arXiv subjects

Yu Meng

Publications and source records attributed to Yu Meng.

At least 55 records · Page 3Linked to original sources

arXiv2025

DragOSM: Extract Building Roofs and Footprints from Aerial Images by Aligning Historical Labels

Extracting polygonal roofs and footprints from remote sensing images is critical for large-scale urban analysis. Most existing methods rely on segmentation-based models that assume clear semantic boundaries of roofs, but these approaches struggle in off- nadir images, where the roof and footprint are significantly displaced, and facade pixels are fused with the roof boundary. With the increasing availability of open vector map annotations, e.g., OpenStreetMap, utilizing historical labels for off-nadir image annotation has become viable because remote sensing images are georeferenced once captured. However, these historical labels commonly suffer from significant positional discrepancies with new images and only have one annotation (roof or footprint), which fails to describe the correct structures of a building. To address these discrepancies, we first introduce a concept of an alignment token, which encodes the correction vector to guide the label correction. Based on this concept, we then propose Drag OpenStreetMap Labels (DragOSM), a novel model designed to align dislocated historical labels with roofs and footprints. Specifically, DragOSM formulates the label alignment as an interactive denoising process, modeling the positional discrepancy as a Gaussian distribution. During training, it learns to correct these errors by simulating misalignment with random Gaussian perturbations; during inference, it iteratively refines the positions of input labels. To validate our method, we further present a new dataset, Repairing Buildings in OSM (ReBO), comprising 179,265 buildings with both OpenStreetMap and manually corrected annotations across 5,473 images from 41 cities. Experimental results on ReBO demonstrate the effectiveness of DragOSM. Code, dataset, and trained models are publicly available at https://github.com/likaiucas/DragOSM.git.

cs.CV↗

arXiv2025

SOPSeg: Prompt-based Small Object Instance Segmentation in Remote Sensing Imagery

Extracting small objects from remote sensing imagery plays a vital role in various applications, including urban planning, environmental monitoring, and disaster management. While current research primarily focuses on small object detection, instance segmentation for small objects remains underexplored, with no dedicated datasets available. This gap stems from the technical challenges and high costs of pixel-level annotation for small objects. While the Segment Anything Model (SAM) demonstrates impressive zero-shot generalization, its performance on small-object segmentation deteriorates significantly, largely due to the coarse 1/16 feature resolution that causes severe loss of fine spatial details. To this end, we propose SOPSeg, a prompt-based framework specifically designed for small object segmentation in remote sensing imagery. It incorporates a region-adaptive magnification strategy to preserve fine-grained details, and employs a customized decoder that integrates edge prediction and progressive refinement for accurate boundary delineation. Moreover, we introduce a novel prompting mechanism tailored to the oriented bounding boxes widely adopted in remote sensing applications. SOPSeg outperforms existing methods in small object segmentation and facilitates efficient dataset construction for remote sensing tasks. We further construct a comprehensive small object instance segmentation dataset based on SODA-A, and will release both the model and dataset to support future research.

cs.CV↗

arXiv2025

IRSAMap:Towards Large-Scale, High-Resolution Land Cover Map Vectorization

With the enhancement of remote sensing image resolution and the rapid advancement of deep learning, land cover mapping is transitioning from pixel-level segmentation to object-based vector modeling. This shift demands more from deep learning models, requiring precise object boundaries and topological consistency. However, existing datasets face three main challenges: limited class annotations, small data scale, and lack of spatial structural information. To overcome these issues, we introduce IRSAMap, the first global remote sensing dataset for large-scale, high-resolution, multi-feature land cover vector mapping. IRSAMap offers four key advantages: 1) a comprehensive vector annotation system with over 1.8 million instances of 10 typical objects (e.g., buildings, roads, rivers), ensuring semantic and spatial accuracy; 2) an intelligent annotation workflow combining manual and AI-based methods to improve efficiency and consistency; 3) global coverage across 79 regions in six continents, totaling over 1,000 km; and 4) multi-task adaptability for tasks like pixel-level classification, building outline extraction, road centerline extraction, and panoramic segmentation. IRSAMap provides a standardized benchmark for the shift from pixel-based to object-based approaches, advancing geographic feature automation and collaborative modeling. It is valuable for global geographic information updates and digital twin construction. The dataset is publicly available at https://github.com/ucas-dlg/IRSAMap

