combines the 2D image features and 3D position embeddings to generate the 3D depth-aware features for query decoding. Additionally, hybrid depth supervision is adopted for complementary depth learning from both metric and distribution aspects. Extensive experiments conducted on the nuScenes dataset demonstrate the effectiveness and superiority of our proposed method.

cs.CV↗

arXiv2025

ChangingGrounding: 3D Visual Grounding in Changing Scenes

Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption that forces costly re-scans and hinders deployment. We argue that 3DVG should be formulated as an active, memory-driven problem, and we introduce ChangingGrounding, the first benchmark that explicitly measures how well an agent can exploit past observations, explore only where needed, and still deliver precise 3D boxes in changing scenes. To set a strong reference point, we also propose Mem-ChangingGrounder, a zero-shot method for this task that marries cross-modal retrieval with lightweight multi-view fusion: it identifies the object type implied by the query, retrieves relevant memories to guide actions, then explores the target efficiently in the scene, falls back when previous operations are invalid, performs multi-view scanning of the target, and projects the fused evidence from multi-view scans to get accurate object bounding boxes. We evaluate different baselines on ChangingGrounding, and our Mem-ChangingGrounder achieves the highest localization accuracy while greatly reducing exploration cost. We hope this benchmark and method catalyze a shift toward practical, memory-centric 3DVG research for real-world applications. Project page: https://hm123450.github.io/CGB/ .

cs.CV↗

arXiv2025

Information-Preserving Reformulation of Reasoning Traces for Antidistillation

Recent advances in Large Language Models (LLMs) show that extending the length of reasoning chains significantly improves performance on complex tasks. While revealing these reasoning traces helps users better follow, verify, and learn from the model's problem-solving process, it also makes them highly vulnerable to unauthorized distillation. To mitigate this risk, proprietary model providers often adopt aggressive protection strategies, such as replacing detailed reasoning with brief summaries, which deprive users of valuable intermediate information. To address this trade-off, we propose PART, an information-preserving antidistillation reformulation of reasoning traces. Motivated by the difference between how humans understand reasoning traces and how LLMs exploit them for supervised fine-tuning, we design a simple but effective two-step reformulation: removing self-talk behaviors and reordering sub-conclusions. A small auxiliary model is trained to perform this reformulation, incurring minimal computational overhead. Extensive experiments demonstrate that PART consistently disrupts distillation across student models of different sizes and types on various reasoning benchmarks. For instance, when training on reformulated traces, even the performance of a large 32B student model decreases from 54.17 to 46.88 on AIME 2024, corresponding to a 13.5% degradation.

cs.CL↗

arXiv2025

Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networks

Inferring the unseen attribute-object composition is critical to make machines learn to decompose and compose complex concepts like people. Most existing methods are limited to the composition recognition of single-attribute-object, and can hardly learn relations between the attributes and objects. In this paper, we propose an attribute-object semantic association graph model to learn the complex relations and enable knowledge transfer between primitives. With nodes representing attributes and objects, the graph can be constructed flexibly, which realizes both single- and multi-attribute-object composition recognition. In order to reduce mis-classifications of similar compositions (e.g., scratched screen and broken screen), driven by the contrastive loss, the anchor image feature is pulled closer to the corresponding label feature and pushed away from other negative label features. Specifically, a novel balance loss is proposed to alleviate the domain bias, where a model prefers to predict seen compositions. In addition, we build a large-scale MultiAttribute Dataset (MAD) with 116,099 images and 8,030 label categories for inferring unseen multi-attribute-object compositions. Along with MAD, we propose two novel metrics Hard and Soft to give a comprehensive evaluation in the multi-attribute setting. Experiments on MAD and two other single-attribute-object benchmarks (MIT-States and UT-Zappos50K) demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2025

MCGM: Multi-stage Clustered Global Modeling for Long-range Interactions in Molecules

Geometric graph neural networks (GNNs) excel at capturing molecular geometry, yet their locality-biased message passing hampers the modeling of long-range interactions. Current solutions have fundamental limitations: extending cutoff radii causes computational costs to scale cubically with distance; physics-inspired kernels (e.g., Coulomb, dispersion) are often system-specific and lack generality; Fourier-space methods require careful tuning of multiple parameters (e.g., mesh size, k-space cutoff) with added computational overhead. We introduce Multi-stage Clustered Global Modeling (MCGM), a lightweight, plug-and-play module that endows geometric GNNs with hierarchical global context through efficient clustering operations. MCGM builds a multi-resolution hierarchy of atomic clusters, distills global information via dynamic hierarchical clustering, and propagates this context back through learned transformations, ultimately reinforcing atomic features via residual connections. Seamlessly integrated into four diverse backbone architectures, MCGM reduces OE62 energy prediction error by an average of 26.2%. On AQM, MCGM achieves state-of-the-art accuracy (17.0 meV for energy, 4.9 meV/Å for forces) while using 20% fewer parameters than Neural P3M. Code will be made available upon acceptance.

