arXiv subjects

Qi An

Publications and source records attributed to Qi An.

At least 19 recordsLinked to original sources

arXiv2026

Open-Set Ego-Noise Separation for Legged-Robot Audition via Annotation-Free Adaptation and Pretrained-Model Transfer

This paper proposes an open-set ego-noise separation framework for legged-robot audition via annotation-free adaptation and pretrained-model transfer. The framework removes robot-specific ego-noise while preserving environmental sounds whose classes are not specified in advance. Acoustic sensing provides cues about a robot's surroundings beyond the visual field, but walking-induced ego-noise from footstep impacts, joint-backlash rattling, and motor noise severely contaminates the recordings. The framework first uses RecurGraph to select ego-noise-dominant clips from the unlabeled recordings by aggregating clip embeddings into an embedding centroid and propagating scores over an audio-embedding graph. The selected clips are mixed with diverse environmental sounds from a large-scale sound-event dataset to provide paired mixture--target supervision for open-set separation. Transfer-DiT then adapts a general-purpose zero-shot neural separator to achieve high-fidelity open-set ego-noise separation for the target robot. Experiments with bipedal and quadrupedal robots show reliable clip selection and improvements in separation quality and downstream task performance over baseline separators. These results demonstrate the feasibility of annotation-free adaptation without separately recorded ego-noise-only data or manual clip-level annotations.

cs.RO↗

arXiv2026

Neutrino mass anarchy and leptogenesis

In this paper, we investigate leptogenesis under the neutrino mass anarchy hypothesis in both type-I and type-II seesaw models. We first revisit the corresponding study in the type-I seesaw framework with two improvements: in contrast to Ref.[25], where an approximate $U(1)$ flavor symmetry was imposed to ensure sizable hierarchies among the right-handed neutrino masses and Yukawa couplings, we adopt a fully general anarchy scenario with completely random and structureless neutrino mass and Yukawa matrices; moreover, given the crucial role of lepton flavors in both the generation and washout of the lepton asymmetry, flavor effects are consistently incorporated throughout our analysis. We then extend our investigation to the type-II seesaw framework, in which leptogenesis proceeds via the out-of-equilibrium decays of a scalar triplet.

hep-ph↗

arXiv2026

VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models

Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we propose Variable Entropy Policy Optimization (VEPO), which leverages Reinforcement Learning with Verifiable Rewards to incorporate deterministic structural constraints into the policy alignment process. This framework ensures prescribed sequence length, robust format consistency, and rigorous linguistic well formedness, all enforced during training. Central to our approach is a variable entropy mechanism that enables the model to dynamically calibrate the equilibrium between literal fidelity and semantic naturalness by modulating the exploration exploitation manifold. By integrating entropy tempered advantage estimation with asymmetric clipping, VEPO sustains robust exploration while mitigating policy collapse. Empirical evaluations across 90 FLORES-200, COMET-22, chrF directions demonstrate that VEPO yields substantial improvements in both tokenization efficiency and translation quality, bridging the performance gap for underrepresented languages.

cs.CL↗

arXiv2025

Charge-dependent spectral softenings of primary cosmic-rays below the knee

In most particle acceleration or propagation theories, the characteristic features of the cosmic ray spectra due to acceleration limits or propagation phase changes are charge dependent. Alternatively, the interaction scenario would expect mass dependent spectral features in general. The observational verification of which relation takes effect in nature is still lack due to the difficulty of measuring the spectra of individual particles up to very high energies. Here we report direct measurements of the carbon, oxygen, and iron spectra from ~20 gigavolts to ~100 teravolts (~60 teravolts for iron) with 9 years of on-orbit data collected by the Dark Matter Particle Explorer. Distinct spectral softenings have been directly detected in these spectra for the first time. Combined with the updated proton and helium spectra, the spectral softening appears universally at a rigidity of ~15 teravolts. A nuclei mass dependent softening is rejected at a confidence level of >99.999%. Possible interpretations of these results, including a nearby cosmic ray source and other models such as the propagation effect, are discussed.

