arXiv subjects

Yifan Tian

Publications and source records attributed to Yifan Tian.

14 recordsLinked to original sources

arXiv2026

RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation

Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image aggregation under occlusions and constrained viewpoints. To mitigate the impact of such inconsistency, we propose RAG-3DSG, which introduces re-shot guided uncertainty estimation. By measuring the semantic consistency between original limited viewpoints and re-shot optimal viewpoints, this method quantifies the underlying semantic ambiguity of each graph object. Based on this quantification, we devise an Object-level Retrieval-Augmented Generation (RAG) that leverages low-uncertainty objects as semantic anchors to retrieve more reliable contextual knowledge, enabling a Vision-Language Model to rectify the predictions of uncertain objects and optimize the final 3DSG. Extensive evaluations across three challenging benchmarks and real-world robot trials demonstrate that RAG-3DSG achieves superior recall and precision, effectively mitigating semantic noise to provide highly reliable scene representations for robotics tasks.

cs.CV↗

arXiv2026

Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics

While 3D Scene Graphs (3DSGs) provide crucial structured representations for embodied agents, conventional Ahead-of-Time, build-everything-then-filter pipelines conflict with the real-time, low-latency demands of edge platforms, inducing a perceptual saturation effect via severe observation redundancy. To resolve this, we present JITOMA (Just-In-Time On-demand Memory Activation), a closed-loop framework that unifies task reasoning, perception, and memory into a just-in-time growth process. Instead of exhaustively mapping the entire environment, JITOMA leverages a top-down task heatmap at the frontend to filter continuous observations, routing minimal streams to maintain a global foundation of low-cost, dormant anchors. Upon a cognitive query, the backend Large Language Model (LLM) parses the robotic intent to dynamically awaken task-relevant anchors, triggering resource-intensive operations -- such as dense node captioning and functional inference -- exclusively within the activated local subgraph. To evaluate these dynamic capabilities and study perceptual saturation trade-offs, we introduce JITOMA-Bench, a comprehensive suite for long-horizon multi-tasking and complex multi-step reasoning. Extensive experiments demonstrate that JITOMA substantially reduces active graph size and captioning latency, while maintaining stable processing time under long-horizon task switching.

cs.CV↗

arXiv2026

DynNPC: Finding More Violations Induced by ADS in Simulation Testing through Dynamic NPC Behavior Generation

Recently, a number of simulation testing approaches have been proposed to generate diverse driving scenarios for autonomous driving systems (ADSs) testing. However, the behaviors of NPC vehicles in these scenarios generated by previous approaches are predefined and mutated before simulation execution, ignoring traffic signals and the behaviors of the Ego vehicle. Thus, a large number of the violations they found are induced by unrealistic behaviors of NPC vehicles, revealing no bugs of ADSs. Besides, the vast scenario search space of NPC behaviors during the iterative mutations limits the efficiency of previous approaches. To address these limitations, we propose a novel scenario-based testing framework, DynNPC, to generate more violation scenarios induced by the ADS. Specifically, DynNPC allows NPC vehicles to dynamically generate behaviors using different driving strategies during simulation execution based on traffic signals and the real-time behavior of the Ego vehicle. We compare DynNPC with state-of-the-art scenario-based testing approaches. Our evaluation has demonstrated the effectiveness and efficiency of DynNPC in finding more violation scenarios induced by the ADS.

cs.SE↗

arXiv2025

Argus: Resilience-Oriented Safety Assurance Framework for End-to-End ADSs

End-to-end autonomous driving systems (ADSs), with their strong capabilities in environmental perception and generalizable driving decisions, are attracting growing attention from both academia and industry. However, once deployed on public roads, ADSs are inevitably exposed to diverse driving hazards that may compromise safety and degrade system performance. This raises a strong demand for resilience of ADSs, particularly the capability to continuously monitor driving hazards and adaptively respond to potential safety violations, which is crucial for maintaining robust driving behaviors in complex driving scenarios. To bridge this gap, we propose a runtime resilience-oriented framework, Argus, to mitigate the driving hazards, thus preventing potential safety violations and improving the driving performance of an ADS. Argus continuously monitors the trajectories generated by the ADS for potential hazards and, whenever the EGO vehicle is deemed unsafe, seamlessly takes control through a hazard mitigator. We integrate Argus with three state-of-the-art end-to-end ADSs, i.e., TCP, UniAD and VAD. Our evaluation has demonstrated that Argus effectively and efficiently enhances the resilience of ADSs, improving the driving score of the ADS by up to 150.30% on average, and preventing up to 64.38% of the violations, with little additional time overhead.

cs.AI↗

arXiv2025

Building Floor Number Estimation from Crowdsourced Street-Level Images: Munich Dataset and Baseline Method