cs.LG↗

arXiv2025

LongReasonArena: A Long Reasoning Benchmark for Large Language Models

Existing long-context benchmarks for Large Language Models (LLMs) focus on evaluating comprehension of long inputs, while overlooking the evaluation of long reasoning abilities. To address this gap, we introduce LongReasonArena, a benchmark specifically designed to assess the long reasoning capabilities of LLMs. Our tasks require models to solve problems by executing multi-step algorithms that reflect key aspects of long reasoning, such as retrieval and backtracking. By controlling the inputs, the required reasoning length can be arbitrarily scaled, reaching up to 1 million tokens of reasoning for the most challenging tasks. Extensive evaluation results demonstrate that LongReasonArena presents a significant challenge for both open-source and proprietary LLMs. For instance, Deepseek-R1 achieves only 7.5% accuracy on our task. Further analysis also reveals that the accuracy exhibits a linear decline with respect to the logarithm of the expected number of reasoning steps. Our code and data is available at https://github.com/LongReasonArena/LongReasonArena.

cs.CL↗

arXiv2025

Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation

Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation. Vision Transformers (ViTs) have advanced global modeling through self-attention but suffer from quadratic computational complexity with respect to token count, limiting their efficiency and scalability to high-resolution inputs, especially on mobile and resource-constrained devices. State Space Models (SSMs), exemplified by Mamba, offer an efficient alternative by combining global receptive fields with linear computational complexity, enabling scalable and resource-friendly sequence modeling. However, when applied to dense prediction tasks, existing visual SSMs face key limitations: weak spatial inductive bias, long-range forgetting from hidden state decay, and low-resolution outputs that hinder fine-grained localization. To address these issues, we propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations to enhance local spatial representations and strengthen spatial inductive biases. Through architectural exploration and theoretical analysis, we incorporate deformable operation into the DVSS block, identifying it as an efficient and effective mechanism to enhance semantic aggregation and mitigate long-range forgetting via input-dependent, adaptive spatial sampling. We embed DVSS into a multi-branch high-resolution architecture to build HRVMamba, a novel model for efficient high-resolution representation learning. Extensive experiments on human pose estimation, image classification, and semantic segmentation show that HRVMamba performs competitively against leading CNN-, ViT-, and SSM-based baselines. Code is available at https://github.com/zhanghao5201/PoseVMamba.

cs.CV↗

arXiv2025

PlaneHEC: Efficient Hand-Eye Calibration for Multi-view Robotic Arm via Any Point Cloud Plane Detection

Hand-eye calibration is an important task in vision-guided robotic systems and is crucial for determining the transformation matrix between the camera coordinate system and the robot end-effector. Existing methods, for multi-view robotic systems, usually rely on accurate geometric models or manual assistance, generalize poorly, and can be very complicated and inefficient. Therefore, in this study, we propose PlaneHEC, a generalized hand-eye calibration method that does not require complex models and can be accomplished using only depth cameras, which achieves the optimal and fastest calibration results using arbitrary planar surfaces like walls and tables. PlaneHEC introduces hand-eye calibration equations based on planar constraints, which makes it strongly interpretable and generalizable. PlaneHEC also uses a comprehensive solution that starts with a closed-form solution and improves it withiterative optimization, which greatly improves accuracy. We comprehensively evaluated the performance of PlaneHEC in both simulated and real-world environments and compared the results with other point-cloud-based calibration methods, proving its superiority. Our approach achieves universal and fast calibration with an innovative design of computational models, providing a strong contribution to the development of multi-agent systems and embodied intelligence.

