arXiv subjects

Yu Meng

Publications and source records attributed to Yu Meng.

At least 37 records · Page 2Linked to original sources

arXiv2026

Lattice determination of the neutrino background for $J/\psi \rightarrow \gamma + \textrm{invisible}$

Searching for dark matter is a primary goal of modern astronomy and particle physics. Invisible decays of heavy quarkonia are particularly promising for probing light dark matter, attracting broad interest due to their unique sensitivity. Experiments searching for radiative invisible decays of the $J/\psi$ have steadily improved upper limits, and upcoming facilities will push sensitivity further--making the precise determination and subtraction of the neutrino background indispensable. Here, we present the first lattice QCD calculation of the Standard Model decay $J/\psi \to \gamma\nu\bar{\nu}$, an irreducible background to $J/\psi \rightarrow \gamma + \textrm{invisible}$. Our result for the branching fraction is $\operatorname{Br}(J/\psi \rightarrow \gamma\nu\bar{\nu})=1.04(7)(8)\times 10^{-10}$, where the first uncertainty is statistical and the second is our systematic estimate. This work advances lattice-based determinations of neutrino backgrounds to quarkonium invisible decays, delivering an ab initio benchmark for $J/\psi \rightarrow \gamma + \textrm{invisible}$. Our approach generalizes to other quarkonium channels (e.g., $\Upsilon/\phi \rightarrow \gamma+\textrm{invisible}$) and provides critical theoretical support for dark matter searches at colliders.

hep-lat↗

arXiv2025

Form factors of the $D_s \to \phi \ell \nu_\ell$ semileptonic decay with (2+1)-flavor lattice QCD

We present a systematic lattice calculation of the vector and axial vector form factors $V$ and $A_i~(i=0,1,2)$ for the $D_s \to \phi \ell \nu_\ell$ semileptonic decay using (2+1)-flavor Wilson-clover fermion configurations generated by the CLQCD collaboration. Seven gauge ensembles with different lattice spacings, from $0.052~\text{fm}$ to $0.105~\text{fm}$, and different pion masses, from about $210~\text{MeV}$ to $320~\text{MeV}$ are utilized, enabling us to take both the continuum limit and physical pion mass extrapolation. The form factor ratios are obtained to be $r_V=1.614(19)$ and $r_2=0.741(31)$. Our results of form factors reach the precision of $1\%-4\%$, which greatly improves the previous lattice QCD results and obtains the most precise determination to date.

hep-lat↗

arXiv2025

AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning

Equipping large language models (LLMs) with search engines via reinforcement learning (RL) promises effective search agents. However, adaptively balancing internal parametric knowledge with external search remains a challenge, as overreliance on search introduces unnecessary cost and risks exposure to noisy or malicious content, while relying solely on parametric knowledge risks hallucination. Prior efforts mitigate search overuse through tool-call reward shaping, which requires heavy reward engineering and conflates necessary and unnecessary search. To address these limitations, we revisit the evaluation of search agents through an F1-based decision metric, revealing that prior methods often overlook readily available parametric knowledge. Motivated by this, we propose AdaSearch, a simple two-stage, outcome-driven RL framework that disentangles problem-solving from the decision to search, making the decision process explicit and interpretable. Extensive experiments demonstrate that AdaSearch significantly improves search-decision quality and reduces unnecessary search calls, with only a small trade-off in QA accuracy relative to always-search.

cs.CL↗

arXiv2025

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or specialized information. A natural strategy to increase the likelihood of retrieving relevant information is to expand the number of retrieved documents. However, involving more documents could introduce significant noise, as many documents may be irrelevant or misleading, thereby reducing the overall accuracy of the generated responses. To overcome the challenge associated with handling a larger number of documents, we propose WinnowRAG, a novel RAG framework designed to systematically filter out noisy documents while preserving valuable content -- a process we refer to as winnowing. WinnowRAG operates in two stages: In Stage I, we perform query-aware clustering to group similar documents and form distinct topic clusters. Each cluster is assigned to an LLM agent for generating a unique answer. In Stage II, we perform winnowing, wherein a critic LLM evaluates the outputs of multiple agents and iteratively separates useful documents from noisy ones. To retain useful documents when discarding agents, we propose two strategic merging techniques to ensure that only relevant knowledge is used for generating the final response. Crucially, WinnowRAG is model-agnostic and does not require any model fine-tuning, making it easily adaptable to various tasks. Extensive experiments on various realistic datasets demonstrate the effectiveness of WinnowRAG over state-of-the-art baselines.

cs.CL↗

arXiv2025

Study of the $D_s \to \phi \ell \nu_\ell$ semileptonic decay with (2+1)-flavor lattice QCD