Accurate information on the number of building floors, or above-ground storeys, is essential for household estimation, utility provision, risk assessment, evacuation planning, and energy modeling. Yet large-scale floor-count data are rarely available in cadastral and 3D city databases. This study proposes an end-to-end deep learning framework that infers floor numbers directly from unrestricted, crowdsourced street-level imagery, avoiding hand-crafted features and generalizing across diverse facade styles. To enable benchmarking, we release the Munich Building Floor Dataset, a public set of over 6800 geo-tagged images collected from Mapillary and targeted field photography, each paired with a verified storey label. On this dataset, the proposed classification-regression network attains 81.2% exact accuracy and predicts 97.9% of buildings within +/-1 floor. The method and dataset together offer a scalable route to enrich 3D city models with vertical information and lay a foundation for future work in urban informatics, remote sensing, and geographic information science. Source code and data will be released under an open license at https://github.com/ya0-sun/Munich-SVI-Floor-Benchmark.

cs.CV↗

arXiv2025

Observation of molecular and polymeric nitrogen stuffed NaCl ionic layers

Sodium chloride (NaCl), a ubiquitous and chemically stable compound, has been considered inert under ambient conditions. Its typical B1 structure is highly isotropic without preferential direction, favoring the growth of a three-dimensional network of strong Na-Cl ionic bonds. Here, we employ first-principles structural searching and synchrotron X-ray diffraction to unravel an unexpected chemical reaction between NaCl and N2 to produce a hybrid salt-NaCl(N2)2, where N2 molecules break the isotropic NaCl structure into two-dimensional layers upon synthesis at 50 GPa. In contrast to the insulating properties of pristine NaCl, the electronic bandgap of the N2-stuffed NaCl narrowed to 1.8 eV, becoming an indirect bandgap semiconductor. Further compression to 130 GPa induced the polymerization of N atoms into zigzag N-chains. Our findings not only demonstrate the possibility of unusual N-chemistry under extreme conditions, but also suggest a feasible approach for the design of layered NaCl frameworks to modulate the polymerization of nitrogen.

cond-mat.mtrl-sci↗

arXiv2024

Who Gets Recommended? Investigating Gender, Race, and Country Disparities in Paper Recommendations from Large Language Models

This paper investigates the performance of several representative large models in the tasks of literature recommendation and explores potential biases in research exposure. The results indicate that not only LLMs' overall recommendation accuracy remains limited but also the models tend to recommend literature with greater citation counts, later publication date, and larger author teams. Yet, in scholar recommendation tasks, there is no evidence that LLMs disproportionately recommend male, white, or developed-country authors, contrasting with patterns of known human biases.

cs.IR↗

arXiv2024

The Unique Taste of LLMs for Papers: Potential issues in Using LLMs for Digital Library Document Recommendation Tasks

This paper investigates the performance of several representative large models in the field of literature recommendation and explores potential biases. The results indicate that while some large models' recommendations can be somewhat satisfactory after simple manual screening, overall, the accuracy of these models in specific literature recommendation tasks is generally moderate. Additionally, the models tend to recommend literature that is timely, collaborative, and expands or deepens the field. In scholar recommendation tasks. There is no evidence to suggest that LLMs exacerbate inequalities related to gender, race, or the level of development of countries.

cs.DL↗

arXiv2023

Towards Large-scale Building Attribute Mapping using Crowdsourced Images: Scene Text Recognition on Flickr and Problems to be Solved

Crowdsourced platforms provide huge amounts of street-view images that contain valuable building information. This work addresses the challenges in applying Scene Text Recognition (STR) in crowdsourced street-view images for building attribute mapping. We use Flickr images, particularly examining texts on building facades. A Berlin Flickr dataset is created, and pre-trained STR models are used for text detection and recognition. Manual checking on a subset of STR-recognized images demonstrates high accuracy. We examined the correlation between STR results and building functions, and analysed instances where texts were recognized on residential buildings but not on commercial ones. Further investigation revealed significant challenges associated with this task, including small text regions in street-view images, the absence of ground truth labels, and mismatches in buildings in Flickr images and building footprints in OpenStreetMap (OSM). To develop city-wide mapping beyond urban hotspot locations, we suggest differentiating the scenarios where STR proves effective while developing appropriate algorithms or bringing in additional data for handling other cases. Furthermore, interdisciplinary collaboration should be undertaken to understand the motivation behind building photography and labeling. The STR-on-Flickr results are publicly available at https://github.com/ya0-sun/STR-Berlin.

cs.CV↗

arXiv2020

Matrix product state recursion methods for strongly correlated quantum systems

We present a method for extrapolation of real-time dynamical correlation functions which can improve the capability of matrix product state methods to compute spectral functions. Unlike the widely used linear prediction method, which ignores the origin of the data being extrapolated, our recursion methods utilize a representation of the wavefunction in terms of an expansion of the same wavefunction and its translations at earlier times. This recursion method is exact for a noninteracting Fermi system. Surprisingly, the recursion method is also more robust than linear prediction at large interaction strength. We test this method on the Hubbard two-leg ladder and present more accurate results for the spectral function than previous studies.