cs.RO↗

arXiv2025

CylinderPlane: Nested Cylinder Representation for 3D-aware Image Generation

While the proposal of the Tri-plane representation has advanced the development of the 3D-aware image generative models, problems rooted in its inherent structure, such as multi-face artifacts caused by sharing the same features in symmetric regions, limit its ability to generate 360$^\circ$ view images. In this paper, we propose CylinderPlane, a novel implicit representation based on Cylindrical Coordinate System, to eliminate the feature ambiguity issue and ensure multi-view consistency in 360$^\circ$. Different from the inevitable feature entanglement in Cartesian coordinate-based Tri-plane representation, the cylindrical coordinate system explicitly separates features at different angles, allowing our cylindrical representation possible to achieve high-quality, artifacts-free 360$^\circ$ image synthesis. We further introduce the nested cylinder representation that composites multiple cylinders at different scales, thereby enabling the model more adaptable to complex geometry and varying resolutions. The combination of cylinders with different resolutions can effectively capture more critical locations and multi-scale features, greatly facilitates fine detail learning and robustness to different resolutions. Moreover, our representation is agnostic to implicit rendering methods and can be easily integrated into any neural rendering pipeline. Extensive experiments on both synthetic dataset and unstructured in-the-wild images demonstrate that our proposed representation achieves superior performance over previous methods.

cs.CV↗

arXiv2025

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) investigates compositional generalization capacity to recognize unknown state-object pairs based on learned primitive concepts. Existing CZSL methods typically derive primitives features through a simple composition-prototype mapping, which is suboptimal for a set of individuals that can be divided into distinct semantic subsets. Moreover, the all-to-one cross-modal primitives matching neglects compositional divergence within identical states or objects, limiting fine-grained image-composition alignment. In this study, we propose EVA, a Mixture-of-Experts Semantic Variant Alignment framework for CZSL. Specifically, we introduce domain-expert adaption, leveraging multiple experts to achieve token-aware learning and model high-quality primitive representations. To enable accurate compositional generalization, we further present semantic variant alignment to select semantically relevant representation for image-primitives matching. Our method significantly outperforms other state-of-the-art CZSL methods on three popular benchmarks in both closed- and open-world settings, demonstrating the efficacy of the proposed insight.

cs.CV↗

arXiv2025

StructVPR++: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition

Visual place recognition is a challenging task for autonomous driving and robotics, which is usually considered as an image retrieval problem. A commonly used two-stage strategy involves global retrieval followed by re-ranking using patch-level descriptors. Most deep learning-based methods in an end-to-end manner cannot extract global features with sufficient semantic information from RGB images. In contrast, re-ranking can utilize more explicit structural and semantic information in one-to-one matching process, but it is time-consuming. To bridge the gap between global retrieval and re-ranking and achieve a good trade-off between accuracy and efficiency, we propose StructVPR++, a framework that embeds structural and semantic knowledge into RGB global representations via segmentation-guided distillation. Our key innovation lies in decoupling label-specific features from global descriptors, enabling explicit semantic alignment between image pairs without requiring segmentation during deployment. Furthermore, we introduce a sample-wise weighted distillation strategy that prioritizes reliable training pairs while suppressing noisy ones. Experiments on four benchmarks demonstrate that StructVPR++ surpasses state-of-the-art global methods by 5-23% in Recall@1 and even outperforms many two-stage approaches, achieving real-time efficiency with a single RGB input.

cs.CV↗

arXiv2025

ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images

Place recognition is essential to maintain global consistency in large-scale localization systems. While research in urban environments has progressed significantly using LiDARs or cameras, applications in natural forest-like environments remain largely under-explored. Furthermore, forests present particular challenges due to high self-similarity and substantial variations in vegetation growth over time. In this work, we propose a robust LiDAR-based place recognition method for natural forests, ForestLPR. We hypothesize that a set of cross-sectional images of the forest's geometry at different heights contains the information needed to recognize revisiting a place. The cross-sectional images are represented by \ac{bev} density images of horizontal slices of the point cloud at different heights. Our approach utilizes a visual transformer as the shared backbone to produce sets of local descriptors and introduces a multi-BEV interaction module to attend to information at different heights adaptively. It is followed by an aggregation layer that produces a rotation-invariant place descriptor. We evaluated the efficacy of our method extensively on real-world data from public benchmarks as well as robotic datasets and compared it against the state-of-the-art (SOTA) methods. The results indicate that ForestLPR has consistently good performance on all evaluations and achieves an average increase of 7.38\% and 9.11\% on Recall@1 over the closest competitor on intra-sequence loop closure detection and inter-sequence re-localization, respectively, validating our hypothesis

