arXiv subjects

Yingying Zhu

Publications and source records attributed to Yingying Zhu.

At least 19 recordsLinked to original sources

arXiv2026

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Vision-language-action (VLA) models commonly adopt an LLM-centric $V \to L \to A$ pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation. In this work, we introduce TurboVLA, a new VLA paradigm that reformulates the conventional $V \to L \to A$ pathway as a direct $V + L \to A$ mapping. Instead of using a large language model as the central interface between perception and action, TurboVLA independently encodes visual observations and language instructions, directly exchanges information between them through lightweight bidirectional vision-language interaction, and predicts continuous action chunks with a compact decoder. This simple design constructs task-conditioned representations directly from visual and linguistic features, significantly reducing the computational and memory costs of VLA inference. On LIBERO, TurboVLA achieves 97.7% average success with only 0.2B parameters, 31.2 ms inference latency, and 0.9 GB inference VRAM on a consumer-grade RTX 4090, matching or outperforming substantially larger VLA policies. These results establish TurboVLA as a simple and effective alternative to the prevailing LLM-centric VLA paradigm, offering a new perspective on how vision, language, and action can be connected for efficient robotic manipulation. Code is available at https://github.com/H-EmbodVis/TurboVLA.

cs.CV↗

arXiv2026

When Prompts Become Pixels: Prompt-Region Grounding for Multimodal Reasoning

Multimodal large language models increasingly reason over screenshots and documents where the task itself may be written in pixels. Yet benchmarks usually place questions in text, leaving it unclear whether models use the same instruction equally well across channels. We introduce Visualized Task Semantics (VTS), a controlled intervention that moves the question into the image while keeping the source problem and answer fixed. Across six MLLMs and four benchmarks, accuracy drops in all 24 model-task pairs, by 17.8 points on average. Models often transcribe the visual question correctly yet fail to use it, exposing a semantic channel gap beyond OCR. To reduce this gap, we present prompt-region grounding, whose core design aligns the question region with typed semantics and recovers its clean representation from a masked view. At matched training cost, our method raises four-benchmark VTS accuracy from 58.0 to 66.3 while preserving accuracy on the original interface, and requires no OCR or region metadata at inference. Reading task-bearing text and grounding it as an instruction for reasoning are distinct capabilities.

cs.AI↗

arXiv2026

MOGeo: Beyond One-to-One Cross-View Object Geo-localization

Cross-View Object Geo-Localization (CVOGL) aims to locate an object of interest in a query image within a corresponding satellite image. Existing methods typically assume that the query image contains only a single object, which does not align with the complex, multi-object geo-localization requirements in real-world applications, making them unsuitable for practical scenarios. To bridge the gap between the realistic setting and existing task, we propose a new task, called Cross-View Multi-Object Geo-Localization (CVMOGL). To advance the CVMOGL task, we first construct a benchmark, CMLocation, which includes two datasets: CMLocation-V1 and CMLocation-V2. Furthermore, we propose a novel cross-view multi-object geo-localization method, MOGeo, and benchmark it against existing state-of-the-art methods. Extensive experiments are conducted under various application scenarios to validate the effectiveness of our method. The results demonstrate that cross-view object geo-localization in the more realistic setting remains a challenging problem, encouraging further research in this area.

cs.CV↗

arXiv2026

From Horizontal to Rotated: Cross-View Object Geo-Localization with Orientation Awareness

Cross-View object geo-localization (CVOGL) aims to precisely determine the geographic coordinates of a query object from a ground or drone perspective by referencing a satellite map. Segmentation-based approaches offer high precision but require prohibitively expensive pixel-level annotations, whereas more economical detection-based methods suffer from lower accuracy. This performance disparity in detection is primarily caused by two factors: the poor geometric fit of Horizontal Bounding Boxes (HBoxes) for oriented objects and the degradation in precision due to feature map scaling. Motivated by these, we propose leveraging Rotated Bounding Boxes (RBoxes) as a natural extension of the detection-based paradigm. RBoxes provide a much tighter geometric fit to oriented objects. Building on this, we introduce OSGeo, a novel geo-localization framework, meticulously designed with a multi-scale perception module and an orientation-sensitive head to accurately regress RBoxes. To support this scheme, we also construct and release CVOGL-R, the first dataset with precise RBox annotations for CVOGL. Extensive experiments demonstrate that our OSGeo achieves state-of-the-art performance, consistently matching or even surpassing the accuracy of leading segmentation-based methods but with an annotation cost that is over an order of magnitude lower.