cs.CV↗

arXiv2025

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective

Large Language Models (LLMs) have revolutionized artificial intelligence with capabilities in reasoning, coding, and communication, driving innovation across industries. Their true potential depends on effective alignment to ensure correct, trustworthy and ethical behavior, addressing challenges like misinformation, hallucinations, bias and misuse. While existing Reinforcement Learning (RL)-based alignment methods are notoriously complex, direct optimization approaches offer a simpler alternative. In this work, we introduce a novel direct optimization approach for LLM alignment by drawing on established Information Retrieval (IR) principles. We present a systematic framework that bridges LLM alignment and IR methodologies, mapping LLM generation and reward models to IR's retriever-reranker paradigm. Building on this foundation, we propose LLM Alignment as Retriever Preference Optimization (LarPO), a new alignment method that enhances overall alignment quality. Extensive experiments validate LarPO's effectiveness with 38.9 % and 13.7 % averaged improvement on AlpacaEval2 and MixEval-Hard respectively. Our work opens new avenues for advancing LLM alignment by integrating IR foundations, offering a promising direction for future research.

cs.CL↗

arXiv2025

GLD-Road:A global-local decoding road network extraction model for remote sensing images

Road networks are crucial for mapping, autonomous driving, and disaster response. While manual annotation is costly, deep learning offers efficient extraction. Current methods include postprocessing (prone to errors), global parallel (fast but misses nodes), and local iterative (accurate but slow). We propose GLD-Road, a two-stage model combining global efficiency and local precision. First, it detects road nodes and connects them via a Connect Module. Then, it iteratively refines broken roads using local searches, drastically reducing computation. Experiments show GLD-Road outperforms state-of-the-art methods, improving APLS by 1.9% (City-Scale) and 0.67% (SpaceNet3). It also reduces retrieval time by 40% vs. Sat2Graph (global) and 92% vs. RNGDet++ (local). The experimental results are available at https://github.com/ucas-dlg/GLD-Road.

cs.CV↗

arXiv2025

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limited by its sequential token generation process, where each token must be generated before the next can be processed. This sequential dependency restricts the ability to fully leverage modern hardware's parallel processing capabilities. Existing methods like speculative decoding and layer skipping offer potential speedups but have notable drawbacks: speculative decoding relies on an auxiliary "drafter" model, which can be challenging to acquire and increases memory overhead, while layer skipping may introduce discrepancies in the outputs due to the missing key-value cache at skipped layers. In this work, we propose AdaDecode, which accelerates LLM decoding without requiring auxiliary models or changes to the original model parameters, while ensuring output consistency. AdaDecode leverages the insight that many tokens can accurately be generated at intermediate layers, as further layers often do not significantly alter predictions once the model reaches a certain confidence. By adaptively generating tokens at intermediate layers when confidence is high, AdaDecode enables the next token's computation to begin immediately. The remaining layer computations for early-predicted tokens are deferred and executed in parallel with subsequent tokens when needed, maximizing hardware utilization and reducing decoding latency. A final verification step ensures that early predictions match the results of standard autoregressive decoding, preserving output parity. Experiments across diverse generation tasks shows that AdaDecode consistently achieves superior decoding throughput with up to 1.73x speedup, while guaranteeing output parity with standard autoregressive decoding.

cs.CL↗

arXiv2025

RAST: Reasoning Activation in LLMs via Small-model Transfer

Reinforcement learning (RL) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs), as evidenced by recent successes such as OpenAI's o1 and Deepseek-R1. However, applying RL at scale remains intimidatingly resource-intensive, requiring multiple model copies and extensive GPU workloads. On the other hand, while being powerful, recent studies suggest that RL does not fundamentally endow models with new knowledge; rather, it primarily reshapes the model's output distribution to activate reasoning capabilities latent in the base model. Building on this insight, we hypothesize that the changes in output probabilities induced by RL are largely model-size invariant, opening the door to a more efficient paradigm: training a small model with RL and transferring its induced probability shifts to larger base models. To verify our hypothesis, we conduct a token-level analysis of decoding trajectories and find high alignment in RL-induced output distributions across model scales, validating our hypothesis. Motivated by this, we propose RAST, a simple yet effective method that transfers reasoning behaviors by injecting RL-induced probability adjustments from a small RL-trained model into larger models. Experiments across multiple mathematical reasoning benchmarks show that RAST substantially and consistently enhances the reasoning capabilities of base models while requiring significantly lower GPU memory than direct RL training, sometimes even yielding better performance than the RL-trained counterparts. Our findings offer new insights into the nature of RL-driven reasoning and practical strategies for scaling its benefits without incurring its full computational cost. The project page of RAST is available at https://ozyyshr.github.io/RAST/.