cs.CV↗

arXiv2024

B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions

Large Vision-Language Models (LVLMs) have shown significant progress in responding well to visual-instructions from users. However, these instructions, encompassing images and text, are susceptible to both intentional and inadvertent attacks. Despite the critical importance of LVLMs' robustness against such threats, current research in this area remains limited. To bridge this gap, we introduce B-AVIBench, a framework designed to analyze the robustness of LVLMs when facing various Black-box Adversarial Visual-Instructions (B-AVIs), including four types of image-based B-AVIs, ten types of text-based B-AVIs, and nine types of content bias B-AVIs (such as gender, violence, cultural, and racial biases, among others). We generate 316K B-AVIs encompassing five categories of multimodal capabilities (ten tasks) and content bias. We then conduct a comprehensive evaluation involving 14 open-source LVLMs to assess their performance. B-AVIBench also serves as a convenient tool for practitioners to evaluate the robustness of LVLMs against B-AVIs. Our findings and extensive experimental results shed light on the vulnerabilities of LVLMs, and highlight that inherent biases exist even in advanced closed-source LVLMs like GeminiProVision and GPT-4V. This underscores the importance of enhancing the robustness, security, and fairness of LVLMs. The source code and benchmark are available at https://github.com/zhanghao5201/B-AVIBench.

cs.CV↗

arXiv2024

DexDiff: Towards Extrinsic Dexterity Manipulation of Ungraspable Objects in Unrestricted Environments

Grasping large and flat objects (e.g. a book or a pan) is often regarded as an ungraspable task, which poses significant challenges due to the unreachable grasping poses. Previous works leverage Extrinsic Dexterity like walls or table edges to grasp such objects. However, they are limited to task-specific policies and lack task planning to find pre-grasp conditions. This makes it difficult to adapt to various environments and extrinsic dexterity constraints. Therefore, we present DexDiff, a robust robotic manipulation method for long-horizon planning with extrinsic dexterity. Specifically, we utilize a vision-language model (VLM) to perceive the environmental state and generate high-level task plans, followed by a goal-conditioned action diffusion (GCAD) model to predict the sequence of low-level actions. This model learns the low-level policy from offline data with the cumulative reward guided by high-level planning as the goal condition, which allows for improved prediction of robot actions. Experimental results demonstrate that our method not only effectively performs ungraspable tasks but also generalizes to previously unseen objects. It outperforms baselines by a 47% higher success rate in simulation and facilitates efficient deployment and manipulation in real-world scenarios.

cs.RO↗

arXiv2024

Molecule Design by Latent Prompt Transformer

This work explores the challenging problem of molecule design by framing it as a conditional generative modeling task, where target biological properties or desired chemical constraints serve as conditioning variables. We propose the Latent Prompt Transformer (LPT), a novel generative model comprising three components: (1) a latent vector with a learnable prior distribution modeled by a neural transformation of Gaussian white noise; (2) a molecule generation model based on a causal Transformer, which uses the latent vector as a prompt; and (3) a property prediction model that predicts a molecule's target properties and/or constraint values using the latent prompt. LPT can be learned by maximum likelihood estimation on molecule-property pairs. During property optimization, the latent prompt is inferred from target properties and constraints through posterior sampling and then used to guide the autoregressive molecule generation. After initial training on existing molecules and their properties, we adopt an online learning algorithm to progressively shift the model distribution towards regions that support desired target properties. Experiments demonstrate that LPT not only effectively discovers useful molecules across single-objective, multi-objective, and structure-constrained optimization tasks, but also exhibits strong sample efficiency.

cs.LG↗

arXiv2024

Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching

Current image-based keypoint detection methods for animal (including human) bodies and faces are generally divided into full-supervised and few-shot class-agnostic approaches. The former typically relies on laborious and time-consuming manual annotations, posing considerable challenges in expanding keypoint detection to a broader range of keypoint categories and animal species. The latter, though less dependent on extensive manual input, still requires necessary support images with annotation for reference during testing. To realize zero-shot keypoint detection without any prior annotation, we introduce the Open-Vocabulary Keypoint Detection (OVKD) task, which is innovatively designed to use text prompts for identifying arbitrary keypoints across any species. In pursuit of this goal, we have developed a novel framework named Open-Vocabulary Keypoint Detection with Semantic-feature Matching (KDSM). This framework synergistically combines vision and language models, creating an interplay between language features and local keypoint visual features. KDSM enhances its capabilities by integrating Domain Distribution Matrix Matching (DDMM) and other special modules, such as the Vision-Keypoint Relational Awareness (VKRA) module, improving the framework's generalizability and overall performance.Our comprehensive experiments demonstrate that KDSM significantly outperforms the baseline in terms of performance and achieves remarkable success in the OVKD task.Impressively, our method, operating in a zero-shot fashion, still yields results comparable to state-of-the-art few-shot species class-agnostic keypoint detection methods.We will make the source code publicly accessible.

cs.CV↗