We present a systematic lattice calculation of the $D_s \to \phi \ell \nu_\ell$ semileptonic decay using (2+1)-flavor Wilson-clover fermion configurations generated by the CLQCD collaboration. Seven gauge ensembles with different lattice spacings, from $0.052~\text{fm}$ to $0.105~\text{fm}$, and different pion masses, from about $210~\text{MeV}$ to $320~\text{MeV}$ are utilized, enabling us to take both the continuum limit and physical pion mass extrapolation. The ratios of form factors are obtained to be $r_V=1.614(19)$ and $r_2=0.741(31)$, with the precision improved by up to an order of magnitude compared to previous lattice studies. The branching fractions are given as $\mathcal{B}(D_s\to\phi e\nu_e)=2.493(66)_{\text{stat}}(31)_{|V_{cs}|}\times 10^{-2}$ and $\mathcal{B}(D_s\to\phi\mu\nu_\mu)=2.351(60)_{\text{stat}}(29)_{|V_{cs}|}\times 10^{-2}$. The corresponding ratio of the branching fractions between the lepton $\mu$ and $e$ is given by $\mathcal{R}_{\mu/e}=0.9432(13)$, which provides essential theoretical support for future high-precision experimental tests of the lepton flavor universality. The CKM matrix element $|V_{cs}|$ is also extracted to be $0.952(12)_{\text{stat}}(23)_{\text{PDG}}$ and $0.945(12)_{\text{stat}}(24)_{\text{PDG}}$ for the $\mu$ and $e$ channels, respectively.

hep-lat↗

arXiv2025

Contextuality-based quantum key distribution with deterministic single-photon sources

Photons are central to quantum technologies, with photonic qubits offering a promising platform for quantum communication. Semiconductor quantum dots stand out for their ability to generate single photons on demand, a key capability for enabling long-distance quantum networks. In this work, we utilize high-purity single-photon sources based on self-assembled InAs(Ga)As quantum dots as quantum information carriers. We demonstrate that such on-demand single photons can generate quantum contextuality. This capability enables a novel protocol for semi-device-independent quantum key distribution over free-space channels. Crucially, our method does not require ideal or perfectly projective measurements, opening a new pathway for robust and practical quantum communication.

quant-ph↗

arXiv2025

A quantum-coherent photon--emitter interface in the original telecom band

Quantum dots stand out as the most advanced and versatile light-matter interface available today. Their ability to deliver high-quality, high-rate, and pure photons has set benchmarks that far surpass other emitters. Yet, a critical frontier has remained elusive: achieving these exceptional capabilities at telecom wavelengths, bridging the gap to fiber-optic infrastructure and scalable silicon photonics. Overcoming this challenge demands high quality quantum materials and devices which, despite extensive efforts, have not been realized yet. Here, we demonstrate waveguide-integrated quantum dots and realize a fully quantum-coherent photon-emitter interface operating in the original telecommunication band. The quality is assessed by recording transform-limited linewidths only 8 % broader than the inverse lifetime and bright 41.7 MHz emission rate under 80 MHz $\pi$-pulse excitation, unlocking the full potential of quantum dots for scalable quantum networks.

physics.optics↗

arXiv2025

Aligning Large Language Models via Fully Self-Synthetic Data

Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the collection of diverse prompts and corresponding responses, often necessitating external reward models or proprietary models like GPT-4 to annotate preference pairs. In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework for LLM alignment, where all training data, including prompts (i.e., user queries), responses, and preferences, are generated by the model itself. Specifically, SAO first instructs the LLM to engage in persona role-play and generate diverse prompts and responses, which are then self-evaluated for preference optimization. Extensive experiments demonstrate that SAO effectively enhances the model's chat capabilities on standard benchmarks like AlpacaEval~2.0, while maintaining strong performance on downstream objective tasks (e.g., question-answering, math reasoning). Our work provides a practical solution for self-improvement in aligning LLMs, and the code for reproducing our results is available at: https://github.com/SJY8460/SAO.

cs.CL↗

arXiv2025

Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents

Enabling large language models (LLMs) to utilize search tools offers a promising path to overcoming fundamental limitations such as knowledge cutoffs and hallucinations. Recent work has explored reinforcement learning (RL) for training search-augmented agents that interleave reasoning and retrieval before answering. These approaches usually rely on outcome-based rewards (e.g., exact match), implicitly assuming that optimizing for final answers will also yield effective intermediate search behaviors. Our analysis challenges this assumption: we uncover multiple systematic deficiencies in search that arise under outcome-only training and ultimately degrade final answer quality, including failure to invoke tools, invalid queries, and redundant searches. To address these shortcomings, we introduce DeSA (Decoupling Search-and-Answering), a simple two-stage training framework that explicitly separates search optimization from answer generation. In Stage 1, agents are trained to improve search effectiveness with retrieval recall-based rewards. In Stage 2, outcome rewards are employed to optimize final answer generation. Across seven QA benchmarks, DeSA-trained agents consistently improve search behaviors, delivering substantially higher search recall and answer accuracy than outcome-only baselines. Notably, DeSA outperforms single-stage training approaches that simultaneously optimize recall and outcome rewards, underscoring the necessity of explicitly decoupling the two objectives.