astro-ph.HE↗

arXiv2025

Moving Object Detection from Moving Camera Using Focus of Expansion Likelihood and Segmentation

Separating moving and static objects from a moving camera viewpoint is essential for 3D reconstruction, autonomous navigation, and scene understanding in robotics. Existing approaches often rely primarily on optical flow, which struggles to detect moving objects in complex, structured scenes involving camera motion. To address this limitation, we propose Focus of Expansion Likelihood and Segmentation (FoELS), a method based on the core idea of integrating both optical flow and texture information. FoELS computes the focus of expansion (FoE) from optical flow and derives an initial motion likelihood from the outliers of the FoE computation. This likelihood is then fused with a segmentation-based prior to estimate the final moving probability. The method effectively handles challenges including complex structured scenes, rotational camera motion, and parallel motion. Comprehensive evaluations on the DAVIS 2016 dataset and real-world traffic videos demonstrate its effectiveness and state-of-the-art performance.

cs.CV↗

arXiv2025

Quantifying Memory Utilization with Effective State-Size

The need to develop a general framework for architecture analysis is becoming increasingly important, given the expanding design space of sequence models. To this end, we draw insights from classical signal processing and control theory, to develop a quantitative measure of \textit{memory utilization}: the internal mechanisms through which a model stores past information to produce future outputs. This metric, which we call \textbf{\textit{effective state-size}} (ESS), is tailored to the fundamental class of systems with \textit{input-invariant} and \textit{input-varying linear operators}, encompassing a variety of computational units such as variants of attention, convolutions, and recurrences. Unlike prior work on memory utilization, which either relies on raw operator visualizations (e.g. attention maps), or simply the total \textit{memory capacity} (i.e. cache size) of a model, our metrics provide highly interpretable and actionable measurements. In particular, we show how ESS can be leveraged to improve initialization strategies, inform novel regularizers and advance the performance-efficiency frontier through model distillation. Furthermore, we demonstrate that the effect of context delimiters (such as end-of-speech tokens) on ESS highlights cross-architectural differences in how large language models utilize their available memory to recall information. Overall, we find that ESS provides valuable insights into the dynamics that dictate memory utilization, enabling the design of more efficient and effective sequence models.

cs.LG↗

arXiv2025

Direct evidence and atomic-scale mechanisms of reduced dislocation mobility in an inorganic semiconductor under illumination

Photo-plasticity in semiconductors, wherein their mechanical properties such as strength, hardness and ductility are influenced by light exposure, has been reported for several decades. Although such phenomena have drawn significant attention for the manufacturability and usage of deformable semiconductor devices, their underlying mechanisms are not well understood due to the lack of direct evidence. Here we provide experimental observation and atomic insights into the reduced mobility of dislocations in zinc sulfide, as a model material, under light. Using photo-nanoindentation and transmission electron microscopy, we observe that dislocations glide shorter distances under light than those in darkness and there are no apparent deformation twins in both conditions. By atomic-scale simulations, we demonstrate that the decreased dislocation mobility is attributed to the increased Peierls stress for dislocation motion and enhanced stress fields around dislocation cores due to photoexcitation. This study improves the understanding of photo-plastic effects in inorganic semiconductors, offering the opportunities for modulating their mechanical properties using light.