cs.LG↗

arXiv2025

PolyFootNet: Extracting Polygonal Building Footprints in Off-Nadir Remote Sensing Images

Extracting polygonal building footprints from off-nadir imagery is crucial for diverse applications. Current deep-learning-based extraction approaches predominantly rely on semantic segmentation paradigms and post-processing algorithms, limiting their boundary precision and applicability. However, existing polygonal extraction methodologies are inherently designed for near-nadir imagery and fail under the geometric complexities introduced by off-nadir viewing angles. To address these challenges, this paper introduces Polygonal Footprint Network (PolyFootNet), a novel deep-learning framework that directly outputs polygonal building footprints without requiring external post-processing steps. PolyFootNet employs a High-Quality Mask Prompter to generate precise roof masks, which guide polygonal vertex extraction in a unified model pipeline. A key contribution of PolyFootNet is introducing the Self Offset Attention mechanism, grounded in Nadaraya-Watson regression, to effectively mitigate the accuracy discrepancy observed between low-rise and high-rise buildings. This approach allows low-rise building predictions to leverage angular corrections learned from high-rise building offsets, significantly enhancing overall extraction accuracy. Additionally, motivated by the inherent ambiguity of building footprint extraction tasks, we systematically investigate alternative extraction paradigms and demonstrate that a combined approach of building masks and offsets achieves superior polygonal footprint results. Extensive experiments validate PolyFootNet's effectiveness, illustrating its promising potential as a robust, generalizable, and precise polygonal building footprint extraction method from challenging off-nadir imagery. To facilitate further research, we will release pre-trained weights of our offset prediction module at https://github.com/likaiucas/PolyFootNet.

cs.CV↗

arXiv2025

Lattice calculation of the $η_cη_c$ and $J/ψJ/ψ$ s-wave scattering length

We calculate the s-wave scattering length in the $0^+$ sector of $η_cη_c$ and the $2^+$ sector of $J/ψJ/ψ$ using three $N_f=2$ twisted mass gauge ensembles with the lattice spacing $a=0.0667,0.085,0.098$ fm, respectively. The scattering lengths are extracted using the conventional L{ü}scher finite size method. We observe sizable discretization effects and the results after a continuum extrapolation are $a^{0^+}_{η_cη_c}=-0.104(09)$ fm and $a^{2^+}_{J/ψJ/ψ}=-0.165(16)$ fm. The slight difference of light quark mass is ignored in this study. Our results indicate that the interaction between the two respective charmonia are repulsive in nature in both cases.

hep-lat↗

arXiv2025

InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce misleading or even erroneous information to the retrieved contents, posing a significant challenge to the generation quality. Existing RAG methods typically address this challenge by directly predicting final answers despite potentially noisy inputs, resulting in an implicit denoising process that is difficult to interpret and verify. On the other hand, the acquisition of explicit denoising supervision is often costly, involving significant human efforts. In this work, we propose InstructRAG, where LMs explicitly learn the denoising process through self-synthesized rationales -- First, we instruct the LM to explain how the ground-truth answer is derived from retrieved documents. Then, these rationales can be used either as demonstrations for in-context learning of explicit denoising or as supervised fine-tuning data to train the model. Compared to standard RAG approaches, InstructRAG requires no additional supervision, allows for easier verification of the predicted answers, and effectively improves generation accuracy. Experiments show InstructRAG consistently outperforms existing RAG methods in both training-free and trainable scenarios, achieving a relative improvement of 8.3% over the best baseline method on average across five knowledge-intensive benchmarks. Extensive analysis indicates that InstructRAG scales well with increased numbers of retrieved documents and consistently exhibits robust denoising ability even in out-of-domain datasets, demonstrating strong generalizability.