cond-mat.str-el↗

arXiv2019

Mapping the Hubbard model to the t-J model using ground state unitary transformations

The effective low-energy models of the Hubbard model are usually derived from perturbation theory. Here we derive the effective model of the Hubbard model in spin space and t-J space using a unitary transformation from numerical optimization. We represent the Hamiltonian as Matrix product state(MPO) and represent the unitary transformation using gates according to tensor network methods. We obtain this unitary transformation by optimizing the unitary transformation between the ground state of the Hubbard model and the projection of the Hubbard model ground state into spin space and t-J space. The unitary transformation we get from numerical optimization yields effective models that are in line with perturbation theories. This numerical optimization method starting from ground state provides another approach to analyze effective low-energy models of strongly correlated electron systems.

cond-mat.str-el↗

arXiv2019

Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications

Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data. Existing approaches, however, primarily focus on improving accuracy and overlook other aspects such as robustness and interpretability. In this paper, we propose adversarial modifications for link prediction models: identifying the fact to add into or remove from the knowledge graph that changes the prediction for a target fact after the model is retrained. Using these single modifications of the graph, we identify the most influential fact for a predicted link and evaluate the sensitivity of the model to the addition of fake facts. We introduce an efficient approach to estimate the effect of such modifications by approximating the change in the embeddings when the knowledge graph changes. To avoid the combinatorial search over all possible facts, we train a network to decode embeddings to their corresponding graph components, allowing the use of gradient-based optimization to identify the adversarial modification. We use these techniques to evaluate the robustness of link prediction models (by measuring sensitivity to additional facts), study interpretability through the facts most responsible for predictions (by identifying the most influential neighbors), and detect incorrect facts in the knowledge base.

cs.LG↗

arXiv2019

CPAR: Cloud-Assisted Privacy-preserving Image Annotation with Randomized KD-Forest

With the explosive growth in the number of pictures taken by smartphones, organizing and searching pictures has become important tasks. To efficiently fulfill these tasks, the key enabler is annotating images with proper keywords, with which keyword-based searching and organizing become available for images. Currently, smartphones usually synchronize photo albums with cloud storage platforms, and have their images annotated with the help of cloud computing. However, the "offloading-to-cloud" solution may cause privacy breach, since photos from smart photos contain various sensitive information. For privacy protection, existing research made effort to support cloud-based image annotation on encrypted images by utilizing cryptographic primitives. Nevertheless, for each annotation, it requires the cloud to perform linear checking on the large-scale encrypted dataset with high computational cost. This paper proposes a cloud-assisted privacy-preserving image annotation with randomized kd-forest, namely CPAR. With CPAR, users are able to automatically assign keywords to their images by leveraging the power of cloud with privacy protected. CPAR proposes a novel privacy-preserving randomized kd-forest structure, which significantly improves the annotation performance compared with existing research. Thorough analysis is carried out to demonstrate the security of CPAR. Experimental evaluation on the well-known IAPR TC-12 dataset validates the efficiency and effectiveness of CPAR.

cs.CR↗

arXiv2019

LEP-CNN: A Lightweight Edge Device Assisted Privacy-preserving CNN Inference Solution for IoT

Supporting convolutional neural network (CNN) inference on resource-constrained IoT devices in a timely manner has been an outstanding challenge for emerging smart systems. To mitigate the burden on IoT devices, the prevailing solution is to offload the CNN inference task, which is usually composed of billions of operations, to public cloud. However, the "offloading-to-cloud" solution may cause privacy breach while moving sensitive data to cloud. For privacy protection, the research community has resorted to advanced cryptographic primitives and approximation techniques to support CNN inference on encrypted data. Consequently, these attempts cause impractical computational overhead on IoT devices and degrade the performance of CNNs. Moreover, relying on the remote cloud can cause additional network latency and even make the system dysfunction when network connection is off. We proposes an extremely lightweight edge device assisted private CNN inference solution for IoT devices, namely LEP-CNN. The main design of LEP-CNN is based on a novel online/offline encryption scheme. The decryption of LEP-CNN is pre-computed offline via utilizing the linear property of the most time-consuming operations of CNNs. As a result, LEP-CNN allows IoT devices to securely offload over 99% CNN operations, and edge devices to execute CNN inference on encrypted data as efficient as on plaintext. LEP-CNN also provides an integrity check option to help IoT devices detect error results with a successful rate over 99%. Experiments on AlexNet show that LEP-CNN can speed up the CNN inference for more than 35 times for resource constrained IoT devices. A homomorphic encryption based AlexNet using CryptoNets is implemented to compare with LEP-CNN to demonstrate that LEP-CNN has a better performance than homomorphic encryption based privacy preserving neural networks under time-sensitive scenarios.

cs.CR↗