cs.CV↗

arXiv2026

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning

Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stall; when one happens to be correct, the update usually ignores why the others are close-but-wrong, and credit can be misassigned to spurious chains. We present CARE (Contrastive Anchored REflection), a failure-centric post-training framework for multimodal reasoning that turns errors into supervision. CARE combines: (i) an anchored-contrastive objective that forms a compact subgroup around the best rollout and a set of semantically proximate hard negatives, performs within-subgroup z-score normalization with negative-only scaling, and includes an all-negative rescue to prevent zero-signal batches; and (ii) Reflection-Guided Resampling (RGR), a one-shot structured self-repair that rewrites a representative failure and re-scores it with the same verifier, converting near-misses into usable positives without any test-time reflection. CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures. On Qwen2.5-VL-7B, CARE lifts macro-averaged accuracy by 4.6 points over GRPO across six verifiable visual-reasoning benchmarks; with Qwen3-VL-8B it reaches competitive or state-of-the-art results on MathVista and MMMU-Pro under an identical evaluation protocol.

cs.LG↗

arXiv2026

CVGL: Causal Learning and Geometric Topology

Cross-view geo-localization (CVGL) aims to estimate the geographic location of a street image by matching it with a corresponding aerial image. This is critical for autonomous navigation and mapping in complex real-world scenarios. However, the task remains challenging due to significant viewpoint differences and the influence of confounding factors. To tackle these issues, we propose the Causal Learning and Geometric Topology (CLGT) framework, which integrates two key components: a Causal Feature Extractor (CFE) that mitigates the influence of confounding factors by leveraging causal intervention to encourage the model to focus on stable, task-relevant semantics; and a Geometric Topology Fusion (GT Fusion) module that injects Bird's Eye View (BEV) road topology into street features to alleviate cross-view inconsistencies caused by extreme perspective changes. Additionally, we introduce a Data-Adaptive Pooling (DA Pooling) module to enhance the representation of semantically rich regions. Extensive experiments on CVUSA, CVACT, and their robustness-enhanced variants (CVUSA-C-ALL and CVACT-C-ALL) demonstrate that CLGT achieves state-of-the-art performance, particularly under challenging real-world corruptions. Our codes are available at https://github.com/oyss-szu/CLGT.

cs.CV↗

arXiv2026

MRGeo: Robust Cross-View Geo-Localization of Corrupted Images via Spatial and Channel Feature Enhancement

Cross-view geo-localization (CVGL) aims to accurately localize street-view images through retrieval of corresponding geo-tagged satellite images. While prior works have achieved nearly perfect performance on certain standard datasets, their robustness in real-world corrupted environments remains under-explored. This oversight causes severe performance degradation or failure when images are affected by corruption such as blur or weather, significantly limiting practical deployment. To address this critical gap, we introduce MRGeo, the first systematic method designed for robust CVGL under corruption. MRGeo employs a hierarchical defense strategy that enhances the intrinsic quality of features and then enforces a robust geometric prior. Its core is the Spatial-Channel Enhancement Block, which contains: (1) a Spatial Adaptive Representation Module that models global and local features in parallel and uses a dynamic gating mechanism to arbitrate their fusion based on feature reliability; and (2) a Channel Calibration Module that performs compensatory adjustments by modeling multi-granularity channel dependencies to counteract information loss. To prevent spatial misalignment under severe corruption, a Region-level Geometric Alignment Module imposes a geometric structure on the final descriptors, ensuring coarse-grained consistency. Comprehensive experiments on both robustness benchmark and standard datasets demonstrate that MRGeo not only achieves an average R@1 improvement of 2.92\% across three comprehensive robustness benchmarks (CVUSA-C-ALL, CVACT\_val-C-ALL, and CVACT\_test-C-ALL) but also establishes superior performance in cross-area evaluation, thereby demonstrating its robustness and generalization capability.