cs.CL↗

arXiv2025

Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model

More accurate extraction of invisible building footprints from very-high-resolution (VHR) aerial images relies on roof segmentation and roof-to-footprint offset extraction. Existing methods based on instance segmentation suffer from poor generalization when extended to large-scale data production and fail to achieve low-cost human interaction. This prompt paradigm inspires us to design a promptable framework for roof and offset extraction, and transforms end-to-end algorithms into promptable methods. Within this framework, we propose a novel Offset-Building Model (OBM). Based on prompt prediction, we first discover a common pattern of predicting offsets and tailored Distance-NMS (DNMS) algorithms for offset optimization. To rigorously evaluate the algorithm's capabilities, we introduce a prompt-based evaluation method, where our model reduces offset errors by 16.6\% and improves roof Intersection over Union (IoU) by 10.8\% compared to other models. Leveraging the common patterns in predicting offsets, DNMS algorithms enable models to further reduce offset vector loss by 6.5\%. To further validate the generalization of models, we tested them using a newly proposed test set, Huizhou test set, with over 7,000 manually annotated instance samples. Our algorithms and dataset will be available at https://github.com/likaiucas/OBM.

cs.CV↗

arXiv2025

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a range of multimodal tasks. However, their inference efficiency is constrained by the large number of visual tokens processed during decoding. To address this challenge, we propose Per-Layer Per-Head Vision Token Pruning (PLPHP), a two-level fine-grained pruning method including Layer-Level Retention Rate Allocation and Head-Level Vision Token Pruning. Motivated by the Vision Token Re-attention phenomenon across decoder layers, we dynamically adjust token retention rates layer by layer. Layers that exhibit stronger attention to visual information preserve more vision tokens, while layers with lower vision attention are aggressively pruned. Furthermore, PLPHP applies pruning at the attention head level, enabling different heads within the same layer to independently retain critical context. Experiments on multiple benchmarks demonstrate that PLPHP delivers an 18% faster decoding speed and reduces the Key-Value Cache (KV Cache) size by over 50%, all at the cost of 0.46% average performance drop, while also achieving notable performance improvements in multi-image tasks. These results highlight the effectiveness of fine-grained token pruning and contribute to advancing the efficiency and scalability of LVLMs. Our source code will be made publicly available.

cs.CV↗

arXiv2025

Seed-Guided Topic Discovery with Out-of-Vocabulary Seeds

Discovering latent topics from text corpora has been studied for decades. Many existing topic models adopt a fully unsupervised setting, and their discovered topics may not cater to users' particular interests due to their inability of leveraging user guidance. Although there exist seed-guided topic discovery approaches that leverage user-provided seeds to discover topic-representative terms, they are less concerned with two factors: (1) the existence of out-of-vocabulary seeds and (2) the power of pre-trained language models (PLMs). In this paper, we generalize the task of seed-guided topic discovery to allow out-of-vocabulary seeds. We propose a novel framework, named SeeTopic, wherein the general knowledge of PLMs and the local semantics learned from the input corpus can mutually benefit each other. Experiments on three real datasets from different domains demonstrate the effectiveness of SeeTopic in terms of topic coherence, accuracy, and diversity.

cs.CL↗

arXiv2025

SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion

Recent advances in diffusion models have led to significant progress in audio-driven lip synchronization. However, existing methods typically rely on constrained audio-visual alignment priors or multi-stage learning of intermediate representations to force lip motion synthesis. This leads to complex training pipelines and limited motion naturalness. In this paper, we present SayAnything, a conditional video diffusion framework that directly synthesizes lip movements from audio input while preserving speaker identity. Specifically, we propose three specialized modules including identity preservation module, audio guidance module, and editing control module. Our novel design effectively balances different condition signals in the latent space, enabling precise control over appearance, motion, and region-specific generation without requiring additional supervision signals or intermediate representations. Extensive experiments demonstrate that SayAnything generates highly realistic videos with improved lip-teeth coherence, enabling unseen characters to say anything, while effectively generalizing to animated characters.

cs.CV↗

arXiv2025

Exploring the boundary of quantum correlations with a time-domain optical processor