cond-mat.mtrl-sci↗

arXiv2025

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

This paper introduces Light-R1, an open-source suite for training long reasoning models using reproducible and cost-effective methodology. Given the proprietary nature of data used in the DeepSeek-R1 series, we develop an alternative approach leveraging exclusively public data and models. Our curriculum training progressively increases data difficulty, combined with multi-staged post-training. Our Light-R1-32B model, trained from Qwen2.5-32B-Instruct, outperforms DeepSeek-R1-Distill-Qwen-32B in math reasoning. Experimental results show that this curriculum approach becomes more effective when distinct, diverse datasets are available for different training stages: fine-tuning DeepSeek-R1-Distilled models (pre-tuned by DeepSeek team on proprietary data) with 3,000 challenging examples from our curriculum dataset yielded state-of-the-art 7B and 14B models, while the 32B model, Light-R1-32B-DS performed comparably to QwQ-32B and DeepSeek-R1. Furthermore, we extend our work by applying GRPO on long reasoning models. Our final Light-R1-14B-DS achieves SOTA performance among 14B models in math, with AIME24 & 25 scores of 74.0 and 60.2 respectively, surpassing many 32B models and DeepSeek-R1-Distill-Llama-70B. Despite math-focused training, Light-R1-14B-DS demonstrates strong cross-domain generalization. Light-R1 represents a significant advancement in making sophisticated reasoning models more accessible and implementable in real-world applications. Our models, training data and code have been made available at https://github.com/Qihoo360/Light-R1.

cs.CL↗

arXiv2025

LEDD: Large Language Model-Empowered Data Discovery in Data Lakes

Data discovery in data lakes with ever increasing datasets has long been recognized as a big challenge in the realm of data management, especially for semantic search of and hierarchical global catalog generation of tables. While large language models (LLMs) facilitate the processing of data semantics, challenges remain in architecting an end-to-end system that comprehensively exploits LLMs for the two semantics-related tasks. In this demo, we propose LEDD, an end-to-end system with an extensible architecture that leverages LLMs to provide hierarchical global catalogs with semantic meanings and semantic table search for data lakes. Specifically, LEDD can return semantically related tables based on natural-language specification. These features make LEDD an ideal foundation for downstream tasks such as model training and schema linking for text-to-SQL tasks. LEDD also provides a simple Python interface to facilitate the extension and the replacement of data discovery algorithms.

cs.DB↗

arXiv2024

Efficient Computation of the Non-convex Quasi-norm Ball Projection with Iterative Reweighted Approach

In this study, we focus on computing the projection onto the $\ell_p$ quasi-norm ball, which is challenging due to the non-convex and non-Lipschitz nature inherent in the $\ell_p$ quasi-norm with $0<p<1$. We propose a novel localized approximation method that yields a Lipschitz continuous concave surrogate function for the $\ell_p$ quasi-norm with improved approximation quality. Building on this approximation, we enhance the state-of-the-art iterative reweighted algorithm proposed by Yang et al. (J Mach Learn Res 23:1-31, 2022) by constructing tighter subproblems. This improved algorithm solves the $\ell_p$ quasinorm ball projection problem through a series of tractable projections onto the weighted $\ell_1$ norm balls. Convergence analyses and numerical studies demonstrate the global convergence and superior computational efficiency of the proposed method.

math.OC↗

arXiv2024

JUNO Sensitivity to Invisible Decay Modes of Neutrons

We explore the decay of bound neutrons into invisible particles (e.g., $n\rightarrow 3 \nu$ or $nn \rightarrow 2 \nu$) in the JUNO liquid scintillator detector, which do not produce an observable signal. The invisible decay includes two decay modes: $ n \rightarrow { inv} $ and $ nn \rightarrow { inv} $. The invisible decays of $s$-shell neutrons in $^{12}{\rm C}$ will leave a highly excited residual nucleus. Subsequently, some de-excitation modes of the excited residual nuclei can produce a time- and space-correlated triple coincidence signal in the JUNO detector. Based on a full Monte Carlo simulation informed with the latest available data, we estimate all backgrounds, including inverse beta decay events of the reactor antineutrino $\bar{\nu}_e$, natural radioactivity, cosmogenic isotopes and neutral current interactions of atmospheric neutrinos. Pulse shape discrimination and multivariate analysis techniques are employed to further suppress backgrounds. With two years of exposure, JUNO is expected to give an order of magnitude improvement compared to the current best limits. After 10 years of data taking, the JUNO expected sensitivities at a 90% confidence level are $\tau/B( n \rightarrow { inv} ) > 5.0 \times 10^{31} \, {\rm yr}$ and $\tau/B( nn \rightarrow { inv} ) > 1.4 \times 10^{32} \, {\rm yr}$.