cs.CV↗

arXiv2026

Large-scale EM Benchmark for Multi-Organelle Instance Segmentation in the Wild

Accurate instance-level segmentation of organelles in electron microscopy (EM) is critical for quantitative analysis of subcellular morphology and inter-organelle interactions. However, current benchmarks, based on small, curated datasets, fail to capture the inherent heterogeneity and large spatial context of in-the-wild EM data, imposing fundamental limitations on current patch-based methods. To address these limitations, we developed a large-scale, multi-source benchmark for multi-organelle instance segmentation, comprising over 100,000 2D EM images across variety cell types and five organelle classes that capture real-world variability. Dataset annotations were generated by our designed connectivity-aware Label Propagation Algorithm (3D LPA) with expert refinement. We further benchmarked several state-of-the-art models, including U-Net, SAM variants, and Mask2Former. Our results show several limitations: current models struggle to generalize across heterogeneous EM data and perform poorly on organelles with global, distributed morphologies (e.g., Endoplasmic Reticulum). These findings underscore the fundamental mismatch between local-context models and the challenge of modeling long-range structural continuity in the presence of real-world variability. The benchmark dataset and labeling tool will be publicly released soon.

cs.CV↗

arXiv2026

AutoBinder Agent: An MCP-Based Agent for End-to-End Protein Binder Design

Modern AI technologies for drug discovery are distributed across heterogeneous platforms-including web applications, desktop environments, and code libraries-leading to fragmented workflows, inconsistent interfaces, and high integration overhead. We present an agentic end-to-end drug design framework that leverages a Large Language Model (LLM) in conjunction with the Model Context Protocol (MCP) to dynamically coordinate access to biochemical databases, modular toolchains, and task-specific AI models. The system integrates four state-of-the-art components: MaSIF (MaSIF-site and MaSIF-seed-search) for geometric deep learning-based identification of protein-protein interaction (PPI) sites, Rosetta for grafting protein fragments onto protein backbones to form mini proteins, ProteinMPNN for amino acid sequences redesign, and AlphaFold3 for near-experimental accuracy in complex structure prediction. Starting from a target structure, the framework supports de novo binder generation via surface analysis, scaffold grafting and pose construction, sequence optimization, and structure prediction. Additionally, by replacing rigid, script-based workflows with a protocol-driven, LLM-coordinated architecture, the framework improves reproducibility, reduces manual overhead, and ensures extensibility, portability, and auditability across the entire drug design process.

q-bio.BM↗

arXiv2026

RFAssigner: A Generic Label Assignment Strategy for Dense Object Detection

Label assignment is a critical component in training dense object detectors. State-of-the-art methods typically assign each training sample a positive and a negative weight, optimizing the assignment scheme during training. However, these strategies often assign an insufficient number of positive samples to small objects, leading to a scale imbalance during training. To address this limitation, we introduce RFAssigner, a novel assignment strategy designed to enhance the multi-scale learning capabilities of dense detectors. RFAssigner first establishes an initial set of positive samples using a point-based prior. It then leverages a Gaussian Receptive Field (GRF) distance to measure the similarity between the GRFs of unassigned candidate locations and the ground-truth objects. Based on this metric, RFAssigner adaptively selects supplementary positive samples from the unassigned pool, promoting a more balanced learning process across object scales. Comprehensive experiments on three datasets with distinct object scale distributions validate the effectiveness and generalizability of our method. Notably, a single FCOS-ResNet-50 detector equipped with RFAssigner achieves state-of-the-art performance across all object scales, consistently outperforming existing strategies without requiring auxiliary modules or heuristics.

cs.CV↗

arXiv2025

Rep-GLS: Report-Guided Generalized Label Smoothing for Robust Disease Detection

Unlike nature image classification where groundtruth label is explicit and of no doubt, physicians commonly interpret medical image conditioned on certainty like using phrase "probable" or "likely". Existing medical image datasets either simply overlooked the nuance and polarise into binary label. Here, we propose a novel framework that leverages a Large Language Model (LLM) to directly mine medical reports to utilise the uncertainty relevant expression for supervision signal. At first, we collect uncertainty keywords from medical reports. Then, we use Qwen-3 4B to identify the textual uncertainty and map them into an adaptive Generalized Label Smoothing (GLS) rate. This rate allows our model to treat uncertain labels not as errors, but as informative signals, effectively incorporating expert skepticism into the training process. We establish a new clinical expert uncertainty-aware benchmark to rigorously evaluate this problem. Experiments demonstrate that our approach significantly outperforms state-of-the-art methods in medical disease detection. The curated uncertainty words database, code, and benchmark will be made publicly available upon acceptance.