cs.AI↗

arXiv2025

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric knowledge. Indeed, truthfulness requires more than accuracy -- models must also recognize uncertainty and abstain when unsure to avoid hallucinations. This presents a fundamental challenge for existing methods: approaches that optimize for accuracy often amplify hallucinations, while those that encourage abstention can become overly conservative, sacrificing correct answers. Both extremes ultimately compromise truthfulness. In this work, we present TruthRL, a general reinforcement learning (RL) framework that directly optimizes the truthfulness of LLMs. Specifically, we implement TruthRL using GRPO with a simple yet effective ternary reward that distinguishes correct answers, hallucinations, and abstentions. It incentivizes models to reduce hallucinations not only by providing correct responses, but also by enabling abstention when uncertain, thereby improving truthfulness. Extensive experiments across four knowledge-intensive benchmarks show that TruthRL significantly reduces hallucinations (e.g., 43.5% $\rightarrow$ 19.4%) and improves truthfulness (e.g., 5.3% $\rightarrow$ 37.2%), with consistent gains across various backbone models. Analysis shows that the improvement of TruthRL arises from enhanced capability of LLMs to recognize their knowledge boundary, hence avoiding being overly conservative as the baselines are.

cs.CL↗

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

RS-OOD: A Vision-Language Augmented Framework for Out-of-Distribution Detection in Remote Sensing

Out-of-distribution (OOD) detection represents a critical challenge in remote sensing applications, where reliable identification of novel or anomalous patterns is essential for autonomous monitoring, disaster response, and environmental assessment. Despite remarkable progress in OOD detection for natural images, existing methods and benchmarks remain poorly suited to remote sensing imagery due to data scarcity, complex multi-scale scene structures, and pronounced distribution shifts. To this end, we propose RS-OOD, a novel framework that leverages remote sensing-specific vision-language modeling to enable robust few-shot OOD detection. Our approach introduces three key innovations: spatial feature enhancement that improved scene discrimination, a dual-prompt alignment mechanism that cross-verifies scene context against fine-grained semantics for spatial-semantic consistency, and a confidence-guided self-training loop that dynamically mines pseudo-labels to expand training data without manual annotation. RS-OOD consistently outperforms existing methods across multiple remote sensing benchmarks and enables efficient adaptation with minimal labeled data, demonstrating the critical value of spatial-semantic integration.

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

Construction of general $N$-body lattice operators with arbitrary momenta

We present a systematic method for constructing lattice QCD operators for systems of an arbitrary number of particles with arbitrary momentum, spin, and internal quantum numbers. Explicit constructions are provided for one-, two-, three-, and four-hadron operators, covering all irreducible representations of the relevant lattice symmetry groups in both rest and moving frames. The construction procedure has been implemented in the open-source package \texttt{OpTion} (Operator construcTion), available at https://github.com/wittscien/OpTion. The paper and the package are designed to serve as a practical and extensible dictionary for future lattice QCD studies, as lattice calculations advance towards increasingly complex hadronic systems.

hep-lat↗

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

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training language models (LMs) on reasoning tasks that elicit emergent long chains of thought (CoTs). Unlike supervised learning, it updates the model using both correct and incorrect samples via policy gradients. To better understand its mechanism, we decompose the learning signal into reinforcing correct responses and penalizing incorrect ones, referred to as Positive and Negative Sample Reinforcement (PSR and NSR), respectively. We train Qwen2.5-Math-7B, Qwen3-4B and Llama-3.1-8B-Instruct on a mathematical reasoning dataset and uncover a surprising result: training with only negative samples -- without reinforcing correct responses -- can be highly effective: it consistently improves performance over the base model across the entire Pass@$k$ spectrum $k$ up to 256), often matching or surpassing PPO and GRPO. In contrast, reinforcing only correct responses improves Pass@1 but degrades performance at higher $k$, due to reduced diversity. These inference-scaling trends highlight that solely penalizing incorrect responses may contribute more to performance than previously recognized. Through gradient analysis, we show that NSR works by suppressing incorrect generations and redistributing probability mass toward other plausible candidates, guided by the model's prior beliefs. It refines the model's existing knowledge rather than introducing entirely new behaviors. Building on this insight, we propose a simple variant of the RL objective that upweights NSR, and show that it consistently improves overall Pass@$k$ performance on MATH, AIME 2025, and AMC23. Our code is available at https://github.com/TianHongZXY/RLVR-Decomposed.

cs.CL↗