Contextuality is a hallmark feature of the quantum theory that captures its incompatibility with any noncontextual hidden-variable model. The Greenberger--Horne--Zeilinger (GHZ)-type paradoxes are proofs of contextuality that reveal this incompatibility with deterministic logical arguments. However, the GHZ-type paradox whose events can be included in the fewest contexts and which brings the strongest nonclassicality remains elusive. Here, we derive a GHZ-type paradox with a context-cover number of three and show this number saturates the lower bound posed by quantum theory. We demonstrate the paradox with a time-domain fiber optical platform and recover the quantum prediction in a 37-dimensional setup based on high-speed modulation, convolution, and homodyne detection of time-multiplexed pulsed coherent light. By proposing and studying a strong form of contextuality in high-dimensional Hilbert space, our results pave the way for the exploration of exotic quantum correlations with time-multiplexed optical systems.

quant-ph↗

arXiv2025

Lattice study of $J/ψ\rightarrow γη_c$ using a method without momentum extrapolation

We present a model-independent method to calculate the radiative transition without the momentum extrapolation for the off-shell transition factors. The on-shell transition factor is directly obtained from the lattice hadronic function. We apply the method to calculate the charmonium radiative transition $J/ψ\rightarrow γη_c$. After a continuous extrapolation under three lattice spacings, we obtain the on-shell transition factor as $V(0)=1.90(4)$, where the error is the statistical error that already takes into account the $a^2$-error in the continuous extrapolation. Finally, we determine the branching fraction of $J/ψ\rightarrow γη_c$ as $\operatorname{Br}(J/ψ\rightarrow γη_c)=2.49(11)_{\textrm{lat}}(5)_{\textrm{exp}}$, where the second error comes from the uncertainty of $J/ψ$ total decay width $92.6(1.7)$ keV.

hep-lat↗

arXiv2025

Charmed meson masses and decay constants in the continuum from the tadpole improved clover ensembles

We present the determination of the charm quark mass, the masses, and decay constants of charmed mesons using thirteen 2+1 flavor gauge ensembles at five different lattice spacings $a\in[0.05,0.11]$ fm, 8 pion masses $m_π\in(130,360)$ MeV, and several values of the strange quark mass, which facilitate us to do the chiral and continuum extrapolation. These ensembles are generated through the stout smeared clover fermion action and Symanzik gauge actions with the tadpole improvement. By absorbing the discretization errors into the masses and field normalization of the charm quark, we manage to suppress the discretization error of the charmed meson mass and all the S-wave open charmed meson decay constants to a few percent or even less at lattice spacing $ a \sim 0.1 $ fm. Moreover, discretization errors for other quantities are also significantly reduced. The continuum extrapolated charm quark mass, $m_c(m_c)=1.2933(72)(95)$ GeV in $\overline{\textrm{MS}}$ scheme, is determined using QED-subtracted $D_s$ meson mass and non-perturbative renormalization. Predictions of the open and close charm mesons using this charm quark mass agree with the experimental values at 0.1-0.5\% level uncertainty. We obtained $D_{(s)}$ decay constants and also by far the most precise $D_{(s)}^*$ decay constants $f_{D^*}=0.2292(26)(17)$ GeV and $f_{D^*_s}=0.2691(30)(03)$ GeV.

hep-lat↗

arXiv2024

Pion mass dependence in $Dπ$ scattering and the $D_0^*(2300)$ resonance from lattice QCD

Lattice QCD results for isospin $I=\frac{1}{2}$ $Dπ$ scattering are presented. Utilizing a series of $N_{\text{f}}=2+1$ Wilson-Clover ensembles with pion masses of $m_π\approx 132, 208, 305$ and $317$ MeV, various two-particle operators are constructed and the corresponding finite-volume spectra are determined. The $S$ and $P$-wave scattering phase shifts are then extracted using the Lüscher approach. A clear trend for the motion of the $D_0^*(2300)$ pole is identified. With the physical pion mass configurations also included, this calculation constitutes the first lattice calculation in which the pion mass dependence of the $D_0^*(2300)$ pole is investigated and the scattering lengths are extrapolated/interpolated to the physical pion mass in $Dπ$ scattering.

hep-lat↗