hep-ex↗

arXiv2024

Potential to identify neutrino mass ordering with reactor antineutrinos at JUNO

The Jiangmen Underground Neutrino Observatory (JUNO) is a multi-purpose neutrino experiment under construction in South China. This paper presents an updated estimate of JUNO's sensitivity to neutrino mass ordering using the reactor antineutrinos emitted from eight nuclear reactor cores in the Taishan and Yangjiang nuclear power plants. This measurement is planned by studying the fine interference pattern caused by quasi-vacuum oscillations in the oscillated antineutrino spectrum at a baseline of 52.5~km and is completely independent of the CP violating phase and neutrino mixing angle $\theta_{23}$. The sensitivity is obtained through a joint analysis of JUNO and Taishan Antineutrino Observatory (TAO) detectors utilizing the best available knowledge to date about the location and overburden of the JUNO experimental site, local and global nuclear reactors, JUNO and TAO detector responses, expected event rates and spectra of signals and backgrounds, and systematic uncertainties of analysis inputs. We find that a 3$\sigma$ median sensitivity to reject the wrong mass ordering hypothesis can be reached with an exposure to approximately 6.5 years $\times$ 26.6 GW thermal power.

hep-ex↗

arXiv2024

Prediction of Energy Resolution in the JUNO Experiment

This paper presents an energy resolution study of the JUNO experiment, incorporating the latest knowledge acquired during the detector construction phase. The determination of neutrino mass ordering in JUNO requires an exceptional energy resolution better than 3\% at 1~MeV. To achieve this ambitious goal, significant efforts have been undertaken in the design and production of the key components of the JUNO detector. Various factors affecting the detection of inverse beta decay signals have an impact on the energy resolution, extending beyond the statistical fluctuations of the detected number of photons, such as the properties of the liquid scintillator, performance of photomultiplier tubes, and the energy reconstruction algorithm. To account for these effects, a full JUNO simulation and reconstruction approach is employed. This enables the modeling of all relevant effects and the evaluation of associated inputs to accurately estimate the energy resolution. The results of study reveal an energy resolution of 2.95\% at 1~MeV. Furthermore, this study assesses the contribution of major effects to the overall energy resolution budget. This analysis serves as a reference for interpreting future measurements of energy resolution during JUNO data collection. Moreover, it provides a guideline for comprehending the energy resolution characteristics of liquid scintillator-based detectors.

hep-ex↗

arXiv2024

State-Free Inference of State-Space Models: The Transfer Function Approach

We approach designing a state-space model for deep learning applications through its dual representation, the transfer function, and uncover a highly efficient sequence parallel inference algorithm that is state-free: unlike other proposed algorithms, state-free inference does not incur any significant memory or computational cost with an increase in state size. We achieve this using properties of the proposed frequency domain transfer function parametrization, which enables direct computation of its corresponding convolutional kernel's spectrum via a single Fast Fourier Transform. Our experimental results across multiple sequence lengths and state sizes illustrates, on average, a 35% training speed improvement over S4 layers -- parametrized in time-domain -- on the Long Range Arena benchmark, while delivering state-of-the-art downstream performances over other attention-free approaches. Moreover, we report improved perplexity in language modeling over a long convolutional Hyena baseline, by simply introducing our transfer function parametrization. Our code is available at https://github.com/ruke1ire/RTF.

cs.LG↗

arXiv2024

Multi-Stage Contrastive Regression for Action Quality Assessment

In recent years, there has been growing interest in the video-based action quality assessment (AQA). Most existing methods typically solve AQA problem by considering the entire video yet overlooking the inherent stage-level characteristics of actions. To address this issue, we design a novel Multi-stage Contrastive Regression (MCoRe) framework for the AQA task. This approach allows us to efficiently extract spatial-temporal information, while simultaneously reducing computational costs by segmenting the input video into multiple stages or procedures. Inspired by the graph contrastive learning, we propose a new stage-wise contrastive learning loss function to enhance performance. As a result, MCoRe demonstrates the state-of-the-art result so far on the widely-adopted fine-grained AQA dataset.