cs.LG↗

arXiv2025

Seeing the Unseen: Mask-Driven Positional Encoding and Strip-Convolution Context Modeling for Cross-View Object Geo-Localization

Cross-view object geo-localization enables high-precision object localization through cross-view matching, with critical applications in autonomous driving, urban management, and disaster response. However, existing methods rely on keypoint-based positional encoding, which captures only 2D coordinates while neglecting object shape information, resulting in sensitivity to annotation shifts and limited cross-view matching capability. To address these limitations, we propose a mask-based positional encoding scheme that leverages segmentation masks to capture both spatial coordinates and object silhouettes, thereby upgrading the model from "location-aware" to "object-aware." Furthermore, to tackle the challenge of large-span objects (e.g., elongated buildings) in satellite imagery, we design a context enhancement module. This module employs horizontal and vertical strip convolutional kernels to extract long-range contextual features, enhancing feature discrimination among strip-like objects. Integrating MPE and CEM, we present EDGeo, an end-to-end framework for robust cross-view object geo-localization. Extensive experiments on two public datasets (CVOGL and VIGOR-Building) demonstrate that our method achieves state-of-the-art performance, with a 3.39% improvement in localization accuracy under challenging ground-to-satellite scenarios. This work provides a robust positional encoding paradigm and a contextual modeling framework for advancing cross-view geo-localization research.

cs.CV↗

arXiv2025

Anchor-free Cross-view Object Geo-localization with Gaussian Position Encoding and Cross-view Association

Most existing cross-view object geo-localization approaches adopt anchor-based paradigm. Although effective, such methods are inherently constrained by predefined anchors. To eliminate this dependency, we first propose an anchor-free formulation for cross-view object geo-localization, termed AFGeo. AFGeo directly predicts the four directional offsets (left, right, top, bottom) to the ground-truth box for each pixel, thereby localizing the object without any predefined anchors. To obtain a more robust spatial prior, AFGeo incorporates Gaussian Position Encoding (GPE) to model the click point in the query image, mitigating the uncertainty of object position that challenges object localization in cross-view scenarios. In addition, AFGeo incorporates a Cross-view Object Association Module (CVOAM) that relates the same object and its surrounding context across viewpoints, enabling reliable localization under large cross-view appearance gaps. By adopting an anchor-free localization paradigm that integrates GPE and CVOAM with minimal parameter overhead, our model is both lightweight and computationally efficient, achieving state-of-the-art performance on benchmark datasets.

cs.CV↗

arXiv2025

SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval

Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image given a reference image and a relative text, without relying on costly triplet annotations. Existing CLIP-based methods face two core challenges: (1) union-based feature fusion indiscriminately aggregates all visual cues, carrying over irrelevant background details that dilute the intended modification, and (2) global cosine similarity from CLIP embeddings lacks the ability to resolve fine-grained semantic relations. To address these issues, we propose SETR (Semantic-enhanced Two-Stage Retrieval). In the coarse retrieval stage, SETR introduces an intersection-driven strategy that retains only the overlapping semantics between the reference image and relative text, thereby filtering out distractors inherent to union-based fusion and producing a cleaner, high-precision candidate set. In the fine-grained re-ranking stage, we adapt a pretrained multimodal LLM with Low-Rank Adaptation to conduct binary semantic relevance judgments ("Yes/No"), which goes beyond CLIP's global feature matching by explicitly verifying relational and attribute-level consistency. Together, these two stages form a complementary pipeline: coarse retrieval narrows the candidate pool with high recall, while re-ranking ensures precise alignment with nuanced textual modifications. Experiments on CIRR, Fashion-IQ, and CIRCO show that SETR achieves new state-of-the-art performance, improving Recall@1 on CIRR by up to 15.15 points. Our results establish two-stage reasoning as a general paradigm for robust and portable ZS-CIR.