cs.CV↗

arXiv2023

Real-time Monitoring for the Next Core-Collapse Supernova in JUNO

The core-collapse supernova (CCSN) is considered one of the most energetic astrophysical events in the universe. The early and prompt detection of neutrinos before (pre-SN) and during the supernova (SN) burst presents a unique opportunity for multi-messenger observations of CCSN events. In this study, we describe the monitoring concept and present the sensitivity of the system to pre-SN and SN neutrinos at the Jiangmen Underground Neutrino Observatory (JUNO), a 20 kton liquid scintillator detector currently under construction in South China. The real-time monitoring system is designed to ensure both prompt alert speed and comprehensive coverage of progenitor stars. It incorporates prompt monitors on the electronic board as well as online monitors at the data acquisition stage. Assuming a false alert rate of 1 per year, this monitoring system exhibits sensitivity to pre-SN neutrinos up to a distance of approximately 1.6 (0.9) kiloparsecs and SN neutrinos up to about 370 (360) kiloparsecs for a progenitor mass of 30 solar masses, considering both normal and inverted mass ordering scenarios. The pointing ability of the CCSN is evaluated by analyzing the accumulated event anisotropy of inverse beta decay interactions from pre-SN or SN neutrinos. This, along with the early alert, can play a crucial role in facilitating follow-up multi-messenger observations of the next galactic or nearby extragalactic CCSN.

hep-ex↗

arXiv2023

Deciphering the Enigma of Cu-Doped Lead Apatite (LK-99): Structural Insights, Electronic Properties, and Implications for Ambient-Pressure Superconductivity

The most recent discovery, the Cu-doped lead apatite LK-99, is a proposed room-temperature superconductor operating under ambient pressure. However, this discovery has brought a slew of conflicting results from different scientific groups. While some observed the absence of electrical resistance, others could not confirm any signs of superconductivity in LK-99. Here, we investigate the structural and electronic properties of LK-99 and its antecedent compounds through quantum mechanics (QM) and QM-based molecular dynamics (QM-MD) simulations. Our study elucidates the insulating nature of base compounds, Pb$_{10}$(PO$_4$)$_6$O and Pb$_{10}$(PO$_4$)$_6$(OH)$_2$, spotlighting their large band gaps. Notably, Cu doping in LK-99 disrupts its symmetry, yielding a distorted ground-state crystal structure with a triclinic P1 symmetry and CuO$_4$ square coordination. Such alterations predispose LK-99 to exhibit semiconducting behaviors, characterized by a flat band above the Fermi energy, arising from Cu-3d and O-2p orbitals. In addition, the S doping sustains the triclinic P1 symmetry but leads to a significantly reduced band gap, with a band emerging primarily from Cu-3d and S-3p orbitals. These findings are important in understanding LK-99's structural and electronic properties and provide a strategic compass for the development of high-T$_C$ superconductors.

cond-mat.supr-con↗

arXiv2023

JUNO sensitivity to the annihilation of MeV dark matter in the galactic halo

We discuss JUNO sensitivity to the annihilation of MeV dark matter in the galactic halo via detecting inverse beta decay reactions of electron anti-neutrinos resulting from the annihilation. We study possible backgrounds to the signature, including the reactor neutrinos, diffuse supernova neutrino background, charged- and neutral-current interactions of atmospheric neutrinos, backgrounds from muon-induced fast neutrons and cosmogenic isotopes. A fiducial volume cut, as well as the pulse shape discrimination and the muon veto are applied to suppress the above backgrounds. It is shown that JUNO sensitivity to the thermally averaged dark matter annihilation rate in 10 years of exposure would be significantly better than the present-day best limit set by Super-Kamiokande and would be comparable to that expected by Hyper-Kamiokande.

hep-ex↗