cs.CV↗

arXiv2025

Computation-Efficient and Recognition-Friendly 3D Point Cloud Privacy Protection

3D point cloud has been widely used in applications such as self-driving cars, robotics, CAD models, etc. To the best of our knowledge, these applications raised the issue of privacy leakage in 3D point clouds, which has not been studied well. Different from the 2D image privacy, which is related to texture and 2D geometric structure, the 3D point cloud is texture-less and only relevant to 3D geometric structure. In this work, we defined the 3D point cloud privacy problem and proposed an efficient privacy-preserving framework named PointFlowGMM that can support downstream classification and segmentation tasks without seeing the original data. Using a flow-based generative model, the point cloud is projected into a latent Gaussian mixture distributed subspace. We further designed a novel angular similarity loss to obfuscate the original geometric structure and reduce the model size from 767MB to 120MB without a decrease in recognition performance. The projected point cloud in the latent space is orthogonally rotated randomly to further protect the original geometric structure, the class-to-class relationship is preserved after rotation, thus, the protected point cloud can support the recognition task. We evaluated our model on multiple datasets and achieved comparable recognition results on encrypted point clouds compared to the original point clouds.

cs.CV↗

arXiv2025

HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation

Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point clouds. While recent Mamba-based approaches offer efficient processing with linear complexity, they struggle with feature representation when extracting 3D features. However, effectively combining these complementary strengths remains an open challenge in this field. In this paper, we propose HybridTM, the first hybrid architecture that integrates Transformer and Mamba for 3D semantic segmentation. In addition, we propose the Inner Layer Hybrid Strategy, which combines attention and Mamba at a finer granularity, enabling simultaneous capture of long-range dependencies and fine-grained local features. Extensive experiments demonstrate the effectiveness and generalization of our HybridTM on diverse indoor and outdoor datasets. Furthermore, our HybridTM achieves state-of-the-art performance on ScanNet, ScanNet200, and nuScenes benchmarks. The code will be made available at https://github.com/deepinact/HybridTM.

cs.CV↗

arXiv2025

PDCNet: a benchmark and general deep learning framework for activity prediction of peptide-drug conjugates

Peptide-drug conjugates (PDCs) represent a promising therapeutic avenue for human diseases, particularly in cancer treatment. Systematic elucidation of structure-activity relationships (SARs) and accurate prediction of the activity of PDCs are critical for the rational design and optimization of these conjugates. To this end, we carefully design and construct a benchmark PDCs dataset compiled from literature-derived collections and PDCdb database, and then develop PDCNet, the first unified deep learning framework for forecasting the activity of PDCs. The architecture systematically captures the complex factors underlying anticancer decisions of PDCs in real-word scenarios through a multi-level feature fusion framework that collaboratively characterizes and learns the features of peptides, linkers, and payloads. Leveraging a curated PDCs benchmark dataset, comprehensive evaluation results show that PDCNet demonstrates superior predictive capability, with the highest AUC, F1, MCC and BA scores of 0.9213, 0.7656, 0.7071 and 0.8388 for the test set, outperforming eight established traditional machine learning models. Multi-level validations, including 5-fold cross-validation, threshold testing, ablation studies, model interpretability analysis and external independent testing, further confirm the superiority, robustness, and usability of the PDCNet architecture. We anticipate that PDCNet represents a novel paradigm, incorporating both a benchmark dataset and advanced models, which can accelerate the design and discovery of new PDC-based therapeutic agents.

cs.LG↗

arXiv2025

Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning

Large Multimodal Models (LMMs) face limitations in geometric reasoning due to insufficient Chain of Thought (CoT) image-text training data. While existing approaches leverage template-based or LLM-assisted methods for geometric CoT data creation, they often face challenges in achieving both diversity and precision. To bridge this gap, we introduce a two-stage Theorem-Validated Reverse Chain-of-Thought Reasoning Synthesis (TR-CoT) framework. The first stage, TR-Engine, synthesizes theorem-grounded geometric diagrams with structured descriptions and properties. The second stage, TR-Reasoner, employs reverse reasoning to iteratively refine question-answer pairs by cross-validating geometric properties and description fragments. Our approach expands theorem-type coverage, corrects long-standing misunderstandings, and enhances geometric reasoning. Fine-grained CoT improves theorem understanding and increases logical consistency by 24.5%. Our best models surpass the baselines in MathVista and GeoQA by 10.1% and 4.7%, outperforming advanced closed-source models like GPT-4o.

cs.AI↗